esmm测试项目增加医院id、日记三级类别

tensnsorflow/es/feature.py

@@ -54,14 +54,20 @@ def get_data():
                             6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "device_id",
                             11: "time",12:"app_list",13:"service_id",14:"level3_ids"})
     print("esmm data ok")
-    print(df.shape)
-    # print(df.head(2)
+
+    print(df.head(2))
     service_id = tuple(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)
+    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"})
+    print(hospital.head())
     df = pd.merge(df, hospital, on='service_id', how='left')
+    df = df.drop("service_id", axis=1)
+
+    print(df.head())
 
     print("before")
     print(df.shape)
@@ -70,9 +76,9 @@ def get_data():
     df = df.drop_duplicates(["ucity_id", "clevel2_id", "ccity_name", "device_type", "manufacturer",
                              "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)
-    level3_number,level3_ids = multi_hot(df, "hospital_id", 1 + app_list_number + level2_number)
+    app_list_number,app_list_map = multi_hot(df,"app_list",2)
+    level2_number,level2_map = multi_hot(df,"clevel2_id",2+app_list_number)
+    level3_number,level3_map = multi_hot(df, "level3_ids", 2 + app_list_number + level2_number)
 
     unique_values = []
     features = ["ucity_id", "ccity_name", "device_type", "manufacturer",
@@ -84,7 +90,7 @@ def get_data():
         df[i] = df[i] + i
         unique_values.extend(list(df[i].unique()))
 
-    temp = list(range(1+app_list_number+level2_number + level3_number, 1 + app_list_number+level2_number + level3_number + len(unique_values)))
+    temp = list(range(2+app_list_number+level2_number + level3_number, 2 + app_list_number+level2_number + level3_number + len(unique_values)))
     value_map = dict(zip(unique_values,temp))
 
     df = df.drop("device_id", axis=1)
@@ -103,7 +109,7 @@ def get_data():
     write_csv(train, "tr",100000)
     write_csv(test, "va",80000)
 
-    return validate_date,value_map,app_list_map,level2_map
+    return validate_date,value_map,app_list_map,level2_map,level3_map
 
 
 def app_list_func(x,l):
@@ -128,10 +134,11 @@ def write_csv(df,name,n):
         temp.to_csv(path + name+ "/{}_{}.csv".format(name,i), index=False)
 
 
-def get_predict(date,value_map,app_list_map,level2_map):
+def get_predict(date,value_map,app_list_map,level2_map,level3_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,feat.level2_ids,e.ccity_name," \
-          "u.device_type,u.manufacturer,u.channel,c.top,e.device_id,e.cid_id,cut.time,dl.app_list " \
+          "u.device_type,u.manufacturer,u.channel,c.top,e.device_id,e.cid_id,cut.time," \
+          "dl.app_list,e.hospital_id,feat.level3_ids " \
           "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 cid_time_cut cut on e.cid_id = cut.cid " \
@@ -139,8 +146,8 @@ def get_predict(date,value_map,app_list_map,level2_map):
           "left join diary_feat feat on e.cid_id = feat.diary_id"
     df = con_sql(db, sql)
     df = df.rename(columns={0: "y", 1: "z", 2: "label", 3: "ucity_id", 4: "clevel2_id", 5: "ccity_name",
-                            6: "device_type", 7: "manufacturer", 8: "channel", 9: "top",
-                            10: "device_id", 11: "cid_id", 12: "time",13:"app_list"})
+                            6: "device_type", 7: "manufacturer", 8: "channel", 9: "top",10: "device_id",
+                            11: "cid_id", 12: "time",13:"app_list",14:"hospital_id",15:"level3_ids"})
 
     df["stat_date"] = date
     print(df.head(6))
@@ -148,13 +155,15 @@ def get_predict(date,value_map,app_list_map,level2_map):
     df["app_list"] = df["app_list"].apply(app_list_func,args=(app_list_map,))
     df["clevel2_id"] = df["clevel2_id"].fillna("lost_na")
     df["clevel2_id"] = df["clevel2_id"].apply(app_list_func, args=(level2_map,))
+    df["level3_ids"] = df["level3_ids"].fillna("lost_na")
+    df["level3_ids"] = df["level3_ids"].apply(app_list_func, args=(level3_map,))
 
     # print("predict shape")
     # print(df.shape)
     df["uid"] = df["device_id"]
     df["city"] = df["ucity_id"]
     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")
@@ -166,7 +175,7 @@ def get_predict(date,value_map,app_list_map,level2_map):
     nearby_pre = nearby_pre.drop("label", axis=1)
 
     for i in ["ucity_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date"]:
+                "channel", "top", "time", "stat_date","hospital_id"]:
         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)
@@ -175,7 +184,6 @@ def get_predict(date,value_map,app_list_map,level2_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)
 
-
     print("native")
     print(native_pre.shape)
 
@@ -192,6 +200,6 @@ def get_predict(date,value_map,app_list_map,level2_map):
 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)
+    date,value,app_list,level2,level3 = get_data()
+    get_predict(date, value,app_list,level2,level3)