Naive Bayes.py

import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

class NaiveBayes:
    def __init__(self):
        self.priors = {}
        self.mean = {}
        self.variance = {}
        self.classes = []

    def fit(self, X, y):
        self.classes = np.unique(y)
        n_samples, n_features = X.shape

        for c in self.classes:
            X_c = X[y == c]
            self.priors[c] = X_c.shape[0] / n_samples
            self.mean[c] = np.mean(X_c, axis=0)
            self.variance[c] = np.var(X_c, axis=0) + 1e-9  # Add small smoothing to avoid zero variance

    def _pdf(self, class_idx, x):
        mean = self.mean[class_idx]
        var = self.variance[class_idx]
        numerator = np.exp(- (x - mean) ** 2 / (2 * var))
        denominator = np.sqrt(2 * np.pi * var)
        return numerator / denominator

    def _predict_single(self, x):
        posteriors = []
        for c in self.classes:
            prior = np.log(self.priors[c])  # Use log-sum to prevent underflow
            conditional = np.sum(np.log(self._pdf(c, x)))
            posterior = prior + conditional
            posteriors.append(posterior)
        return self.classes[np.argmax(posteriors)]

    def predict(self, X):
        return np.array([self._predict_single(x) for x in X])

# Usage
data = load_iris()
X, y = data.data, data.target  # Fixed 'data.targets' to 'data.target'
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

naive_bayes = NaiveBayes()
naive_bayes.fit(X_train, y_train)
predictions = naive_bayes.predict(X_test)

# Evaluate performance
print("Accuracy:", np.mean(predictions == y_test))