贝叶斯模型代码python

下面是一个简单的贝叶斯分类器的 Python 代码示例：

import numpy as np

class NaiveBayes:
    def fit(self, X, y):
        n_samples, n_features = X.shape
        self._classes = np.unique(y)
        n_classes = len(self._classes)
        self._mean = np.zeros((n_classes, n_features), dtype=np.float64)
        self._var = np.zeros((n_classes, n_features), dtype=np.float64)
        self._priors = np.zeros(n_classes, dtype=np.float64)

        for c in self._classes:
            X_c = X[c == y]
            self._mean[c, :] = X_c.mean(axis=0)
            self._var[c, :] = X_c.var(axis=0)
            self._priors[c] = X_c.shape[0] / float(n_samples)

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

    def _predict(self, x):
        posteriors = []

        for idx, c in enumerate(self._classes):
            prior = np.log(self._priors[idx])
            class_conditional = np.sum(np.log(self._pdf(idx, x)))
            posterior = prior + class_conditional
            posteriors.append(posterior)

        return self._classes[np.argmax(posteriors)]

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

使用示例：

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

nb = NaiveBayes()
nb.fit(X_train, y_train)

y_pred = nb.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print('Accuracy:', accuracy)