⚖️ Logistic Regression

Despite the name, this is NOT a regression algorithm. It's for Classification!

🐶 Cat vs. Dog

Logistic Regression predicts probabilities (Is this a Cat or a Dog? Spam or Not Spam?). It squishes a straight line into an S-shape (the Sigmoid curve), guaranteeing the output is a clean percentage between 0% and 100%.

🐍 Python Implementation

from sklearn.linear_model import LogisticRegression
import numpy as np

# X = Hours Studied, y = Pass (1) or Fail (0)
X_train = np.array([[1], [2], [5], [8], [10]])
y_train = np.array([0, 0, 1, 1, 1])

model = LogisticRegression()
model.fit(X_train, y_train)

# If a student studies 4 hours, what's the probability they pass?
probabilities = model.predict_proba([[4]])
# Output is [Prob(Fail), Prob(Pass)]
print(f"Probability of passing: {probabilities[0][1]*100:.1f}%")