Commit a8f0a631 authored by 赵威's avatar 赵威

update click df

parent a6d6d06e
......@@ -6,7 +6,10 @@ def click_feature_engineering(click_df, conversion_df):
# conversion_df = conversion_df.copy()
click_df.rename(columns={"label": "click_label"}, inplace=True)
click_df = click_df.sample(conversion_df.shape[0] * 10)
print("click_df: " + str(click_df.shape))
conversion_df.rename(columns={"label": "conversion_label"}, inplace=True)
print("conversion_df: " + str(conversion_df.shape))
cc_df = pd.merge(click_df, conversion_df, how="left", left_on=["cl_id", "card_id"], right_on=["cl_id", "card_id"])
cc_df.drop(["partition_date_x", "partition_date_y"], axis=1, inplace=True)
cc_df["conversion_label"].fillna(0, inplace=True)
......
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