删除歧义样本

7a5e54d0 · 张彦钊 · bbc59eed · 7a5e54d0
Commit 7a5e54d0 authored Jan 15, 2019 by 张彦钊
Hide whitespace changes
Inline Side-by-side

Showing with 2 additions and 0 deletions

data2ffm.py eda/esmm/Feature_pipline/data2ffm.py +2 -0

No files found.
--- a/eda/esmm/Feature_pipline/data2ffm.py
+++ b/eda/esmm/Feature_pipline/data2ffm.py
@@ -166,6 +166,8 @@ def get_data():
    print(df.shape)
    print("after")
    df = df.drop_duplicates()
+    df = df.drop_duplicates(["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
+                             "channel", "top", "level2_ids", "time","stat_date"])
    print(df.shape)

    df["clevel1_id"] = df["clevel1_id"].astype("str")