Commit eab6e659 authored by 张彦钊's avatar 张彦钊

add hospital and doctor

parent c678b151
...@@ -146,7 +146,7 @@ def get_data(): ...@@ -146,7 +146,7 @@ def get_data():
print(start) print(start)
db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test') 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," \ 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,cid_time.time,s.doctor_id " \ "u.device_type,u.manufacturer,u.channel,c.top,cid_time.time,s.doctor_id,s.hospital_id " \
"from esmm_train_data e left join user_feature u on e.device_id = u.device_id " \ "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 cid_time on e.cid_id = cid_time.cid_id " \ "left join cid_type_top c on e.device_id = c.device_id left join cid_time on e.cid_id = cid_time.cid_id " \
"left join service_hospital s on e.diary_service_id = s.id " \ "left join service_hospital s on e.diary_service_id = s.id " \
...@@ -154,11 +154,12 @@ def get_data(): ...@@ -154,11 +154,12 @@ def get_data():
df = con_sql(db, sql) df = con_sql(db, sql)
print(df.shape) print(df.shape)
df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id",4: "clevel1_id", 5: "ccity_name", 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:"time",11:"hospital_id"}) 6:"device_type",7:"manufacturer",8:"channel",9:"top",10:"time",
11:"doctor_id",12:"hospital_id"})
print("esmm data ok") print("esmm data ok")
print(df.head(2)) print(df.head(2))
features = 0 features = 0
category = ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top","hospital_id"] category = ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top","hospital_id","doctor_id"]
for i in category: for i in category:
df[i] = df[i].fillna("na") df[i] = df[i].fillna("na")
features = features + len(df[i].unique()) features = features + len(df[i].unique())
...@@ -196,8 +197,8 @@ def transform(a,validate_date): ...@@ -196,8 +197,8 @@ def transform(a,validate_date):
test = test.drop("stat_date",axis=1) test = test.drop("stat_date",axis=1)
# print("train shape") # print("train shape")
# print(train.shape) # print(train.shape)
train.to_csv(path + "tr_doctor.csv", sep="\t", index=False) train.to_csv(path + "tr_all.csv", sep="\t", index=False)
test.to_csv(path + "va_doctor.csv", sep="\t", index=False) test.to_csv(path + "va_all.csv", sep="\t", index=False)
return model return model
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment