sif_addition¶

[3]:

from EduNLP.SIF import is_sif, to_sif,sif4sci

is_sif¶

[4]:

 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)

[4]:

True

[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...'
is_sif(text)

[5]:

False

to_sif¶

[6]:

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)

[6]:

'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...'

sif4sci¶

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

[14]:

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

[14]:

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

[15]:

t1.describe()

[15]:

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

[17]:

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

['如图所示', '面积']

[18]:

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

['如图所示', '面积']

[19]:

with t1.filter():
    print(t1)

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

[20]:

t1.text_tokens

[20]:

['如图所示', '面积']

[23]:

t1.formula_tokens

[23]:

['\\bigtriangleup', 'ABC']

[24]:

t1.figure_tokens

[24]:

[\FigureID{1}]

[25]:

t1.ques_mark_tokens

[25]:

['\\SIFBlank']

[26]:

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

[26]:

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

[27]:

sif4sci(test_item, symbol="tfgm")

[27]:

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

[28]:

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

[28]:

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

[29]:

 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"$y < x$"]
  }

[30]:

 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"])
     ]

[33]:

tls

[33]:

[['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']]

[34]:

tls[1:]

[34]:

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

[35]:

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

[35]:

'$\\SIFTag{stem}$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$'

[36]:

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

[37]:

tl1.get_segments()[0]

[37]:

['\\SIFTag{stem}']

[38]:

tl1.get_segments()[1:3]

[38]:

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

[39]:

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

[39]:

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

[41]:

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

[42]:

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

[43]:

test_item_2_str

[43]:

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

[44]:

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

[44]:

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

[45]:

tl2.get_segments(add_seg_type=False)

[45]:

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

[46]:

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

[46]:

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

[47]:

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

[47]:

[['说法', '正确']]

[48]:

tl3.formula_segments

[48]:

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

[49]:

tl3.figure_segments

[49]:

[]

[50]:

tl3.ques_mark_segments

[50]:

[['\\SIFChoice']]

[ ]: