import pandas as pd import numpy as np from bs4 import BeautifulSoup import re import nltk from nltk.corpus import stopwords nltk.download('stopwords') import distance from fuzzywuzzy import fuzz import pickle import sklearn from sklearn.feature_extraction.text import CountVectorizer cv = pickle.load(open('cv.pkl', 'rb')) def preprocess(q): q = str(q).lower().strip() q = q.replace('%', ' percent') q = q.replace('$', ' dollar ') q = q.replace('₹', ' rupee ') q = q.replace('€', ' euro ') q = q.replace('@', ' at ') contractions = { "ain't": "am not", "aren't": "are not", "can't": "can not", "can't've": "can not have", "'cause": "because", "could've": "could have", "couldn't": "could not", "couldn't've": "could not have", "didn't": "did not", "doesn't": "does not", "don't": "do not", "hadn't": "had not", "hadn't've": "had not have", "hasn't": "has not", "haven't": "have not", "he'd": "he would", "he'd've": "he would have", "he'll": "he will", "he'll've": "he will have", "he's": "he is", "how'd": "how did", "how'd'y": "how do you", "how'll": "how will", "how's": "how is", "i'd": "i would", "i'd've": "i would have", "i'll": "i will", "i'll've": "i will have", "i'm": "i am", "i've": "i have", "isn't": "is not", "it'd": "it would", "it'd've": "it would have", "it'll": "it will", "it'll've": "it will have", "it's": "it is", "let's": "let us", "ma'am": "madam", "mayn't": "may not", "might've": "might have", "mightn't": "might not", "mightn't've": "might not have", "must've": "must have", "mustn't": "must not", "mustn't've": "must not have", "needn't": "need not", "needn't've": "need not have", "o'clock": "of the clock", "oughtn't": "ought not", "oughtn't've": "ought not have", "shan't": "shall not", "sha'n't": "shall not", "shan't've": "shall not have", "she'd": "she would", "she'd've": "she would have", "she'll": "she will", "she'll've": "she will have", "she's": "she is", "should've": "should have", "shouldn't": "should not", "shouldn't've": "should not have", "so've": "so have", "so's": "so as", "that'd": "that would", "that'd've": "that would have", "that's": "that is", "there'd": "there would", "there'd've": "there would have", "there's": "there is", "they'd": "they would", "they'd've": "they would have", "they'll": "they will", "they'll've": "they will have", "they're": "they are", "they've": "they have", "to've": "to have", "wasn't": "was not", "we'd": "we would", "we'd've": "we would have", "we'll": "we will", "we'll've": "we will have", "we're": "we are", "we've": "we have", "weren't": "were not", "what'll": "what will", "what'll've": "what will have", "what're": "what are", "what's": "what is", "what've": "what have", "when's": "when is", "when've": "when have", "where'd": "where did", "where's": "where is", "where've": "where have", "who'll": "who will", "who'll've": "who will have", "who's": "who is", "who've": "who have", "why's": "why is", "why've": "why have", "will've": "will have", "won't": "will not", "won't've": "will not have", "would've": "would have", "wouldn't": "would not", "wouldn't've": "would not have", "y'all": "you all", "y'all'd": "you all would", "y'all'd've": "you all would have", "y'all're": "you all are", "y'all've": "you all have", "you'd": "you would", "you'd've": "you would have", "you'll": "you will", "you'll've": "you will have", "you're": "you are", "you've": "you have" } q_decontracted = [] for word in q.split(): if word in contractions: word = contractions[word] q_decontracted.append(word) q = ' '.join(q_decontracted) q = q.replace("'ve", " have") q = q.replace("n't", " not") q = q.replace("'re", " are") q = q.replace("'ll", " will") # Removing HTML tags q = BeautifulSoup(q) q = q.get_text() # Remove punctuations pattern = re.compile('\W') q = re.sub(pattern, ' ', q).strip() return q def test_common_words(q1, q2): w1 = set(map(lambda words : words.lower().strip(), q1.split(" "))) w2 = set(map(lambda words : words.lower().strip(), q2.split(" "))) return len(w1 & w2) def test_total_words(q1, q2): w1 = set(map(lambda words : words.strip(), q1.split(" "))) w2 = set(map(lambda words : words.strip(), q2.split(" "))) return (len(w1) + len(w2)) def fetch_test_features(q1, q2): SAFE_DIV = 0.00001 STOP_WORDS = stopwords.words('english') token_features = [0.0] * 11 q1_tokens = q1.split() q2_tokens = q2.split() if len(q1_tokens) == 0 or len(q2_tokens) == 0: return token_features q1_words = set([word for word in q1_tokens if word not in STOP_WORDS]) q2_words = set([word for word in q2_tokens if word not in STOP_WORDS]) q1_stop = set([word for word in q1_tokens if word in STOP_WORDS]) q2_stop = set([word for word in q2_tokens if word in STOP_WORDS]) common_word_cnt = len(q1_words.intersection(q2_words)) common_stop_cnt = len(q1_stop.intersection(q2_stop)) common_token_cnt = len(set(q1_tokens).intersection(set(q2_tokens))) token_features[0] = round(common_word_cnt / (min(len(q1_words), len(q2_words)) + SAFE_DIV), 2) token_features[1] = round(common_word_cnt / (max(len(q1_words), len(q2_words)) + SAFE_DIV), 2) token_features[2] = round(common_stop_cnt / (min(len(q1_stop), len(q2_stop)) + SAFE_DIV), 2) token_features[3] = round(common_stop_cnt / (max(len(q1_stop), len(q2_stop)) + SAFE_DIV), 2) token_features[4] = round(common_token_cnt / (min(len(q1_tokens), len(q2_tokens)) + SAFE_DIV), 2) token_features[5] = round(common_token_cnt / (max(len(q1_tokens), len(q2_tokens)) + SAFE_DIV), 2) token_features[6] = int(q1_tokens[-1] == q2_tokens[-1]) token_features[7] = int(q1_tokens[0] == q2_tokens[0]) token_features[8] = abs(len(q1_tokens) - len(q2_tokens)) token_features[9] = round((len(q1_tokens) - len(q2_tokens)) / 2, 2) strs = list(distance.lcsubstrings(q1, q2)) token_features[10] = round(len(strs[0]) / (min(len(q1), len(q2)) + 1), 2) return token_features def fetch_test_fuzzy_features(q1, q2): fuzzy_features = [0.0] * 4 # fuzz_ratio fuzzy_features[0] = fuzz.QRatio(q1, q2) # fuzz_partial_ratio fuzzy_features[1] = fuzz.partial_ratio(q1, q2) # token_sort_ratio fuzzy_features[2] = fuzz.token_sort_ratio(q1, q2) # token_set_ratio fuzzy_features[3] = fuzz.token_set_ratio(q1, q2) return fuzzy_features def query_point_creator(q1, q2): input_query = [] q1 = preprocess(q1) q2 = preprocess(q2) input_query.append(len(q1)) input_query.append(len(q2)) input_query.append(len(q1.split(" "))) input_query.append(len(q2.split(" "))) input_query.append(test_common_words(q1, q2)) input_query.append(test_total_words(q1, q2)) input_query.append(round(input_query[4] / input_query[5], 2)) token_features = fetch_test_features(q1, q2) input_query.extend(token_features) fuzzy_features = fetch_test_fuzzy_features(q1, q2) input_query.extend(fuzzy_features) q1_arr = cv.transform([q1]).toarray() q2_arr = cv.transform([q2]).toarray() return np.hstack((np.array(input_query).reshape(1, 22), q1_arr, q2_arr))