Merge pull request #106 from bigdata-ustc/dev

[FEATURE] version upgrade

Author: tswsxk

AUTHORS.md

@@ -16,5 +16,7 @@
 
 [Meikai Bao](https://github.com/BAOOOOOM)
 
+[Yuting Ning](https://github.com/nnnyt)
+
 
 The stared contributors are the corresponding authors. 

CHANGE.txt

@@ -1,3 +1,12 @@
+v0.0.7:
+    1. add BERT and pretrained model (luna_bert)
+    2. speed up the process in sif
+    3. handling OOV in word2vec
+    4. add English tutorials
+    5. add api docs and prettify tutorials
+    6. fix the np.error in gensim_vec.W2V.infer_vector
+    7. fix the parameters lost in tokenization
+
 v0.0.6:
     1. dev: add half-pretrained rnn model
     2. important!!!: rename TextTokenizer to PureTextTokenizer, and add a new tokenizer named TextTokenizer (the two have similar but not the same behaviours).

EduNLP/Formula/Formula.py

@@ -15,6 +15,18 @@
 
 class Formula(object):
     """
+    The part transform a formula to the parsed abstracted syntax tree.
+
+    Parameters
+    ----------
+    formula: str or List[Dict]
+        latex formula string or the parsed abstracted syntax tree
+    variable_standardization
+    const_mathord
+    init
+    args
+    kwargs
+
     Examples
     --------
     >>> f = Formula("x")
@@ -29,22 +41,21 @@ class Formula(object):
     <Formula: x>
     >>> f.elements
     [{'id': 0, 'type': 'mathord', 'text': 'x', 'role': None, 'var': 0}]
-    """
 
+        Attributes
+    ------------
+    ast
+        show all ast details
+    elements
+        just show elements' id, type, text and role
+    ast_graph
+        draw a ast graph
+    to_str
+    resetable
+        return bool
+    """
     def __init__(self, formula: (str, List[Dict]), variable_standardization=False, const_mathord=None,
                  init=True, *args, **kwargs):
-        """
-
-        Parameters
-        ----------
-        formula: str or List[Dict]
-            latex formula string or the parsed abstracted syntax tree
-        variable_standardization
-        const_mathord
-        init
-        args
-        kwargs
-        """
         self._formula = formula
         self._ast = None
         if init is True:
@@ -55,6 +66,15 @@ def __init__(self, formula: (str, List[Dict]), variable_standardization=False, c
             )
 
     def variable_standardization(self, inplace=False, const_mathord=None, variable_connect_dict=None):
+        """
+        It makes same parmeters have the same number.
+
+        Parameters
+        ----------
+        inplace
+        const_mathord
+        variable_connect_dict
+        """
         const_mathord = const_mathord if const_mathord is not None else CONST_MATHORD
         ast_tree = self._ast if inplace else deepcopy(self._ast)
         var_code = variable_connect_dict["var_code"] if variable_connect_dict is not None else {}
@@ -118,6 +138,26 @@ def resetable(self):
 
 class FormulaGroup(object):
     """
+    The part transform a group of formula to the parsed abstracted syntax forest.
+
+    Attributes
+    ------------
+    to_str
+    ast
+        show all ast details
+    elements
+        just show elements' id, type, text and role
+    ast_graph
+        draw a ast graph
+
+    Parameters
+    ----------
+    formula: str or List[Dict] or List[Formula]
+        latex formula string or the parsed abstracted syntax tree or a group of parsed abstracted syntax tree
+    variable_standardization
+    const_mathord
+    detach
+
     Examples
     ---------
     >>> fg = FormulaGroup(["x + y", "y + x", "z + x"])
@@ -128,15 +168,16 @@ class FormulaGroup(object):
     <FormulaGroup: <Formula: x + y>;<Formula: y + x>;<Formula: z + x>>
     >>> fg = FormulaGroup(["x", Formula("y"), "x"])
     >>> fg.elements
-    [{'id': 0, 'type': 'mathord', 'text': 'x', 'role': None}, {'id': 1, 'type': 'mathord', 'text': 'y', 'role': None},\
- {'id': 2, 'type': 'mathord', 'text': 'x', 'role': None}]
+    [{'id': 0, 'type': 'mathord', 'text': 'x', 'role': None}, \
+{'id': 1, 'type': 'mathord', 'text': 'y', 'role': None}, \
+{'id': 2, 'type': 'mathord', 'text': 'x', 'role': None}]
     >>> fg = FormulaGroup(["x", Formula("y"), "x"], variable_standardization=True)
     >>> fg.elements
     [{'id': 0, 'type': 'mathord', 'text': 'x', 'role': None, 'var': 0}, \
 {'id': 1, 'type': 'mathord', 'text': 'y', 'role': None, 'var': 1}, \
 {'id': 2, 'type': 'mathord', 'text': 'x', 'role': None, 'var': 0}]
-    """
 
+    """
     def __init__(self,
                  formula_list: (list, List[str], List[Formula]),
                  variable_standardization=False,
@@ -186,6 +227,15 @@ def __contains__(self, item) -> bool:
         return item in self._formulas
 
     def variable_standardization(self, inplace=False, const_mathord=None, variable_connect_dict=None):
+        """
+        It makes same parmeters have the same number.
+
+        Parameters
+        ----------
+        inplace
+        const_mathord
+        variable_connect_dict
+        """
         ret = []
         for formula in self._formulas:
             ret.append(formula.variable_standardization(inplace=inplace, const_mathord=const_mathord,
@@ -220,6 +270,15 @@ def ast_graph(self) -> (nx.Graph, nx.DiGraph):
 
 
 def link_formulas(*formula: Formula, link_vars=True, **kwargs):
+    """
+
+    Parameters
+    ----------
+    formula
+        the parsed abstracted syntax tree
+    link_vars
+    kwargs
+    """
     forest = []
     for form in formula:
         forest += form.reset_ast(

EduNLP/Formula/ast/ast.py

@@ -8,10 +8,12 @@
 
 
 def katex_parse(formula):
+    """将公式传入katex进行语法解析"""
     return katex.katex.__parse(formula,{'displayMode':True,'trust': True}).to_list()
 
 
 def str2ast(formula: str, *args, **kwargs):
+    """给字符串的接口"""
     return ast(formula, is_str=True, *args, **kwargs)
 
 

EduNLP/Formula/viz/__init__.py

@@ -2,5 +2,5 @@
 # 2021/3/8 @ tongshiwei
 
 import warnings
-warnings.warn("Do not use this package")
+# warnings.warn("Do not use this package")
 from .tree_viz import TreePlotter, ForestPlotter

EduNLP/I2V/__init__.py

@@ -2,4 +2,4 @@
 # 2021/8/1 @ tongshiwei
 
 from .i2v import I2V, get_pretrained_i2v
-from .i2v import D2V, W2V
+from .i2v import D2V, W2V, Bert