2020腾讯广告大赛 ：13.5 baseline

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


import os
from qcloud_cos import CosConfig
from qcloud_cos import CosS3Client
from ti.utils import get_temporary_secret_and_token

#### 指定本地文件路径，可根据需要修改。
local_file = "/home/tione/notebook/df_fea_result.csv"

#### 用户的存储桶，修改为存放所需数据文件的存储桶，存储桶获取参考腾讯云对象存储
bucket="game"

#### 用户的数据，修改为对应的数据文件路径，文件路径获取参考腾讯云对象存储
data_key="contest/df_fea_result.csv"

#### 获取用户临时密钥
secret_id, secret_key, token = get_temporary_secret_and_token()
config = CosConfig(Region=os.environ.get('REGION'), SecretId=secret_id, SecretKey=secret_key, Token=token, Scheme='https')
client = CosS3Client(config)

####  获取文件到本地
response = client.get_object(
    Bucket=bucket,
    Key=data_key,
)
response['Body'].get_stream_to_file(local_file)


data_key="contest/df_fea_tfidf.csv"

# cos 文件会被复制到本地文件，所以local_file 就是本地文件，notebook中要读取的是本地文件
local_file = "/home/tione/notebook/df_fea_tfidf.csv"


response = client.get_object(
    Bucket=bucket,
    Key=data_key,
)
response['Body'].get_stream_to_file(local_file)

print("load data file over ")

1
2
3

!pip install lightgbm

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
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326

!pip install wget
import wget, tarfile
import zipfile


def getData(file):
    filename = wget.download(file)
    print(filename)
    zFile = zipfile.ZipFile(filename, "r")
    res=[]
    for fileM in zFile.namelist(): 
        
        zFile.extract(fileM, "./")
        res.append(fileM)
        
    zFile.close();
    return res
    
train_file ="https://tesla-ap-shanghai-1256322946.cos.ap-shanghai.myqcloud.com/cephfs/tesla_common/deeplearning/dataset/algo_contest/train_preliminary.zip"    
test_file = "https://tesla-ap-shanghai-1256322946.cos.ap-shanghai.myqcloud.com/cephfs/tesla_common/deeplearning/dataset/algo_contest/test.zip"

train_data_file = getData(train_file)
print("train_data_file = ",train_data_file)

test_data_file = getData(test_file)
print("test_data_file = ",test_data_file)

print("load data file over ")



%matplotlib inline

import pandas as pd
import numpy as np
import os
from tqdm import tqdm
from sklearn.model_selection import StratifiedKFold
from sklearn import metrics
import time
#import lightgbm as lgb
import os, sys, gc, time, warnings, pickle, random

from sklearn.decomposition import TruncatedSVD
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
#from gensim.models import Word2Vec
import gc
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')


%%time


def q10(x):
    return x.quantile(0.1)


def q20(x):
    return x.quantile(0.2)


def q30(x):
    return x.quantile(0.3)


def q40(x):
    return x.quantile(0.4)


def q60(x):
    return x.quantile(0.6)


def q70(x):
    return x.quantile(0.7)


def q80(x):
    return x.quantile(0.8)


def q90(x):
    return x.quantile(0.9)


# 组合变量的统计数据
def basic3_digital_features(group):
    data = group
    fea = []
    fea.append(data.mode().values[0])
    fea.append(data.max())
    fea.append(data.min())
    fea.append(data.mean())
    fea.append(data.ptp())
    fea.append(data.std())
    fea.append(data.median())
    return fea


# 获取这个特征下的统计次数
def get_fea_max(df,df_train,cols,flag):
    
    for col in cols:
        df[col+'_click_sum'] = df.groupby(['user_id',col])['click_times'].transform('sum')
        df = df.sort_values([col+'_click_sum','product_id'], ascending=[False,False])
        df_new=df.drop_duplicates('user_id', keep='first')
        
        #df_new = df.sort_values([col+'_click_sum','product_id'], ascending=[False,False])[['user_id',col+'_click_sum',col]].groupby('user_id', as_index=False).first()

        df_new[str(flag)+'_max_'+col]=df_new[col].astype(int)
        df_train = pd.merge(df_train, df_new[['user_id',str(flag)+'_max_'+col]], on='user_id', how='left')

    return df_train

def get_fea_time_max(df,cols,flag):
    print(" - - "*5+" flag = "+str(flag)+" - - "*5)
    timeSplit = getSplitList(df,"time",flag)
    
    df_fea = df[['user_id']].drop_duplicates('user_id')
    
    i=1
    for times in timeSplit:
        time_set = set(times)
        df_new = df.loc[df['time'].isin(time_set)]
        
        
        #print("  df_new.shape =  ",df_new.shape)
        
        
        df_key=df_new[['user_id']].drop_duplicates('user_id')
        df_fea_max = get_fea_max(df_new,df_key,cols,str(flag)+"_"+str(i))
        #df_fea = pd.concat([df_fea,df_fea_max],ignore_index=True)
        #print("df_fea_max.columns",df_fea_max.columns)
        df_fea = pd.merge(df_fea, df_fea_max, on='user_id', how='left')
        
        i=i+1

    return df_fea


def get_fea_time(df,df_train,cols):

#     df_new = get_fea_time_max(df,cols,1)
#     df_train = pd.merge(df_train, df_new, on='user_id', how='left')
#     del df_new

    df_new = get_fea_time_max(df,cols,7)
    df_train = pd.merge(df_train, df_new, on='user_id', how='left')
    del df_new

    df_new = get_fea_time_max(df,cols,10)
    df_train = pd.merge(df_train, df_new, on='user_id', how='left')
    del df_new
    return df_train


# 点击次数统计
def get_click_max(df,df_train):
    df['click_sum'] = df.groupby('user_id')['click_times'].transform('sum')
    df_new=df.drop_duplicates('user_id')

    df_train = pd.merge(df_train, df_new[['user_id','click_sum']], on='user_id', how='left')
    
    print("get_click_max df_train.shape=",df_train.shape)
    return df_train

def get_fea(df):
    df_train = df[['user_id']].drop_duplicates('user_id') #.to_frame()
    
    fea_columns=['creative_id', 'ad_id', 'product_id', 'product_category','advertiser_id', 'industry']
    df_train = get_fea_time(df,df_train,fea_columns)
    #print("df_train.shpe = ",df_train.shape)
    
    df_train = get_click_max(df,df_train)
    
    #df_train = get_statistic_fea(df,df_train,fea_columns)
    
    stat_functions = ['min',  'mean', 'median', 'nunique',  q20,  q40, q60, q80]
    stat_ways = ['min', 'mean', 'median', 'nunique',  'q_20',  'q_40', 'q_60', 'q_80']

    feat_col = ['creative_id', 'ad_id','advertiser_id',]
    group_tmp = df.groupby('user_id')[feat_col].agg(stat_functions).reset_index()

    group_tmp.columns = ['user_id'] + ['{}_{}'.format(i, j) for i in feat_col for j in stat_ways]
    df_train = df_train.merge(group_tmp, on='user_id', how='left')

    df_train.replace("\N",'0',inplace=True)

    return df_train


def get_data_fea(df_train,df_test):
    #df_litt = df_train[(df_train['time']<92) & (df_train['time']>88) ]
    df_all = pd.concat([df_train,df_test],ignore_index=True)
    print("df_all.shape=",df_all.shape)

    user_key = df_all[['user_id','age','gender']].drop_duplicates('user_id')#.to_frame()

    df_fea = pd.DataFrame()

    keys = list(df_all['user_id'].drop_duplicates())
    print("keys.keys=",len(keys))
    page_size = 100000
    user_list = [keys[i:i+page_size] for i in range(0,len(keys),page_size)]
    #user_list = np.array(keys).reshape(-1, 10)
    i=0
    for users in user_list:
        i=i+1
        print(' i = ',i)
        user_set = set(users)
        df_new = df_all.loc[df_all['user_id'].isin(user_set)]
        df_new_fea = get_fea(df_new)

        df_fea = pd.concat([df_fea,df_new_fea],ignore_index=True)
        print("df_fea.shape=",df_fea.shape)
        del df_new_fea
        gc.collect()
    
    df_fea = df_fea.merge(user_key, on='user_id', how='left')

    return df_fea




train_data_file =  ['train_preliminary/', 'train_preliminary/ad.csv', 'train_preliminary/click_log.csv', 'train_preliminary/user.csv', 'train_preliminary/README']

test_data_file =  ['test/', 'test/ad.csv', 'test/click_log.csv', 'test/README']



file_Path = '/Users/zn/Public/work/data/train_preliminary/'

file_Path = "train_preliminary/"

click_file_name = 'click_log.csv'

user_file_name = 'user.csv'

ad_file_name = 'ad.csv'

file_Path_test = "test/"

test_ad_file_name = 'ad.csv'
test_click_file_name = 'click_log.csv'

bool_only_test_flag = False # True False

train_filter = False

df_user =pd.read_csv(file_Path+user_file_name,na_values=['n'])
df_ad =pd.read_csv(file_Path+ad_file_name,na_values=['n'])

df_ad_test =pd.read_csv(file_Path_test+test_ad_file_name,na_values=['n'])


%%time
# 这个数据集最大

def get_data(file_name,flag,sample_flag):
    df_click = pd.DataFrame()
    nrows = 40000
    if sample_flag:
        df_click = pd.read_csv(file_name,nrows=nrows,na_values=['n']) 
    else :
        df_click =pd.read_csv(file_name,na_values=['n']) 

    if flag =="train":
        df = pd.merge(df_click,df_ad,on='creative_id', how='left')
        df = pd.merge(df,df_user,on='user_id', how='left')
    else :
        df = pd.merge(df_click,df_ad_test,on='creative_id', how='left')
        
    df = df.fillna(0)
    print("df.shape=",df.shape)
    return df

sample_flag = False  # False  True

df_train = get_data(file_Path+click_file_name,"train",sample_flag)  


keys = list(df_train['user_id'].drop_duplicates())
print("df_train keys.keys=",len(keys))

df_test = get_data(file_Path_test+test_click_file_name,"test",sample_flag)


keys = list(df_test['user_id'].drop_duplicates())
print("df_test keys.keys=",len(keys))

print(" load data over")



#df_train = df_train[(df_train['time']<92) & (df_train['time']>80) ]

df_test['age'] = -1
df_test['gender'] = -1

df_train.replace("\N",'0',inplace=True)
print("df_train.shape",df_train.shape)

df_test.replace("\N",'0',inplace=True)
print("df_test.shape",df_test.shape)

df_fea = get_data_fea(df_train,df_test)

#df_fea_test = get_data_fea(pd.DataFrame(),df_test)


#df_fea = pd.concat([df_fea_train,df_fea_test],ignore_index=True)

fea_path = 'df_fea_result.csv'
df_fea.to_csv(fea_path, index=None, encoding='utf_8_sig')
print("df_fea.shape = ",df_fea.shape)

from ti import session
ti_session = session.Session()
inputs = ti_session.upload_data(path=fea_path, bucket="game-1253710071", key_prefix="contest")
print("upload over ")

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
%matplotlib inline

import pandas as pd
import numpy as np
import os
from tqdm import tqdm
from sklearn.model_selection import StratifiedKFold
from sklearn import metrics
import time
import lightgbm as lgb
import os, sys, gc, time, warnings, pickle, random

from sklearn.decomposition import TruncatedSVD
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
#from gensim.models import Word2Vec

from ti import session

import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')


%%time
def lgb_model(X,y,x_test,user_label,n_class,flag):

    params = {
        'learning_rate': 0.05,
        'boosting_type': 'gbdt',
        'objective': 'multiclass',
        'metric': 'None',
        'num_leaves': 63,
        'feature_fraction': 0.8,
        'bagging_fraction': 0.8,
        'bagging_freq': 5,
        'seed': 1,
        'bagging_seed': 1,
        'feature_fraction_seed': 7,
        'min_data_in_leaf': 20,
        'num_class': n_class,
        'nthread': 8,
        'verbose': -1
    }

    fold = StratifiedKFold(n_splits=5, shuffle=True, random_state=64)
    
    lgb_models = []
    lgb_pred = np.zeros((len(user_label),n_class))
    lgb_oof = np.zeros((len(X), n_class))
    for index, (train_idx, val_idx) in enumerate(fold.split(X, y)):

        train_set = lgb.Dataset(X.iloc[train_idx], y.iloc[train_idx])
        val_set = lgb.Dataset(X.iloc[val_idx], y.iloc[val_idx])

        model = lgb.train(params, train_set, valid_sets=[train_set, val_set], verbose_eval=200)
        lgb_models.append(model)

        val_pred = model.predict(X.iloc[val_idx])
        #result_to_csv(train_label,model.predict(X),"lgb_"+str(index))
        lgb_oof[val_idx] = val_pred
        val_y = y.iloc[val_idx]
        val_pred = np.argmax(val_pred, axis=1)
        print(index, 'val f1', metrics.f1_score(val_y, val_pred, average='macro'))
        test_pred = model.predict(x_test)
        lgb_pred += test_pred/5
    
    oof_new = np.argmax(lgb_oof, axis=1)
    print('oof f1', metrics.f1_score(oof_new, y, average='macro'))

    pred_new = np.argmax(lgb_pred, axis=1)
    sub = user_label[['user_id']]
    sub[flag] = pred_new+1

    print(sub[flag].value_counts(1))
    sub.to_csv(flag+'_result.csv', index=None, encoding='utf_8_sig')



file_Path = "df_fea_result.csv"

df_fea =pd.read_csv(file_Path,na_values=['n'])

print("df_fea.shape = ",df_fea.shape)
print("df_fea.columns = ",df_fea.columns)

#df_fea = pd.read_csv(file_Path,nrows=50000,na_values=['n']) 

tfidf_file_Path="df_fea_tfidf.csv"

df_fea_tfidf =pd.read_csv(tfidf_file_Path,na_values=['n'])

print("df_fea_tfidf.shape = ",df_fea_tfidf.shape)
print("df_fea_tfidf.columns = ",df_fea_tfidf.columns)

#df = df_fea.merge(df_fea_tfidf)

fea = df_fea_tfidf.columns
fea_filter= ['age','gender']
fea_merge = [col for col in fea if col not in fea_filter]


df = pd.merge(df_fea,df_fea_tfidf[fea_merge], on="user_id",how='left')

print(" df.shape = ",df.shape)
print(" merge data over ")


%%time

fea = df.columns
fea_filter= ['user_id','age','gender']
fea_train = [col for col in fea if col not in fea_filter]

df_train = df[df['age']> -1]

df_test = df[df['age']==-1]

print(" df_train.shape = ",df_train.shape)

print(" df_test.shape = ",df_test.shape)

X= df_train[fea_train]
y= df_train['age']-1

x_test = df_test[fea_train]
user_label = df_test['user_id']
print("len(user_label)=",len(user_label))
age_class =10

lgb_model(X,y,x_test,df_test,age_class,'predicted_age')

print(" - "*7+" 性别 "+" - "*7)
x_test = df_test[fea_train]
user_label = df_test['user_id']
y= df_train['gender']-1
gender_class = 2
lgb_model(X,y,x_test,df_test,gender_class,'predicted_gender')


age_result = "predicted_age_result.csv"

gender_result = "predicted_gender_result.csv"

df_age_test = pd.read_csv(age_result) 
df_gender_test = pd.read_csv(gender_result)


print(df_age_test.head(3))

df = pd.merge(df_age_test,df_gender_test[['user_id','predicted_gender']],on='user_id',how='left')

df.to_csv('submission.csv', index=None, encoding='utf_8_sig')