Merge branch 'hotfix/0.2.6'

Makefile

@@ -3,21 +3,25 @@ RM = rm -rf
 TWINE = twine
 TOX = tox
 LINT = pylint --rcfile=./.pylintrc
+FORMAT = $(PY) -m black --color --diff
 
-.PHONY: all check dist sdist test tox tox-v tox-vv tox-report lint doc upload clean
+.PHONY: all check dist sdist test tox tox-v tox-vv tox-report lint format doc upload clean
 
 all: dist check test
 
 dist: sdist bdist_wheel
 
-test: tox lint
+test: tox format lint
 
 sdist bdist_wheel:
 	$(PY) setup.py $@
 
 lint:
 	$(LINT) ckip_transformers
 
+format:
+	$(FORMAT) ckip_transformers
+
 check:
 	$(TWINE) check dist/*
 

README.rst

@@ -304,7 +304,7 @@ NLP Tools Usage
 .. code-block:: python
 
    # Initialize drivers
-   ws_driver  = CkipWordSegmenter(level=3)
+   ws_driver = CkipWordSegmenter(level=3)
    pos_driver = CkipPosTagger(level=3)
    ner_driver = CkipNerChunker(level=3)
 
@@ -314,9 +314,9 @@ NLP Tools Usage
 .. code-block:: python
 
    # Initialize drivers with custom checkpoints
-   ws_driver  = CkipWordSegmenter(model_name='path_to_your_model')
-   pos_driver = CkipPosTagger(model_name='path_to_your_model')
-   ner_driver = CkipNerChunker(model_name='path_to_your_model')
+   ws_driver  = CkipWordSegmenter(model_name="path_to_your_model")
+   pos_driver = CkipPosTagger(model_name="path_to_your_model")
+   ner_driver = CkipNerChunker(model_name="path_to_your_model")
 
 | To use GPU, one may specify device ID while initialize the drivers. Set to -1 (default) to disable GPU.
 | 可於宣告斷詞等工具時指定 device 以使用 GPU，設為 -1 （預設值）代表不使用 GPU。
@@ -341,9 +341,9 @@ NLP Tools Usage
 
    # Input text
    text = [
-      '傅達仁今將執行安樂死，卻突然爆出自己20年前遭緯來體育台封殺，他不懂自己哪裡得罪到電視台。',
-      '美國參議院針對今天總統布什所提名的勞工部長趙小蘭展開認可聽證會，預料她將會很順利通過參議院支持，成為該國有史以來第一位的華裔女性內閣成員。',
-      '空白 也是可以的～',
+      "傅達仁今將執行安樂死，卻突然爆出自己20年前遭緯來體育台封殺，他不懂自己哪裡得罪到電視台。",
+      "美國參議院針對今天總統布什所提名的勞工部長趙小蘭展開認可聽證會，預料她將會很順利通過參議院支持，成為該國有史以來第一位的華裔女性內閣成員。",
+      "空白 也是可以的～",
    ]
 
    # Run pipeline
@@ -386,8 +386,8 @@ NLP Tools Usage
       assert len(sentence_ws) == len(sentence_pos)
       res = []
       for word_ws, word_pos in zip(sentence_ws, sentence_pos):
-         res.append(f'{word_ws}({word_pos})')
-      return '\u3000'.join(res)
+         res.append(f"{word_ws}({word_pos})")
+      return "\u3000".join(res)
 
    # Show results
    for sentence, sentence_ws, sentence_pos, sentence_ner in zip(text, ws, pos, ner):

ckip_transformers/__init__.py

@@ -5,14 +5,14 @@
 The CKIP Transformers.
 """
 
-__author_name__ = 'Mu Yang'
-__author_email__ = 'emfomy@gmail.com'
-__copyright__ = '2020 CKIP Lab'
+__author_name__ = "Mu Yang"
+__author_email__ = "emfomy@gmail.com"
+__copyright__ = "2020 CKIP Lab"
 
-__title__ = 'CKIP Transformers'
-__version__ = '0.2.5'
-__description__ = 'CKIP Transformers'
-__license__ = 'GPL-3.0'
+__title__ = "CKIP Transformers"
+__version__ = "0.2.6"
+__description__ = "CKIP Transformers"
+__license__ = "GPL-3.0"
 
-__url__ = 'https://ckip-transformers.readthedocs.io'
-__download_url__ = __url__+'/tarball/'+__version__
+__url__ = "https://ckip-transformers.readthedocs.io"
+__download_url__ = __url__ + "/tarball/" + __version__

ckip_transformers/nlp/__init__.py

@@ -1,12 +1,13 @@
 #!/usr/bin/env python3
 # -*- coding:utf-8 -*-
+
 """
 This module provides the CKIP Transformers NLP drivers.
 """
 
-__author__ = 'Mu Yang <http://muyang.pro>'
-__copyright__ = '2020 CKIP Lab'
-__license__ = 'GPL-3.0'
+__author__ = "Mu Yang <http://muyang.pro>"
+__copyright__ = "2020 CKIP Lab"
+__license__ = "GPL-3.0"
 
 from .driver import (
     CkipWordSegmenter,

ckip_transformers/nlp/driver.py

@@ -1,15 +1,17 @@
 #!/usr/bin/env python3
 # -*- coding:utf-8 -*-
+
 """
 This module implements the CKIP Transformers NLP drivers.
 """
 
-__author__ = 'Mu Yang <http://muyang.pro>'
-__copyright__ = '2020 CKIP Lab'
-__license__ = 'GPL-3.0'
+__author__ = "Mu Yang <http://muyang.pro>"
+__copyright__ = "2020 CKIP Lab"
+__license__ = "GPL-3.0"
 
 from typing import (
-    List, )
+    List,
+)
 
 import numpy as np
 
@@ -24,30 +26,29 @@
 class CkipWordSegmenter(CkipTokenClassification):
     """The word segmentation driver.
 
-        Parameters
-        ----------
-            level : ``str`` *optional*, defaults to 3, must be 1—3
-                The model level. The higher the level is, the more accurate and slower the model is.
-            model_name : ``str`` *optional*, overwrites **level**
-                The pretrained model name (e.g. ``'ckiplab/bert-base-chinese-ws'``).
-            device : ``int``, *optional*, defaults to -1,
-                Device ordinal for CPU/GPU supports.
-                Setting this to -1 will leverage CPU, a positive will run the model on the associated CUDA device id.
+    Parameters
+    ----------
+        level : ``str`` *optional*, defaults to 3, must be 1—3
+            The model level. The higher the level is, the more accurate and slower the model is.
+        model_name : ``str`` *optional*, overwrites **level**
+            The pretrained model name (e.g. ``'ckiplab/bert-base-chinese-ws'``).
+        device : ``int``, *optional*, defaults to -1,
+            Device ordinal for CPU/GPU supports.
+            Setting this to -1 will leverage CPU, a positive will run the model on the associated CUDA device id.
     """
 
     _model_names = {
-        1: 'ckiplab/albert-tiny-chinese-ws',
-        2: 'ckiplab/albert-base-chinese-ws',
-        3: 'ckiplab/bert-base-chinese-ws',
+        1: "ckiplab/albert-tiny-chinese-ws",
+        2: "ckiplab/albert-base-chinese-ws",
+        3: "ckiplab/bert-base-chinese-ws",
     }
 
     def __init__(
         self,
         level: int = 3,
         **kwargs,
     ):
-        model_name = kwargs.pop('model_name',
-                                self._get_model_name_from_level(level))
+        model_name = kwargs.pop("model_name", self._get_model_name_from_level(level))
         super().__init__(model_name=model_name, **kwargs)
 
     def __call__(
@@ -91,13 +92,13 @@ def __call__(
         output_text = []
         for sent_data in zip(input_text, index_map):
             output_sent = []
-            word = ''
+            word = ""
             for input_char, logits_index in zip(*sent_data):
                 if logits_index is None:
                     if word:
                         output_sent.append(word)
                     output_sent.append(input_char)
-                    word = ''
+                    word = ""
                 else:
                     logits_b, logits_i = logits[logits_index]
 
@@ -121,30 +122,29 @@ def __call__(
 class CkipPosTagger(CkipTokenClassification):
     """The part-of-speech tagging driver.
 
-        Parameters
-        ----------
-            level : ``str`` *optional*, defaults to 3, must be 1—3
-                The model level. The higher the level is, the more accurate and slower the model is.
-            model_name : ``str`` *optional*, overwrites **level**
-                The pretrained model name (e.g. ``'ckiplab/bert-base-chinese-pos'``).
-            device : ``int``, *optional*, defaults to -1,
-                Device ordinal for CPU/GPU supports.
-                Setting this to -1 will leverage CPU, a positive will run the model on the associated CUDA device id.
+    Parameters
+    ----------
+        level : ``str`` *optional*, defaults to 3, must be 1—3
+            The model level. The higher the level is, the more accurate and slower the model is.
+        model_name : ``str`` *optional*, overwrites **level**
+            The pretrained model name (e.g. ``'ckiplab/bert-base-chinese-pos'``).
+        device : ``int``, *optional*, defaults to -1,
+            Device ordinal for CPU/GPU supports.
+            Setting this to -1 will leverage CPU, a positive will run the model on the associated CUDA device id.
     """
 
     _model_names = {
-        1: 'ckiplab/albert-tiny-chinese-pos',
-        2: 'ckiplab/albert-base-chinese-pos',
-        3: 'ckiplab/bert-base-chinese-pos',
+        1: "ckiplab/albert-tiny-chinese-pos",
+        2: "ckiplab/albert-base-chinese-pos",
+        3: "ckiplab/bert-base-chinese-pos",
     }
 
     def __init__(
         self,
         level: int = 3,
         **kwargs,
     ):
-        model_name = kwargs.pop('model_name',
-                                self._get_model_name_from_level(level))
+        model_name = kwargs.pop("model_name", self._get_model_name_from_level(level))
         super().__init__(model_name=model_name, **kwargs)
 
     def __call__(
@@ -193,7 +193,7 @@ def __call__(
             output_sent = []
             for input_char, logits_index in zip(*sent_data):
                 if logits_index is None or input_char.isspace():
-                    label = 'WHITESPACE'
+                    label = "WHITESPACE"
                 else:
                     label = id2label[np.argmax(logits[logits_index])]
                 output_sent.append(label)
@@ -208,30 +208,29 @@ def __call__(
 class CkipNerChunker(CkipTokenClassification):
     """The named-entity recognition driver.
 
-        Parameters
-        ----------
-            level : ``str`` *optional*, defaults to 3, must be 1—3
-                The model level. The higher the level is, the more accurate and slower the model is.
-            model_name : ``str`` *optional*, overwrites **level**
-                The pretrained model name (e.g. ``'ckiplab/bert-base-chinese-ner'``).
-            device : ``int``, *optional*, defaults to -1,
-                Device ordinal for CPU/GPU supports.
-                Setting this to -1 will leverage CPU, a positive will run the model on the associated CUDA device id.
+    Parameters
+    ----------
+        level : ``str`` *optional*, defaults to 3, must be 1—3
+            The model level. The higher the level is, the more accurate and slower the model is.
+        model_name : ``str`` *optional*, overwrites **level**
+            The pretrained model name (e.g. ``'ckiplab/bert-base-chinese-ner'``).
+        device : ``int``, *optional*, defaults to -1,
+            Device ordinal for CPU/GPU supports.
+            Setting this to -1 will leverage CPU, a positive will run the model on the associated CUDA device id.
     """
 
     _model_names = {
-        1: 'ckiplab/albert-tiny-chinese-ner',
-        2: 'ckiplab/albert-base-chinese-ner',
-        3: 'ckiplab/bert-base-chinese-ner',
+        1: "ckiplab/albert-tiny-chinese-ner",
+        2: "ckiplab/albert-base-chinese-ner",
+        3: "ckiplab/bert-base-chinese-ner",
     }
 
     def __init__(
         self,
         level: int = 3,
         **kwargs,
     ):
-        model_name = kwargs.pop('model_name',
-                                self._get_model_name_from_level(level))
+        model_name = kwargs.pop("model_name", self._get_model_name_from_level(level))
         super().__init__(model_name=model_name, **kwargs)
 
     def __call__(
@@ -282,21 +281,21 @@ def __call__(
             entity_ner = None
             entity_idx0 = None
             for index_char, (
-                    input_char,
-                    logits_index,
+                input_char,
+                logits_index,
             ) in enumerate(zip(*sent_data)):
                 if logits_index is None:
-                    label = 'O'
+                    label = "O"
                 else:
                     label = id2label[np.argmax(logits[logits_index])]
 
-                if label == 'O':
+                if label == "O":
                     entity_ner = None
                     continue
 
-                bioes, ner = label.split('-')
+                bioes, ner = label.split("-")
 
-                if bioes == 'S':
+                if bioes == "S":
                     output_sent.append(
                         NerToken(
                             word=input_char,
@@ -305,18 +304,19 @@ def __call__(
                                 index_char,
                                 index_char + len(input_char),
                             ),
-                        ))
+                        )
+                    )
                     entity_ner = None
-                elif bioes == 'B':
+                elif bioes == "B":
                     entity_word = input_char
                     entity_ner = ner
                     entity_idx0 = index_char
-                elif bioes == 'I':
+                elif bioes == "I":
                     if entity_ner == ner:
                         entity_word += input_char
                     else:
                         entity_ner = None
-                elif bioes == 'E':
+                elif bioes == "E":
                     if entity_ner == ner:
                         entity_word += input_char
                         output_sent.append(
@@ -327,7 +327,8 @@ def __call__(
                                     entity_idx0,
                                     index_char + len(input_char),
                                 ),
-                            ))
+                            )
+                        )
                     entity_ner = None
 
             output_text.append(output_sent)