P20. Hypothesis Testing Anova Test - Iris Flower dataset.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hypothesis Testing Anova Test - Iris Flower dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn import datasets\n",
    "from scipy import stats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'data': array([[5.1, 3.5, 1.4, 0.2],\n",
       "        [4.9, 3. , 1.4, 0.2],\n",
       "        [4.7, 3.2, 1.3, 0.2],\n",
       "        [4.6, 3.1, 1.5, 0.2],\n",
       "        [5. , 3.6, 1.4, 0.2],\n",
       "        [5.4, 3.9, 1.7, 0.4],\n",
       "        [4.6, 3.4, 1.4, 0.3],\n",
       "        [5. , 3.4, 1.5, 0.2],\n",
       "        [4.4, 2.9, 1.4, 0.2],\n",
       "        [4.9, 3.1, 1.5, 0.1],\n",
       "        [5.4, 3.7, 1.5, 0.2],\n",
       "        [4.8, 3.4, 1.6, 0.2],\n",
       "        [4.8, 3. , 1.4, 0.1],\n",
       "        [4.3, 3. , 1.1, 0.1],\n",
       "        [5.8, 4. , 1.2, 0.2],\n",
       "        [5.7, 4.4, 1.5, 0.4],\n",
       "        [5.4, 3.9, 1.3, 0.4],\n",
       "        [5.1, 3.5, 1.4, 0.3],\n",
       "        [5.7, 3.8, 1.7, 0.3],\n",
       "        [5.1, 3.8, 1.5, 0.3],\n",
       "        [5.4, 3.4, 1.7, 0.2],\n",
       "        [5.1, 3.7, 1.5, 0.4],\n",
       "        [4.6, 3.6, 1. , 0.2],\n",
       "        [5.1, 3.3, 1.7, 0.5],\n",
       "        [4.8, 3.4, 1.9, 0.2],\n",
       "        [5. , 3. , 1.6, 0.2],\n",
       "        [5. , 3.4, 1.6, 0.4],\n",
       "        [5.2, 3.5, 1.5, 0.2],\n",
       "        [5.2, 3.4, 1.4, 0.2],\n",
       "        [4.7, 3.2, 1.6, 0.2],\n",
       "        [4.8, 3.1, 1.6, 0.2],\n",
       "        [5.4, 3.4, 1.5, 0.4],\n",
       "        [5.2, 4.1, 1.5, 0.1],\n",
       "        [5.5, 4.2, 1.4, 0.2],\n",
       "        [4.9, 3.1, 1.5, 0.2],\n",
       "        [5. , 3.2, 1.2, 0.2],\n",
       "        [5.5, 3.5, 1.3, 0.2],\n",
       "        [4.9, 3.6, 1.4, 0.1],\n",
       "        [4.4, 3. , 1.3, 0.2],\n",
       "        [5.1, 3.4, 1.5, 0.2],\n",
       "        [5. , 3.5, 1.3, 0.3],\n",
       "        [4.5, 2.3, 1.3, 0.3],\n",
       "        [4.4, 3.2, 1.3, 0.2],\n",
       "        [5. , 3.5, 1.6, 0.6],\n",
       "        [5.1, 3.8, 1.9, 0.4],\n",
       "        [4.8, 3. , 1.4, 0.3],\n",
       "        [5.1, 3.8, 1.6, 0.2],\n",
       "        [4.6, 3.2, 1.4, 0.2],\n",
       "        [5.3, 3.7, 1.5, 0.2],\n",
       "        [5. , 3.3, 1.4, 0.2],\n",
       "        [7. , 3.2, 4.7, 1.4],\n",
       "        [6.4, 3.2, 4.5, 1.5],\n",
       "        [6.9, 3.1, 4.9, 1.5],\n",
       "        [5.5, 2.3, 4. , 1.3],\n",
       "        [6.5, 2.8, 4.6, 1.5],\n",
       "        [5.7, 2.8, 4.5, 1.3],\n",
       "        [6.3, 3.3, 4.7, 1.6],\n",
       "        [4.9, 2.4, 3.3, 1. ],\n",
       "        [6.6, 2.9, 4.6, 1.3],\n",
       "        [5.2, 2.7, 3.9, 1.4],\n",
       "        [5. , 2. , 3.5, 1. ],\n",
       "        [5.9, 3. , 4.2, 1.5],\n",
       "        [6. , 2.2, 4. , 1. ],\n",
       "        [6.1, 2.9, 4.7, 1.4],\n",
       "        [5.6, 2.9, 3.6, 1.3],\n",
       "        [6.7, 3.1, 4.4, 1.4],\n",
       "        [5.6, 3. , 4.5, 1.5],\n",
       "        [5.8, 2.7, 4.1, 1. ],\n",
       "        [6.2, 2.2, 4.5, 1.5],\n",
       "        [5.6, 2.5, 3.9, 1.1],\n",
       "        [5.9, 3.2, 4.8, 1.8],\n",
       "        [6.1, 2.8, 4. , 1.3],\n",
       "        [6.3, 2.5, 4.9, 1.5],\n",
       "        [6.1, 2.8, 4.7, 1.2],\n",
       "        [6.4, 2.9, 4.3, 1.3],\n",
       "        [6.6, 3. , 4.4, 1.4],\n",
       "        [6.8, 2.8, 4.8, 1.4],\n",
       "        [6.7, 3. , 5. , 1.7],\n",
       "        [6. , 2.9, 4.5, 1.5],\n",
       "        [5.7, 2.6, 3.5, 1. ],\n",
       "        [5.5, 2.4, 3.8, 1.1],\n",
       "        [5.5, 2.4, 3.7, 1. ],\n",
       "        [5.8, 2.7, 3.9, 1.2],\n",
       "        [6. , 2.7, 5.1, 1.6],\n",
       "        [5.4, 3. , 4.5, 1.5],\n",
       "        [6. , 3.4, 4.5, 1.6],\n",
       "        [6.7, 3.1, 4.7, 1.5],\n",
       "        [6.3, 2.3, 4.4, 1.3],\n",
       "        [5.6, 3. , 4.1, 1.3],\n",
       "        [5.5, 2.5, 4. , 1.3],\n",
       "        [5.5, 2.6, 4.4, 1.2],\n",
       "        [6.1, 3. , 4.6, 1.4],\n",
       "        [5.8, 2.6, 4. , 1.2],\n",
       "        [5. , 2.3, 3.3, 1. ],\n",
       "        [5.6, 2.7, 4.2, 1.3],\n",
       "        [5.7, 3. , 4.2, 1.2],\n",
       "        [5.7, 2.9, 4.2, 1.3],\n",
       "        [6.2, 2.9, 4.3, 1.3],\n",
       "        [5.1, 2.5, 3. , 1.1],\n",
       "        [5.7, 2.8, 4.1, 1.3],\n",
       "        [6.3, 3.3, 6. , 2.5],\n",
       "        [5.8, 2.7, 5.1, 1.9],\n",
       "        [7.1, 3. , 5.9, 2.1],\n",
       "        [6.3, 2.9, 5.6, 1.8],\n",
       "        [6.5, 3. , 5.8, 2.2],\n",
       "        [7.6, 3. , 6.6, 2.1],\n",
       "        [4.9, 2.5, 4.5, 1.7],\n",
       "        [7.3, 2.9, 6.3, 1.8],\n",
       "        [6.7, 2.5, 5.8, 1.8],\n",
       "        [7.2, 3.6, 6.1, 2.5],\n",
       "        [6.5, 3.2, 5.1, 2. ],\n",
       "        [6.4, 2.7, 5.3, 1.9],\n",
       "        [6.8, 3. , 5.5, 2.1],\n",
       "        [5.7, 2.5, 5. , 2. ],\n",
       "        [5.8, 2.8, 5.1, 2.4],\n",
       "        [6.4, 3.2, 5.3, 2.3],\n",
       "        [6.5, 3. , 5.5, 1.8],\n",
       "        [7.7, 3.8, 6.7, 2.2],\n",
       "        [7.7, 2.6, 6.9, 2.3],\n",
       "        [6. , 2.2, 5. , 1.5],\n",
       "        [6.9, 3.2, 5.7, 2.3],\n",
       "        [5.6, 2.8, 4.9, 2. ],\n",
       "        [7.7, 2.8, 6.7, 2. ],\n",
       "        [6.3, 2.7, 4.9, 1.8],\n",
       "        [6.7, 3.3, 5.7, 2.1],\n",
       "        [7.2, 3.2, 6. , 1.8],\n",
       "        [6.2, 2.8, 4.8, 1.8],\n",
       "        [6.1, 3. , 4.9, 1.8],\n",
       "        [6.4, 2.8, 5.6, 2.1],\n",
       "        [7.2, 3. , 5.8, 1.6],\n",
       "        [7.4, 2.8, 6.1, 1.9],\n",
       "        [7.9, 3.8, 6.4, 2. ],\n",
       "        [6.4, 2.8, 5.6, 2.2],\n",
       "        [6.3, 2.8, 5.1, 1.5],\n",
       "        [6.1, 2.6, 5.6, 1.4],\n",
       "        [7.7, 3. , 6.1, 2.3],\n",
       "        [6.3, 3.4, 5.6, 2.4],\n",
       "        [6.4, 3.1, 5.5, 1.8],\n",
       "        [6. , 3. , 4.8, 1.8],\n",
       "        [6.9, 3.1, 5.4, 2.1],\n",
       "        [6.7, 3.1, 5.6, 2.4],\n",
       "        [6.9, 3.1, 5.1, 2.3],\n",
       "        [5.8, 2.7, 5.1, 1.9],\n",
       "        [6.8, 3.2, 5.9, 2.3],\n",
       "        [6.7, 3.3, 5.7, 2.5],\n",
       "        [6.7, 3. , 5.2, 2.3],\n",
       "        [6.3, 2.5, 5. , 1.9],\n",
       "        [6.5, 3. , 5.2, 2. ],\n",
       "        [6.2, 3.4, 5.4, 2.3],\n",
       "        [5.9, 3. , 5.1, 1.8]]),\n",
       " 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]),\n",
       " 'frame': None,\n",
       " 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10'),\n",
       " 'DESCR': '.. _iris_dataset:\\n\\nIris plants dataset\\n--------------------\\n\\n**Data Set Characteristics:**\\n\\n    :Number of Instances: 150 (50 in each of three classes)\\n    :Number of Attributes: 4 numeric, predictive attributes and the class\\n    :Attribute Information:\\n        - sepal length in cm\\n        - sepal width in cm\\n        - petal length in cm\\n        - petal width in cm\\n        - class:\\n                - Iris-Setosa\\n                - Iris-Versicolour\\n                - Iris-Virginica\\n                \\n    :Summary Statistics:\\n\\n    ============== ==== ==== ======= ===== ====================\\n                    Min  Max   Mean    SD   Class Correlation\\n    ============== ==== ==== ======= ===== ====================\\n    sepal length:   4.3  7.9   5.84   0.83    0.7826\\n    sepal width:    2.0  4.4   3.05   0.43   -0.4194\\n    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)\\n    petal width:    0.1  2.5   1.20   0.76    0.9565  (high!)\\n    ============== ==== ==== ======= ===== ====================\\n\\n    :Missing Attribute Values: None\\n    :Class Distribution: 33.3% for each of 3 classes.\\n    :Creator: R.A. Fisher\\n    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\\n    :Date: July, 1988\\n\\nThe famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\\nfrom Fisher\\'s paper. Note that it\\'s the same as in R, but not as in the UCI\\nMachine Learning Repository, which has two wrong data points.\\n\\nThis is perhaps the best known database to be found in the\\npattern recognition literature.  Fisher\\'s paper is a classic in the field and\\nis referenced frequently to this day.  (See Duda & Hart, for example.)  The\\ndata set contains 3 classes of 50 instances each, where each class refers to a\\ntype of iris plant.  One class is linearly separable from the other 2; the\\nlatter are NOT linearly separable from each other.\\n\\n.. topic:: References\\n\\n   - Fisher, R.A. \"The use of multiple measurements in taxonomic problems\"\\n     Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\\n     Mathematical Statistics\" (John Wiley, NY, 1950).\\n   - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\\n     (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.\\n   - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\\n     Structure and Classification Rule for Recognition in Partially Exposed\\n     Environments\".  IEEE Transactions on Pattern Analysis and Machine\\n     Intelligence, Vol. PAMI-2, No. 1, 67-71.\\n   - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\".  IEEE Transactions\\n     on Information Theory, May 1972, 431-433.\\n   - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al\"s AUTOCLASS II\\n     conceptual clustering system finds 3 classes in the data.\\n   - Many, many more ...',\n",
       " 'feature_names': ['sepal length (cm)',\n",
       "  'sepal width (cm)',\n",
       "  'petal length (cm)',\n",
       "  'petal width (cm)'],\n",
       " 'filename': 'C:\\\\Users\\\\Hitesh Koli\\\\anaconda3\\\\lib\\\\site-packages\\\\sklearn\\\\datasets\\\\data\\\\iris.csv'}"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# load the dataset\n",
    "iris=datasets.load_iris()\n",
    "iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['sepal length (cm)',\n",
       " 'sepal width (cm)',\n",
       " 'petal length (cm)',\n",
       " 'petal width (cm)']"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get the column / feature names \n",
    "iris.feature_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['setosa', 'versicolor', 'virginica'], dtype='<U10')"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris.target_names"
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "Anova ftest statistics: Analysis of varaince between more than 2 samples or columns\n",
    "\n",
    "Assume Null Hypothesis Ho as No Varaince: All samples population means are same\n",
    "Thus Alternate Hypothesis Ha as It has Variance: Atleast one population mean is different    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>6.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>6.3</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>6.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>6.2</td>\n",
       "      <td>3.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>5.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       0    1    2    3\n",
       "0    5.1  3.5  1.4  0.2\n",
       "1    4.9  3.0  1.4  0.2\n",
       "2    4.7  3.2  1.3  0.2\n",
       "3    4.6  3.1  1.5  0.2\n",
       "4    5.0  3.6  1.4  0.2\n",
       "..   ...  ...  ...  ...\n",
       "145  6.7  3.0  5.2  2.3\n",
       "146  6.3  2.5  5.0  1.9\n",
       "147  6.5  3.0  5.2  2.0\n",
       "148  6.2  3.4  5.4  2.3\n",
       "149  5.9  3.0  5.1  1.8\n",
       "\n",
       "[150 rows x 4 columns]"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Converting array into tabular format using DataFrame (for non-pandas array)\n",
    "df=pd.DataFrame(iris.data)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "F_onewayResult(statistic=482.91531656927964, pvalue=4.660592480454751e-159)"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Anova ftest statistics: stats.f_oneway(column-1,column-2,column-3,column-4)\n",
    "p_value=stats.f_oneway(df.iloc[:,0],df.iloc[:,1],df.iloc[:,2],df.iloc[:,3])\n",
    "p_value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4.660592480454751e-159"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "p_value[1]  # compare it with α = 0.05"
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "As (p_value = 0) < (α = 0.05); Reject Null Hypothesis\n",
    "i.e. Atleast one population mean is different    \n",
    "Thus there is variance in more than 2 samples"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}