-
Notifications
You must be signed in to change notification settings - Fork 0
/
clase_perfiles.py
141 lines (80 loc) · 4.01 KB
/
clase_perfiles.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
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Jun 21 18:46:01 2017
@author: pablotempone
"""
import pandas as pd
import numpy as np
total = train.append(test)
total = pd.merge(total,movie_genres,how='left',left_on='movieID',right_on='movieID')
usuarios_generos = pd.get_dummies(total[['userID','genre']])
usuarios_generos = usuarios_generos.groupby('userID',as_index=False).sum()
usuarios_generos["sum"] = usuarios_generos.sum(axis=1)
usuarios_generos_perfil = usuarios_generos.loc[:,'genre_Action':'genre_Western'].div(usuarios_generos["sum"], axis=0)
usuarios_generos_perfil.index = usuarios_generos.userID
train_total, test_total = total[0:770088], total[770089:8555598]
train_generos = pd.merge(train,usuarios_generos,how='left',left_on='userID',right_on='userID')
test_generos = pd.merge(test,usuarios_generos,how='left',left_on='userID',right_on='userID')
from sklearn.metrics.pairwise import pairwise_distances
#matriz coseno de usuarios
user_matrix = usuarios_generos.as_matrix()
user_similarity = pairwise_distances(user_matrix, metric='cosine')
#matriz coseno de movies
movies_genres = pd.get_dummies(movie_genres)
movies_genres = movies_genres.groupby('movieID',as_index=False).sum()
movies_genres["sum"] = movies_genres.sum(axis=1)
movies_generos_perfil = movies_genres.loc[:,'genre_Action':'genre_Western'].div(movies_genres["sum"], axis=0)
movies_generos_perfil.index = movies_genres.movieID
movie_matrix = movies_generos_perfil.as_matrix()
movie_similarity = pairwise_distances(movie_matrix, metric='cosine')
#predecir en base a los puntajes
R_df = train_df.pivot(index = 'userID', columns ='movieID', values = 'rating').fillna(0)
R_df.head()
R_df_na = train_df.pivot(index = 'userID', columns ='movieID', values = 'rating')
R_na = R_df_na.as_matrix()
R = R_df.as_matrix()
user_ratings_mean = np.nanmean(R_na, axis = 1)
user_similarity = pairwise_distances(R, metric='cosine')
def predict(ratings,ratings_na, similarity, type='user'):
if type == 'user':
mean_user_rating = np.nanmean(ratings_na,axis=1)
#You use np.newaxis so that mean_user_rating has same format as ratings
ratings_diff = (ratings - mean_user_rating[:, np.newaxis])
pred = mean_user_rating[:, np.newaxis] + similarity.dot(ratings_diff) / np.array([np.abs(similarity).sum(axis=1)]).T
elif type == 'item':
pred = ratings.dot(similarity) / np.array([np.abs(similarity).sum(axis=1)])
return pred
prueba_mean
mean_user_rating = R_na.nanmean(axis=1)
ratings_diff = (R - user_ratings_mean[:, np.newaxis])
promedios = user_ratings_mean[:, np.newaxis]
matriz = user_similarity.dot(ratings_diff)
divisor = np.array([np.abs(user_similarity).sum(axis=1)]).T
division = matriz/divisor
user_prediction = predict(R,R_na, user_similarity, type='user')
#evaluacion
from sklearn.metrics import mean_squared_error
from math import sqrt
def rmse(prediction, ground_truth):
prediction = prediction[ground_truth.nonzero()].flatten()
ground_truth = ground_truth[ground_truth.nonzero()].flatten()
return sqrt(mean_squared_error(prediction, ground_truth))
#prediction = prediction[ground_truth.nonzero()].flatten()
print( 'basado en similaridad CF RMSE: ' + str(rmse(user_prediction, R)))
#normalizado los valores y modificado columnas e indices
R = R_df.as_matrix()
user_ratings_mean = np.mean(R, axis = 1)
R_demeaned = R - user_ratings_mean.reshape(-1, 1)
from scipy.sparse.linalg import svds
U, sigma, Vt = svds(R, k = 50)
sigma = np.diag(sigma)
all_user_predicted_ratings = np.dot(np.dot(U, sigma), Vt) + user_ratings_mean.reshape(-1, 1)
preds_df = pd.DataFrame(all_user_predicted_ratings, columns = R_df.columns)
from scipy.sparse.linalg import svds
U, sigma, Vt = svds(R_demeaned, k = 50)
normalized = (preds_df-min(preds_df))/(max(preds_df)-min(preds_df))
from sklearn import preprocessing
min_max_scaler = preprocessing.MinMaxScaler(feature_range=(0, 5))
x_scaled = min_max_scaler.fit_transform(preds_df)
df = pd.DataFrame(x_scaled,columns=train.movieID.unique(),index=train.userID.unique())