feature_engineering.py

# Copy the original data
features = data.copy()

# Select the numeric columns
numeric_subset = data.select_dtypes('number')

# Create columns with log of numeric columns
for col in numeric_subset.columns:
    # Skip the Energy Star Score column
    if col == 'score':
        next
    else:
        numeric_subset['log_' + col] = np.log(numeric_subset[col])
        
# Select the categorical columns
categorical_subset = data[['Borough', 'Largest Property Use Type']]

# One hot encode
categorical_subset = pd.get_dummies(categorical_subset)

# Join the two dataframes using concat
# Make sure to use axis = 1 to perform a column bind
features = pd.concat([numeric_subset, categorical_subset], axis = 1)