admin/38894-vm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix: added document as argument to get_questions_dict

Browse Source
This commit is contained in:
telescopic 2020-10-10 03:10:18 +05:30
parent 91a4426d4b
commit 37af1c41fd
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
question_extraction.py
View File

@ -1,13 +1,13 @@
'''This file contains the module for generating '''This file contains the module for generating
''' '''
import nltk import nltk
import spacy
from nltk.corpus import stopwords from nltk.corpus import stopwords
from nltk.tokenize import sent_tokenize, word_tokenize from nltk.tokenize import sent_tokenize, word_tokenize
from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.feature_extraction.text import TfidfVectorizer
import spacy
class QuestionExtraction: class QuestionExtractor:
''' This class contains all the methods ''' This class contains all the methods
required for extracting questions from required for extracting questions from
a given document a given document
@ -27,7 +27,7 @@ class QuestionExtraction:
self.questions_dict = dict() self.questions_dict = dict()
def get_questions(self, document): def get_questions_dict(self, document):
''' '''
Returns a dict of questions in the format: Returns a dict of questions in the format:
question_number: { question_number: {
@ -98,7 +98,7 @@ class QuestionExtraction:
''' Sets the tf-idf scores for each word''' ''' Sets the tf-idf scores for each word'''
self.unfiltered_sentences = sent_tokenize(document) self.unfiltered_sentences = sent_tokenize(document)
self.filtered_sentences = self.get_filtered_sentences(document) self.filtered_sentences = self.get_filtered_sentences(document)
print(self.unfiltered_sentences)
self.word_score = dict() # (word, score) self.word_score = dict() # (word, score)
# (word, sentence where word score is max) # (word, sentence where word score is max)