Created
April 29, 2020 13:40
-
-
Save cereniyim/61e5def417a94de32b323e787d40be77 to your computer and use it in GitHub Desktop.
median imputer function
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
def ImputeWithMedian(train_df, test_df, cols=["price", "year"]): | |
# function to impute price and year | |
# columns with the median value of each | |
# median imputer is fitted on train dataset | |
# transformation done on the train and test set | |
train_df = pd.DataFrame(train_df[cols]) | |
test_df = pd.DataFrame(test_df[cols]) | |
median_imputer = SimpleImputer(strategy="median") | |
median_imputer.fit(train_df) | |
imputed_train_set = median_imputer.transform(train_df) | |
imputed_train_df = pd.DataFrame(imputed_train_set, columns=train_df.columns) | |
imputed_test_set = median_imputer.transform(test_df) | |
imputed_test_df = pd.DataFrame(imputed_test_set, columns=test_df.columns) | |
return imputed_train_df, imputed_test_df |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment