Linear regression with scikit-learn in ML Python

Introduction

Linear regression helps us find a straight line that best fits data points. It predicts one value from another using a simple formula.

Predicting house prices based on size

Estimating sales from advertising budget

Forecasting temperature based on time of day

Understanding relationship between study hours and exam scores

Syntax

ML Python

from sklearn.linear_model import LinearRegression

model = LinearRegression()
model.fit(X_train, y_train)
predictions = model.predict(X_test)

X_train should be a 2D array with features (like size, age).

y_train is a 1D array with target values (like price).

Examples

Simple example: predicting y = 2 * x.

ML Python

from sklearn.linear_model import LinearRegression

model = LinearRegression()
X = [[1], [2], [3], [4]]
y = [2, 4, 6, 8]
model.fit(X, y)
pred = model.predict([[5]])

Example without intercept (line forced through zero).

ML Python

model = LinearRegression(fit_intercept=False)
model.fit(X, y)
pred = model.predict([[5]])

Sample Program

This program trains a linear regression model to predict exam scores based on hours studied. It prints the slope, intercept, prediction for 6 hours, and training accuracy.

ML Python

from sklearn.linear_model import LinearRegression
import numpy as np

# Sample data: hours studied vs exam score
X = np.array([[1], [2], [3], [4], [5]])
y = np.array([50, 60, 65, 70, 80])

# Create and train model
model = LinearRegression()
model.fit(X, y)

# Predict score for 6 hours studied
predicted_score = model.predict([[6]])

# Print coefficients and prediction
print(f"Coefficient (slope): {model.coef_[0]:.2f}")
print(f"Intercept: {model.intercept_:.2f}")
print(f"Predicted score for 6 hours: {predicted_score[0]:.2f}")

# Check training accuracy
score = model.score(X, y)
print(f"Training R^2 score: {score:.2f}")

Important Notes

Linear regression assumes a straight-line relationship between input and output.

Input features must be numeric and shaped correctly (2D array).

R^2 score shows how well the model fits the data (1.0 is perfect).

Summary

Linear regression finds a line to predict one value from another.

Use scikit-learn's LinearRegression to train and predict easily.

Check model quality with R^2 score and understand slope/intercept.