Commit a8e00aa1 authored by 赵威's avatar 赵威

update field

parent 735c83c9
...@@ -86,7 +86,7 @@ def device_feature_engineering(df): ...@@ -86,7 +86,7 @@ def device_feature_engineering(df):
nullseries = device_df.isnull().sum() nullseries = device_df.isnull().sum()
print("device:") print("device:")
print(nullseries[nullseries > 0]) print(nullseries[nullseries > 0])
print(device_df.size) print(device_df.shape)
device_columns = [ device_columns = [
"device_id", "active_type", "active_days", "past_consume_ability_history", "potential_consume_ability_history", "device_id", "active_type", "active_days", "past_consume_ability_history", "potential_consume_ability_history",
...@@ -128,7 +128,7 @@ def diary_feature_engineering(df, from_redis=False): ...@@ -128,7 +128,7 @@ def diary_feature_engineering(df, from_redis=False):
print("diary:") print("diary:")
nullseries = diary_df.isnull().sum() nullseries = diary_df.isnull().sum()
print(nullseries[nullseries > 0]) print(nullseries[nullseries > 0])
print(diary_df.size) print(diary_df.shape)
diary_columns = [ diary_columns = [
"card_id", "is_pure_author", "is_have_reply", "is_have_pure_reply", "content_level", "topic_num", "favor_num", "vote_num", "card_id", "is_pure_author", "is_have_reply", "is_have_pure_reply", "content_level", "topic_num", "favor_num", "vote_num",
...@@ -151,7 +151,7 @@ def click_feature_engineering(click_df, conversion_df): ...@@ -151,7 +151,7 @@ def click_feature_engineering(click_df, conversion_df):
print("click:") print("click:")
nullseries = cc_df.isnull().sum() nullseries = cc_df.isnull().sum()
print(nullseries[nullseries > 0]) print(nullseries[nullseries > 0])
print(cc_df.size) print(cc_df.shape)
return cc_df return cc_df
...@@ -209,7 +209,7 @@ def join_features(device_df, diary_df, cc_df): ...@@ -209,7 +209,7 @@ def join_features(device_df, diary_df, cc_df):
print("df:") print("df:")
nullseries = df.isnull().sum() nullseries = df.isnull().sum()
print(nullseries[nullseries > 0]) print(nullseries[nullseries > 0])
print(df.size) print(df.shape)
drop_columns = [ drop_columns = [
"cl_id", "first_demands_x", "first_demands_y", "first_demands", "second_demands_x", "second_demands_y", "second_demands", "cl_id", "first_demands_x", "first_demands_y", "first_demands", "second_demands_x", "second_demands_y", "second_demands",
......
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