20191111用户行为日志

eda/smart_rank/gyz_test.py

@@ -69,7 +69,7 @@ device_info = []
 # sql: select cl_id, collect_set(params["query"]) from bl_hdfs_maidian_updates where partition_date="20191111" and action="do_search" group by cl_id
 with open("/home/gmuser/gyz/log/have_search_device_20191111.csv", "r") as f:
     for line in f.readlines():
-        data = line.strip().split("=")
+        data = line.strip().split("gyz")
         device = data[0]
         search_words = eval(data[1])
         device_info.append([device, search_words])