Commit 595b77d3 authored by 张彦钊's avatar 张彦钊

修改测试文件

parent ca8dbaa3
...@@ -81,7 +81,7 @@ def feature_engineer(): ...@@ -81,7 +81,7 @@ def feature_engineer():
# df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer", # df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
# "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids"]) # "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids"])
# #
# df = df.fillna("na") df = df.fillna("na")
v = set(df.select("app_list").rdd.map(lambda x: x[0]).collect()) v = set(df.select("app_list").rdd.map(lambda x: x[0]).collect())
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment