firstuseafter column removed from contextual imputation
parent
9b3447febd
commit
6286e7a44c
|
@ -89,8 +89,7 @@ def straw_cleaning(sensor_data_files, provider):
|
||||||
"timefirstcall" in col or
|
"timefirstcall" in col or
|
||||||
"timelastcall" in col or
|
"timelastcall" in col or
|
||||||
"timefirstmessages" in col or
|
"timefirstmessages" in col or
|
||||||
"timelastmessages" in col or
|
"timelastmessages" in col]
|
||||||
"firstuseafter" in col]
|
|
||||||
features[impute_w_hn] = impute(features[impute_w_hn], method="high_number")
|
features[impute_w_hn] = impute(features[impute_w_hn], method="high_number")
|
||||||
|
|
||||||
# Impute phone locations with median
|
# Impute phone locations with median
|
||||||
|
|
|
@ -63,7 +63,6 @@ def rapids_features(sensor_data_files, time_segment, provider, filter_data_by_se
|
||||||
|
|
||||||
if not screen_features.empty:
|
if not screen_features.empty:
|
||||||
screen_features.fillna(value={feature_name: 0 for feature_name in screen_features.columns if not feature_name.startswith(("stdduration", "firstuseafter"))}, inplace=True)
|
screen_features.fillna(value={feature_name: 0 for feature_name in screen_features.columns if not feature_name.startswith(("stdduration", "firstuseafter"))}, inplace=True)
|
||||||
screen_features["firstuseafter"] = screen_features["firstuseafter"].fillna(1000000)
|
|
||||||
screen_features = screen_features.reset_index()
|
screen_features = screen_features.reset_index()
|
||||||
|
|
||||||
return screen_features
|
return screen_features
|
||||||
|
|
Loading…
Reference in New Issue