Supervised Feature Engineering

This example demonstrates supervised feature engineering transformers that use the target variable to generate features. These include RF proximity, spectral proximity, and DirectR

# %%
# 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.

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

print(f"Features: {len(ds.feature_names)}")
print(f"Target: {ds.target_feature_name}")

# %%
# RF Proximity Features
# ---------------------
# Train a random forest and use leaf co-occurrence as a similarity kernel.
# The Nystrom method computes a fixed-width feature map from landmark points.

ds.fe_rf_proximity(n_estimators=50, max_depth=4, n_landmarks=20)

# %%
# DirectRS Stretch Features
# -------------------------
# Build a weighted outer-product matrix from per-leaf centroids and variances,
# decompose via eigendecomposition, and apply the resulting stretch matrix.

ds.fe_direct_rs(n_estimators=30, max_depth=3, regularization=1e-8)

# %%
# Execute All Steps
# -----------------

ds.engineer_features()

print(f"Total features after engineering: {len(ds.all_feature_names)}")

# %%
# Feature Engineering Status
# --------------------------

fe = ds.get_feature_engineer()
status = fe.get_status()
for step in status['executed_steps']:
    print(f"  - {step['name']}")