修改测试文件

tensnsorflow/multi.py

@@ -39,8 +39,6 @@ def feature_engineer():
           "where e.stat_date >= '{}'".format(start)
 
     df = spark.sql(sql)
-    print(df.count())
-    df.show(6)
 
     url = "jdbc:mysql://172.16.30.143:3306/zhengxing"
     jdbcDF = spark.read.format("jdbc").option("driver", "com.mysql.jdbc.Driver").option("url", url) \
@@ -55,19 +53,11 @@ def feature_engineer():
     hospital = spark.sql(sql)
 
     df = df.join(hospital,"diary_service_id","left_outer").fillna("na")
-    df.show(6)
     print(df.count())
     df = df.drop(["level2","diary_service_id"])
-
-
-
-
-
-
-
-
-    # df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
-    #                           "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids"])
+    df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
+                              "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids"])
+    print(df.count())