Recommender_System/Recommender_System.py at master · tejasai97/Recommender_System · GitHub

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

# coding: utf-8


# In[136]:

import numpy as np
import pandas as pd


# ## Get the Data

# In[137]:

column_names = ['user_id', 'item_id', 'rating', 'timestamp']
df = pd.read_csv('u.data', sep='\t', names=column_names)


# In[138]:

df.head()


# Now let's get the movie titles:

# In[139]:

movie_titles = pd.read_csv("Movie_Id_Titles")
movie_titles.head()


# We can merge them together:

# In[140]:

df = pd.merge(df,movie_titles,on='item_id')
df.head()


# # EDA
#
#
# ## Visualization Imports

# In[160]:

import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style('white')
get_ipython().magic('matplotlib inline')


# In[142]:

df.groupby('title')['rating'].mean().sort_values(ascending=False).head()


# In[143]:

df.groupby('title')['rating'].count().sort_values(ascending=False).head()


# In[144]:

ratings = pd.DataFrame(df.groupby('title')['rating'].mean())
ratings.head()


# In[159]:

ratings['num of ratings'] = pd.DataFrame(df.groupby('title')['rating'].count())
ratings.head()


# In[146]:

plt.figure(figsize=(10,4))
ratings['num of ratings'].hist(bins=70)


# In[147]:

plt.figure(figsize=(10,4))
ratings['rating'].hist(bins=70)


# In[148]:

sns.jointplot(x='rating',y='num of ratings',data=ratings,alpha=0.5)


# In[149]:

moviemat = df.pivot_table(index='user_id',columns='title',values='rating')
moviemat.head()


# Most rated movie:

# In[150]:

ratings.sort_values('num of ratings',ascending=False).head(10)


# Let's choose two movies: starwars, a sci-fi movie. And Liar Liar, a comedy.

# In[161]:

ratings.head()


# In[162]:

starwars_user_ratings = moviemat['Star Wars (1977)']
liarliar_user_ratings = moviemat['Liar Liar (1997)']
starwars_user_ratings.head()


# In[163]:

similar_to_starwars = moviemat.corrwith(starwars_user_ratings)
similar_to_liarliar = moviemat.corrwith(liarliar_user_ratings)


# In[164]:

corr_starwars = pd.DataFrame(similar_to_starwars,columns=['Correlation'])
corr_starwars.dropna(inplace=True)
corr_starwars.head()


# In[155]:

corr_starwars.sort_values('Correlation',ascending=False).head(10)


# In[165]:

corr_starwars = corr_starwars.join(ratings['num of ratings'])
corr_starwars.head()


# In[157]:

corr_starwars[corr_starwars['num of ratings']>100].sort_values('Correlation',ascending=False).head()


# In[158]:

corr_liarliar = pd.DataFrame(similar_to_liarliar,columns=['Correlation'])
corr_liarliar.dropna(inplace=True)
corr_liarliar = corr_liarliar.join(ratings['num of ratings'])
corr_liarliar[corr_liarliar['num of ratings']>100].sort_values('Correlation',ascending=False).head()