训练集增加日记三级标签、医院id

tensnsorflow/es/feature.py

@@ -40,8 +40,8 @@ def get_data():
     start = (temp - datetime.timedelta(days=300)).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,feat.level2_ids,e.ccity_name," \
-          "u.device_type,u.manufacturer,u.channel,c.top,e.device_id,cut.time,dl.app_list " \
+    sql = "select e.y,e.z,e.stat_date,e.ucity_id,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer," \
+          "u.channel,c.top,e.device_id,cut.time,dl.app_list,e.diary_service_id,feat.level3_ids " \
           "from {} 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_cut cut on e.cid_id = cut.cid " \
@@ -52,31 +52,31 @@ def get_data():
     # print(df.shape)
     df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id", 4: "clevel2_id", 5: "ccity_name",
                             6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "device_id",
-                            11: "time",12:"app_list"})
+                            11: "time",12:"app_list",13:"service_id",14:"level3_ids"})
     print("esmm data ok")
+    print(df.shape)
     # print(df.head(2)
+    service_id = df["service_id"].unique()
+    db = pymysql.connect(host='rdsfewzdmf0jfjp9un8xj.mysql.rds.aliyuncs.com', port=3306, user='work', passwd='BJQaT9VzDcuPBqkd', db='zhengxing')
+    sql = "select s.id,d.hospital_id from api_service s left join api_doctor d on s.doctor_id = d.id where s.id in {}".format(service_id)
+    hospital = con_sql(db, sql)
+    hospital = hospital.rename(columns={0: "service_id", 1: "hospital_id"})
+    df = pd.merge(df, hospital, on='service_id', how='left')
+
     print("before")
     print(df.shape)
     print("after")
     df = df.drop_duplicates()
     df = df.drop_duplicates(["ucity_id", "clevel2_id", "ccity_name", "device_type", "manufacturer",
-                             "channel", "top", "time", "stat_date","app_list"])
+                             "channel", "top", "time", "stat_date","app_list","hospital_id","level3_ids"])
 
     app_list_number,app_list_map = multi_hot(df,"app_list",1)
     level2_number,level2_map = multi_hot(df,"clevel2_id",1+app_list_number)
-    # df["app_list"] = df["app_list"].fillna("lost_na")
-    # app_list_value = [i.split(",") for i in df["app_list"].unique()]
-    # app_list_unique = []
-    # for i in app_list_value:
-    #     app_list_unique.extend(i)
-    # app_list_unique = list(set(app_list_unique))
-    # app_list_map = dict(zip(app_list_unique, list(range(1, len(app_list_unique) + 1))))
-    # df["app_list"] = df["app_list"].apply(app_list_func,args=(app_list_map,))
-
+    level3_number,level3_ids = multi_hot(df, "hospital_id", 1 + app_list_number + level2_number)
 
     unique_values = []
     features = ["ucity_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date"]
+                "channel", "top", "time", "stat_date","hospital_id"]
     for i in features:
         df[i] = df[i].astype("str")
         df[i] = df[i].fillna("lost")
@@ -84,14 +84,14 @@ def get_data():
         df[i] = df[i] + i
         unique_values.extend(list(df[i].unique()))
 
-    temp = list(range(1+app_list_number+level2_number, 1 + app_list_number+level2_number + len(unique_values)))
+    temp = list(range(1+app_list_number+level2_number + level3_number, 1 + app_list_number+level2_number + level3_number + len(unique_values)))
     value_map = dict(zip(unique_values,temp))
 
     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 ["ucity_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date"]:
+                "channel", "top", "time", "stat_date","hospital_id"]:
         train[i] = train[i].map(value_map)
         test[i] = test[i].map(value_map)
 
@@ -193,5 +193,5 @@ if __name__ == '__main__':
     train_data_set = "esmm_train_data"
     path = "/data/esmm/"
     date,value,app_list,level2 = get_data()
-    get_predict(date, value,app_list,level2)
+    # get_predict(date, value,app_list,level2)