-
Notifications
You must be signed in to change notification settings - Fork 289
/
movierecommandation.py
152 lines (131 loc) · 5.73 KB
/
movierecommandation.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
import numpy as np
import pandas as pd
from flask import Flask, render_template, request
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import json
import bs4 as bs
import urllib.request
import pickle
import requests
# load the nlp model and tfidf vectorizer from disk
filename = 'nlp_model.pkl'
clf = pickle.load(open(filename, 'rb'))
vectorizer = pickle.load(open('tranform.pkl','rb'))
def create_similarity():
data = pd.read_csv('main_data.csv')
# creating a count matrix
cv = CountVectorizer()
count_matrix = cv.fit_transform(data['comb'])
# creating a similarity score matrix
similarity = cosine_similarity(count_matrix)
return data,similarity
def rcmd(m):
m = m.lower()
try:
data.head()
similarity.shape
except:
data, similarity = create_similarity()
if m not in data['movie_title'].unique():
return('Sorry! The movie that you have requested is not in our database. Please check the spelling or try with some other movies')
else:
i = data.loc[data['movie_title']==m].index[0]
lst = list(enumerate(similarity[i]))
lst = sorted(lst, key = lambda x:x[1] ,reverse=True)
lst = lst[1:11] # excluding first item since it is the requested movie itself
l = []
for i in range(len(lst)):
a = lst[i][0]
l.append(data['movie_title'][a])
return l
# converting list of string to list (eg. "["abc","def"]" to ["abc","def"])
def convert_to_list(my_list):
my_list = my_list.split('","')
my_list[0] = my_list[0].replace('["','')
my_list[-1] = my_list[-1].replace('"]','')
return my_list
def get_suggestions():
data = pd.read_csv('main_data.csv')
return list(data['movie_title'].str.capitalize())
app = Flask(__name__)
@app.route("/")
@app.route("/home")
def home():
suggestions = get_suggestions()
return render_template('home.html',suggestions=suggestions)
@app.route("/similarity",methods=["POST"])
def similarity():
movie = request.form['name']
rc = rcmd(movie)
if type(rc)==type('string'):
return rc
else:
m_str="---".join(rc)
return m_str
@app.route("/recommend",methods=["POST"])
def recommend():
# getting data from AJAX request
title = request.form['title']
cast_ids = request.form['cast_ids']
cast_names = request.form['cast_names']
cast_chars = request.form['cast_chars']
cast_bdays = request.form['cast_bdays']
cast_bios = request.form['cast_bios']
cast_places = request.form['cast_places']
cast_profiles = request.form['cast_profiles']
imdb_id = request.form['imdb_id']
poster = request.form['poster']
genres = request.form['genres']
overview = request.form['overview']
vote_average = request.form['rating']
vote_count = request.form['vote_count']
release_date = request.form['release_date']
runtime = request.form['runtime']
status = request.form['status']
rec_movies = request.form['rec_movies']
rec_posters = request.form['rec_posters']
# get movie suggestions for auto complete
suggestions = get_suggestions()
# call the convert_to_list function for every string that needs to be converted to list
rec_movies = convert_to_list(rec_movies)
rec_posters = convert_to_list(rec_posters)
cast_names = convert_to_list(cast_names)
cast_chars = convert_to_list(cast_chars)
cast_profiles = convert_to_list(cast_profiles)
cast_bdays = convert_to_list(cast_bdays)
cast_bios = convert_to_list(cast_bios)
cast_places = convert_to_list(cast_places)
# convert string to list (eg. "[1,2,3]" to [1,2,3])
cast_ids = cast_ids.split(',')
cast_ids[0] = cast_ids[0].replace("[","")
cast_ids[-1] = cast_ids[-1].replace("]","")
# rendering the string to python string
for i in range(len(cast_bios)):
cast_bios[i] = cast_bios[i].replace(r'\n', '\n').replace(r'\"','\"')
# combining multiple lists as a dictionary which can be passed to the html file so that it can be processed easily and the order of information will be preserved
movie_cards = {rec_posters[i]: rec_movies[i] for i in range(len(rec_posters))}
casts = {cast_names[i]:[cast_ids[i], cast_chars[i], cast_profiles[i]] for i in range(len(cast_profiles))}
cast_details = {cast_names[i]:[cast_ids[i], cast_profiles[i], cast_bdays[i], cast_places[i], cast_bios[i]] for i in range(len(cast_places))}
# web scraping to get user reviews from IMDB site
sauce = urllib.request.urlopen('https://www.imdb.com/title/{}/reviews?ref_=tt_ov_rt'.format(imdb_id)).read()
soup = bs.BeautifulSoup(sauce,'lxml')
soup_result = soup.find_all("div",{"class":"text show-more__control"})
reviews_list = [] # list of reviews
reviews_status = [] # list of comments (good or bad)
for reviews in soup_result:
if reviews.string:
reviews_list.append(reviews.string)
# passing the review to our model
movie_review_list = np.array([reviews.string])
movie_vector = vectorizer.transform(movie_review_list)
pred = clf.predict(movie_vector)
reviews_status.append('Good' if pred else 'Bad')
# combining reviews and comments into a dictionary
movie_reviews = {reviews_list[i]: reviews_status[i] for i in range(len(reviews_list))}
# passing all the data to the html file
return render_template('recommend.html',title=title,poster=poster,overview=overview,vote_average=vote_average,
vote_count=vote_count,release_date=release_date,runtime=runtime,status=status,genres=genres,
movie_cards=movie_cards,reviews=movie_reviews,casts=casts,cast_details=cast_details)
if __name__ == '__main__':
app.run(debug=True)