[DOC]Update documents

EduNLP/Formula/Formula.py

@@ -15,6 +15,7 @@
 
 class Formula(object):
     """
+    The part transform a formula to the parsed abstracted syntax tree.
 
     Parameters
     ----------
@@ -41,9 +42,6 @@ class Formula(object):
     >>> f.elements
     [{'id': 0, 'type': 'mathord', 'text': 'x', 'role': None, 'var': 0}]
 
-    Returns
-    --------
-    the parsed abstracted syntax tree
     """
     def __init__(self, formula: (str, List[Dict]), variable_standardization=False, const_mathord=None,
                  init=True, *args, **kwargs):
@@ -129,6 +127,7 @@ def resetable(self):
 
 class FormulaGroup(object):
     """
+    The part transform a group of formula to the parsed abstracted syntax forest.
 
     Parameters
     ----------
@@ -157,9 +156,6 @@ class FormulaGroup(object):
 {'id': 1, 'type': 'mathord', 'text': 'y', 'role': None, 'var': 1}, \
 {'id': 2, 'type': 'mathord', 'text': 'x', 'role': None, 'var': 0}]
 
-    Returns
-    --------
-    the parsed abstracted syntax forest
     """
     def __init__(self,
                  formula_list: (list, List[str], List[Formula]),

EduNLP/I2V/i2v.py

@@ -108,8 +108,11 @@ def vector_size(self):
 
 class D2V(I2V):
     """
+    The model aims to transfer item to vector directly.
 
-    Bases: I2V
+    Bases
+    -------
+    I2V
 
     Parameters
     -----------
@@ -144,6 +147,7 @@ class D2V(I2V):
     def infer_vector(self, items, tokenize=True, indexing=False, padding=False, key=lambda x: x, *args,
                      **kwargs) -> tuple:
         '''
+        It is a function to switch item to vector. And before using the function, it is nesseary to load model.
 
         Parameters
         -----------
@@ -175,8 +179,11 @@ def from_pretrained(cls, name, model_dir=MODEL_DIR, *args, **kwargs):
 
 class W2V(I2V):
     """
+    The model aims to transfer tokens to vector.
 
-    Bases: I2V
+    Bases
+    --------
+    I2V
 
     Parameters
     -----------
@@ -209,6 +216,7 @@ class W2V(I2V):
     def infer_vector(self, items, tokenize=True, indexing=False, padding=False, key=lambda x: x, *args,
                      **kwargs) -> tuple:
         '''
+        It is a function to switch item to vector. And before using the function, it is nesseary to load model.
 
         Parameters
         -----------

EduNLP/ModelZoo/rnn/rnn.py

@@ -91,7 +91,8 @@ def forward(self, seq_idx, seq_len):
 
         Returns
         --------
-        a PackedSequence object
+        sequence
+            a PackedSequence object
         """
         seq = self.embedding(seq_idx)
         pack = pack_padded_sequence(seq, seq_len, batch_first=True)

EduNLP/ModelZoo/utils/masker.py

@@ -15,7 +15,7 @@ class Masker(object):
     seed
 
     Examples
-    -------
+    ---------
     >>> masker = Masker(per=0.5, seed=10)
     >>> items = [[1, 1, 3, 4, 6], [2], [5, 9, 1, 4]]
     >>> masked_seq, mask_label = masker(items)
@@ -39,7 +39,8 @@ class Masker(object):
 
     Returns
     ----------
-    list:list of masked_seq and list of masked_list
+    list
+        list of masked_seq and list of masked_list
     """
     def __init__(self, mask: (int, str, ...) = 0, per=0.2, seed=None):
         self.seed = np.random.default_rng(seed)

EduNLP/ModelZoo/utils/padder.py

@@ -21,7 +21,8 @@ class PadSequence(object):
 
     Returns
     -------
-    ret : list of number
+    ret
+        list of number
     """
     def __init__(self, length, pad_val=0, clip=True):
         self._length = length
@@ -53,7 +54,8 @@ def pad_sequence(sequence: list, max_length=None, pad_val=0, clip=True):
 
     Returns
     -------
-    Modified list:padding the sequence in the same size.
+    Modified list:list
+        padding the sequence in the same size.
 
     Examples
     --------

EduNLP/Pretrain/gensim_vec.py

@@ -194,11 +194,8 @@ def train_vector(items, w2v_prefix, embedding_dim=None, method="sg", binary=None
     ... 若$x,y$满足约束条件公式$\\FormFigureBase64{wrong2?}$,$\\SIFSep$，则$z=x+7 y$的最大值为$\\SIFBlank$")
     >>> print(token_item[:10])
     [['公式'], [\\FormFigureID{wrong1?}], ['如图'], ['[FIGURE]'],...['最大值'], ['[MARK]']]
-    >>> tokenizer = GensimSegTokenizer(symbol="fgm", depth=None)
-    >>> token_item = tokenizer("有公式$\\FormFigureID{wrong1?}$，如图$\\FigureID{088f15ea-xxx}$,\
-    ... 若$x,y$满足约束条件公式$\\FormFigureBase64{wrong2?}$,$\\SIFSep$，则$z=x+7 y$的最大值为$\\SIFBlank$")
-    >>> print(token_item[:10])
-    [['公式'], ['[FORMULA]'], ['如图'], ['[FIGURE]'], ['[FORMULA]'],...['最大值'], ['[MARK]']]
+    >>> train_vector(token_item[:10], "examples/test_model/data/gensim_luna_stem_t_", 100) #doctest: +ELLIPSIS
+    'examples/test_model/data/gensim_luna_stem_t_sg_100.kv'
     """
     monitor = MonitorCallback(["word", "I", "less"])
     _train_params = dict(

EduNLP/SIF/parser/parser.py

@@ -3,8 +3,8 @@
 
 
 class Parser:
+    """initial data and special variable"""
     def __init__(self, data):
-        """initial data and special variable"""
         self.lookahead = 0
         self.head = 0
         self.text = data

EduNLP/SIF/segment/segment.py

@@ -89,7 +89,8 @@ class SegmentList(object):
 
     Returns
     ----------
-    list:tokenizated item
+    list
+        tokenizated item
 
     Examples
     --------
@@ -159,36 +160,45 @@ def append(self, segment) -> None:
 
     @property
     def segments(self):
+        """return segments"""
         if self._seg_idx is None:
             return self._segments
         else:
             return [s for i, s in enumerate(self._segments) if i in self._seg_idx]
 
     @property
     def text_segments(self):
+        """return text segments"""
         return [self._segments[i] for i in self._text_segments]
 
     @property
     def formula_segments(self):
+        """return formula segments"""
         return [self._segments[i] for i in self._formula_segments]
 
     @property
     def figure_segments(self):
+        """return figure segments"""
         return [self._segments[i] for i in self._figure_segments]
 
     @property
     def ques_mark_segments(self):
+        """return question mark segments"""
         return [self._segments[i] for i in self._ques_mark_segments]
 
     @property
     def tag_segments(self):
+        """return tag segments"""
         return [self._segments[i] for i in self._tag_segments]
 
     def to_symbol(self, idx, symbol):
+        """switch element to its symbol"""
         self._segments[idx] = symbol
 
     def symbolize(self, to_symbolize="fgm"):
         """
+        Switch designated elements to symbol. \
+        It is a good way to protect or preserve the elements which we don't want to tokenize.
 
         Parameters
         ----------
@@ -226,6 +236,7 @@ def symbolize(self, to_symbolize="fgm"):
     @contextmanager
     def filter(self, drop: (set, str) = "", keep: (set, str) = "*"):
         """
+        Output special element list selective.Drop means not show.Keep means show.
 
         Parameters
         ----------
@@ -267,6 +278,7 @@ def describe(self):
 
 def seg(item, figures=None, symbol=None):
     r"""
+    It is a interface for SegmentList. And show it in an appropriate way.
 
     Parameters
     ----------
@@ -276,7 +288,8 @@ def seg(item, figures=None, symbol=None):
 
     Returns
     -------
-    list:segmented item
+    list
+        segmented item
 
     Examples
     --------

EduNLP/SIF/sif.py

@@ -12,16 +12,19 @@
 
 def is_sif(item):
     r"""
+    the part aims to check whether the input is sif format
+
     Parameters
     ----------
     item:str
-        the text of question
+        a raw item which respects stem
 
     Returns
     -------
-    when item can not be parsed correctly, raise Error;
-    when item doesn't need to be modified, return Ture;
-    when item needs to be modified, return False;
+    bool
+        when item can not be parsed correctly, raise Error;
+        when item doesn't need to be modified, return Ture;
+        when item needs to be modified, return False;
 
     Examples
     --------
@@ -45,15 +48,17 @@ def is_sif(item):
 
 def to_sif(item):
     r"""
+    the part aims to switch item to sif formate
+
     Parameters
     ----------
     items:str
-        the text of question
+        a raw item which respects stem
 
     Returns
     -------
     item:str
-        the question's text after sif correction
+        the item which accords with sif format
 
     Examples
     --------
@@ -77,7 +82,7 @@ def sif4sci(item: str, figures: (dict, bool) = None, safe=True, symbol: str = No
     Parameters
     ----------
     item:str
-        the text of question
+        a raw item which respects stem
     figures:dict
         {"FigureID": Base64 encoding of the figure}
 
@@ -113,8 +118,9 @@ def sif4sci(item: str, figures: (dict, bool) = None, safe=True, symbol: str = No
 
     Returns
     -------
-    When tokenization is False, return SegmentList;
-    When tokenization is True, return TokenList
+    list
+        When tokenization is False, return SegmentList;
+        When tokenization is True, return TokenList
 
     Examples
     --------

EduNLP/SIF/tokenization/formula/ast_token.py

@@ -35,6 +35,10 @@
 #     return nodes
 
 def traversal_formula(ast, ord2token=False, var_numbering=False, strategy="post", *args, **kwargs):
+    """
+    The part will run only when the return type is list. And it provides two strategy: post and linear.
+    Besides, tokens list will append node follow its type.
+    """
     tokens = []
     if strategy == "post":
         order = nx.dfs_postorder_nodes(ast)
@@ -58,6 +62,7 @@ def traversal_formula(ast, ord2token=False, var_numbering=False, strategy="post"
 
 def ast_tokenize(formula, ord2token=False, var_numbering=False, return_type="formula", *args, **kwargs):
     """
+    According to return type, tokenizing formula by different methods.
 
     Parameters
     ----------

EduNLP/SIF/tokenization/formula/formula.py

@@ -9,6 +9,7 @@
 
 def tokenize(formula, method="linear", errors="raise", **kwargs):
     """
+    The total function to tokenize formula by linear or ast.
 
     Parameters
     ----------

EduNLP/SIF/tokenization/formula/linear_token.py

@@ -7,6 +7,7 @@
 def cut(formula, preserve_braces=True, with_dollar=False,
         preserve_dollar=False, number_as_tag=False, preserve_src=True):  # pragma: no cover
     """
+    cut formula thoroughly
 
     Parameters
     ----------
@@ -24,6 +25,7 @@ def cut(formula, preserve_braces=True, with_dollar=False,
     Returns
     --------
     list
+        return a preliminary list which cut fully
 
     Examples
     ----------
@@ -232,6 +234,8 @@ def latex_parse(formula, preserve_braces=True, with_dollar=True,
 
 def linear_tokenize(formula, preserve_braces=True, number_as_tag=False, *args, **kwargs):
     """
+    linear tokenize formula.
+    It includes three processes:cut, reduce and connect_char.
 
     Parameters
     ----------

EduNLP/SIF/tokenization/text/tokenization.py

@@ -9,6 +9,7 @@
 
 def tokenize(text, granularity="word", stopwords="default"):
     """
+    Using jieba library to tokenize item by word or char.
 
     Parameters
     ----------