修改esmm测试项目

tensnsorflow/es/feature.py

@@ -32,29 +32,33 @@ def get_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=300)).strftime("%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=3)).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,e.diary_service_id,feat.level3_ids,k.treatment_method," \
-          "k.price_min,k.price_max,k.treatment_time,k.maintain_time,k.recover_time " \
+          "u.channel,c.top,e.device_id,cut.time,dl.app_list,e.diary_service_id,feat.level3_ids,feat.level2 " \
           "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 " \
           "left join device_app_list dl on e.device_id = dl.device_id " \
           "left join diary_feat feat on e.cid_id = feat.diary_id " \
-          "left join train_Knowledge_network_data k on feat.level2 = k.level2_id " \
           "where e.stat_date >= '{}'".format(train_data_set,start)
     df = con_sql(db, sql)
     # 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",13:"service_id",14:"level3_ids",
-                            15:"method",16:"min",17:"max",18:"treatment_time",19:"maintain_time",20:"recover_time"})
+                            11: "time",12:"app_list",13:"service_id",14:"level3_ids",15:"level2"})
     print("esmm data ok")
 
-    # print(df["method","min","max","treatment_time","maintain_time","recover_time"].head(6))
-    # print(df.count())
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select level2_id,treatment_method,price_min,price_max,treatment_time,maintain_time,recover_time " \
+          "from train_Knowledge_network_data"
+    knowledge = con_sql(db, sql)
+    knowledge = knowledge.rename(columns={0: "level2", 1: "method", 2: "min", 3: "max",
+                                          4: "treatment_time", 5: "maintain_time",6: "recover_time"})
+    print("beifor",df.shape)
+    df = pd.merge(df, knowledge, on='level2', how='left')
+    print("after",df.shape)
 
     service_id = tuple(df["service_id"].unique())
     db = pymysql.connect(host='rdsfewzdmf0jfjp9un8xj.mysql.rds.aliyuncs.com', port=3306, user='work',