change test file

tensnsorflow/multi_hot.py

@@ -206,15 +206,15 @@ def feature_engineer():
 
     df = spark.sql(sql)
 
-    print("train number")
-    print(df.count())
-
     df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
                              "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids",
                              "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7","search_tag2","search_tag3"])
 
     df = df.na.fill(dict(zip(features, features)))
 
+    print("train number")
+    print(df.count())
+
     rdd = df.select("stat_date", "y", "z", "app_list", "level2_ids", "level3_ids",
                     "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7",
                     "ucity_id", "ccity_name", "device_type", "manufacturer", "channel", "top", "time",