Improve docstring

Author: bact

pythainlp/tag/locations.py

@@ -12,6 +12,8 @@ def tag_provinces(tokens: List[str]) -> List[Tuple[str, str]]:
     """
     This function recognize Thailand provinces in text.
 
+    Note that it uses exact match and considers no context.
+
     :param list[str] tokens: a list of words
     :reutrn: a list of tuple indicating NER for `LOCATION` in IOB format
     :rtype: list[tuple[str, str]]
@@ -24,13 +26,6 @@ def tag_provinces(tokens: List[str]) -> List[Tuple[str, str]]:
         text = ['หนองคาย', 'น่าอยู่']
         tag_provinces(text)
         # output: [('หนองคาย', 'B-LOCATION'), ('น่าอยู่', 'O')]
-
-        text = ['อำเภอ', 'ฝาง','เป็น','ส่วน','หนึ่ง','ของ', 'จังหวัด', \\
-            'เชียงใหม่']
-        tag_provinces(text)
-        # output: [('อำเภอ', 'O'), ('ฝาง', 'O'), ('เป็น', 'O'), ('ส่วน', 'O'),
-        #   ('หนึ่ง', 'O'), ('ของ', 'O'), ('จังหวัด', 'O'),
-        #   ('เชียงใหม่', 'B-LOCATION')]
     """
     province_list = provinces()
     output = [

pythainlp/tag/perceptron.py

@@ -51,8 +51,8 @@ def _lst20_tagger():
 def tag(words: List[str], corpus: str = "pud") -> List[Tuple[str, str]]:
     """
     :param list words: a list of tokenized words
-    :param str corpus: name corpus (orchid or pud)
-    :return: returns a list of labels regarding which part of speech it is
+    :param str corpus: corpus name (orchid, pud, or lst20)
+    :return: a list of tuples (word, POS tag)
     :rtype: list[tuple[str, str]]
     """
     if not words:

pythainlp/tag/pos_tag.py

@@ -25,7 +25,7 @@ def pos_tag(
         * *pud* - `Parallel Universal Dependencies (PUD)\
             <https://github.com/UniversalDependencies/UD_Thai-PUD>`_ \
             treebanks, natively use Universal POS tags
-    :return: a list of (word, POS) as their members
+    :return: a list of tuples (word, POS tag)
     :rtype: list[tuple[str, str]]
 
     :Example:
@@ -121,7 +121,7 @@ def pos_tag_sents(
         * *pud* - `Parallel Universal Dependencies (PUD)\
             <https://github.com/UniversalDependencies/UD_Thai-PUD>`_ \
             treebanks, natively use Universal POS tags
-    :return: returns a list of lists with (word, POS) as their members
+    :return: a list of lists of tuples (word, POS tag)
     :rtype: list[list[tuple[str, str]]]
 
     :Example:

pythainlp/tag/unigram.py

@@ -59,9 +59,12 @@ def _find_tag(
     ]
 
 
-def tag(words: List[str], corpus: str) -> List[Tuple[str, str]]:
+def tag(words: List[str], corpus: str = "pud") -> List[Tuple[str, str]]:
     """
-    รับค่าเป็น ''list'' คืนค่าเป็น ''list'' เช่น [('คำ', 'ชนิดคำ'), ('คำ', 'ชนิดคำ'), ...]
+    :param list words: a list of tokenized words
+    :param str corpus: corpus name (orchid, pud, or lst20)
+    :return: a list of tuples (word, POS tag)
+    :rtype: list[tuple[str, str]]
     """
     if not words:
         return []