Last active
March 19, 2019 12:31
-
-
Save datarian/117995b0999d7f734815a91f0750afe3 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from category_encoders.binary import BinaryEncoder | |
from category_encoders.basen import BaseNEncoder | |
from sklearn.compose import ColumnTransformer | |
import pandas as pd | |
import pickle | |
with open("osource.pkl", "rb") as f: | |
osource = pickle.load(f) | |
be = BinaryEncoder(handle_missing="return_nan") | |
osrc_trans = be.fit_transform(osource) | |
print("Returned by calling encoder directly:") | |
print(osrc_trans.info()) | |
print(osrc_trans.isna().sum()) | |
trans = ColumnTransformer([ | |
("be_osource", | |
BinaryEncoder(return_df=False, handle_missing="return_nan"), | |
['OSOURCE']) | |
]) | |
osrc_trans_2 = trans.fit_transform(osource) | |
print("\n\nReturned after processing with columntransformer:") | |
print(pd.DataFrame(osrc_trans_2).info()) | |
print(pd.DataFrame(osrc_trans_2).isna().sum()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment