测试知识图谱的数据,测试300天

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=3)).strftime("%Y-%m-%d")
+    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," \
@@ -46,7 +46,7 @@ def get_data():
           "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)
+    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",
@@ -74,7 +74,8 @@ def get_data():
     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","hospital_id","level3_ids"])
+                             "channel", "top", "time", "stat_date","app_list","hospital_id","level3_ids",
+                             "method","min","max","treatment_time","maintain_time","recover_time"])
 
     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)