test_df

eda/smart_rank/gyz_test.py

@@ -84,7 +84,5 @@ spark.sparkContext.setLogLevel("WARN")
 spark.sparkContext.addPyFile("/srv/apps/ffm-baseline_git/eda/smart_rank/tool.py")
 device_ids_lst_rdd = spark.sparkContext.parallelize(device_info)
 result = device_ids_lst_rdd.repartition(100).map(lambda x: get_user_service_portrait(x, all_word_tags, all_tag_tag_type, all_3tag_2tag, all_tags_name, size=None, pay_time=pay_time))
-# result.foreach(print)
-result_df = result.toDF()
-result_df.to_csv("~/test_df.csv")
+result.write.format('csv').save("~/test_df.csv")
 spark.stop()