change test fliw

eda/esmm/Model_pipline/feature_engineering.py

@@ -267,6 +267,8 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
 
     df = spark.sql(sql)
     df = df.drop_duplicates(["treatment_method","price_min","price_max","treatment_time","maintain_time","recover_time"])
+    print("pre test")
+    print(df.count())
     df = df.na.fill(dict(zip(features, features)))
     f = time.time()
     rdd = df.select("label", "y", "z", "ucity_id", "device_id", "cid_id", "app_list", "level2_ids", "level3_ids",
@@ -297,8 +299,6 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
     print("native csv")
     native_pre.toPandas().to_csv(local_path+"native.csv", header=True)
 
-    print("预测集总数")
-    print(rdd.count())
 # TODO 写成csv文件改成下面这样
     # native_pre.coalesce(1).write.format('com.databricks.spark.csv').save(path+"native/",header = 'true')