Lab 1: Python Foundation & Regression

NumPy Essentials

Purpose	Functions
Combine	np.concatenate np.stack np.hstack np.vstack
Split	np.split(arr, [i1, i2], axis=0) (cumulative indices)
Statistics	np.min np.max np.mean np.sum (axis=)
Index lookup	np.argmin np.argmax np.argsort np.where

Ridge Regression with scikit-learn

from sklearn.linear_model import Ridge
from sklearn.metrics import mean_squared_error

X_train, X_test, y_train, y_test = X[:80], X[80:], y[:80], y[80:]  # 80/20 split

model = Ridge(alpha=1)            # alpha = λ
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
rmse = np.sqrt(mean_squared_error(y_test, y_pred))

Assignment

Dataset: CMS calorimeter data (hgcal.csv). Predict deposited energy from cell positions.

1. scale_data() — standard scaling: $z=(x-\mu )/\sigma$
2. split_data() — split an array by ratios along an axis
3. ridge_regression() — fit on 80%, predict on 20%, report RMSE on the original scale