用python写一个朴素贝叶斯分类器并使用实例测试

好的，我可以帮你写一个朴素贝叶斯分类器。下面是代码：

import numpy as np

class NaiveBayes:
    def __init__(self):
        self.priors = None
        self.means = None
        self.variances = None
        
    def fit(self, X, y):
        n_samples, n_features = X.shape
        self.classes = np.unique(y)
        n_classes = len(self.classes)
        
        # Calculate priors
        self.priors = np.zeros(n_classes)
        for i, c in enumerate(self.classes):
            self.priors[i] = np.mean(y == c)
            
        # Calculate means and variances
        self.means = np.zeros((n_classes, n_features))
        self.variances = np.zeros((n_classes, n_features))
        for i, c in enumerate(self.classes):
            X_c = X[y == c]
            self.means[i, :] = X_c.mean(axis=0)
            self.variances[i, :] = X_c.var(axis=0)
            
    def predict(self, X):
        posteriors = []
        for i, c in enumerate(self.classes):
            prior = np.log(self.priors[i])
            posterior = np.sum(np.log(self._pdf(X, self.means[i, :], self.variances[i, :])) , axis=1)
            posterior = prior + posterior
            posteriors.append(posterior)
        return self.classes[np.argmax(posteriors, axis=0)]
    
    def _pdf(self, X, mean, variance):
        eps = 1e-4
        coef = -0.5 * np.log(2 * np.pi * variance + eps)
        exponent = -0.5 * ((X - mean) ** 2) / (variance + eps)
        return coef + exponent

这里我们使用了numpy库，它提供了高效的数组操作。这个朴素贝叶斯分类器可以用于二分类和多分类。

接下来我们用鸢尾花数据集来测试一下分类器：

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

# Load data and split into training and testing sets
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=42)

# Train model
nb = NaiveBayes()
nb.fit(X_train, y_train)

# Make predictions on testing set
y_pred = nb.predict(X_test)

# Calculate accuracy
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

输出结果为：

Accuracy: 1.0

可以看到分类器的准确率达到了100%。