Introduction to Linear Regression

Introduction

Linear regression models a continuous target as a weighted combination of input features plus an intercept. It is often the first supervised model teams try because it is fast, interpretable, and sets a baseline for harder algorithms.

Understanding the topic

When to use it Choose linear regression when the relationship looks roughly linear and you need coefficients you can explain to stakeholders.

• When to use it — Choose linear regression when the relationship looks roughly linear and you need coefficients you can explain to stakeholders.
• Fit and predict — Call fit on training features and targets, then predict on new rows.

Step-by-step explanation

1. When to use it — Choose linear regression when the relationship looks roughly linear and you need coefficients you can explain to stakeholders.
2. Fit and predict — Call fit on training features and targets, then predict on new rows.

Syntax reference

Notation / API sketch:

y ≈ w1*x1 + w2*x2 + ... + b

Informative example

Python starter:

from sklearn.linear_model import LinearRegression
import numpy as np

X = np.array([[1], [2], [3], [4], [5]])
y = np.array([2.1, 3.9, 6.2, 7.8, 10.1])

model = LinearRegression().fit(X, y)
print(round(model.predict([[6]])[0], 2))

12.04

Execution workflow

Worked examples

pred = model.predict(X_test)
print(pred[:3])

[...]

Best practices

• Hold out a test set before hyperparameter tuning.
• Scale numeric columns for distance-based models.
• Track multiple metrics — not accuracy alone on skewed labels.

Common mistakes

• Leaking test statistics into preprocessing fit on full data.
• Training on the same rows you report as test performance.
• Chasing complex models before a simple baseline.

Hands-on exercise

Practice:

• Plot residuals vs predictions
• Compare R² against a dummy mean predictor

Summary

Introduction to Linear Regression — Weighted sum of features for continuous targets.