sif_addition¶

[1]:

from EduNLP.SIF import is_sif, to_sif,sif4sci

D:\MySoftwares\Anaconda\envs\data\lib\site-packages\gensim\similarities\__init__.py:15: UserWarning: The gensim.similarities.levenshtein submodule is disabled, because the optional Levenshtein package <https://pypi.org/project/python-Levenshtein/> is unavailable. Install Levenhstein (e.g. `pip install python-Levenshtein`) to suppress this warning.
  warnings.warn(msg)

is_sif¶

[2]:

text = '若$x,y$满足约束条件' \
     '$\\left\\{\\begin{array}{c}2 x+y-2 \\leq 0 \\\\ x-y-1 \\geq 0 \\\\ y+1 \\geq 0\\end{array}\\right.$，' \
    '则$z=x+7 y$的最大值$\\SIFUnderline$'

is_sif(text)

[2]:

True

[3]:

text = '某校一个课外学习小组为研究某作物的发芽率y和温度x（单位...'
is_sif(text)

[3]:

False

[4]:

text = '某校一个课外学习小组为研究某作物的发芽率y和温度x（单位...'
is_sif(text, return_parser=True)

[4]:

(False, <EduNLP.SIF.parser.parser.Parser at 0x2a3083fa978>)

to_sif¶

[5]:

text = '某校一个课外学习小组为研究某作物的发芽率y和温度x（单位...'
to_sif(text)

[5]:

'某校一个课外学习小组为研究某作物的发芽率$y$和温度$x$（单位...'

[6]:

import time
# ------------不使用‘加速’机制--------------- #
text = '某校一个课外学习小组为研究某作物的发芽率y和温度x（单位...'*150
start = time.time()
if not is_sif(text):
    siftext = to_sif(text)
print("[1]siftext : {} ,consume time [{}s]".format(siftext[:35], time.time() - start))

# ------------使用‘加速’机制--------------- #
start = time.time()
ret = is_sif(text, return_parser=True)
print("[2]return : ", ret)
if ret[0] is not True:
    siftext = to_sif(text, parser=ret[1])
print("[2]siftext : {} ,consume time [{}s]".format(siftext[:35], time.time() - start))

[1]siftext : 某校一个课外学习小组为研究某作物的发芽率$y$和温度$x$（单位... ,consume time [0.018142223358154297s]
[2]return :  (False, <EduNLP.SIF.parser.parser.Parser object at 0x000002A30840FC88>)
[2]siftext : 某校一个课外学习小组为研究某作物的发芽率$y$和温度$x$（单位... ,consume time [0.008990764617919922s]

sif4sci¶

to_symbolize: - “t”: text - “f”: formula - “g”: figure - “m”: question mark

[7]:

test_item = r"如图所示，则$\bigtriangleup ABC$的面积是$\SIFBlank$。$\FigureID{1}$"
t1 = sif4sci(test_item)
t1

[7]:

['如图所示', '\\bigtriangleup', 'ABC', '面积', '\\SIFBlank', \FigureID{1}]

[8]:

t1.describe()

[8]:

{'t': 2, 'f': 2, 'g': 1, 'm': 1}

[9]:

with t1.filter('fgm'):
    print(t1)

['如图所示', '面积']

[10]:

with t1.filter(keep='t'):
    print(t1)

['如图所示', '面积']

[11]:

with t1.filter():
    print(t1)

['如图所示', '\\bigtriangleup', 'ABC', '面积', '\\SIFBlank', \FigureID{1}]

[12]:

t1.text_tokens

[12]:

['如图所示', '面积']

[13]:

t1.formula_tokens

[13]:

['\\bigtriangleup', 'ABC']

[14]:

t1.figure_tokens

[14]:

[\FigureID{1}]

[15]:

t1.ques_mark_tokens

[15]:

['\\SIFBlank']

[16]:

sif4sci(test_item, symbol="gm", tokenization_params={"formula_params": {"method": "ast"}})

[16]:

['如图所示', <Formula: \bigtriangleup ABC>, '面积', '[MARK]', '[FIGURE]']

[17]:

sif4sci(test_item, symbol="tfgm")

[17]:

['[TEXT]', '[FORMULA]', '[TEXT]', '[MARK]', '[TEXT]', '[FIGURE]']

[18]:

sif4sci(test_item, symbol="gm", tokenization_params={"formula_params": {"method": "ast", "return_type": "list"}})

[18]:

['如图所示', '\\bigtriangleup', 'A', 'B', 'C', '面积', '[MARK]', '[FIGURE]']

[19]:

test_item_1 = {
    "stem": r"若$x=2$, $y=\sqrt{x}$，则下列说法正确的是$\SIFChoice$",
    "options": [r"$x < y$", r"$y = x$", r"$y < x$"]
}

[20]:

tls = [
        sif4sci(e, symbol="gm",
        tokenization_params={
        "formula_params": {
                "method": "ast", "return_type": "list", "ord2token": True, "var_numbering": True,
                "link_variable": False}
        })
        for e in ([test_item_1["stem"]] + test_item_1["options"])
]

[21]:

tls

[21]:

[['mathord_0', '=', 'textord', 'mathord_1', '=', 'mathord_0', '{ }', '\\sqrt', '说法', '正确', '[MARK]'],
 ['mathord_0', '<', 'mathord_1'],
 ['mathord_0', '=', 'mathord_1'],
 ['mathord_0', '<', 'mathord_1']]

[22]:

tls[1:]

[22]:

[['mathord_0', '<', 'mathord_1'],
 ['mathord_0', '=', 'mathord_1'],
 ['mathord_0', '<', 'mathord_1']]

[23]:

from EduNLP.utils import dict2str4sif

test_item_1_str = dict2str4sif(test_item_1, tag_mode="head", add_list_no_tag=False)
test_item_1_str

[23]:

'$\\SIFTag{stem}$若$x=2$, $y=\\sqrt{x}$，则下列说法正确的是$\\SIFChoice$$\\SIFTag{options}$$x < y$$\\SIFSep$$y = x$$\\SIFSep$$y < x$'

[24]:

tl1 = sif4sci(
    test_item_1_str,
    symbol="gm",
    tokenization_params={
        "formula_params": {"method": "ast", "return_type": "list", "ord2token": True}
    })

[25]:

tl1.get_segments()[0]

[25]:

['\\SIFTag{stem}']

[26]:

tl1.get_segments()[1:3]

[26]:

[['[TEXT_BEGIN]', '[TEXT_END]'],
 ['[FORMULA_BEGIN]', 'mathord', '=', 'textord', '[FORMULA_END]']]

[27]:

tl1.get_segments(add_seg_type=False)[0:3]

[27]:

[['\\SIFTag{stem}'],
 ['mathord', '=', 'textord'],
 ['mathord', '=', 'mathord', '{ }', '\\sqrt']]

[28]:

test_item_2 = {"options": [r"$x < y$", r"$y = x$", r"$y < x$"]}

[29]:

test_item_2_str = dict2str4sif(test_item_2, tag_mode="head", add_list_no_tag=False)

[30]:

test_item_2_str

[30]:

'$\\SIFTag{options}$$x < y$$\\SIFSep$$y = x$$\\SIFSep$$y < x$'

[31]:

tl2 = sif4sci(test_item_2_str, symbol="gms",
     tokenization_params={"formula_params": {"method": "ast", "return_type": "list"}})
tl2

[31]:

['\\SIFTag{options}', 'x', '<', 'y', '[SEP]', 'y', '=', 'x', '[SEP]', 'y', '<', 'x']

[32]:

tl2.get_segments(add_seg_type=False)

[32]:

[['\\SIFTag{options}'],
 ['x', '<', 'y'],
 ['[SEP]'],
 ['y', '=', 'x'],
 ['[SEP]'],
 ['y', '<', 'x']]

[33]:

tl2.get_segments(add_seg_type=False, drop="s")

[33]:

[['\\SIFTag{options}'], ['x', '<', 'y'], ['y', '=', 'x'], ['y', '<', 'x']]

[34]:

tl3 = sif4sci(test_item_1["stem"], symbol="gs")
tl3.text_segments

[34]:

[['说法', '正确']]

[35]:

tl3.formula_segments

[35]:

[['x', '=', '2'], ['y', '=', '\\sqrt', '{', 'x', '}']]

[36]:

tl3.figure_segments

[36]:

[]

[37]:

tl3.ques_mark_segments

[37]:

[['\\SIFChoice']]

[ ]: