HopeSpeechEDI_IndicBERT_Malayalam.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "HopeSpeechEDI_IndicBERT_Malayalam.ipynb",
      "provenance": [],
      "toc_visible": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "c0d606ca1a83452aa1ad129ff458e5b5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_cd77ea52c87741e79374c62c140b1a8c",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_0183af8ab28b44a2af3892885c697143",
              "IPY_MODEL_37fe3cbc00a649e1917c02b880b664dd"
            ]
          }
        },
        "cd77ea52c87741e79374c62c140b1a8c": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "0183af8ab28b44a2af3892885c697143": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_2319616d96d84559af4fa4276481bccd",
            "_dom_classes": [],
            "description": "Downloading: 100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 507,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 507,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_4a9ad567270c4cdf8eaab25f9e3e45d2"
          }
        },
        "37fe3cbc00a649e1917c02b880b664dd": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_b98b89b144ba4286b1eb0f3cc3d495ad",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 507/507 [00:00&lt;00:00, 912B/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_2e1a491457394fb08e63a7833310c2c4"
          }
        },
        "2319616d96d84559af4fa4276481bccd": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "4a9ad567270c4cdf8eaab25f9e3e45d2": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "b98b89b144ba4286b1eb0f3cc3d495ad": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "2e1a491457394fb08e63a7833310c2c4": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "f5db80c6872e44ddb53123bf350e8a19": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_14cfb4558e9a4580bea719fa9d14b3cc",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_1032f4c7eb30426788e8dfabbd0f1ad7",
              "IPY_MODEL_21482b10c549418d8d73406ee02f3e85"
            ]
          }
        },
        "14cfb4558e9a4580bea719fa9d14b3cc": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "1032f4c7eb30426788e8dfabbd0f1ad7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_ada21f05a66940f9bdf9e3fbea907815",
            "_dom_classes": [],
            "description": "Downloading: 100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 5646064,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 5646064,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_d63c1e883e2e44a4afe64b300b336af6"
          }
        },
        "21482b10c549418d8d73406ee02f3e85": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_cfb4c7dc667548f0af84b918d1ff1feb",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 5.65M/5.65M [00:02&lt;00:00, 2.21MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_61cd194de0fa4fdda80f00f78594051a"
          }
        },
        "ada21f05a66940f9bdf9e3fbea907815": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "d63c1e883e2e44a4afe64b300b336af6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "cfb4c7dc667548f0af84b918d1ff1feb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "61cd194de0fa4fdda80f00f78594051a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "1a8c70d58c9f408a9c8a3e85b4925967": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_e2490ef98f6b4bbe83772eeef9442d0a",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_7792da63cc2547479a9bc74064acf35f",
              "IPY_MODEL_cc5f4445dcf3415399413b1594aad904"
            ]
          }
        },
        "e2490ef98f6b4bbe83772eeef9442d0a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "7792da63cc2547479a9bc74064acf35f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_dae9c865e716406c9ffc9034c91cc1b6",
            "_dom_classes": [],
            "description": "Downloading: 100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 134982446,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 134982446,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_43a94a8d30674e899ddc4b77752982a5"
          }
        },
        "cc5f4445dcf3415399413b1594aad904": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_cdb0dcca44e24b6cafc5e1b611d0f919",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 135M/135M [00:02&lt;00:00, 50.2MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_cb970d5806224031ab7b5ab97c2a9a58"
          }
        },
        "dae9c865e716406c9ffc9034c91cc1b6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "43a94a8d30674e899ddc4b77752982a5": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "cdb0dcca44e24b6cafc5e1b611d0f919": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "cb970d5806224031ab7b5ab97c2a9a58": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "elqe9PQrVH6P"
      },
      "source": [
        "### Performing checks for the resources available"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fSELLChxa5su",
        "outputId": "1f9aafad-9f27-4710-d705-4b31c7416c12"
      },
      "source": [
        "import torch\r\n",
        "\r\n",
        "# If there's a GPU available...\r\n",
        "if torch.cuda.is_available():    \r\n",
        "\r\n",
        "    # Tell PyTorch to use the GPU.    \r\n",
        "    device = torch.device(\"cuda\")\r\n",
        "\r\n",
        "    print('There are %d GPU(s) available.' % torch.cuda.device_count())\r\n",
        "\r\n",
        "    print('We will use the GPU:', torch.cuda.get_device_name(0))\r\n",
        "\r\n",
        "# If not...\r\n",
        "else:\r\n",
        "    print('No GPU available, using the CPU instead.')\r\n",
        "    device = torch.device(\"cpu\")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "There are 1 GPU(s) available.\n",
            "We will use the GPU: Tesla P100-PCIE-16GB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wFrXUyYThK5D",
        "outputId": "df1edcef-09f3-453c-8c8f-2e5b3595e5e2"
      },
      "source": [
        "!nvidia-smi"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Fri Feb  5 11:57:54 2021       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 460.39       Driver Version: 418.67       CUDA Version: 10.1     |\n",
            "|-------------------------------+----------------------+----------------------+\n",
            "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
            "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
            "|                               |                      |               MIG M. |\n",
            "|===============================+======================+======================|\n",
            "|   0  Tesla P100-PCIE...  Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   35C    P0    27W / 250W |     10MiB / 16280MiB |      0%      Default |\n",
            "|                               |                      |                 ERR! |\n",
            "+-------------------------------+----------------------+----------------------+\n",
            "                                                                               \n",
            "+-----------------------------------------------------------------------------+\n",
            "| Processes:                                                                  |\n",
            "|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |\n",
            "|        ID   ID                                                   Usage      |\n",
            "|=============================================================================|\n",
            "|  No running processes found                                                 |\n",
            "+-----------------------------------------------------------------------------+\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "K-gbOgflVRxg"
      },
      "source": [
        "### Installing huggingface transformers library"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DbDuxKy0a9Zl",
        "outputId": "91564a5f-7226-4aa5-d8b2-7c16340e840f"
      },
      "source": [
        "!pip install transformers sentencepiece"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting transformers\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/88/b1/41130a228dd656a1a31ba281598a968320283f48d42782845f6ba567f00b/transformers-4.2.2-py3-none-any.whl (1.8MB)\n",
            "\u001b[K     |████████████████████████████████| 1.8MB 8.0MB/s \n",
            "\u001b[?25hCollecting sentencepiece\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/14/67/e42bd1181472c95c8cda79305df848264f2a7f62740995a46945d9797b67/sentencepiece-0.1.95-cp36-cp36m-manylinux2014_x86_64.whl (1.2MB)\n",
            "\u001b[K     |████████████████████████████████| 1.2MB 34.9MB/s \n",
            "\u001b[?25hRequirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from transformers) (2.23.0)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.6/dist-packages (from transformers) (2019.12.20)\n",
            "Requirement already satisfied: importlib-metadata; python_version < \"3.8\" in /usr/local/lib/python3.6/dist-packages (from transformers) (3.4.0)\n",
            "Requirement already satisfied: dataclasses; python_version < \"3.7\" in /usr/local/lib/python3.6/dist-packages (from transformers) (0.8)\n",
            "Collecting sacremoses\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/7d/34/09d19aff26edcc8eb2a01bed8e98f13a1537005d31e95233fd48216eed10/sacremoses-0.0.43.tar.gz (883kB)\n",
            "\u001b[K     |████████████████████████████████| 890kB 51.8MB/s \n",
            "\u001b[?25hCollecting tokenizers==0.9.4\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/0f/1c/e789a8b12e28be5bc1ce2156cf87cb522b379be9cadc7ad8091a4cc107c4/tokenizers-0.9.4-cp36-cp36m-manylinux2010_x86_64.whl (2.9MB)\n",
            "\u001b[K     |████████████████████████████████| 2.9MB 55.7MB/s \n",
            "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.6/dist-packages (from transformers) (3.0.12)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from transformers) (1.19.5)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.6/dist-packages (from transformers) (20.9)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.6/dist-packages (from transformers) (4.41.1)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (3.0.4)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (2.10)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (1.24.3)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (2020.12.5)\n",
            "Requirement already satisfied: typing-extensions>=3.6.4; python_version < \"3.8\" in /usr/local/lib/python3.6/dist-packages (from importlib-metadata; python_version < \"3.8\"->transformers) (3.7.4.3)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.6/dist-packages (from importlib-metadata; python_version < \"3.8\"->transformers) (3.4.0)\n",
            "Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (1.15.0)\n",
            "Requirement already satisfied: click in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (7.1.2)\n",
            "Requirement already satisfied: joblib in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (1.0.0)\n",
            "Requirement already satisfied: pyparsing>=2.0.2 in /usr/local/lib/python3.6/dist-packages (from packaging->transformers) (2.4.7)\n",
            "Building wheels for collected packages: sacremoses\n",
            "  Building wheel for sacremoses (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for sacremoses: filename=sacremoses-0.0.43-cp36-none-any.whl size=893261 sha256=0b20e96dbad31bf19143ca0b9135075a7698045278b7fdb1fe0dcc5243e9160f\n",
            "  Stored in directory: /root/.cache/pip/wheels/29/3c/fd/7ce5c3f0666dab31a50123635e6fb5e19ceb42ce38d4e58f45\n",
            "Successfully built sacremoses\n",
            "Installing collected packages: sacremoses, tokenizers, transformers, sentencepiece\n",
            "Successfully installed sacremoses-0.0.43 sentencepiece-0.1.95 tokenizers-0.9.4 transformers-4.2.2\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bPwaYLiRSNPC"
      },
      "source": [
        "## Importing necessary packages"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0XdFrhr8SRG0"
      },
      "source": [
        "import pandas as pd\r\n",
        "import numpy as np \r\n",
        "import random\r\n",
        "from sklearn.preprocessing import LabelEncoder\r\n",
        "from sklearn.utils.class_weight import compute_class_weight\r\n",
        "import time\r\n",
        "import datetime\r\n",
        "from sklearn.metrics import classification_report,confusion_matrix\r\n",
        "import random\r\n",
        "import time\r\n",
        "import torch.nn as nn\r\n",
        "from transformers import AutoModel , AutoModelForSequenceClassification, AutoConfig , AutoTokenizer , AdamW ,get_linear_schedule_with_warmup \r\n",
        "import torch\r\n",
        "import matplotlib.pyplot as plt\r\n",
        "import seaborn as sns\r\n",
        "from matplotlib import rc\r\n",
        "from matplotlib.ticker import MaxNLocator"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "dROX3juhVCxC"
      },
      "source": [
        "## Setting some configuration values"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Kzafv4BzVCC9"
      },
      "source": [
        "# Use plot styling from seaborn.\r\n",
        "sns.set(style='darkgrid')\r\n",
        "\r\n",
        "# Increase the plot size and font size.\r\n",
        "sns.set(font_scale=1.5)\r\n",
        "plt.rcParams[\"figure.figsize\"] = (16,12)\r\n",
        "\r\n",
        "# Set the seed value all over the place to make this reproducible.\r\n",
        "seed_val = 42\r\n",
        "\r\n",
        "random.seed(seed_val)\r\n",
        "np.random.seed(seed_val)\r\n",
        "torch.manual_seed(seed_val)\r\n",
        "torch.cuda.manual_seed_all(seed_val)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2v1AIN_OVX4t"
      },
      "source": [
        "## Importing drive into the colaboratory"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Lofimyh2a_tp",
        "outputId": "923deb40-2911-489e-a3fc-689f2742f4cb"
      },
      "source": [
        "from google.colab import drive \r\n",
        "drive.mount('/content/drive')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Mounted at /content/drive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yOK-M00dVeW2"
      },
      "source": [
        "## Importing dataset directories"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-y-JRPKBbCTv"
      },
      "source": [
        "from os import getcwd , listdir \r\n",
        "from os.path import join\r\n",
        "curr_dir = getcwd()\r\n",
        "drive_dir = join(curr_dir , 'drive','MyDrive')\r\n",
        "dataset_dir = join(drive_dir,'Codalab','HopeSpeech Detection For Equality,DiversityAnd Inclusion','Dataset')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7YU1h8WhmqvK",
        "outputId": "c25b01fd-2118-4872-db10-e1fd7af8d618"
      },
      "source": [
        "listdir(dataset_dir)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['english_hope_dev.csv',\n",
              " 'english_hope_train.csv',\n",
              " 'malayalam_hope_dev.csv',\n",
              " 'malayalam_hope_train.csv',\n",
              " 'tamil_hope_first_dev.csv',\n",
              " 'tamil_hope_first_train.csv',\n",
              " 'tamil_hope_test.csv',\n",
              " 'malayalam_hope_test.csv',\n",
              " 'english_hope_test.csv',\n",
              " 'english_hope_test _labels.csv',\n",
              " 'malayalam_hope_test _labels.csv',\n",
              " 'tamil_hope_test _labels.csv',\n",
              " 'malayalam_hope_test_labels.csv']"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FUPkZxjLVjLK"
      },
      "source": [
        "## Loading training data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "joone3H4bINR",
        "outputId": "66e69742-d5ee-494c-95d6-35c775d64091"
      },
      "source": [
        "train_df_path = join(dataset_dir,'malayalam_hope_train.csv')\r\n",
        "# Load the dataset into a pandas dataframe.\r\n",
        "train_df = pd.read_csv(train_df_path)\r\n",
        "\r\n",
        "# Report the number of sentences.\r\n",
        "print('Number of training sentences: {:,}\\n'.format(train_df.shape[0]))\r\n",
        "\r\n",
        "# Display 10 random rows from the data.\r\n",
        "train_df.sample(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of training sentences: 8,564\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>7913</th>\n",
              "      <td>Iniyippo ningal pubg kalichalum kuzhappamilla ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6065</th>\n",
              "      <td>ആ ചെങ്ങായിക്കെല്ലും എത്ര നല്ല മൊഞ്ചത്തി പെണ്ണി...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1649</th>\n",
              "      <td>Suryammaa ishanikkaaaa happy wedding anniversa...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>710</th>\n",
              "      <td>Ente bayi ittekkana shoe muthal jaddy vare ava...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1918</th>\n",
              "      <td>Ayaal entha parayunath ennu ayaalkk tahnne ari...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3617</th>\n",
              "      <td>ചക്ക കുരു പൊട്ടിയോ</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>233</th>\n",
              "      <td>പിന്നെ അമ്മയെയും എന്റെ അന്വേഷണം അറിയിക്കണം</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6927</th>\n",
              "      <td>Helo  iku പകരം എന്തുണ്ട് ?</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2094</th>\n",
              "      <td>Kevin mandane kaanumbhaz santhosh pandittine o...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3114</th>\n",
              "      <td>പൊളിച്ചു bro</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text            label\n",
              "7913  Iniyippo ningal pubg kalichalum kuzhappamilla ...  Non_hope_speech\n",
              "6065  ആ ചെങ്ങായിക്കെല്ലും എത്ര നല്ല മൊഞ്ചത്തി പെണ്ണി...  Non_hope_speech\n",
              "1649  Suryammaa ishanikkaaaa happy wedding anniversa...      Hope_speech\n",
              "710   Ente bayi ittekkana shoe muthal jaddy vare ava...  Non_hope_speech\n",
              "1918  Ayaal entha parayunath ennu ayaalkk tahnne ari...  Non_hope_speech\n",
              "3617                                 ചക്ക കുരു പൊട്ടിയോ  Non_hope_speech\n",
              "233          പിന്നെ അമ്മയെയും എന്റെ അന്വേഷണം അറിയിക്കണം      Hope_speech\n",
              "6927                         Helo  iku പകരം എന്തുണ്ട് ?  Non_hope_speech\n",
              "2094  Kevin mandane kaanumbhaz santhosh pandittine o...  Non_hope_speech\n",
              "3114                                       പൊളിച്ചു bro      Hope_speech"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "w4VW351225YK",
        "outputId": "5f1e9eee-fd5b-4cee-f09e-e9d7a2abc1ed"
      },
      "source": [
        "train_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    6205\n",
              "Hope_speech        1668\n",
              "not-malayalam       691\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ooOv9QZtnLIF"
      },
      "source": [
        "\r\n",
        "le = LabelEncoder()\r\n",
        "train_df['label'] = le.fit_transform(train_df['label'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "a89Bf4LpnigU",
        "outputId": "f096085a-0215-4dbc-9dae-c4ecee05a935"
      },
      "source": [
        "train_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    6205\n",
              "0    1668\n",
              "2     691\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bvNeR4lTVnK0"
      },
      "source": [
        "### Loading `train_sentences` and `train_labels`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EufQZx2dbKMT"
      },
      "source": [
        "# Get the lists of sentences and their labels.\r\n",
        "train_sentences = train_df['text'].values\r\n",
        "train_labels = train_df['label'].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wnZSg5f7ZWs_"
      },
      "source": [
        "## Saving Class Names"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "83tTT-wbZa1o",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "abb5653e-a395-4343-e65c-529920be2f6e"
      },
      "source": [
        "class_names = le.inverse_transform(range(0,len(train_df['label'].unique())))\r\n",
        "class_names"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Hope_speech', 'Non_hope_speech', 'not-malayalam'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ToUbAgZ9ap63"
      },
      "source": [
        "## Loading the validation data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "Dle8VzoAjOLS",
        "outputId": "52b27dde-677e-4ad7-f1cb-5125f01b24a2"
      },
      "source": [
        "val_df_path = join(dataset_dir,'malayalam_hope_dev.csv')\r\n",
        "# Load the dataset into a pandas dataframe.\r\n",
        "val_df = pd.read_csv(val_df_path)\r\n",
        "\r\n",
        "# Report the number of sentences.\r\n",
        "print('Number of training sentences: {:,}\\n'.format(val_df.shape[0]))\r\n",
        "\r\n",
        "# Display 10 random rows from the data.\r\n",
        "val_df.sample(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of training sentences: 1,070\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>424</th>\n",
              "      <td>ഇന്ത്യൻ മതേതര ജനാധിപത്യ രാജ്യമാണ്</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>722</th>\n",
              "      <td>@Mallu crafts thanik or gay aya kutti ondavath...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>306</th>\n",
              "      <td>Helo. Lesbiann.. chodichal. Vanno</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>116</th>\n",
              "      <td>Nikesh  nte  kada  kettapol  sangadam  തോന്നി...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>551</th>\n",
              "      <td>Ithil parenjekana korey app onnum njan kettit ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>263</th>\n",
              "      <td>Gay enn kandappo nice aayitt kaanan vanirikkka</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>333</th>\n",
              "      <td>Public reactions kalakki but kurach koodi leng...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>575</th>\n",
              "      <td>പോയി ചതൂ ഡേ</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>597</th>\n",
              "      <td>Dr ഈ പ്രതിരോധ ശേഷി ധാരാളം ഉള്ള ആൾക്ക് എത്ര തവണ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>634</th>\n",
              "      <td>Happy mother's day surya amma.. nകരയിപ്പിച്ചു ...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                  text            label\n",
              "424                  ഇന്ത്യൻ മതേതര ജനാധിപത്യ രാജ്യമാണ്  Non_hope_speech\n",
              "722  @Mallu crafts thanik or gay aya kutti ondavath...  Non_hope_speech\n",
              "306                  Helo. Lesbiann.. chodichal. Vanno  Non_hope_speech\n",
              "116   Nikesh  nte  kada  kettapol  sangadam  തോന്നി...  Non_hope_speech\n",
              "551  Ithil parenjekana korey app onnum njan kettit ...  Non_hope_speech\n",
              "263     Gay enn kandappo nice aayitt kaanan vanirikkka  Non_hope_speech\n",
              "333  Public reactions kalakki but kurach koodi leng...  Non_hope_speech\n",
              "575                                        പോയി ചതൂ ഡേ  Non_hope_speech\n",
              "597  Dr ഈ പ്രതിരോധ ശേഷി ധാരാളം ഉള്ള ആൾക്ക് എത്ര തവണ...  Non_hope_speech\n",
              "634  Happy mother's day surya amma.. nകരയിപ്പിച്ചു ...      Hope_speech"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AypCmtBcDV6v",
        "outputId": "211b343b-89ef-4dca-80b3-569c74f5968b"
      },
      "source": [
        "val_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    784\n",
              "Hope_speech        190\n",
              "not-malayalam       96\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-CgK81lGDPKC"
      },
      "source": [
        "val_df['label'] = le.transform(val_df['label'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Yfgn-E6JDZQZ",
        "outputId": "72c45635-9297-40d4-c617-da489fa10947"
      },
      "source": [
        "val_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    784\n",
              "0    190\n",
              "2     96\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DMdNNVqrDCuN"
      },
      "source": [
        "### Loading `val_sentences` and `val_labels`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LvGhjUkaDCuO"
      },
      "source": [
        "# Get the lists of sentences and their labels.\r\n",
        "val_sentences = val_df['text'].values\r\n",
        "val_labels = val_df['label'].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4mgM6b0yL0NM"
      },
      "source": [
        "## Loading the test data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "d7tVWiIeL0NN",
        "outputId": "c2cd613e-16b0-4ba1-a51d-3bd1206f3b65"
      },
      "source": [
        "test_df_path = join(dataset_dir,'malayalam_hope_test_labels.csv')\r\n",
        "# Load the dataset into a pandas dataframe.\r\n",
        "test_df = pd.read_csv(test_df_path)\r\n",
        "\r\n",
        "# Report the number of sentences.\r\n",
        "print('Number of test sentences: {:,}\\n'.format(test_df.shape[0]))\r\n",
        "\r\n",
        "# Display 10 random rows from the data.\r\n",
        "test_df.sample(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of test sentences: 1,071\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "      <th>Unnamed: 2</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>673</th>\n",
              "      <td>Sir online വഴി സാധനം വാങ്ങിയാൽ കൊറോണ പകരാൻ ചാൻ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>180</th>\n",
              "      <td>Kundanmar Ennanu Nchangal Vilikkua</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>474</th>\n",
              "      <td>നല്ല മനസ്സുള്ളവർ ഒരുമിച്ചു ജീവിക്കുന്നതല്ലേ മന...</td>\n",
              "      <td>Hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>834</th>\n",
              "      <td>ഇതൊക്കെ രാജ്യം നിരോധിക്കണം</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>668</th>\n",
              "      <td>നായിന്റ മക്കളെ.. പോയി തൂങ്ങി മരിച്ചൂടെ. അവന്റെ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1055</th>\n",
              "      <td>@Vyas Deep brother swarganuragam thettanu yoji...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "      <td>not-malayalam</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>448</th>\n",
              "      <td>ഇവർ പുരുഷന്മാർ ആണ്.. nപുരുഷനോട് ആകർഷണം ഉള്ള പു...</td>\n",
              "      <td>Hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>629</th>\n",
              "      <td>@Manikandan Sivan മതത്തിലല്ലടോ nഐൻസ്റ്റീൻ കണ്ട...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>488</th>\n",
              "      <td>@rafid pu അവരുടെ ജീവിതം എങ്ങനെയാടോ തകരുന്നേ വീ...</td>\n",
              "      <td>Hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text  ... Unnamed: 2\n",
              "673   Sir online വഴി സാധനം വാങ്ങിയാൽ കൊറോണ പകരാൻ ചാൻ...  ...        NaN\n",
              "180                  Kundanmar Ennanu Nchangal Vilikkua  ...        NaN\n",
              "474   നല്ല മനസ്സുള്ളവർ ഒരുമിച്ചു ജീവിക്കുന്നതല്ലേ മന...  ...        NaN\n",
              "834                          ഇതൊക്കെ രാജ്യം നിരോധിക്കണം  ...        NaN\n",
              "668   നായിന്റ മക്കളെ.. പോയി തൂങ്ങി മരിച്ചൂടെ. അവന്റെ...  ...        NaN\n",
              "1055  @Vyas Deep brother swarganuragam thettanu yoji...  ...        NaN\n",
              "4                                       I respect you..  ...        NaN\n",
              "448   ഇവർ പുരുഷന്മാർ ആണ്.. nപുരുഷനോട് ആകർഷണം ഉള്ള പു...  ...        NaN\n",
              "629   @Manikandan Sivan മതത്തിലല്ലടോ nഐൻസ്റ്റീൻ കണ്ട...  ...        NaN\n",
              "488   @rafid pu അവരുടെ ജീവിതം എങ്ങനെയാടോ തകരുന്നേ വീ...  ...        NaN\n",
              "\n",
              "[10 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wkt73boTL0NO",
        "outputId": "f0c2b368-7b43-4792-c0b9-0d0ba0fddd4b"
      },
      "source": [
        "test_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    776\n",
              "Hope_speech        194\n",
              "not-malayalam      101\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ProewaglL0NP"
      },
      "source": [
        "test_df['label'] = le.transform(test_df['label'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GYR2XokSL0NP",
        "outputId": "a26974fb-31db-4dd9-ddf7-069ff3f0039f"
      },
      "source": [
        "test_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    776\n",
              "0    194\n",
              "2    101\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eCCNrKNmL0NQ"
      },
      "source": [
        "### Loading `test_sentences` and `test_labels`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NvBSOGdkL0NR"
      },
      "source": [
        "# Get the lists of sentences and their labels.\r\n",
        "test_sentences = test_df['text'].values\r\n",
        "test_labels = test_df['label'].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fS2UcOiEVuhm"
      },
      "source": [
        "## Handling class imbalance using `sklearn's compute_class_weight`\r\n",
        "\r\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WL4tP_YkI1mY",
        "outputId": "c3752b90-5d50-42cc-968a-7cdb8f0cc82b"
      },
      "source": [
        "\r\n",
        "#compute the class weights\r\n",
        "class_wts = compute_class_weight('balanced', np.unique(train_labels), train_labels)\r\n",
        "\r\n",
        "print(class_wts)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[1.71143086 0.46005909 4.13121081]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "z_WjMTuibsrf"
      },
      "source": [
        "## Helper Functions"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Bef28eHNV-_d"
      },
      "source": [
        "#### 1) Update Interval Function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lBK0ujfEbMir"
      },
      "source": [
        "def good_update_interval(total_iters, num_desired_updates):\r\n",
        "    '''\r\n",
        "    This function will try to pick an intelligent progress update interval \r\n",
        "    based on the magnitude of the total iterations.\r\n",
        "\r\n",
        "    Parameters:\r\n",
        "      `total_iters` - The number of iterations in the for-loop.\r\n",
        "      `num_desired_updates` - How many times we want to see an update over the \r\n",
        "                              course of the for-loop.\r\n",
        "    '''\r\n",
        "    # Divide the total iterations by the desired number of updates. Most likely\r\n",
        "    # this will be some ugly number.\r\n",
        "    exact_interval = total_iters / num_desired_updates\r\n",
        "\r\n",
        "    # The `round` function has the ability to round down a number to, e.g., the\r\n",
        "    # nearest thousandth: round(exact_interval, -3)\r\n",
        "    #\r\n",
        "    # To determine the magnitude to round to, find the magnitude of the total,\r\n",
        "    # and then go one magnitude below that.\r\n",
        "\r\n",
        "    # Get the order of magnitude of the total.\r\n",
        "    order_of_mag = len(str(total_iters)) - 1\r\n",
        "\r\n",
        "    # Our update interval should be rounded to an order of magnitude smaller. \r\n",
        "    round_mag = order_of_mag - 1\r\n",
        "\r\n",
        "    # Round down and cast to an int.\r\n",
        "    update_interval = int(round(exact_interval, -round_mag))\r\n",
        "\r\n",
        "    # Don't allow the interval to be zero!\r\n",
        "    if update_interval == 0:\r\n",
        "        update_interval = 1\r\n",
        "\r\n",
        "    return update_interval"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eMGycwGAWFyO"
      },
      "source": [
        "#### 2) Format time function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "c9zVyNQLm-3q"
      },
      "source": [
        "def format_time(elapsed):\r\n",
        "    '''\r\n",
        "    Takes a time in seconds and returns a string hh:mm:ss\r\n",
        "    '''\r\n",
        "    # Round to the nearest second.\r\n",
        "    elapsed_rounded = int(round((elapsed)))\r\n",
        "    \r\n",
        "    # Format as hh:mm:ss\r\n",
        "    return str(datetime.timedelta(seconds=elapsed_rounded))\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EBAo04ENWw3n"
      },
      "source": [
        "#### 3) Make Smart Batches function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nof-AUeoiZc2"
      },
      "source": [
        "def make_smart_batches(text_samples, labels, batch_size,tokenizer,max_input_length):\r\n",
        "    '''\r\n",
        "    This function combines all of the required steps to prepare batches.\r\n",
        "    '''\r\n",
        "\r\n",
        "    print('Creating Smart Batches from {:,} examples with batch size {:,}...\\n'.format(len(text_samples), batch_size))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #   Tokenize & Truncate\r\n",
        "    # =========================\r\n",
        "\r\n",
        "    full_input_ids = []\r\n",
        "\r\n",
        "    # Tokenize all training examples\r\n",
        "    print('Tokenizing {:,} samples...'.format(len(labels)))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(labels), num_desired_updates=10)\r\n",
        "\r\n",
        "    # For each training example...\r\n",
        "    for text in text_samples:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(full_input_ids) % update_interval) == 0):\r\n",
        "            print('  Tokenized {:,} samples.'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "        # Tokenize the sample.\r\n",
        "        input_ids = tokenizer.encode(text=text,              # Text to encode.\r\n",
        "                                    add_special_tokens=True, # Do add specials.\r\n",
        "                                    max_length=max_input_length,      \r\n",
        "                                    truncation=True,         # Do Truncate!\r\n",
        "                                    padding=False)           # DO NOT pad.\r\n",
        "                                    \r\n",
        "        # Add the tokenized result to our list.\r\n",
        "        full_input_ids.append(input_ids)\r\n",
        "        \r\n",
        "    print('DONE.')\r\n",
        "    print('{:>10,} samples\\n'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #      Select Batches\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    # Sort the two lists together by the length of the input sequence.\r\n",
        "    samples = sorted(zip(full_input_ids, labels), key=lambda x: len(x[0]))\r\n",
        "\r\n",
        "    print('{:>10,} samples after sorting\\n'.format(len(samples)))\r\n",
        "\r\n",
        "    import random\r\n",
        "\r\n",
        "    # List of batches that we'll construct.\r\n",
        "    batch_ordered_sentences = []\r\n",
        "    batch_ordered_labels = []\r\n",
        "\r\n",
        "    print('Creating batches of size {:}...'.format(batch_size))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(samples), num_desired_updates=10)\r\n",
        "    \r\n",
        "    # Loop over all of the input samples...    \r\n",
        "    while len(samples) > 0:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(batch_ordered_sentences) % update_interval) == 0 \\\r\n",
        "            and not len(batch_ordered_sentences) == 0):\r\n",
        "            print('  Selected {:,} batches.'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "        # `to_take` is our actual batch size. It will be `batch_size` until \r\n",
        "        # we get to the last batch, which may be smaller. \r\n",
        "        to_take = min(batch_size, len(samples))\r\n",
        "\r\n",
        "        # Pick a random index in the list of remaining samples to start\r\n",
        "        # our batch at.\r\n",
        "        select = random.randint(0, len(samples) - to_take)\r\n",
        "\r\n",
        "        # Select a contiguous batch of samples starting at `select`.\r\n",
        "        #print(\"Selecting batch from {:} to {:}\".format(select, select+to_take))\r\n",
        "        batch = samples[select:(select + to_take)]\r\n",
        "\r\n",
        "        #print(\"Batch length:\", len(batch))\r\n",
        "\r\n",
        "        # Each sample is a tuple--split them apart to create a separate list of \r\n",
        "        # sequences and a list of labels for this batch.\r\n",
        "        batch_ordered_sentences.append([s[0] for s in batch])\r\n",
        "        batch_ordered_labels.append([s[1] for s in batch])\r\n",
        "\r\n",
        "        # Remove these samples from the list.\r\n",
        "        del samples[select:select + to_take]\r\n",
        "\r\n",
        "    print('\\n  DONE - Selected {:,} batches.\\n'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #        Add Padding\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    print('Padding out sequences within each batch...')\r\n",
        "\r\n",
        "    py_inputs = []\r\n",
        "    py_attn_masks = []\r\n",
        "    py_labels = []\r\n",
        "\r\n",
        "    # For each batch...\r\n",
        "    for (batch_inputs, batch_labels) in zip(batch_ordered_sentences, batch_ordered_labels):\r\n",
        "\r\n",
        "        # New version of the batch, this time with padded sequences and now with\r\n",
        "        # attention masks defined.\r\n",
        "        batch_padded_inputs = []\r\n",
        "        batch_attn_masks = []\r\n",
        "        \r\n",
        "        # First, find the longest sample in the batch. \r\n",
        "        # Note that the sequences do currently include the special tokens!\r\n",
        "        max_size = max([len(sen) for sen in batch_inputs])\r\n",
        "\r\n",
        "        # For each input in this batch...\r\n",
        "        for sen in batch_inputs:\r\n",
        "            \r\n",
        "            # How many pad tokens do we need to add?\r\n",
        "            num_pads = max_size - len(sen)\r\n",
        "\r\n",
        "            # Add `num_pads` padding tokens to the end of the sequence.\r\n",
        "            padded_input = sen + [tokenizer.pad_token_id]*num_pads\r\n",
        "\r\n",
        "            # Define the attention mask--it's just a `1` for every real token\r\n",
        "            # and a `0` for every padding token.\r\n",
        "            attn_mask = [1] * len(sen) + [0] * num_pads\r\n",
        "\r\n",
        "            # Add the padded results to the batch.\r\n",
        "            batch_padded_inputs.append(padded_input)\r\n",
        "            batch_attn_masks.append(attn_mask)\r\n",
        "\r\n",
        "        # Our batch has been padded, so we need to save this updated batch.\r\n",
        "        # We also need the inputs to be PyTorch tensors, so we'll do that here.\r\n",
        "        # Todo - Michael's code specified \"dtype=torch.long\"\r\n",
        "        py_inputs.append(torch.tensor(batch_padded_inputs))\r\n",
        "        py_attn_masks.append(torch.tensor(batch_attn_masks))\r\n",
        "        py_labels.append(torch.tensor(batch_labels))\r\n",
        "    \r\n",
        "    print('  DONE.')\r\n",
        "\r\n",
        "    # Return the smart-batched dataset!\r\n",
        "    return (py_inputs, py_attn_masks, py_labels)\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "d3-BH_94PXsO"
      },
      "source": [
        "### 4) Make Smart Batches On Test Set (Without labels)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ggH8AkAEaV9N"
      },
      "source": [
        "def make_smart_batches_on_test(text_samples, text_ids, batch_size,tokenizer,max_input_length):\r\n",
        "    '''\r\n",
        "    This function combines all of the required steps to prepare batches.\r\n",
        "    '''\r\n",
        "\r\n",
        "    print('Creating Smart Batches from {:,} examples with batch size {:,}...\\n'.format(len(text_samples), batch_size))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #   Tokenize & Truncate\r\n",
        "    # =========================\r\n",
        "\r\n",
        "    full_input_ids = []\r\n",
        "\r\n",
        "    # Tokenize all training examples\r\n",
        "    print('Tokenizing {:,} samples...'.format(len(text_samples)))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(text_samples), num_desired_updates=10)\r\n",
        "\r\n",
        "    # For each training example...\r\n",
        "    for text in text_samples:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(full_input_ids) % update_interval) == 0):\r\n",
        "            print('  Tokenized {:,} samples.'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "        # Tokenize the sample.\r\n",
        "        input_ids = tokenizer.encode(text=text,              # Text to encode.\r\n",
        "                                    add_special_tokens=True, # Do add specials.\r\n",
        "                                    max_length=max_input_length,      \r\n",
        "                                    truncation=True,         # Do Truncate!\r\n",
        "                                    padding=False)           # DO NOT pad.\r\n",
        "                                    \r\n",
        "        # Add the tokenized result to our list.\r\n",
        "        full_input_ids.append(input_ids)\r\n",
        "        \r\n",
        "    print('DONE.')\r\n",
        "    print('{:>10,} samples\\n'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #      Select Batches\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    # Sort the two lists together by the length of the input sequence.\r\n",
        "    samples = sorted(zip(full_input_ids, text_ids), key=lambda x: len(x[0]))\r\n",
        "\r\n",
        "    print('{:>10,} samples after sorting\\n'.format(len(samples)))\r\n",
        "\r\n",
        "    import random\r\n",
        "\r\n",
        "    # List of batches that we'll construct.\r\n",
        "    batch_ordered_sentences = []\r\n",
        "    batch_ordered_ids = []\r\n",
        "\r\n",
        "    print('Creating batches of size {:}...'.format(batch_size))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(samples), num_desired_updates=10)\r\n",
        "    \r\n",
        "    # Loop over all of the input samples...    \r\n",
        "    while len(samples) > 0:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(batch_ordered_sentences) % update_interval) == 0 \\\r\n",
        "            and not len(batch_ordered_sentences) == 0):\r\n",
        "            print('  Selected {:,} batches.'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "        # `to_take` is our actual batch size. It will be `batch_size` until \r\n",
        "        # we get to the last batch, which may be smaller. \r\n",
        "        to_take = min(batch_size, len(samples))\r\n",
        "\r\n",
        "        # Pick a random index in the list of remaining samples to start\r\n",
        "        # our batch at.\r\n",
        "        select = random.randint(0, len(samples) - to_take)\r\n",
        "\r\n",
        "        # Select a contiguous batch of samples starting at `select`.\r\n",
        "        #print(\"Selecting batch from {:} to {:}\".format(select, select+to_take))\r\n",
        "        batch = samples[select:(select + to_take)]\r\n",
        "\r\n",
        "        #print(\"Batch length:\", len(batch))\r\n",
        "\r\n",
        "        # Each sample is a tuple--split them apart to create a separate list of \r\n",
        "        # sequences and a list of labels for this batch.\r\n",
        "        batch_ordered_sentences.append([s[0] for s in batch])\r\n",
        "        batch_ordered_ids.append([s[1] for s in batch])\r\n",
        "\r\n",
        "        # Remove these samples from the list.\r\n",
        "        del samples[select:select + to_take]\r\n",
        "\r\n",
        "    print('\\n  DONE - Selected {:,} batches.\\n'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #        Add Padding\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    print('Padding out sequences within each batch...')\r\n",
        "\r\n",
        "    py_inputs = []\r\n",
        "    py_attn_masks = []\r\n",
        "    py_ids = []\r\n",
        "\r\n",
        "    # For each batch...\r\n",
        "    for (batch_inputs, batch_ids) in zip(batch_ordered_sentences, batch_ordered_ids):\r\n",
        "\r\n",
        "        # New version of the batch, this time with padded sequences and now with\r\n",
        "        # attention masks defined.\r\n",
        "        batch_padded_inputs = []\r\n",
        "        batch_attn_masks = []\r\n",
        "        \r\n",
        "        # First, find the longest sample in the batch. \r\n",
        "        # Note that the sequences do currently include the special tokens!\r\n",
        "        max_size = max([len(sen) for sen in batch_inputs])\r\n",
        "\r\n",
        "        # For each input in this batch...\r\n",
        "        for sen in batch_inputs:\r\n",
        "            \r\n",
        "            # How many pad tokens do we need to add?\r\n",
        "            num_pads = max_size - len(sen)\r\n",
        "\r\n",
        "            # Add `num_pads` padding tokens to the end of the sequence.\r\n",
        "            padded_input = sen + [tokenizer.pad_token_id]*num_pads\r\n",
        "\r\n",
        "            # Define the attention mask--it's just a `1` for every real token\r\n",
        "            # and a `0` for every padding token.\r\n",
        "            attn_mask = [1] * len(sen) + [0] * num_pads\r\n",
        "\r\n",
        "            # Add the padded results to the batch.\r\n",
        "            batch_padded_inputs.append(padded_input)\r\n",
        "            batch_attn_masks.append(attn_mask)\r\n",
        "\r\n",
        "        # Our batch has been padded, so we need to save this updated batch.\r\n",
        "        # We also need the inputs to be PyTorch tensors, so we'll do that here.\r\n",
        "        # Todo - Michael's code specified \"dtype=torch.long\"\r\n",
        "        py_inputs.append(torch.tensor(batch_padded_inputs))\r\n",
        "        py_attn_masks.append(torch.tensor(batch_attn_masks))\r\n",
        "        py_ids.append(torch.tensor(batch_ids))\r\n",
        "    \r\n",
        "    print('  DONE.')\r\n",
        "\r\n",
        "    # Return the smart-batched dataset!\r\n",
        "    return (py_inputs, py_attn_masks, py_ids)\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "sOWk_8lpWO17"
      },
      "source": [
        "### 5) Function for plotting training history"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "R7-FAyfnWM65"
      },
      "source": [
        "def plot_training_history(history):\r\n",
        "  fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(18, 6))\r\n",
        "\r\n",
        "  ax1.plot(history['train_loss'], label='train loss')\r\n",
        "  ax1.plot(history['val_loss'], label='validation loss')\r\n",
        "\r\n",
        "  ax1.xaxis.set_major_locator(MaxNLocator(integer=True))\r\n",
        "  ax1.set_ylim([-0.05, 1.05])\r\n",
        "  ax1.legend()\r\n",
        "  ax1.set_ylabel('Loss')\r\n",
        "  ax1.set_xlabel('Epoch')\r\n",
        "\r\n",
        "  ax2.plot(history['train_acc'], label='train accuracy')\r\n",
        "  ax2.plot(history['val_acc'], label='validation accuracy')\r\n",
        "\r\n",
        "  ax2.xaxis.set_major_locator(MaxNLocator(integer=True))\r\n",
        "  ax2.set_ylim([-0.05, 1.05])\r\n",
        "  ax2.legend()\r\n",
        "\r\n",
        "  ax2.set_ylabel('Accuracy')\r\n",
        "  ax2.set_xlabel('Epoch')\r\n",
        "\r\n",
        "  fig.suptitle('Training history')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "A7QOTORh_JHa"
      },
      "source": [
        "### 6) Function to check accuracy"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yzRDobQ6MwaR"
      },
      "source": [
        "def check_accuracy(predictions,true_labels):\r\n",
        "  # Combine the results across the batches.\r\n",
        "  predictions = np.concatenate(predictions, axis=0)\r\n",
        "  true_labels = np.concatenate(true_labels, axis=0)\r\n",
        "\r\n",
        "  # Choose the label with the highest score as our prediction.\r\n",
        "  preds = np.argmax(predictions, axis=1).flatten()\r\n",
        "\r\n",
        "  # Calculate simple flat accuracy -- number correct over total number.\r\n",
        "  accuracy = (preds == true_labels).mean()\r\n",
        "\r\n",
        "  return accuracy"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "D7TtFkV5_Olz"
      },
      "source": [
        "### 7) Function to evaluate model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TSBNdYHYMA7Q"
      },
      "source": [
        "def eval_model(model,py_inputs, py_attn_masks, py_labels):\r\n",
        "# Prediction on test set\r\n",
        "  t0 = time.time()\r\n",
        "\r\n",
        "  print('Doing validation on {:,} sentences...'.format(len(py_labels)))\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # Tracking variables \r\n",
        "  predictions , true_labels = [], []\r\n",
        "\r\n",
        "  # Choose an interval on which to print progress updates.\r\n",
        "  update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "  # Measure elapsed time.\r\n",
        "  t0 = time.time()\r\n",
        "  total_val_loss = 0\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # For each batch of training data...\r\n",
        "  for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "      # Progress update every 100 batches.\r\n",
        "      if step % update_interval == 0 and not step == 0:\r\n",
        "          # Calculate elapsed time in minutes.\r\n",
        "          elapsed = format_time(time.time() - t0)\r\n",
        "          \r\n",
        "          # Calculate the time remaining based on our progress.\r\n",
        "          steps_per_sec = (time.time() - t0) / step\r\n",
        "          remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "          remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "          # Report progress.\r\n",
        "          print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "      # Copy the batch to the GPU.\r\n",
        "      b_input_ids = py_inputs[step].to(device)\r\n",
        "      b_input_mask = py_attn_masks[step].to(device)\r\n",
        "      b_labels = py_labels[step].to(device)\r\n",
        "    \r\n",
        "      # Telling the model not to compute or store gradients, saving memory and \r\n",
        "      # speeding up prediction\r\n",
        "      with torch.no_grad():\r\n",
        "        output = model(b_input_ids, \r\n",
        "                             token_type_ids=None, \r\n",
        "                             attention_mask=b_input_mask, \r\n",
        "                             labels=b_labels)\r\n",
        "\r\n",
        "\r\n",
        "      logits = output.logits \r\n",
        "      loss = output.loss\r\n",
        "      # Move logits and labels to CPU\r\n",
        "      logits = logits.detach().cpu().numpy()\r\n",
        "      label_ids = b_labels.to('cpu').numpy()\r\n",
        "    \r\n",
        "      # Store predictions and true labels\r\n",
        "      predictions.append(logits)\r\n",
        "      true_labels.append(label_ids)\r\n",
        "\r\n",
        "      total_val_loss += loss.item()\r\n",
        "  \r\n",
        "  val_accuracy = check_accuracy(predictions,true_labels)\r\n",
        "\r\n",
        "  validation_time = format_time(time.time() - t0)\r\n",
        "  \r\n",
        "  # Calculate the average loss over all of the batches.\r\n",
        "  avg_val_loss = total_val_loss / len(py_inputs)     \r\n",
        "    \r\n",
        "\r\n",
        "  # print('Accuracy: {:.3f}'.format(val_accuracy))\r\n",
        "  return (avg_val_loss,val_accuracy,validation_time)\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Lrt_FyJIbC8j"
      },
      "source": [
        "### 8) Function for making predictions on our test dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eylCkH2Zipq5"
      },
      "source": [
        "def get_predictions(py_inputs, py_attn_masks, py_labels):\r\n",
        "\r\n",
        "  print('Predicting labels for {:,} test batches...'.format(len(py_labels)))\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # Tracking variables \r\n",
        "  predictions , true_labels = [], []\r\n",
        "\r\n",
        "  # Choose an interval on which to print progress updates.\r\n",
        "  update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "  # Measure elapsed time.\r\n",
        "  t0 = time.time()\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # For each batch of training data...\r\n",
        "  for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "      # Progress update every 100 batches.\r\n",
        "      if step % update_interval == 0 and not step == 0:\r\n",
        "          # Calculate elapsed time in minutes.\r\n",
        "          elapsed = format_time(time.time() - t0)\r\n",
        "          \r\n",
        "          # Calculate the time remaining based on our progress.\r\n",
        "          steps_per_sec = (time.time() - t0) / step\r\n",
        "          remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "          remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "          # Report progress.\r\n",
        "          print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "      # Copy the batch to the GPU.\r\n",
        "      b_input_ids = py_inputs[step].to(device)\r\n",
        "      b_input_mask = py_attn_masks[step].to(device)\r\n",
        "      b_labels = py_labels[step].to(device)\r\n",
        "    \r\n",
        "      # Telling the model not to compute or store gradients, saving memory and \r\n",
        "      # speeding up prediction\r\n",
        "      with torch.no_grad():\r\n",
        "          # Forward pass, calculate logit predictions\r\n",
        "          outputs = model(b_input_ids, b_input_mask)\r\n",
        "\r\n",
        "      logits = outputs.logits \r\n",
        "\r\n",
        "      # Move logits and labels to CPU\r\n",
        "      logits = logits.detach().cpu().numpy()\r\n",
        "      label_ids = b_labels.to('cpu').numpy()\r\n",
        "    \r\n",
        "      # Store predictions and true labels\r\n",
        "      predictions.append(logits)\r\n",
        "      true_labels.append(label_ids)\r\n",
        "      # Combine the results across the batches.\r\n",
        "  predictions = np.concatenate(predictions, axis=0)\r\n",
        "  true_labels = np.concatenate(true_labels, axis=0)\r\n",
        "\r\n",
        "      # Choose the label with the highest score as our prediction.\r\n",
        "  preds = np.argmax(predictions, axis=1).flatten()\r\n",
        "\r\n",
        "  return (preds,true_labels)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eiRNCS-EbZmy"
      },
      "source": [
        "### 9) Function for making predictions on test dataset(without labels)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RIuwhVSmZvkd"
      },
      "source": [
        "def get_predictions_test(py_inputs, py_attn_masks,py_ids):\r\n",
        "\r\n",
        "  print('Predicting labels for {:,} test batches...'.format(len(py_inputs)))\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # Tracking variables \r\n",
        "  predictions , true_labels ,ids = [], [] , []\r\n",
        "\r\n",
        "  # Choose an interval on which to print progress updates.\r\n",
        "  update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "  # Measure elapsed time.\r\n",
        "  t0 = time.time()\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # For each batch of training data...\r\n",
        "  for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "      # Progress update every 100 batches.\r\n",
        "      if step % update_interval == 0 and not step == 0:\r\n",
        "          # Calculate elapsed time in minutes.\r\n",
        "          elapsed = format_time(time.time() - t0)\r\n",
        "          \r\n",
        "          # Calculate the time remaining based on our progress.\r\n",
        "          steps_per_sec = (time.time() - t0) / step\r\n",
        "          remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "          remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "          # Report progress.\r\n",
        "          print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "      # Copy the batch to the GPU.\r\n",
        "      b_input_ids = py_inputs[step].to(device)\r\n",
        "      b_input_mask = py_attn_masks[step].to(device)\r\n",
        "      b_ids = py_ids[step].to(device)\r\n",
        "    \r\n",
        "      # Telling the model not to compute or store gradients, saving memory and \r\n",
        "      # speeding up prediction\r\n",
        "      with torch.no_grad():\r\n",
        "          # Forward pass, calculate logit predictions\r\n",
        "          outputs = model(b_input_ids, b_input_mask)\r\n",
        "\r\n",
        "      logits = outputs.logits \r\n",
        "\r\n",
        "      # Move logits and labels to CPU\r\n",
        "      logits = logits.detach().cpu().numpy()\r\n",
        "      b_ids = b_ids.detach().cpu().numpy()\r\n",
        "      # Store predictions\r\n",
        "      predictions.append(logits)\r\n",
        "      ids.append(b_ids)\r\n",
        "      # Combine the results across the batches.\r\n",
        "  predictions = np.concatenate(predictions, axis=0)\r\n",
        "  ids = np.concatenate(ids,axis=0)\r\n",
        "  # Choose the label with the highest score as our prediction.\r\n",
        "  preds = np.argmax(predictions, axis=1).flatten()\r\n",
        "\r\n",
        "  return ids,preds"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4IM8r_ddYZZS"
      },
      "source": [
        "### 10) Confusion Matrix Helper Function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DqNaS8SrBox5"
      },
      "source": [
        "def show_confusion_matrix(confusion_matrix, class_names):\r\n",
        "\r\n",
        "  cm = confusion_matrix.copy()\r\n",
        "\r\n",
        "  cell_counts = cm.flatten()\r\n",
        "\r\n",
        "  cm_row_norm = cm / cm.sum(axis=1)[:, np.newaxis]\r\n",
        "\r\n",
        "  row_percentages = [\"{0:.2f}\".format(value) for value in cm_row_norm.flatten()]\r\n",
        "\r\n",
        "  cell_labels = [f\"{cnt}\\n{per}\" for cnt, per in zip(cell_counts, row_percentages)]\r\n",
        "  cell_labels = np.asarray(cell_labels).reshape(cm.shape[0], cm.shape[1])\r\n",
        "\r\n",
        "  df_cm = pd.DataFrame(cm_row_norm, index=class_names, columns=class_names)\r\n",
        "\r\n",
        "  hmap = sns.heatmap(df_cm, annot=cell_labels, fmt=\"\", cmap=\"Blues\")\r\n",
        "  hmap.yaxis.set_ticklabels(hmap.yaxis.get_ticklabels(), rotation=0, ha='right')\r\n",
        "  hmap.xaxis.set_ticklabels(hmap.xaxis.get_ticklabels(), rotation=30, ha='right')\r\n",
        "  plt.ylabel('True Sign')\r\n",
        "  plt.xlabel('Predicted Sign');"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Mfv2faJy3p04"
      },
      "source": [
        "## Loading tokenizer from AutoTokenizer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 131,
          "referenced_widgets": [
            "c0d606ca1a83452aa1ad129ff458e5b5",
            "cd77ea52c87741e79374c62c140b1a8c",
            "0183af8ab28b44a2af3892885c697143",
            "37fe3cbc00a649e1917c02b880b664dd",
            "2319616d96d84559af4fa4276481bccd",
            "4a9ad567270c4cdf8eaab25f9e3e45d2",
            "b98b89b144ba4286b1eb0f3cc3d495ad",
            "2e1a491457394fb08e63a7833310c2c4",
            "f5db80c6872e44ddb53123bf350e8a19",
            "14cfb4558e9a4580bea719fa9d14b3cc",
            "1032f4c7eb30426788e8dfabbd0f1ad7",
            "21482b10c549418d8d73406ee02f3e85",
            "ada21f05a66940f9bdf9e3fbea907815",
            "d63c1e883e2e44a4afe64b300b336af6",
            "cfb4c7dc667548f0af84b918d1ff1feb",
            "61cd194de0fa4fdda80f00f78594051a"
          ]
        },
        "id": "fIlwEvcMb4pb",
        "outputId": "d7ec5860-ade6-4515-c52a-0d48f1eb0e1c"
      },
      "source": [
        "model_name = 'ai4bharat/indic-bert'\r\n",
        "# Load the BERT tokenizer.\r\n",
        "print(f'Loading {model_name} tokenizer...')\r\n",
        "tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Loading ai4bharat/indic-bert tokenizer...\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "c0d606ca1a83452aa1ad129ff458e5b5",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=507.0, style=ProgressStyle(description_…"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "f5db80c6872e44ddb53123bf350e8a19",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=5646064.0, style=ProgressStyle(descript…"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OVs3Jb3Vb89i"
      },
      "source": [
        "## Smart Batching of the training data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cWNt4eOLofmF"
      },
      "source": [
        "lengths = []\r\n",
        "for text in train_sentences:\r\n",
        "  lengths.append(len(text))       "
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "hbdGRA3Bo02O",
        "outputId": "e89f7bf1-370c-403b-f18b-0cf88141f352"
      },
      "source": [
        "\r\n",
        "# Use plot styling from seaborn.\r\n",
        "sns.set(style='darkgrid')\r\n",
        "\r\n",
        "# Increase the plot size and font size.\r\n",
        "sns.set(font_scale=1.5)\r\n",
        "plt.rcParams[\"figure.figsize\"] = (12,6)\r\n",
        "\r\n",
        "plt.scatter(range(0, len(lengths)), lengths, marker=\"|\")\r\n",
        "\r\n",
        "plt.xlabel('Sample Number')\r\n",
        "plt.ylabel('Sequence Length')\r\n",
        "plt.title('Samples BEFORE Tokenizing')\r\n",
        "\r\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9rMhLNhPcZjU"
      },
      "source": [
        "### Tokenizing the sequences"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "t7JsLi3EdEje"
      },
      "source": [
        "max_input_length = 400"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J968o8RJcUEd",
        "outputId": "9738cbf1-1664-4d54-832d-825e1cf7cb6b"
      },
      "source": [
        "full_input_ids = []\r\n",
        "labels = []\r\n",
        "\r\n",
        "# Tokenize all training examples\r\n",
        "print('Tokenizing {:,} training samples...'.format(len(train_sentences)))\r\n",
        "\r\n",
        "# Choose an interval on which to print progress updates.\r\n",
        "update_interval = good_update_interval(total_iters=len(train_sentences), num_desired_updates=10)\r\n",
        "\r\n",
        "# For each training example...\r\n",
        "for text in train_sentences:\r\n",
        "    \r\n",
        "    # Report progress.\r\n",
        "    if ((len(full_input_ids) % update_interval) == 0):\r\n",
        "        print('  Tokenized {:,} samples.'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "    # Tokenize the sentence.\r\n",
        "    input_ids = tokenizer.encode(text=text,           \r\n",
        "                                 add_special_tokens=True, \r\n",
        "                                 max_length=max_input_length,  \r\n",
        "                                 truncation=True,     \r\n",
        "                                 padding=False)       \r\n",
        "                                 \r\n",
        "    # Add the tokenized result to our list.\r\n",
        "    full_input_ids.append(input_ids)\r\n",
        "    \r\n",
        "print('DONE.')\r\n",
        "print('{:>10,} samples'.format(len(full_input_ids)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Tokenizing 8,564 training samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rZzhO2tZeXur"
      },
      "source": [
        "# Get all of the lengths.\r\n",
        "unsorted_lengths = [len(x) for x in full_input_ids]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "x7c_mYuVed_H",
        "outputId": "0790d97c-e73c-4001-9ea1-57f1d051ce97"
      },
      "source": [
        "\r\n",
        "# Use plot styling from seaborn.\r\n",
        "sns.set(style='darkgrid')\r\n",
        "\r\n",
        "# Increase the plot size and font size.\r\n",
        "sns.set(font_scale=1.5)\r\n",
        "plt.rcParams[\"figure.figsize\"] = (12,6)\r\n",
        "\r\n",
        "plt.scatter(range(0, len(unsorted_lengths)), unsorted_lengths, marker=\"|\")\r\n",
        "\r\n",
        "plt.xlabel('Sample Number')\r\n",
        "plt.ylabel('Sequence Length')\r\n",
        "plt.title('Samples BEFORE Sorting')\r\n",
        "\r\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7PaeohUVegmv"
      },
      "source": [
        "# Sort the two lists together by the length of the input sequence.\r\n",
        "train_samples = sorted(zip(full_input_ids, train_labels), key=lambda x: len(x[0]))"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_9nyx-BtepE4",
        "outputId": "36618d50-524c-4ed4-aaec-fb04edf6cc1c"
      },
      "source": [
        "train_samples[0:5]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[([2, 2052, 3], 2),\n",
              " ([2, 11855, 21289, 3], 2),\n",
              " ([2, 2052, 12955, 3], 2),\n",
              " ([2, 85415, 133461, 3], 0),\n",
              " ([2, 11855, 21289, 3], 2)]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 44
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rBxJhEieetFh",
        "outputId": "43eb5893-d2c6-471f-9080-4fdf1eaeac8f"
      },
      "source": [
        "print('Shortest sample:', len(train_samples[0][0]))\r\n",
        "print('Longest sample:', len(train_samples[-1][0]))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Shortest sample: 3\n",
            "Longest sample: 322\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "P44bFOI-e7hW"
      },
      "source": [
        "# Get the new list of lengths after sorting.\r\n",
        "sorted_lengths = [len(s[0]) for s in train_samples]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "9P5ZX99le_G1",
        "outputId": "0ad5b077-76a6-481a-b563-2b877eafc332"
      },
      "source": [
        "\r\n",
        "plt.plot(range(0, len(sorted_lengths)), sorted_lengths)\r\n",
        "\r\n",
        "plt.xlabel('Sample Number')\r\n",
        "plt.ylabel('Sequence Length')\r\n",
        "plt.title('Samples after Sorting')\r\n",
        "\r\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Eh1z0xugfF2t"
      },
      "source": [
        "### Random Batch Selections"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gPrYkFMcgm5H",
        "outputId": "24f41e76-4ec8-4d8b-9d4c-56f1cce42cdf"
      },
      "source": [
        "train_samples[0]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "([2, 2052, 3], 2)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 48
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "isMxwgezfAvO"
      },
      "source": [
        "batch_size = 16"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "s0tjD8pIfJ0S",
        "outputId": "0098c5f1-8f99-42d6-bade-c86a1098b97a"
      },
      "source": [
        "# List of batches that we'll construct.\r\n",
        "batch_ordered_sentences = []\r\n",
        "batch_ordered_labels = []\r\n",
        "\r\n",
        "print('Creating training batches of size {:}'.format(batch_size))\r\n",
        "\r\n",
        "# Loop over all of the input samples...    \r\n",
        "while len(train_samples) > 0:\r\n",
        "    \r\n",
        "    # Report progress.\r\n",
        "    if ((len(batch_ordered_sentences) % 100) == 0):\r\n",
        "        print('  Selected {:,} batches.'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "    # `to_take` is our actual batch size. It will be `batch_size` until \r\n",
        "    # we get to the last batch, which may be smaller. \r\n",
        "    to_take = min(batch_size, len(train_samples))\r\n",
        "\r\n",
        "    # Pick a random index in the list of remaining samples to start\r\n",
        "    # our batch at.\r\n",
        "    select = random.randint(0, len(train_samples) - to_take)\r\n",
        "\r\n",
        "    # Select a contiguous batch of samples starting at `select`.\r\n",
        "    batch = train_samples[select:(select + to_take)]\r\n",
        "\r\n",
        "    # Each sample is a tuple--split them apart to create a separate list of \r\n",
        "    # sequences and a list of labels for this batch.\r\n",
        "    batch_ordered_sentences.append([s[0] for s in batch])\r\n",
        "    batch_ordered_labels.append([s[1] for s in batch])\r\n",
        "\r\n",
        "    # Remove these samples from the list.\r\n",
        "    del train_samples[select:select + to_take]\r\n",
        "\r\n",
        "print('\\n  DONE - {:,} batches.'.format(len(batch_ordered_sentences)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating training batches of size 16\n",
            "  Selected 0 batches.\n",
            "  Selected 100 batches.\n",
            "  Selected 200 batches.\n",
            "  Selected 300 batches.\n",
            "  Selected 400 batches.\n",
            "  Selected 500 batches.\n",
            "\n",
            "  DONE - 536 batches.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rf91Dd3LhBaP",
        "outputId": "247e69dd-f559-4fe5-fd68-57b66a291347"
      },
      "source": [
        "print(batch_ordered_sentences[0])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[2, 1514, 91022, 6631, 913, 115770, 239, 51280, 9, 411, 183965, 3], [2, 2611, 7357, 17302, 91647, 104542, 19249, 4899, 33954, 19062, 50909, 3], [2, 131761, 2545, 8, 130031, 24053, 9067, 5060, 46046, 27738, 11226, 3], [2, 41951, 9, 91364, 73773, 33025, 4984, 67663, 68716, 195599, 840, 3], [2, 8, 157265, 9, 8, 14830, 14830, 9, 8, 171562, 136256, 3], [2, 92291, 514, 64242, 3628, 93417, 112363, 13743, 71618, 71618, 244, 3], [2, 27393, 53972, 91438, 28582, 861, 9218, 5366, 124834, 9, 5, 3], [2, 14035, 7418, 33, 57729, 389, 23150, 106438, 85195, 9089, 840, 3], [2, 8, 142798, 175527, 27738, 4207, 87730, 25129, 2338, 8, 38845, 3], [2, 8, 196358, 4659, 4707, 5173, 51722, 75928, 739, 121683, 192199, 3], [2, 8, 196358, 4659, 4707, 5173, 51722, 75928, 10391, 17302, 192199, 3], [2, 2611, 8101, 26427, 116744, 15702, 146537, 61415, 3628, 24659, 90772, 3], [2, 2441, 10889, 22682, 51280, 85415, 840, 445, 92307, 22684, 840, 3], [2, 138216, 4791, 121059, 24053, 1848, 120905, 11855, 33, 13867, 88345, 3], [2, 8, 174312, 97305, 9472, 8, 134467, 2464, 54, 104456, 52948, 3], [2, 82809, 4360, 8496, 8496, 8613, 8496, 92904, 62986, 80039, 1, 3]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qmkQK_gVgiTu",
        "outputId": "cf8c350d-b482-4a1c-b112-1166fe7feafe"
      },
      "source": [
        "batch_ordered_labels[0]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 52
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xZ0TFA8Mfn6m"
      },
      "source": [
        "### Padding"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "c9rdswcpfTip"
      },
      "source": [
        "py_inputs = []\r\n",
        "py_attn_masks = []\r\n",
        "py_labels = []\r\n",
        "\r\n",
        "# For each batch...\r\n",
        "for (batch_inputs, batch_labels) in zip(batch_ordered_sentences, batch_ordered_labels):\r\n",
        "\r\n",
        "    # New version of the batch, this time with padded sequences and now with\r\n",
        "    # attention masks defined.\r\n",
        "    batch_padded_inputs = []\r\n",
        "    batch_attn_masks = []\r\n",
        "    \r\n",
        "    # First, find the longest sample in the batch. \r\n",
        "    # Note that the sequences do currently include the special tokens!\r\n",
        "    max_size = max([len(sen) for sen in batch_inputs])\r\n",
        "\r\n",
        "    #print('Max size:', max_size)\r\n",
        "\r\n",
        "    # For each input in this batch...\r\n",
        "    for sen in batch_inputs:\r\n",
        "        \r\n",
        "        # How many pad tokens do we need to add?\r\n",
        "        num_pads = max_size - len(sen)\r\n",
        "\r\n",
        "        # Add `num_pads` padding tokens to the end of the sequence.\r\n",
        "        padded_input = sen + [tokenizer.pad_token_id]*num_pads\r\n",
        "\r\n",
        "        # Define the attention mask--it's just a `1` for every real token\r\n",
        "        # and a `0` for every padding token.\r\n",
        "        attn_mask = [1] * len(sen) + [0] * num_pads\r\n",
        "\r\n",
        "        # Add the padded results to the batch.\r\n",
        "        batch_padded_inputs.append(padded_input)\r\n",
        "        batch_attn_masks.append(attn_mask)\r\n",
        "\r\n",
        "    # Our batch has been padded, so we need to save this updated batch.\r\n",
        "    # We also need the inputs to be PyTorch tensors, so we'll do that here.\r\n",
        "    py_inputs.append(torch.tensor(batch_padded_inputs))\r\n",
        "    py_attn_masks.append(torch.tensor(batch_attn_masks))\r\n",
        "    py_labels.append(torch.tensor(batch_labels))\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "roS5lLWdX-5J"
      },
      "source": [
        "### Check the number of token reductions because of smart batching"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wlh7cteVfroV",
        "outputId": "75cf2469-a00f-42fe-f1ff-18ca433f925a"
      },
      "source": [
        "# Get the new list of lengths after sorting.\r\n",
        "\r\n",
        "padded_lengths = []\r\n",
        "\r\n",
        "# For each batch...\r\n",
        "for batch in py_inputs:\r\n",
        "    \r\n",
        "    # For each sample...\r\n",
        "    for s in batch:\r\n",
        "    \r\n",
        "        # Record its length.\r\n",
        "        padded_lengths.append(len(s))\r\n",
        "\r\n",
        "# Sum up the lengths to the get the total number of tokens after smart batching.\r\n",
        "smart_token_count = np.sum(padded_lengths)\r\n",
        "\r\n",
        "# To get the total number of tokens in the dataset using fixed padding, it's\r\n",
        "# as simple as the number of samples times our `max_len` parameter (that we\r\n",
        "# would pad everything to).\r\n",
        "fixed_token_count = len(train_sentences) * max_input_length\r\n",
        "\r\n",
        "# Calculate the percentage reduction.\r\n",
        "prcnt_reduced = (fixed_token_count - smart_token_count) / float(fixed_token_count) \r\n",
        "\r\n",
        "print('Total tokens:')\r\n",
        "print('   Fixed Padding: {:,}'.format(fixed_token_count))\r\n",
        "print('  Smart Batching: {:,}  ({:.1%} less)'.format(smart_token_count, prcnt_reduced))\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Total tokens:\n",
            "   Fixed Padding: 3,425,600\n",
            "  Smart Batching: 281,460  (91.8% less)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8wgdhsI-YIAL"
      },
      "source": [
        "## Load the model configuration from the transformers library using AutoConfig"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9er7EHvdfudf",
        "outputId": "65d7683a-a26c-4ed7-9543-b0faf1ce56c9"
      },
      "source": [
        "# Load the Config object, with an output configured for classification.\r\n",
        "config = AutoConfig.from_pretrained(pretrained_model_name_or_path=model_name,\r\n",
        "                                    num_labels=len(class_names))\r\n",
        "\r\n",
        "print('Config type:', str(type(config)), '\\n')\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Config type: <class 'transformers.models.albert.configuration_albert.AlbertConfig'> \n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 170,
          "referenced_widgets": [
            "1a8c70d58c9f408a9c8a3e85b4925967",
            "e2490ef98f6b4bbe83772eeef9442d0a",
            "7792da63cc2547479a9bc74064acf35f",
            "cc5f4445dcf3415399413b1594aad904",
            "dae9c865e716406c9ffc9034c91cc1b6",
            "43a94a8d30674e899ddc4b77752982a5",
            "cdb0dcca44e24b6cafc5e1b611d0f919",
            "cb970d5806224031ab7b5ab97c2a9a58"
          ]
        },
        "id": "bWvc9Ikv4HtD",
        "outputId": "6814016a-b41c-40bd-c3b8-702f31c2917e"
      },
      "source": [
        "model = AutoModelForSequenceClassification.from_pretrained(pretrained_model_name_or_path=model_name,config = config)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "1a8c70d58c9f408a9c8a3e85b4925967",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=134982446.0, style=ProgressStyle(descri…"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Some weights of the model checkpoint at ai4bharat/indic-bert were not used when initializing AlbertForSequenceClassification: ['predictions.bias', 'predictions.LayerNorm.weight', 'predictions.LayerNorm.bias', 'predictions.dense.weight', 'predictions.dense.bias', 'predictions.decoder.weight', 'predictions.decoder.bias', 'sop_classifier.classifier.weight', 'sop_classifier.classifier.bias']\n",
            "- This IS expected if you are initializing AlbertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing AlbertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "Some weights of AlbertForSequenceClassification were not initialized from the model checkpoint at ai4bharat/indic-bert and are newly initialized: ['classifier.weight', 'classifier.bias']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Xouf5M2B55ei",
        "outputId": "b2abed4d-9ea4-444a-d5b0-195f4720969a"
      },
      "source": [
        "model.cuda()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "AlbertForSequenceClassification(\n",
              "  (albert): AlbertModel(\n",
              "    (embeddings): AlbertEmbeddings(\n",
              "      (word_embeddings): Embedding(200000, 128, padding_idx=0)\n",
              "      (position_embeddings): Embedding(512, 128)\n",
              "      (token_type_embeddings): Embedding(2, 128)\n",
              "      (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)\n",
              "      (dropout): Dropout(p=0, inplace=False)\n",
              "    )\n",
              "    (encoder): AlbertTransformer(\n",
              "      (embedding_hidden_mapping_in): Linear(in_features=128, out_features=768, bias=True)\n",
              "      (albert_layer_groups): ModuleList(\n",
              "        (0): AlbertLayerGroup(\n",
              "          (albert_layers): ModuleList(\n",
              "            (0): AlbertLayer(\n",
              "              (full_layer_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (attention): AlbertAttention(\n",
              "                (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "                (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "                (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "                (attention_dropout): Dropout(p=0, inplace=False)\n",
              "                (output_dropout): Dropout(p=0, inplace=False)\n",
              "                (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              )\n",
              "              (ffn): Linear(in_features=768, out_features=3072, bias=True)\n",
              "              (ffn_output): Linear(in_features=3072, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0, inplace=False)\n",
              "            )\n",
              "          )\n",
              "        )\n",
              "      )\n",
              "    )\n",
              "    (pooler): Linear(in_features=768, out_features=768, bias=True)\n",
              "    (pooler_activation): Tanh()\n",
              "  )\n",
              "  (dropout): Dropout(p=0.1, inplace=False)\n",
              "  (classifier): Linear(in_features=768, out_features=3, bias=True)\n",
              ")"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 57
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SXJHBVlxYR-l"
      },
      "source": [
        "## Load the model from the transformers library using AutoModel"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "n8J4r6KyhveR"
      },
      "source": [
        "# # Load the pre-trained model for classification, passing in the `config` from\r\n",
        "# # above.\r\n",
        "# bert = AutoModel.from_pretrained(\r\n",
        "#     pretrained_model_name_or_path=model_name,\r\n",
        "#     config=config)\r\n",
        "\r\n",
        "# print('\\nModel type:', str(type(bert)))\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RcFMgf5EuPAF"
      },
      "source": [
        "# # freeze all the parameters\r\n",
        "# for param in bert.parameters():\r\n",
        "#     param.requires_grad = False"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NS_-0rBDYeY5"
      },
      "source": [
        "## Creating a custom BERT model "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bmGtZwykJ39i"
      },
      "source": [
        "\r\n",
        "# class BERT_Model(nn.Module):\r\n",
        "#     ## defining the constructor for the class\r\n",
        "#     def __init__(self, bert,num_labels):\r\n",
        "#       ## calling the super class constructor\r\n",
        "#       super(BERT_Model, self).__init__()\r\n",
        "#       ## adding the bert layer to the model\r\n",
        "#       self.bert = bert        \r\n",
        "#       # relu activation function\r\n",
        "#       self.relu =  nn.ReLU()\r\n",
        "#       # adding a dense layer to our custom model\r\n",
        "#       self.fc1 = nn.Linear(768,512)\r\n",
        "#       # adding another dense layer to our custom model ,i.e., the Output layer\r\n",
        "#       self.fc2 = nn.Linear(512,num_labels)\r\n",
        "#       # adding a softmax  activation function for our custom model's output layer\r\n",
        "#       self.softmax = nn.LogSoftmax(dim=1)\r\n",
        "\r\n",
        "#     #defining the forward pass\r\n",
        "#     def forward(self, input_id, mask):\r\n",
        "#       #pass the inputs to the model  \r\n",
        "#       outputs = self.bert(input_id,mask)\r\n",
        "  \r\n",
        "#       last_hidden_state = outputs.last_hidden_state       ## last hidden state from the model\r\n",
        "#       pooler_output = outputs.pooler_output               ## pooler output from the model\r\n",
        "#       ## adding a fully connected layer to the BERT model\r\n",
        "#       x = self.fc1(pooler_output)\r\n",
        "#       ## applying relu activation function\r\n",
        "#       x = self.relu(x)\r\n",
        "#       # the final output layer\r\n",
        "#       x = self.fc2(x)\r\n",
        "#       # apply softmax activation to our output layer\r\n",
        "#       x = self.softmax(x)\r\n",
        "\r\n",
        "#       return x"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jvOs0G5sh02S"
      },
      "source": [
        "\r\n",
        "\r\n",
        "# print('\\nLoading model ...')\r\n",
        "# # pass the pre-trained BERT to our define architecture\r\n",
        "# model = BERT_Model(bert,num_labels=3)\r\n",
        "\r\n",
        "# model.cuda()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LjQSUqCWJTbI"
      },
      "source": [
        "## Custom Loss function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iOHVl1RRJSUB"
      },
      "source": [
        "# # convert class weights to tensor\r\n",
        "# weights= torch.tensor(class_wts,dtype=torch.float)\r\n",
        "# weights = weights.to(device)\r\n",
        "\r\n",
        "# # loss function\r\n",
        "# cross_entropy  = nn.NLLLoss(weight=weights) \r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "evYV0yrQ2u_b"
      },
      "source": [
        "## Loading Optimizer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8tAijXBEh7t8"
      },
      "source": [
        "# Note: AdamW is a class from the huggingface library (as opposed to pytorch) \r\n",
        "# I believe the 'W' stands for 'Weight Decay fix\"\r\n",
        "optimizer = AdamW(model.parameters(),\r\n",
        "                  lr = 2e-5, # This is the value Michael used.\r\n",
        "                  eps = 1e-8 # args.adam_epsilon  - default is 1e-8.\r\n",
        "                )\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "s9n3_5jI2ywo"
      },
      "source": [
        "## Loading lr scheduler"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "agidP6D6iBFI"
      },
      "source": [
        "# Number of training epochs. I chose to train for 1 simply because the training\r\n",
        "# time is long. More epochs may improve the model's accuracy.\r\n",
        "epochs = 4\r\n",
        "\r\n",
        "# Total number of training steps is [number of batches] x [number of epochs]. \r\n",
        "# Note that it's the number of *batches*, not *samples*!\r\n",
        "total_steps = len(py_inputs) * epochs\r\n",
        "\r\n",
        "# Create the learning rate scheduler.\r\n",
        "scheduler = get_linear_schedule_with_warmup(optimizer, \r\n",
        "                                            num_warmup_steps = 0, # Default value in run_glue.py\r\n",
        "                                            num_training_steps = total_steps)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MDDp05Cm245e"
      },
      "source": [
        "## Training Loop"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "H4ERR8fBiEJn",
        "outputId": "6a9632bf-e99f-4139-b9ed-a4e92023d3b6"
      },
      "source": [
        "# We'll store a number of quantities such as training and validation loss, \r\n",
        "# validation accuracy, and timings.\r\n",
        "training_stats = {\r\n",
        "    'epoch':[],\r\n",
        "    'train_loss':[],\r\n",
        "    'Training Time':[],\r\n",
        "    'val_loss':[],\r\n",
        "    'Validation Time':[],\r\n",
        "    'train_acc':[],\r\n",
        "    'val_acc':[]\r\n",
        "}\r\n",
        "\r\n",
        "# Update every `update_interval` batches.\r\n",
        "update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "# Measure the total training time for the whole run.\r\n",
        "total_t0 = time.time()\r\n",
        "best_accuracy = 0\r\n",
        "# For each epoch...\r\n",
        "for epoch_i in range(0, epochs):\r\n",
        "\r\n",
        "    predictions = []\r\n",
        "    true_labels = []\r\n",
        "    \r\n",
        "    # ========================================\r\n",
        "    #               Training\r\n",
        "    # ========================================\r\n",
        "    \r\n",
        "    # Perform one full pass over the training set.\r\n",
        "\r\n",
        "    print(\"\")\r\n",
        "    print('======== Epoch {:} / {:} ========'.format(epoch_i + 1, epochs))\r\n",
        "    \r\n",
        "    # At the start of each epoch (except for the first) we need to re-randomize\r\n",
        "    # our training data.\r\n",
        "    if epoch_i > 0:\r\n",
        "        # Use our `make_smart_batches` function (from 6.1.) to re-shuffle the \r\n",
        "        # dataset into new batches.\r\n",
        "        (py_inputs, py_attn_masks, py_labels) = make_smart_batches(train_sentences, train_labels, batch_size,tokenizer,max_input_length)\r\n",
        "    \r\n",
        "    print('Training on {:,} batches...'.format(len(py_inputs)))\r\n",
        "\r\n",
        "    # Measure how long the training epoch takes.\r\n",
        "    t0 = time.time()\r\n",
        "\r\n",
        "    # Reset the total loss for this epoch.\r\n",
        "    total_train_loss = 0\r\n",
        "\r\n",
        "    # Put the model into training mode. Don't be mislead--the call to \r\n",
        "    # `train` just changes the *mode*, it doesn't *perform* the training.\r\n",
        "    # `dropout` and `batchnorm` layers behave differently during training\r\n",
        "    # vs. test (source: https://stackoverflow.com/questions/51433378/what-does-model-train-do-in-pytorch)\r\n",
        "    model.train()\r\n",
        "\r\n",
        "    # For each batch of training data...\r\n",
        "    for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "        # Progress update every, e.g., 100 batches.\r\n",
        "        if step % update_interval == 0 and not step == 0:\r\n",
        "            # Calculate elapsed time in minutes.\r\n",
        "            elapsed = format_time(time.time() - t0)\r\n",
        "            \r\n",
        "            # Calculate the time remaining based on our progress.\r\n",
        "            steps_per_sec = (time.time() - t0) / step\r\n",
        "            remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "            remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "            # Report progress.\r\n",
        "            print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "        # Copy the current training batch to the GPU using the `to` method.\r\n",
        "        b_input_ids = py_inputs[step].to(device)\r\n",
        "        b_input_mask = py_attn_masks[step].to(device)\r\n",
        "        b_labels = py_labels[step].to(device)\r\n",
        "\r\n",
        "        # Always clear any previously calculated gradients before performing a\r\n",
        "        # backward pass.\r\n",
        "        model.zero_grad()        \r\n",
        "\r\n",
        "        # Perform a forward pass (evaluate the model on this training batch).\r\n",
        "        # The call returns the loss (because we provided labels) and the \r\n",
        "        # \"logits\"--the model outputs prior to activation.\r\n",
        "        output = model(b_input_ids, \r\n",
        "                             token_type_ids=None, \r\n",
        "                             attention_mask=b_input_mask, \r\n",
        "                             labels=b_labels)\r\n",
        "\r\n",
        "        # Accumulate the training loss over all of the batches so that we can\r\n",
        "        # calculate the average loss at the end. `loss` is a Tensor containing a\r\n",
        "        # single value; the `.item()` function just returns the Python value \r\n",
        "        # from the tensor.\r\n",
        "        loss = output.loss \r\n",
        "        logits = output.logits\r\n",
        "\r\n",
        "        # Move logits and labels to CPU\r\n",
        "        logits = logits.detach().cpu().numpy()\r\n",
        "        label_ids = b_labels.to('cpu').numpy()\r\n",
        "      \r\n",
        "        # Store predictions and true labels\r\n",
        "        predictions.append(logits)\r\n",
        "        true_labels.append(label_ids)\r\n",
        "        \r\n",
        "        # Accumulate the training loss over all of the batches so that we can\r\n",
        "        # calculate the average loss at the end. `loss` is a Tensor containing a\r\n",
        "        # single value; the `.item()` function just returns the Python value \r\n",
        "        # from the tensor.\r\n",
        "        total_train_loss += loss.item()\r\n",
        "\r\n",
        "        # Perform a backward pass to calculate the gradients.\r\n",
        "        loss.backward()\r\n",
        "\r\n",
        "        # Clip the norm of the gradients to 1.0.\r\n",
        "        # This is to help prevent the \"exploding gradients\" problem.\r\n",
        "        torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)\r\n",
        "\r\n",
        "        # Update parameters and take a step using the computed gradient.\r\n",
        "        # The optimizer dictates the \"update rule\"--how the parameters are\r\n",
        "        # modified based on their gradients, the learning rate, etc.\r\n",
        "        optimizer.step()\r\n",
        "\r\n",
        "        # Update the learning rate.\r\n",
        "        scheduler.step()\r\n",
        "\r\n",
        "    # Calculate the average loss over all of the batches.\r\n",
        "    avg_train_loss = total_train_loss / len(py_inputs)     \r\n",
        "       \r\n",
        "    training_accuracy = check_accuracy(predictions,true_labels)       \r\n",
        "    \r\n",
        "    # Measure how long this epoch took.\r\n",
        "    training_time = format_time(time.time() - t0)\r\n",
        "\r\n",
        "    print(\"\")\r\n",
        "    print(\"  Average training loss: {0:.2f}\".format(avg_train_loss))\r\n",
        "    print(\"  Training Accuracy: {0:.2f}\".format(training_accuracy))\r\n",
        "    print(\"  Training epoch took: {:}\".format(training_time))\r\n",
        "        \r\n",
        "    (py_inputs, py_attn_masks, py_labels) = make_smart_batches(val_sentences, val_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "    val_loss,val_accuracy,validation_time = eval_model(model,py_inputs, py_attn_masks, py_labels)  \r\n",
        "\r\n",
        "    if val_accuracy > best_accuracy:\r\n",
        "        torch.save(model.state_dict(), 'best_model_state.bin')\r\n",
        "        best_accuracy = val_accuracy\r\n",
        "    # Record all statistics from this epoch.\r\n",
        "\r\n",
        "    print(\"\")\r\n",
        "    print(\"  Average validation loss: {0:.2f}\".format(val_loss))\r\n",
        "    print(\"  Validation Accuracy: {0:.2f}\".format(val_accuracy))\r\n",
        "    print(\"  Validation epoch took: {:}\".format(validation_time))\r\n",
        "    \r\n",
        "    \r\n",
        "    training_stats['epoch'].append(epoch_i + 1)\r\n",
        "    training_stats['train_loss'].append(avg_train_loss)\r\n",
        "    training_stats['Training Time'].append(training_time)\r\n",
        "    training_stats['val_loss'].append(val_loss)\r\n",
        "    training_stats['Validation Time'].append(validation_time)\r\n",
        "    training_stats['train_acc'].append(training_accuracy)\r\n",
        "    training_stats['val_acc'].append(val_accuracy)\r\n",
        "\r\n",
        "print(f'Best val accuracy: {best_accuracy}')\r\n",
        "  \r\n",
        "model.load_state_dict(torch.load('best_model_state.bin'))\r\n",
        "\r\n",
        "print(\"\")\r\n",
        "print(\"Training complete!\")\r\n",
        "\r\n",
        "print(\"Total training took {:} (h:mm:ss)\".format(format_time(time.time()-total_t0)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "======== Epoch 1 / 4 ========\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:03.  Remaining: 0:00:32\n",
            "  Batch     100  of      536.    Elapsed: 0:00:06.  Remaining: 0:00:28\n",
            "  Batch     150  of      536.    Elapsed: 0:00:10.  Remaining: 0:00:26\n",
            "  Batch     200  of      536.    Elapsed: 0:00:13.  Remaining: 0:00:23\n",
            "  Batch     250  of      536.    Elapsed: 0:00:17.  Remaining: 0:00:19\n",
            "  Batch     300  of      536.    Elapsed: 0:00:20.  Remaining: 0:00:16\n",
            "  Batch     350  of      536.    Elapsed: 0:00:23.  Remaining: 0:00:12\n",
            "  Batch     400  of      536.    Elapsed: 0:00:27.  Remaining: 0:00:09\n",
            "  Batch     450  of      536.    Elapsed: 0:00:30.  Remaining: 0:00:06\n",
            "  Batch     500  of      536.    Elapsed: 0:00:33.  Remaining: 0:00:02\n",
            "\n",
            "  Average training loss: 0.60\n",
            "  Training Accuracy: 0.75\n",
            "  Training epoch took: 0:00:36\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.53\n",
            "  Validation Accuracy: 0.76\n",
            "  Validation epoch took: 0:00:02\n",
            "\n",
            "======== Epoch 2 / 4 ========\n",
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:03.  Remaining: 0:00:33\n",
            "  Batch     100  of      536.    Elapsed: 0:00:07.  Remaining: 0:00:30\n",
            "  Batch     150  of      536.    Elapsed: 0:00:10.  Remaining: 0:00:26\n",
            "  Batch     200  of      536.    Elapsed: 0:00:13.  Remaining: 0:00:22\n",
            "  Batch     250  of      536.    Elapsed: 0:00:17.  Remaining: 0:00:19\n",
            "  Batch     300  of      536.    Elapsed: 0:00:20.  Remaining: 0:00:16\n",
            "  Batch     350  of      536.    Elapsed: 0:00:23.  Remaining: 0:00:12\n",
            "  Batch     400  of      536.    Elapsed: 0:00:26.  Remaining: 0:00:09\n",
            "  Batch     450  of      536.    Elapsed: 0:00:29.  Remaining: 0:00:06\n",
            "  Batch     500  of      536.    Elapsed: 0:00:33.  Remaining: 0:00:02\n",
            "\n",
            "  Average training loss: 0.46\n",
            "  Training Accuracy: 0.81\n",
            "  Training epoch took: 0:00:36\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.50\n",
            "  Validation Accuracy: 0.83\n",
            "  Validation epoch took: 0:00:02\n",
            "\n",
            "======== Epoch 3 / 4 ========\n",
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:03.  Remaining: 0:00:28\n",
            "  Batch     100  of      536.    Elapsed: 0:00:07.  Remaining: 0:00:28\n",
            "  Batch     150  of      536.    Elapsed: 0:00:10.  Remaining: 0:00:26\n",
            "  Batch     200  of      536.    Elapsed: 0:00:13.  Remaining: 0:00:22\n",
            "  Batch     250  of      536.    Elapsed: 0:00:16.  Remaining: 0:00:19\n",
            "  Batch     300  of      536.    Elapsed: 0:00:20.  Remaining: 0:00:16\n",
            "  Batch     350  of      536.    Elapsed: 0:00:23.  Remaining: 0:00:12\n",
            "  Batch     400  of      536.    Elapsed: 0:00:26.  Remaining: 0:00:09\n",
            "  Batch     450  of      536.    Elapsed: 0:00:30.  Remaining: 0:00:06\n",
            "  Batch     500  of      536.    Elapsed: 0:00:33.  Remaining: 0:00:02\n",
            "\n",
            "  Average training loss: 0.37\n",
            "  Training Accuracy: 0.87\n",
            "  Training epoch took: 0:00:36\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.52\n",
            "  Validation Accuracy: 0.81\n",
            "  Validation epoch took: 0:00:02\n",
            "\n",
            "======== Epoch 4 / 4 ========\n",
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:03.  Remaining: 0:00:34\n",
            "  Batch     100  of      536.    Elapsed: 0:00:07.  Remaining: 0:00:30\n",
            "  Batch     150  of      536.    Elapsed: 0:00:10.  Remaining: 0:00:27\n",
            "  Batch     200  of      536.    Elapsed: 0:00:13.  Remaining: 0:00:22\n",
            "  Batch     250  of      536.    Elapsed: 0:00:17.  Remaining: 0:00:19\n",
            "  Batch     300  of      536.    Elapsed: 0:00:20.  Remaining: 0:00:16\n",
            "  Batch     350  of      536.    Elapsed: 0:00:23.  Remaining: 0:00:12\n",
            "  Batch     400  of      536.    Elapsed: 0:00:27.  Remaining: 0:00:09\n",
            "  Batch     450  of      536.    Elapsed: 0:00:30.  Remaining: 0:00:06\n",
            "  Batch     500  of      536.    Elapsed: 0:00:33.  Remaining: 0:00:02\n",
            "\n",
            "  Average training loss: 0.30\n",
            "  Training Accuracy: 0.90\n",
            "  Training epoch took: 0:00:36\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.53\n",
            "  Validation Accuracy: 0.82\n",
            "  Validation epoch took: 0:00:02\n",
            "Best val accuracy: 0.8261682242990654\n",
            "\n",
            "Training complete!\n",
            "Total training took 0:02:39 (h:mm:ss)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 450
        },
        "id": "GOmua_S1eXNM",
        "outputId": "6c6b831d-0d6e-4b66-e60c-de98f2fddfb4"
      },
      "source": [
        "plot_training_history(training_stats)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1296x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "3c-6bOIxVyrM"
      },
      "source": [
        "## Evaluating Performance Over Training Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2QmKPNAeWHkZ",
        "outputId": "93c1c23c-ffab-4a15-8b22-22d692177e86"
      },
      "source": [
        "(py_inputs, py_attn_masks, py_labels) = make_smart_batches(train_sentences, train_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "\r\n",
        "y_pred , y_true = get_predictions(py_inputs, py_attn_masks, py_labels)\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 536 test batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:01.  Remaining: 0:00:10\n",
            "  Batch     100  of      536.    Elapsed: 0:00:02.  Remaining: 0:00:09\n",
            "  Batch     150  of      536.    Elapsed: 0:00:03.  Remaining: 0:00:08\n",
            "  Batch     200  of      536.    Elapsed: 0:00:04.  Remaining: 0:00:07\n",
            "  Batch     250  of      536.    Elapsed: 0:00:05.  Remaining: 0:00:06\n",
            "  Batch     300  of      536.    Elapsed: 0:00:06.  Remaining: 0:00:05\n",
            "  Batch     350  of      536.    Elapsed: 0:00:07.  Remaining: 0:00:04\n",
            "  Batch     400  of      536.    Elapsed: 0:00:08.  Remaining: 0:00:03\n",
            "  Batch     450  of      536.    Elapsed: 0:00:09.  Remaining: 0:00:02\n",
            "  Batch     500  of      536.    Elapsed: 0:00:10.  Remaining: 0:00:01\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uXsVn0wngZhv",
        "outputId": "7dfef202-8bff-40a4-e996-c8a0228c86ef"
      },
      "source": [
        "print(classification_report(y_true, y_pred, target_names=class_names))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "                 precision    recall  f1-score   support\n",
            "\n",
            "    Hope_speech       0.81      0.62      0.70      1668\n",
            "Non_hope_speech       0.87      0.96      0.92      6205\n",
            "  not-malayalam       0.91      0.60      0.72       691\n",
            "\n",
            "       accuracy                           0.87      8564\n",
            "      macro avg       0.86      0.73      0.78      8564\n",
            "   weighted avg       0.86      0.87      0.86      8564\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 479
        },
        "id": "guClUdRhYPql",
        "outputId": "e76dbd4a-70cf-47f3-990b-caf316e774e7"
      },
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\r\n",
        "show_confusion_matrix(cm, class_names)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VM2N-X1tV3il"
      },
      "source": [
        "## Evaluating Performance Over Validation Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BnadNvtxWIYw",
        "outputId": "85b57150-4f92-4497-b532-062c51293796"
      },
      "source": [
        "(py_inputs, py_attn_masks, py_labels) = make_smart_batches(val_sentences, val_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "\r\n",
        "y_pred , y_true = get_predictions(py_inputs, py_attn_masks, py_labels)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 67 test batches...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wAjlATBPgh7c",
        "outputId": "4d42b4e3-d350-44b6-90de-bc7198293e5d"
      },
      "source": [
        "print(classification_report(y_true, y_pred, target_names=class_names))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "                 precision    recall  f1-score   support\n",
            "\n",
            "    Hope_speech       0.66      0.49      0.56       190\n",
            "Non_hope_speech       0.85      0.94      0.89       784\n",
            "  not-malayalam       0.86      0.57      0.69        96\n",
            "\n",
            "       accuracy                           0.83      1070\n",
            "      macro avg       0.79      0.67      0.71      1070\n",
            "   weighted avg       0.82      0.83      0.82      1070\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 479
        },
        "id": "7nELY57NYshD",
        "outputId": "22b4be1b-a3b4-4459-f7f0-348837f9db40"
      },
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\r\n",
        "show_confusion_matrix(cm, class_names)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "j_Ev8kTSNT6L"
      },
      "source": [
        "## Evaluating Performance Over Test Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "knzcVqvONT6N",
        "outputId": "e9bb366e-db14-48c7-cdb0-8a77ab2594b6"
      },
      "source": [
        "(py_inputs, py_attn_masks, py_labels) = make_smart_batches(test_sentences, test_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "\r\n",
        "y_pred , y_true = get_predictions(py_inputs, py_attn_masks, py_labels)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 1,071 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,071 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,071 samples\n",
            "\n",
            "     1,071 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 67 test batches...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "l6EJfj0TNT6R",
        "outputId": "d5593239-d409-4e36-a406-7f2b81412705"
      },
      "source": [
        "print(classification_report(y_true, y_pred, target_names=class_names))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "                 precision    recall  f1-score   support\n",
            "\n",
            "    Hope_speech       0.63      0.52      0.57       194\n",
            "Non_hope_speech       0.83      0.93      0.88       776\n",
            "  not-malayalam       0.88      0.43      0.57       101\n",
            "\n",
            "       accuracy                           0.81      1071\n",
            "      macro avg       0.78      0.62      0.67      1071\n",
            "   weighted avg       0.80      0.81      0.79      1071\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 479
        },
        "id": "ZE3EG9RTNT6S",
        "outputId": "e9065ffd-0748-4da4-e81d-c50ff0efbcd1"
      },
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\r\n",
        "show_confusion_matrix(cm, class_names)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2fOJyH_c3ON2"
      },
      "source": [
        "## Saving the model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3PXqG-VpurVS"
      },
      "source": [
        "torch.save(model,\"./drive/MyDrive/Codalab/HopeSpeech Detection For Equality,DiversityAnd Inclusion/Models/IndicBERT_Malayalam_def\")"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "a9M_91z1yj0F"
      },
      "source": [
        "## Loading the model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5NfWwz6Qztsg"
      },
      "source": [
        "model = torch.load('./drive/MyDrive/Codalab/HopeSpeech Detection For Equality,DiversityAnd Inclusion/Models/IndicBERT_Malayalam',map_location=device)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sAaHpZdIzsnT",
        "outputId": "a8fc95e1-51eb-463a-932b-bd7a8d70c106"
      },
      "source": [
        "model.cuda()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "XLMRobertaForSequenceClassification(\n",
              "  (roberta): RobertaModel(\n",
              "    (embeddings): RobertaEmbeddings(\n",
              "      (word_embeddings): Embedding(250002, 768, padding_idx=1)\n",
              "      (position_embeddings): Embedding(514, 768, padding_idx=1)\n",
              "      (token_type_embeddings): Embedding(1, 768)\n",
              "      (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "      (dropout): Dropout(p=0.1, inplace=False)\n",
              "    )\n",
              "    (encoder): RobertaEncoder(\n",
              "      (layer): ModuleList(\n",
              "        (0): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (1): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (2): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (3): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (4): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (5): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (6): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (7): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (8): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (9): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (10): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (11): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "      )\n",
              "    )\n",
              "  )\n",
              "  (classifier): RobertaClassificationHead(\n",
              "    (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "    (dropout): Dropout(p=0.1, inplace=False)\n",
              "    (out_proj): Linear(in_features=768, out_features=5, bias=True)\n",
              "  )\n",
              ")"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 70
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_crczjW6V-QK"
      },
      "source": [
        "## Making Predictions on Test Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lETtjTatLo91"
      },
      "source": [
        "test_df_path = join(dataset_dir,'malayalam_hope_test.csv')\r\n",
        "test_df = pd.read_csv(test_df_path,sep = '\\t')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "d_83fOUwqn0w",
        "outputId": "dce77c0b-c98e-4735-884a-39e3e9862097"
      },
      "source": [
        "test_df"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>@Albin Baiju</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>@surya ishaan</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 1 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text\n",
              "0                               അതെ അണപൊട്ടി ഒഴുകുകയാണ്\n",
              "1                               കെവിൻ avde pettupoyi🤣🤣🤣\n",
              "2     @my voice ullup illa daaa tayoli ath kond alle...\n",
              "3                                          @Albin Baiju\n",
              "4                                       I respect you..\n",
              "...                                                 ...\n",
              "1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...\n",
              "1067                                      @surya ishaan\n",
              "1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ\n",
              "1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...\n",
              "1070                              Poorru  angodu chellu\n",
              "\n",
              "[1071 rows x 1 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 66
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NjAQaP_na7HN"
      },
      "source": [
        "## Loading `test_sentences`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WnnscvKOjl6b"
      },
      "source": [
        "test_sentences = test_df['text'].values \r\n",
        "test_ids = test_df.index.values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "slovGuCRThW1",
        "outputId": "9af68508-1d66-4d7b-f4ab-0c7c0358ec86"
      },
      "source": [
        "test_ids"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([   0,    1,    2, ..., 1068, 1069, 1070])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 68
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gL7aCG2HTjv6",
        "outputId": "5bb218db-ec54-4a60-9055-12bc17ad27aa"
      },
      "source": [
        "test_sentences"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['അതെ അണപൊട്ടി ഒഴുകുകയാണ്', 'കെവിൻ avde pettupoyi🤣🤣🤣',\n",
              "       '@my voice ullup illa daaa tayoli ath kond alle ninte ammaye njan panniyatha monee',\n",
              "       ..., 'ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ',\n",
              "       'ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...',\n",
              "       'Poorru  angodu chellu'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 69
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "glrG0ZI4imGN",
        "outputId": "f388b1ec-fc0c-4633-c854-28f420b2875f"
      },
      "source": [
        "(py_inputs, py_attn_masks,py_ids) = make_smart_batches_on_test(test_sentences,test_ids, 16,tokenizer,max_input_length)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 1,071 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,071 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,071 samples\n",
            "\n",
            "     1,071 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "a4FMxCyZbJaG"
      },
      "source": [
        "## Evaluating accuracy over test set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PiuSwCUDiv8p",
        "outputId": "009e18be-bec4-4014-fa32-c6c1b062efce"
      },
      "source": [
        "y_ids,y_preds  = get_predictions_test(py_inputs, py_attn_masks,py_ids)\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Predicting labels for 67 test batches...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      56  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cyNSDdXQhL9F",
        "outputId": "9cfdb90e-0376-4652-ccd4-3eae06ed3e57"
      },
      "source": [
        "print(y_preds)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[1 1 1 ... 0 0 1]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kWWWjz7eUPc7",
        "outputId": "57106c16-b04d-43d5-e551-8fc33c8567d6"
      },
      "source": [
        "print(y_ids)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[ 609  669  683 ...   40  214 1004]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "P2rVvmYVhguG",
        "outputId": "f8bb2df1-775e-46bb-89ec-1a664ea6090c"
      },
      "source": [
        "le.inverse_transform(y_preds)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Non_hope_speech', 'Non_hope_speech', 'Non_hope_speech', ...,\n",
              "       'Hope_speech', 'Hope_speech', 'Non_hope_speech'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 74
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "CYN9Z8gAhrMy",
        "outputId": "b970779f-4aa5-4ba7-f162-ecb46a13870e"
      },
      "source": [
        "sns.countplot(y =le.inverse_transform(y_preds))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7fc5f4e10710>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 75
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4KXOXwH9U2MT",
        "outputId": "0209864f-c762-4259-c87f-288daf063479"
      },
      "source": [
        "len(y_ids)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1071"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 76
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9-fkBgOxU4bX",
        "outputId": "63be3ed6-8ebd-4dcb-a5bd-a7b439110bd2"
      },
      "source": [
        "len(le.inverse_transform(y_preds))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1071"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 77
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "sWPDqogJrjIZ"
      },
      "source": [
        "## Creating Submission DataFrame"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "o4Hb7RD1yHol"
      },
      "source": [
        "df_new = pd.DataFrame({\r\n",
        "    'id':y_ids,\r\n",
        "    'label':le.inverse_transform(y_preds)\r\n",
        "})"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "twQAkVzcn4Lg"
      },
      "source": [
        "test_df['id'] = test_df.index"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "qov36eWmqawv",
        "outputId": "d8a26ca0-b1cf-4c92-8d46-878bbba18210"
      },
      "source": [
        "df_new"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>609</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>669</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>683</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>692</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>694</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>482</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>569</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>40</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>214</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>1004</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "        id            label\n",
              "0      609  Non_hope_speech\n",
              "1      669  Non_hope_speech\n",
              "2      683  Non_hope_speech\n",
              "3      692    not-malayalam\n",
              "4      694  Non_hope_speech\n",
              "...    ...              ...\n",
              "1066   482  Non_hope_speech\n",
              "1067   569      Hope_speech\n",
              "1068    40      Hope_speech\n",
              "1069   214      Hope_speech\n",
              "1070  1004  Non_hope_speech\n",
              "\n",
              "[1071 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 80
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "z0CEApHmqdLr",
        "outputId": "e7b4efea-4b08-4f01-8d19-6bba259f3387"
      },
      "source": [
        "test_df"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>id</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>@Albin Baiju</td>\n",
              "      <td>3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "      <td>1066</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>@surya ishaan</td>\n",
              "      <td>1067</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "      <td>1068</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "      <td>1069</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "      <td>1070</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text    id\n",
              "0                               അതെ അണപൊട്ടി ഒഴുകുകയാണ്     0\n",
              "1                               കെവിൻ avde pettupoyi🤣🤣🤣     1\n",
              "2     @my voice ullup illa daaa tayoli ath kond alle...     2\n",
              "3                                          @Albin Baiju     3\n",
              "4                                       I respect you..     4\n",
              "...                                                 ...   ...\n",
              "1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...  1066\n",
              "1067                                      @surya ishaan  1067\n",
              "1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ  1068\n",
              "1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...  1069\n",
              "1070                              Poorru  angodu chellu  1070\n",
              "\n",
              "[1071 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 81
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "vxReWWmxn7Hj",
        "outputId": "8d36025a-1b36-4a0a-c57e-5315a2707f06"
      },
      "source": [
        "df_f = pd.merge(test_df,df_new,on = 'id')\r\n",
        "df_f"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>id</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "      <td>0</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "      <td>1</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "      <td>2</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>@Albin Baiju</td>\n",
              "      <td>3</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "      <td>4</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "      <td>1066</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>@surya ishaan</td>\n",
              "      <td>1067</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "      <td>1068</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "      <td>1069</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "      <td>1070</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 3 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text    id            label\n",
              "0                               അതെ അണപൊട്ടി ഒഴുകുകയാണ്     0  Non_hope_speech\n",
              "1                               കെവിൻ avde pettupoyi🤣🤣🤣     1  Non_hope_speech\n",
              "2     @my voice ullup illa daaa tayoli ath kond alle...     2  Non_hope_speech\n",
              "3                                          @Albin Baiju     3  Non_hope_speech\n",
              "4                                       I respect you..     4    not-malayalam\n",
              "...                                                 ...   ...              ...\n",
              "1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...  1066  Non_hope_speech\n",
              "1067                                      @surya ishaan  1067    not-malayalam\n",
              "1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ  1068  Non_hope_speech\n",
              "1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...  1069  Non_hope_speech\n",
              "1070                              Poorru  angodu chellu  1070  Non_hope_speech\n",
              "\n",
              "[1071 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 82
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "1kuASymYn9aV",
        "outputId": "76bb4552-b2de-4350-e27d-7f63927a2d91"
      },
      "source": [
        "df_f = df_f[['id','text','label']]\r\n",
        "df_f"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>@Albin Baiju</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>I respect you..</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>1066</td>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>1067</td>\n",
              "      <td>@surya ishaan</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>1068</td>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>1069</td>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>1070</td>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 3 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "        id                                               text            label\n",
              "0        0                            അതെ അണപൊട്ടി ഒഴുകുകയാണ്  Non_hope_speech\n",
              "1        1                            കെവിൻ avde pettupoyi🤣🤣🤣  Non_hope_speech\n",
              "2        2  @my voice ullup illa daaa tayoli ath kond alle...  Non_hope_speech\n",
              "3        3                                       @Albin Baiju  Non_hope_speech\n",
              "4        4                                    I respect you..    not-malayalam\n",
              "...    ...                                                ...              ...\n",
              "1066  1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...  Non_hope_speech\n",
              "1067  1067                                      @surya ishaan    not-malayalam\n",
              "1068  1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ  Non_hope_speech\n",
              "1069  1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...  Non_hope_speech\n",
              "1070  1070                              Poorru  angodu chellu  Non_hope_speech\n",
              "\n",
              "[1071 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 83
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "p3FtBVTVroJi"
      },
      "source": [
        "## Saving Submission DataFrame"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SzoT0p9rqrO-"
      },
      "source": [
        "path = './drive/MyDrive/Codalab/HopeSpeech Detection For Equality,DiversityAnd Inclusion/SubmissionFiles'"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LZmgZFM4qi7F"
      },
      "source": [
        "df_f.to_csv(join(path,'indicbert_malayalam.csv'),index=False)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jW9g_qgMv7mq"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}