测试知识图谱的数据,测试60天

tensnsorflow/es/feature.py

@@ -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",
@@ -63,18 +63,20 @@ def get_data():
           "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())
+    # print(hospital.head())
     df = pd.merge(df, hospital, on='service_id', how='left')
     df = df.drop("service_id", axis=1)
 
-    print(df.head())
+    # print(df.head())
 
     print("before")
     print(df.shape)
     print("after")
     df = df.drop_duplicates()
+    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)
 
     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)