New sklearn Pipeline for OHE and Imputing vs Pandas homonym

Cat_Cont_Simple_Pipeline.py

# Option 1: Pandas
import pandas as pd
def apply_pipeline(df, categorical_columns, numerical_columns):
    '''
    One Hot Encoding to categorical_columns
    Fill missing values tonumerical_columns
    '''
    for cat_col in categorical_columns:
        df = pd.concat([df, pd.get_dummies(df[cat_col], prefix=cat_col)],axis=1)
        df.drop([cat_col],axis=1, inplace=True)

    for num_col in numerical_columns:
        df[num_col] = df[num_col].fillna(value=-999)

    return df

# Option 2: sklearn 0.20. Careful, it doesn't manage memory as well as Pandas
import pandas as pd
from sklearn.preprocessing import OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline

from sklearn.model_selection import train_test_split

# do not use this function
def apply_pipeline(df, categorical_columns, numerical_columns):
    transformers = []
    features = []
    
    if categorical_columns:
        cat_si_step = ('cat_si', SimpleImputer(strategy='constant',
                           fill_value='MISSING'))
        cat_ohe_step = ('cat_ohe', OneHotEncoder(sparse=False,
                            handle_unknown='ignore'))
        cat_steps = [cat_si_step, cat_ohe_step]
        cat_pipe = Pipeline(cat_steps)
        transformers.append(('cat', cat_pipe, categorical_columns))
    print(1)
    if numerical_columns:
        num_si_step = ('num_si', SimpleImputer(strategy='constant',
                           fill_value=-999))
        num_ohe_step = ('num_ohe', OneHotEncoder(sparse=False,
                            handle_unknown='ignore'))

        num_steps = [num_si_step, num_ohe_step]
        num_pipe = Pipeline(num_steps)
        transformers.append(('num', num_pipe, numerical_columns))
    print(2)
    ct = ColumnTransformer(transformers=transformers)

    df_transformed = ct.fit_transform(df) # memory problems in this line, computer freezes when large (>1M rows) data
    print(3)
    if categorical_columns:
        cat_features = ct.named_transformers_['cat'].named_steps['cat_ohe'].get_feature_names()
        #print('cat_features', cat_features)
        features.extend(cat_features)
    print(4)
    if numerical_columns:
        num_features = ct.named_transformers_['num'].named_steps['num_ohe'].get_feature_names()
        #print('num_features', num_features)
        features.extend(num_features)

    print(5)
    df = pd.concat([df, pd.DataFrame(df_transformed, columns=features, index=df.index)], axis=1)
    print(6)
    df.drop(columns=categorical_columns, inplace=True)
    print(7)
    return df