-
Notifications
You must be signed in to change notification settings - Fork 0
/
movie_recommender.py
66 lines (43 loc) · 1.81 KB
/
movie_recommender.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
import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics.pairwise import cosine_similarity
cv = CountVectorizer()
###### helper functions. Use them when needed #######
def get_title_from_index(index):
return df[df.index == index]["title"].values[0]
def get_index_from_title(title):
return df[df.title == title]["index"].values[0]
##################################################
##Step 1: Read CSV
df = pd.read_csv("D:\Movie Recommendations System\movie_dataset.csv")
# print(df.columns)
##Step 2: Select Features
features = ['keywords','cast','genres','director']
for feature in features:
df[feature] = df[feature].fillna('')
##Step 3: Create a column in DF which combines all selected features
def combine_features(row):
try:
return row['keywords']+" "+row['cast']+" "+row['genres']+" "+row['director']
except:
print('Error:',row)
df['combined_features'] = df.apply(combine_features,axis=1)
# print(df['combined_features'].head())
##Step 4: Create count matrix from this new combined column
count_matrix=cv.fit_transform(df['combined_features'])
##Step 5: Compute the Cosine Similarity based on the count_matrix
cosine_similar = cosine_similarity(count_matrix)
movie_user_likes = "Avatar"
## Step 6: Get index of this movie from its title
movie_index = get_index_from_title(movie_user_likes)
similar_movies = list(enumerate(cosine_similar[movie_index]))
## Step 7: Get a list of similar movies in descending order of similarity score
sorted_similar_movies = sorted(similar_movies,key = lambda x:x[1],reverse=True)
## Step 8: Print titles of first 50 movies
i = 0
for movie in sorted_similar_movies:
print(get_title_from_index(movie[0]))
i = i+1
if(i>=50):
break