Feature Engineering Basics

This example demonstrates the basic feature engineering workflow in MoDeVa: queue transformers, execute them, and inspect the results. We use the CaliforniaHousing dataset with thr

Open In Colab 

# %%
# Setup
# -----
# Import libraries and suppress warnings.

import warnings
warnings.filterwarnings("ignore")

import numpy as np
from modeva import DataSet

# %%
# Load Dataset
# ------------
# Load the CaliforniaHousing dataset and create a random train/test split.

ds = DataSet()
ds.load(name="CaliforniaHousing")
ds.set_random_split()

# Keep a copy of the raw (un-engineered) data to demonstrate transforming
# new data later; ds.to_df() reflects the engineered frame after execution.
raw_df = ds.to_df()

print(f"Features: {ds.feature_names}")
print(f"Number of features: {len(ds.feature_names)}")
print(f"Training samples: {ds.train_x.shape[0]}")

# %%
# Queue Feature Engineering Steps
# -------------------------------
# Feature engineering uses a deferred execution pattern: first queue
# the transformers, then execute them all at once.

# Bivector features: pairwise products x_i * x_j
ds.fe_bivector(max_features=20, selection="variance")

# Whitening: SVD-based whitening (GA Mahalanobis transform)
ds.fe_whitening(regularization=1e-8)

# Density: RBF kernel density estimate per sample
ds.fe_density(bandwidth="median", n_reference=200)

# %%
# Execute Feature Engineering
# ---------------------------
# Run all queued steps. Each step fits on the data and appends new columns.

ds.engineer_features()

print(f"Features after engineering: {len(ds.all_feature_names)}")
print(f"New feature names (first 10): {ds.all_feature_names[:10]}")

# %%
# Inspect Results
# ---------------
# Check the feature engineering status.

fe = ds.get_feature_engineer()
status = fe.get_status()
print(f"Executed steps: {[s['name'] for s in status['executed_steps']]}")
print(f"Pending steps: {[s['name'] for s in status['pending_steps']]}")

# %%
# Transform New Data
# ------------------
# Apply the fitted pipeline to the test set.

test_df = raw_df.iloc[:5]
transformed = ds.transform_features(test_df)
print(f"Transformed shape: {transformed.shape}")
print(f"Columns: {list(transformed.columns[:15])}...")

# %%
# Reset
# -----
# Reset feature engineering to restore original features.

ds.reset_feature_engineering()
print(f"Features after reset: {len(ds.all_feature_names)}")