Spaces:
Runtime error
Runtime error
# Copyright 2020 The HuggingFace Datasets Authors and the current | |
# dataset script contributor. | |
# | |
# Licensed under the Apache License, Version 2.0 (the "License"); | |
# you may not use this file except in compliance with the License. | |
# You may obtain a copy of the License at | |
# | |
# http://www.apache.org/licenses/LICENSE-2.0 | |
# | |
# Unless required by applicable law or agreed to in writing, software | |
# distributed under the License is distributed on an "AS IS" BASIS, | |
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
# See the License for the specific language governing permissions and | |
# limitations under the License. | |
""" | |
Get the co-occurance count for two words in each sentece in a dataset. | |
""" | |
import evaluate | |
import datasets | |
from sklearn.feature_extraction.text import CountVectorizer | |
import numpy as np | |
import stanza | |
_DESCRIPTION = """\ | |
Returns the co-occurrence count of two words in the input. | |
""" | |
_CITATION = "" | |
_KWARGS_DESCRIPTION = """ | |
Calculates the co-occurence of two words in each sentence. | |
Args: | |
`data`: a list of `str` which containes a dataset. | |
`words`: list of list of two words that we want to check for | |
Returns: | |
Examples: | |
>>> data = ["hello sun","hello moon", "hello sun"] | |
>>> c_count = evaluate.load("prb977/cooccurrence_count") | |
>>> results = c_count.compute(data=data, words=[['hello','sun']\) | |
>>> print(results) | |
[['hello','sun',3,2]] | |
""" | |
def check_count(x): | |
if x[0].all() <= 0: | |
return 0 | |
return 1 | |
nlp = stanza.Pipeline(lang='en', processors='tokenize') | |
def stanza_tokenizer(sen): | |
doc = nlp(sen) | |
tokens = [] | |
for sen in doc.sentences: | |
for token in sen.tokens: | |
tokens.append(token.text) | |
return tokens | |
class CooccurrenceCount(evaluate.Measurement): | |
"""This measurement returns the co-occurrence count of two words.""" | |
def _info(self): | |
return evaluate.MeasurementInfo( | |
module_type="measurement", | |
description=_DESCRIPTION, | |
citation=_CITATION, | |
inputs_description=_KWARGS_DESCRIPTION, | |
features=datasets.Features({ | |
'data': datasets.Value('string') | |
}), | |
) | |
def _download_and_prepare(self, dl_manager): | |
stanza.download('en', processors='tokenize') | |
def _compute(self, data, words): | |
for each in words: | |
word1 = each[0] | |
word2 = each[1] | |
print(word1) | |
print(word2) | |
len1 = len(stanza_tokenizer(word1)) | |
len2 = len(stanza_tokenizer(word2)) | |
if len1 > len2: | |
ugram = len1 | |
lgram = len2 | |
elif len1 < len2: | |
ugram = len2 | |
lgram = len1 | |
else: | |
ugram = len1 | |
lgram = len1 | |
v = CountVectorizer( | |
ngram_range=(lgram, ugram), | |
tokenizer=stanza_tokenizer, | |
lowercase=True | |
) | |
analyzer = v.build_analyzer() | |
vectorizer = CountVectorizer( | |
ngram_range=(lgram, ugram), | |
vocabulary={ | |
analyzer(word1)[-1]: 0, | |
analyzer(word2)[-1]: 1 | |
}, | |
tokenizer=stanza_tokenizer, | |
lowercase=True | |
) | |
co_occurrences = vectorizer.fit_transform(data) | |
dense_mat = co_occurrences.todense() | |
count = len(data) | |
co_occurrence_count = np.sum( | |
np.apply_along_axis(check_count, axis=1, arr=dense_mat) | |
) | |
each.append(count) | |
each.append(co_occurrence_count) | |
return words | |