Last active
May 31, 2018 08:49
-
-
Save dekromp/a9628dc707687ce86e62aff89397af41 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
def encode_categorical(train_data, test_data, feature_name): | |
# Get the unique elements from the training set. | |
unique_elements = train_data[feature_name].dropna().unique() | |
for data in [train_data, test_data]: | |
element_indices = [] | |
for unique_element in unique_elements: | |
# Collect all row indices the element occurs in the data. | |
element_indices += [data[feature_name].index[ | |
data[feature_name].apply(lambda x: x == unique_element)]] | |
# Encode the elements with a category index. | |
for element_encoding, element_indices_i in enumerate(element_indices): | |
data.loc[element_indices_i, feature_name] = element_encoding | |
data[feature_name] = data[feature_name].astype(np.int) | |
# Encode categorical columns as categorical indices. | |
encode_categorical(train_data, test_data, 'Pclass') | |
encode_categorical(train_data, test_data, 'Embarked') | |
encode_categorical(train_data, test_data, 'Sex') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment