def fit(self, pipeline_config, X, Y, dataset_info):
categorical_features = dataset_info.categorical_features
ohe = OneHotEncoder(categories="auto",
sparse=False,
handle_unknown="ignore")
encoder = ColumnTransformer(transformers=[
("ohe", ohe, [i for i, f in enumerate(categorical_features) if f])
],
remainder="passthrough")
encoder.categories_ = np.array([])
encoder.categorical_features = categorical_features
if any(categorical_features) and not dataset_info.is_sparse:
# encode X
X = encoder.fit_transform(X)
encoder.categories_ = encoder.transformers_[0][1].categories_
# Y to matrix
Y, y_encoder = self.complete_y_tranformation(Y)
dataset_info.categorical_features = None
return {
'X': X,
'one_hot_encoder': encoder,
'Y': Y,
'y_one_hot_encoder': y_encoder,
'dataset_info': dataset_info
}
def fit(self, pipeline_config, X_train, X_valid, Y_train, Y_valid,
categorical_features):
ohe = OneHotEncoder(categories="auto",
sparse=False,
handle_unknown="ignore")
encoder = ColumnTransformer(transformers=[
("ohe", ohe, [i for i, f in enumerate(categorical_features) if f])
],
remainder="passthrough")
encoder.categories_ = np.array([])
encoder.categorical_features = categorical_features
if any(categorical_features) and not scipy.sparse.issparse(X_train):
# encode X
X_train = encoder.fit_transform(X_train)
if (X_valid is not None):
X_valid = encoder.transform(X_valid)
encoder.categories_ = encoder.transformers_[0][1].categories_
# Y to matrix
y_encoder = None
Y_train = Y_train.astype(np.float32)
if len(Y_train.shape) == 1:
Y_train = Y_train.reshape(-1, 1)
if Y_valid is not None and len(Y_valid.shape) == 1:
Y_valid = Y_valid.reshape(-1, 1)
# encode Y
if self.encode_Y and not scipy.sparse.issparse(Y_train):
y_encoder = OneHotEncoder(sparse=False,
categories="auto",
handle_unknown='ignore')
y_encoder.categories_ = np.array([])
Y_train = y_encoder.fit_transform(Y_train)
if Y_valid is not None:
Y_valid = y_encoder.transform(Y_valid)
return {
'X_train': X_train,
'X_valid': X_valid,
'one_hot_encoder': encoder,
'Y_train': Y_train,
'Y_valid': Y_valid,
'y_one_hot_encoder': y_encoder,
'categorical_features': None
}
