Commit 832532be authored by 张彦钊's avatar 张彦钊

增加查看缺失值的代码

parent a4439c2f
2 merge requests!14nearby queue取top50% 日记队列,因为日记队列变长,造成写入数据库失败,!13nearby queue 取top50%的日记队列,否则日记队列过长,写不进数据库里
...@@ -47,6 +47,7 @@ def get_data(): ...@@ -47,6 +47,7 @@ def get_data():
df = df.drop_duplicates(["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer", df = df.drop_duplicates(["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
"channel", "top", "l1","l2", "time", "stat_date"]) "channel", "top", "l1","l2", "time", "stat_date"])
print(df.shape) print(df.shape)
print(df.count())
unique_values = [] unique_values = []
features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer", features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
......
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