修改esmm测试项目

tensnsorflow/es/feature.py

@@ -69,8 +69,8 @@ def get_data():
     hospital = con_sql(db, sql)
     hospital = hospital.rename(columns={0: "service_id", 1: "hospital_id"})
     # print(hospital.head())
-    print("hospital")
-    print(hospital.count())
+    # print("hospital")
+    # print(hospital.count())
     hospital["service_id"] = hospital["service_id"].astype("str")
     df = pd.merge(df, hospital, on='service_id', how='left')
     df = df.drop("service_id", axis=1)
@@ -80,7 +80,10 @@ def get_data():
     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"])
+                             "channel", "top", "time", "stat_date","app_list"])
+
+    # 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)