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
243
244
245
246
| import elasticsearch
import elasticsearch.helpers
import re
import numpy as np
import operator
import datetime
es_client = elasticsearch.Elasticsearch(hosts=["localhost:9200"])
def trim_song_name(song_name):
"""
处理歌名，过滤掉无用内容和空白
"""
song_name = song_name.strip()
song_name = re.sub("【.*?】", "", song_name)
song_name = re.sub("（.*?）", "", song_name)
return song_name
def trim_address_name(address_name):
"""
处理地址
"""
return str(address_name).strip()
def get_data(size=0):
"""
获取uid=>作品名list的字典
"""
cur_size=0
song_dic = {}
user_address_dic = {}
user_decades_dic = {}
search_result = elasticsearch.helpers.scan(
es_client,
index="ktv_user_info",
doc_type="ktv_works",
scroll="10m",
query={
"query":{
"range": {
"birthday": {
"gt": 63072662400
}
)
for hit_item in search_result:
cur_size += 1
if size>0 and cur_size>size:
break
user_info = hit_item["_source"]
item = get_work_info(hit_item["_id"])
if item is None:
continue
work_list = item['item_list']
if len(work_list)<2:
if user_info['gender']==0:
if user_info['gender']==1:
user_info['gender']="男"
if user_info['gender']==2:
user_info['gender']="女"
song_dic[item['uid']] = [trim_song_name(item['songname']) for item in work_list]
user_decades_dic[item['uid']] = user_info['gender']
user_address_dic[item['uid']] = trim_address_name(user_info['address'])
return (song_dic, user_address_dic, user_decades_dic)
def get_user_info(uid):
"""
获取用户信息
"""
ret = es_client.get(
id=uid
)
return ret['_source']
def get_work_info(uid):
"""
"""
try:
index="ktv_works",
)
except Exception as ex:
return None
def get_uniq_song_sort_list(song_dict):
"""
合并重复歌曲并按歌曲名排序
"""
return sorted(list(set(np.concatenate(list(song_dict.values())).tolist())))
from sklearn import preprocessing
%run label_encoder.ipynb
user_count = 4000
song_count = 0
# 获得用户唱歌数据
song_dict, user_address_dict, user_decades_dict = get_data(user_count)
# 歌曲字典
song_label_encoder = LabelEncoder()
song_label_encoder.fit_dict(song_dict, "", True)
song_hot_matrix = song_label_encoder.encode_hot_dict(song_dict, True)
user_decades_encoder = LabelEncoder()
user_decades_encoder.fit_dict(user_decades_dict)
decades_hot_matrix = user_decades_encoder.encode_hot_dict(user_decades_dict, False)
```
##### song_hot_matrix
uid
洗刷刷
麻雀
你的答案
0
0
1
0
1
1
1
0
2
1
0
0
3
0
0
0
##### decades_hot_matrix
uid
男
女
0
1
0
1
0
1
2
1
0
3
0
1
##### 模型训练
```sql
from keras.models import Sequential
from keras.layers import Dense, Activation, Embedding,Flatten
import matplotlib.pyplot as plt
from keras.utils import np_utils
from sklearn import datasets
from sklearn.model_selection import train_test_split
n_class=user_decades_encoder.get_class_count()
song_count=song_label_encoder.get_class_count()
print(n_class)
print(song_count)
# 拆分训练数据和测试数据
train_X,test_X, train_y, test_y = train_test_split(song_hot_matrix,
decades_hot_matrix,
test_size = 0.2,
random_state = 0)
train_count = np.shape(train_X)[0]
# 构建神经网络模型
model = Sequential()
model.add(Dense(input_dim=8, units=n_class))
model.add(Activation('softmax'))
# 选定loss函数和优化器
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
# 训练过程
print('Training -----------')
for step in range(train_count):
scores = model.train_on_batch(train_X, train_y)
if step % 50 == 0:
print("训练样本 %d 个, 损失: %f, 准确率: %f" % (step, scores[0], scores[1]*100))
print('finish!')
```
##### 准确率测试集评估
数据训练完了用拆分出来的20%数据测试一下：
# 准确率评估
```java
from sklearn.metrics import classification_report
scores = model.evaluate(test_X, test_y, verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
Y_test = np.argmax(test_y, axis=1)
y_pred = model.predict_classes(test_X)
print(classification_report(Y_test, y_pred))
|
