修改测试文件

tensnsorflow/multi.py

@@ -28,7 +28,7 @@ def feature_engineer():
     ti.tidbMapDatabase("jerry_test")
     spark.sparkContext.setLogLevel("WARN")
     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," \
+          "u.channel,c.top,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 " \
           "from esmm_train_data 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 " \
@@ -57,13 +57,13 @@ def feature_engineer():
     df = df.join(hospital,"diary_service_id","left_outer").fillna("na")
     df.show(6)
     print(df.count())
+    df = df.drop(["level2","diary_service_id"])
+
 
 
 
 
 
-    # db = pymysql.connect(host='172.16.30.143', port=3306, user='work',
-    #                      passwd='BJQaT9VzDcuPBqkd', db='zhengxing')
 
 
     # df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
@@ -76,35 +76,8 @@ def feature_engineer():
     #                         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"})
     #
-    # db = pymysql.connect(host='172.16.40.158', 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"})
-    # knowledge["level2"] = knowledge["level2"].astype("str")
-    #
-    # df = pd.merge(df, knowledge, on='level2', how='left')
-    # df = df.drop("level2", axis=1)
-    #
-    # service_id = tuple(df["service_id"].unique())
-    # db = pymysql.connect(host='172.16.30.143', port=3306, user='work',
-    #                      passwd='BJQaT9VzDcuPBqkd', db='zhengxing')
-    # sql = "select s.id,d.hospital_id from api_service s left join api_doctor d on s.doctor_id = d.id " \
-    #       "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")
-    # # 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)
-    #
-    # print(df.count())
-    #
-    # print("before")
-    # 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"])