Spaces:
Runtime error
Runtime error
File size: 4,460 Bytes
d9ab710 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 |
# -*- coding: utf-8 -*-
"""Movie_Recommender_System.ipynb
import os
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
"""## Loading Data"""
movies = pd.read_csv('tmdb_5000_movies.csv')
credits = pd.read_csv('tmdb_5000_credits.csv')
movies.head(5)
movies.info()
credits.info()
credits.head(5)
"""## Merging both dataframes : Movies & Credits"""
movies = movies.merge(credits,on='title')
movies.shape
movies.head(1)
"""## Data Pre-Processing"""
#> important columns to be used in recommendation system :
# genres
# id
# keywords
# title
# overview
# cast
# crew
movies = movies[['movie_id','title','overview','genres','cast','keywords','crew']]
movies.head(5)
movies.isnull().sum()
movies.dropna(inplace=True)
movies.isnull().sum()
movies.duplicated().sum()
movies.iloc[0].genres
import ast
# extracting genres from raw data for the creation of tags
def convert(obj):
L = []
for i in ast.literal_eval(obj):
L.append(i['name'])
return L
movies['genres'] = movies['genres'].apply(convert)
movies['keywords'] = movies['keywords'].apply(convert)
movies.head(5)
#function for extracting top 3 actors from the movie
def convert3(obj):
L = []
counter = 0
for i in ast.literal_eval(obj):
if counter !=3:
L.append(i['name'])
counter+=1
else:
break
return L
movies['cast'] = movies['cast'].apply(convert3)
movies.head(5)
#function to fetch the director of movie from crew column
def fetch_director(obj):
L = []
for i in ast.literal_eval(obj):
if i['job'] == 'Director':
L.append(i['name'])
break
return L
movies['crew'] = movies['crew'].apply(fetch_director)
movies.head(5)
movies['overview'] = movies['overview'].apply(lambda x:x.split())
movies.head()
# applying a transformation to remove spaces between words
movies['genres'] = movies['genres'].apply(lambda x:[i.replace(" ","") for i in x])
movies['keywords'] = movies['keywords'].apply(lambda x:[i.replace(" ","") for i in x])
movies['cast'] = movies['cast'].apply(lambda x:[i.replace(" ","") for i in x])
movies['crew'] = movies['crew'].apply(lambda x:[i.replace(" ","") for i in x])
movies.head()
movies['tags'] = movies['overview'] + movies['genres'] + movies['keywords'] + movies['cast'] + movies['crew']
movies.head()
new_df = movies[['movie_id','title','tags']]
new_df['tags'] = new_df['tags'].apply(lambda x:" ".join(x))
new_df.head()
new_df['tags'][0]
new_df['tags'] = new_df['tags'].apply(lambda x:x.lower())
new_df['tags'][0]
"""## Text Vectorization"""
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(max_features=5000,stop_words='english')
vectors = cv.fit_transform(new_df['tags']).toarray()
## Most frequent 5000 words
# cv.get_feature_names()
"""## Applying Stemming Process"""
import nltk #for stemming process
from nltk.stem.porter import PorterStemmer
ps = PorterStemmer()
#defining the stemming function
def stem(text):
y=[]
for i in text.split():
y.append(ps.stem(i))
return " ".join(y)
stem('In the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, but becomes torn between following orders and protecting an alien civilization. Action Adventure Fantasy ScienceFiction cultureclash future spacewar spacecolony society spacetravel futuristic romance space alien tribe alienplanet cgi marine soldier battle loveaffair antiwar powerrelations mindandsoul 3d SamWorthington ZoeSaldana SigourneyWeaver JamesCameron')
new_df['tags'] = new_df['tags'].apply(stem)
"""## Similarity Measures"""
# For calculating similarity, the cosine distance between different vectors will be used.
from sklearn.metrics.pairwise import cosine_similarity
similarity = cosine_similarity(vectors)
"""## Making the recommendation function"""
def recommend(movie):
movie_index = new_df[new_df['title'] == movie].index[0]
distances = similarity[movie_index]
movies_list = sorted(list(enumerate(distances)),reverse=True, key=lambda x:x[1])[1:6]
for i in movies_list:
print(new_df.iloc[i[0]].title)
"""## Recommendation"""
recommend('Batman Begins') #enter movies only which are in the dataset, otherwise it would result in error
new_df.iloc[1216]
"""## Exporting the Model"""
import pickle
pickle.dump(new_df,open('movies.pkl','wb'))
pickle.dump(new_df.to_dict(),open('movie_dict.pkl','wb'))
pickle.dump(similarity,open('similarity.pkl','wb')) |