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
import pandas as pd
import pymysql
import datetime
def con_sql(db,sql):
cursor = db.cursor()
try:
cursor.execute(sql)
result = cursor.fetchall()
df = pd.DataFrame(list(result))
except Exception:
print("发生异常", Exception)
df = pd.DataFrame()
finally:
db.close()
return df
def get_data():
db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
sql = "select max(stat_date) from esmm_train_data"
validate_date = con_sql(db, sql)[0].values.tolist()[0]
print("validate_date:" + validate_date)
temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
start = (temp - datetime.timedelta(days=30)).strftime("%Y-%m-%d")
print(start)
db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
sql = "select e.y,e.z,e.stat_date,e.ucity_id,e.clevel1_id,e.ccity_name," \
"u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id,cut.time " \
"from esmm_train_data e left join user_feature u on e.device_id = u.device_id " \
"left join cid_type_top c on e.device_id = c.device_id " \
"left join diary_feat df on e.cid_id = df.diary_id " \
"left join cid_time_cut cut on e.cid_id = cut.cid " \
"where e.stat_date >= '{}'".format(start)
df = con_sql(db, sql)
# print(df.shape)
df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id", 4: "clevel1_id", 5: "ccity_name",
6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "level2_ids",
11: "device_id", 12: "time"})
print("esmm data ok")
# print(df.head(2)
print("before")
print(df.shape)
print("after")
df = df.drop_duplicates()
features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
"channel", "top", "level2_ids", "time", "stat_date"]
df = df.drop_duplicates(features)
print(df.shape)
unique_values = []
for i in features:
df[i] = df[i].astype("str")
df[i] = df[i].fillna("lost")
df[i] = df[i] + i
unique_values.extend(list(df[i].unique()))
print(df.head(2))
value_map = {v: k for k, v in enumerate(unique_values)}
df = df.drop("device_id", axis=1)
train = df[df["stat_date"] != validate_date+"stat_date"]
test = df[df["stat_date"] == validate_date+"stat_date"]
for i in features:
train[i] = train[i].map(value_map)
train[i] = train[i].astype('int64')
test[i] = test[i].map(value_map)
test[i] = test[i].astype('int64')
print("train shape")
print(train.shape)
print("test shape")
print(test.shape)
write_csv(train, "tr",100000)
write_csv(test, "va",80000)
return validate_date,value_map
def write_csv(df,name,n):
for i in range(0, df.shape[0], n):
if i == 0:
temp = df.iloc[0:n]
elif i + n > df.shape[0]:
temp = df.iloc[i:]
else:
temp = df.loc[i:i + n]
temp.to_csv(path + name+ "/{}{}.csv".format(name,i), index=False)
def get_predict(date,value_map):
db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
sql = "select e.y,e.z,e.label,e.ucity_id,e.clevel1_id,e.ccity_name," \
"u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id,e.cid_id,cut.time " \
"from esmm_pre_data e left join user_feature u on e.device_id = u.device_id " \
"left join cid_type_top c on e.device_id = c.device_id " \
"left join diary_feat df on e.cid_id = df.diary_id " \
"left join cid_time_cut cut on e.cid_id = cut.cid"
df = con_sql(db, sql)
df = df.rename(columns={0: "y", 1: "z", 2: "label", 3: "ucity_id", 4: "clevel1_id", 5: "ccity_name",
6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "level2_ids",
11: "device_id", 12: "cid_id", 13: "time"})
df["stat_date"] = date
print("predict shape")
print(df.shape)
features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
"channel", "top", "level2_ids", "time", "stat_date"]
for i in features:
df[i] = df[i].astype("str")
df[i] = df[i].fillna("lost")
df[i] = df[i] + i
native_pre = df[df["label"] == 0]
native_pre = native_pre.drop("label", axis=1)
nearby_pre = df[df["label"] == 1]
nearby_pre = nearby_pre.drop("label", axis=1)
for i in features:
native_pre[i] = native_pre[i].map(value_map)
# TODO 没有覆盖到的类别会处理成na，暂时用0填充，后续完善一下
native_pre[i] = native_pre[i].fillna(0)
native_pre[i] = native_pre[i].astype('int64')
nearby_pre[i] = nearby_pre[i].map(value_map)
# TODO 没有覆盖到的类别会处理成na，暂时用0填充，后续完善一下
nearby_pre[i] = nearby_pre[i].fillna(0)
nearby_pre[i] = nearby_pre[i].astype('int64')
print("native")
print(native_pre.shape)
write_csv(native_pre, "native",200000)
print("nearby")
print(nearby_pre.shape)
write_csv(nearby_pre, "nearby", 160000)
if __name__ == '__main__':
path = "/home/gmuser/esmm_data/"
date,value = get_data()
get_predict(date, value)