-
-
Notifications
You must be signed in to change notification settings - Fork 362
/
Copy pathrecommendation_system_tutorial_netflix.py
242 lines (186 loc) · 9.96 KB
/
recommendation_system_tutorial_netflix.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
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
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
# Recommendation System Tutorial - Netflix
# URL: https://towardsai.net/recommendation-system-tutorial
# Download datasets
!wget https://datasets.towardsai.net/combined_data_4.txt
!wget https://raw.githubusercontent.com/towardsai/tutorials/master/recommendation_system_tutorial/movie_titles.csv
!wget https://raw.githubusercontent.com/towardsai/tutorials/master/recommendation_system_tutorial/new_features.csv
!pip install scikit-surprise
from datetime import datetime
import pandas as pd
import numpy as np
import seaborn as sns
import os
import random
import matplotlib
import matplotlib.pyplot as plt
from scipy import sparse
from sklearn.metrics.pairwise import cosine_similarity
from sklearn.metrics import mean_squared_error
import xgboost as xgb
from surprise import Reader, Dataset
from surprise import BaselineOnly
from surprise import KNNBaseline
from surprise import SVD
from surprise import SVDpp
from surprise.model_selection import GridSearchCV
def load_data():
netflix_csv_file = open("netflix_rating.csv", mode = "w")
rating_files = ['combined_data_4.txt']
for file in rating_files:
with open(file) as f:
for line in f:
line = line.strip()
if line.endswith(":"):
movie_id = line.replace(":", "")
else:
row_data = []
row_data = [item for item in line.split(",")]
row_data.insert(0, movie_id)
netflix_csv_file.write(",".join(row_data))
netflix_csv_file.write('\n')
netflix_csv_file.close()
df = pd.read_csv('netflix_rating.csv', sep=",", names = ["movie_id","customer_id", "rating", "date"])
return df
netflix_rating_df = load_data()
netflix_rating_df
netflix_rating_df.head()
netflix_rating_df.duplicated(["movie_id","customer_id", "rating", "date"]).sum()
split_value = int(len(netflix_rating_df) * 0.80)
train_data = netflix_rating_df[:split_value]
test_data = netflix_rating_df[split_value:]
plt.figure(figsize = (12, 8))
ax = sns.countplot(x="rating", data=train_data)
ax.set_yticklabels([num for num in ax.get_yticks()])
plt.tick_params(labelsize = 15)
plt.title("Count Ratings in train data", fontsize = 20)
plt.xlabel("Ratings", fontsize = 20)
plt.ylabel("Number of Ratings", fontsize = 20)
plt.show()
def get_user_item_sparse_matrix(df):
sparse_data = sparse.csr_matrix((df.rating, (df.customer_id, df.movie_id)))
return sparse_data
train_sparse_data = get_user_item_sparse_matrix(train_data)
test_sparse_data = get_user_item_sparse_matrix(test_data)
global_average_rating = train_sparse_data.sum()/train_sparse_data.count_nonzero()
print("Global Average Rating: {}".format(global_average_rating))
def get_average_rating(sparse_matrix, is_user):
ax = 1 if is_user else 0
sum_of_ratings = sparse_matrix.sum(axis = ax).A1
no_of_ratings = (sparse_matrix != 0).sum(axis = ax).A1
rows, cols = sparse_matrix.shape
average_ratings = {i: sum_of_ratings[i]/no_of_ratings[i] for i in range(rows if is_user else cols) if no_of_ratings[i] != 0}
return average_ratings
average_rating_user = get_average_rating(train_sparse_data, True)
avg_rating_movie = get_average_rating(train_sparse_data, False)
total_users = len(np.unique(netflix_rating_df["customer_id"]))
train_users = len(average_rating_user)
uncommonUsers = total_users - train_users
print("Total no. of Users = {}".format(total_users))
print("No. of Users in train data= {}".format(train_users))
print("No. of Users not present in train data = {}({}%)".format(uncommonUsers, np.round((uncommonUsers/total_users)*100), 2))
total_movies = len(np.unique(netflix_rating_df["movie_id"]))
train_movies = len(avg_rating_movie)
uncommonMovies = total_movies - train_movies
print("Total no. of Movies = {}".format(total_movies))
print("No. of Movies in train data= {}".format(train_movies))
print("No. of Movies not present in train data = {}({}%)".format(uncommonMovies, np.round((uncommonMovies/total_movies)*100), 2))
def compute_user_similarity(sparse_matrix, limit=100):
row_index, col_index = sparse_matrix.nonzero()
rows = np.unique(row_index)
similar_arr = np.zeros(61700).reshape(617,100)
for row in rows[:limit]:
sim = cosine_similarity(sparse_matrix.getrow(row), train_sparse_data).ravel()
similar_indices = sim.argsort()[-limit:]
similar = sim[similar_indices]
similar_arr[row] = similar
return similar_arr
similar_user_matrix = compute_user_similarity(train_sparse_data, 100)
similar_user_matrix[0]
movie_titles_df = pd.read_csv("movie_titles.csv",sep = ",",
header = None, names=['movie_id', 'year_of_release', 'movie_title'],
index_col = "movie_id", encoding = "iso8859_2")
movie_titles_df.head()
def compute_movie_similarity_count(sparse_matrix, movie_titles_df, movie_id):
similarity = cosine_similarity(sparse_matrix.T, dense_output = False)
no_of_similar_movies = movie_titles_df.loc[movie_id][1], similarity[movie_id].count_nonzero()
return no_of_similar_movies
similar_movies = compute_movie_similarity_count(train_sparse_data, movie_titles_df, 1775)
print("Similar Movies = {}".format(similar_movies))
def get_sample_sparse_matrix(sparse_matrix, no_of_users, no_of_movies):
users, movies, ratings = sparse.find(sparse_matrix)
uniq_users = np.unique(users)
uniq_movies = np.unique(movies)
np.random.seed(15)
user = np.random.choice(uniq_users, no_of_users, replace = False)
movie = np.random.choice(uniq_movies, no_of_movies, replace = True)
mask = np.logical_and(np.isin(users, user), np.isin(movies, movie))
sparse_matrix = sparse.csr_matrix((ratings[mask], (users[mask], movies[mask])),
shape = (max(user)+1, max(movie)+1))
return sparse_matrix
train_sample_sparse_matrix = get_sample_sparse_matrix(train_sparse_data, 400, 40)
test_sparse_matrix_matrix = get_sample_sparse_matrix(test_sparse_data, 200, 20)
def create_new_similar_features(sample_sparse_matrix):
global_avg_rating = get_average_rating(sample_sparse_matrix, False)
global_avg_users = get_average_rating(sample_sparse_matrix, True)
global_avg_movies = get_average_rating(sample_sparse_matrix, False)
sample_train_users, sample_train_movies, sample_train_ratings = sparse.find(sample_sparse_matrix)
new_features_csv_file = open("new_features.csv", mode = "w")
for user, movie, rating in zip(sample_train_users, sample_train_movies, sample_train_ratings):
similar_arr = list()
similar_arr.append(user)
similar_arr.append(movie)
similar_arr.append(sample_sparse_matrix.sum()/sample_sparse_matrix.count_nonzero())
similar_users = cosine_similarity(sample_sparse_matrix[user], sample_sparse_matrix).ravel()
indices = np.argsort(-similar_users)[1:]
ratings = sample_sparse_matrix[indices, movie].toarray().ravel()
top_similar_user_ratings = list(ratings[ratings != 0][:5])
top_similar_user_ratings.extend([global_avg_rating[movie]] * (5 - len(ratings)))
similar_arr.extend(top_similar_user_ratings)
similar_movies = cosine_similarity(sample_sparse_matrix[:,movie].T, sample_sparse_matrix.T).ravel()
similar_movies_indices = np.argsort(-similar_movies)[1:]
similar_movies_ratings = sample_sparse_matrix[user, similar_movies_indices].toarray().ravel()
top_similar_movie_ratings = list(similar_movies_ratings[similar_movies_ratings != 0][:5])
top_similar_movie_ratings.extend([global_avg_users[user]] * (5-len(top_similar_movie_ratings)))
similar_arr.extend(top_similar_movie_ratings)
similar_arr.append(global_avg_users[user])
similar_arr.append(global_avg_movies[movie])
similar_arr.append(rating)
new_features_csv_file.write(",".join(map(str, similar_arr)))
new_features_csv_file.write("\n")
new_features_csv_file.close()
new_features_df = pd.read_csv('new_features.csv', names = ["user_id", "movie_id", "gloabl_average", "similar_user_rating1",
"similar_user_rating2", "similar_user_rating3",
"similar_user_rating4", "similar_user_rating5",
"similar_movie_rating1", "similar_movie_rating2",
"similar_movie_rating3", "similar_movie_rating4",
"similar_movie_rating5", "user_average",
"movie_average", "rating"])
return new_features_df
train_new_similar_features = create_new_similar_features(train_sample_sparse_matrix)
train_new_similar_features = train_new_similar_features.fillna(0)
train_new_similar_features.head()
test_new_similar_features = create_new_similar_features(test_sparse_matrix_matrix)
test_new_similar_features = test_new_similar_features.fillna(0)
test_new_similar_features.head()
x_train = train_new_similar_features.drop(["user_id", "movie_id", "rating"], axis = 1)
x_test = test_new_similar_features.drop(["user_id", "movie_id", "rating"], axis = 1)
y_train = train_new_similar_features["rating"]
y_test = test_new_similar_features["rating"]
def error_metrics(y_true, y_pred):
rmse = np.sqrt(mean_squared_error(y_true, y_pred))
return rmse
clf = xgb.XGBRegressor(n_estimators = 100, silent = False, n_jobs = 10)
clf.fit(x_train, y_train)
y_pred_test = clf.predict(x_test)
rmse_test = error_metrics(y_test, y_pred_test)
print("RMSE = {}".format(rmse_test))
def plot_importance(model, clf):
fig = plt.figure(figsize = (8, 6))
ax = fig.add_axes([0,0,1,1])
model.plot_importance(clf, ax = ax, height = 0.3)
plt.xlabel("F Score", fontsize = 20)
plt.ylabel("Features", fontsize = 20)
plt.title("Feature Importance", fontsize = 20)
plt.tick_params(labelsize = 15)
plt.show()
plot_importance(xgb, clf)