修改esmm测试项目

tensnsorflow/es/feature.py

@@ -32,7 +32,7 @@ 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=60)).strftime("%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,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer," \
@@ -44,7 +44,7 @@ def get_data():
           "left join diary_feat feat on e.cid_id = feat.diary_id " \
           "where e.stat_date >= '{}'".format(train_data_set,start)
     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: "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:"level2"})
@@ -54,11 +54,13 @@ def get_data():
     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)
+    print("knowledge",knowledge.shape)
     knowledge = knowledge.rename(columns={0: "level2", 1: "method", 2: "min", 3: "max",
                                           4: "treatment_time", 5: "maintain_time",6: "recover_time"})
-    print("before",df.shape)
+
     df = pd.merge(df, knowledge, on='level2', how='left')
     print("after",df.shape)
+    print(df.count())
     df = df.drop("level2", axis=1)
 
     service_id = tuple(df["service_id"].unique())
@@ -76,8 +78,7 @@ def get_data():
 
     print("before")
     print(df.shape)
-    print("after")
-    print(df.shape)
+
     df = df.drop_duplicates(["ucity_id", "clevel2_id", "ccity_name", "device_type", "manufacturer",
                              "channel", "top", "time", "stat_date","app_list","hospital_id","level3_ids"])
     print("去重后样本数量:",df.shape)
@@ -152,7 +153,7 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map):
           "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 limit 600"
+          "left join train_Knowledge_network_data k on feat.level2 = k.level2_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",