Created
April 29, 2020 13:45
-
-
Save cereniyim/add5e70c6ac87e5353aaaf65804c6e9e to your computer and use it in GitHub Desktop.
most frequent 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 ImputeWithMostFrequent(train_df, test_df, | |
cols=["country", "province", | |
"region_1", "variety"]): | |
# function to impute country, province, region_1, variety | |
# columns with the most_frequent value of each feature | |
# most_frequent 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]) | |
most_frequent_imputer = SimpleImputer(strategy="most_frequent") | |
most_frequent_imputer.fit(train_df) | |
imputed_train_set = most_frequent_imputer.transform(train_df) | |
imputed_train_df = pd.DataFrame(imputed_train_set, columns=train_df.columns) | |
imputed_test_set = most_frequent_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