update

eda/smart_rank/gyz_test.py

@@ -58,7 +58,7 @@ def get_user_service_portrait(x, all_word_tags, all_tag_tag_type, all_3tag_2tag,
             gmkv_tag_score3_sum_dict = {all_tags_name[i]: gmkv_tag_score2_sum_dict[i] for i in gmkv_tag_score2_sum_dict}
             gmkv_tag_score3_sum_dict_sort_list = sorted(gmkv_tag_score3_sum_dict.items(), key=lambda x:x[1],reverse=True)
             portrait_result = [i[0] for i in gmkv_tag_score3_sum_dict_sort_list]
-            return cl_id, str(search_info), str(portrait_result)
+            return cl_id, search_info, portrait_result
 
 # data
 device_info = []
@@ -94,8 +94,8 @@ 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))
-print(result.take(10))
-df = result.toDF()
-df.show()
+print(result.take(100))
+# df = result.toDF()
+# df.show()
 # result.write.format('csv').save("~/test_df.csv")
 spark.stop()