softmax回归代码

当然，以下是一个使用softmax回归进行多类别分类的示例代码：

import numpy as np

def softmax(z):
    exps = np.exp(z - np.max(z, axis=1, keepdims=True))
    return exps / np.sum(exps, axis=1, keepdims=True)

class SoftmaxRegression:
    def __init__(self, num_classes, num_features, learning_rate=0.01, num_iterations=1000):
        self.num_classes = num_classes
        self.num_features = num_features
        self.learning_rate = learning_rate
        self.num_iterations = num_iterations
        self.weights = np.zeros((self.num_features, self.num_classes))
        self.bias = np.zeros((1, self.num_classes))

    def train(self, X, y):
        for iteration in range(self.num_iterations):
            scores = np.dot(X, self.weights) + self.bias
            probabilities = softmax(scores)

            # Compute gradient
            dW = (1 / X.shape[0]) * np.dot(X.T, (probabilities - y))
            db = (1 / X.shape[0]) * np.sum(probabilities - y, axis=0)

            # Update weights and bias
            self.weights -= self.learning_rate * dW
            self.bias -= self.learning_rate * db

    def predict(self, X):
        scores = np.dot(X, self.weights) + self.bias
        probabilities = softmax(scores)
        return np.argmax(probabilities, axis=1)

使用示例:

# 准备训练数据
X_train = np.array([[2.5, 1.2], [1.5, 2.5], [3.5, 1.9], [3.0, 2.8]])
y_train = np.array([0, 1, 1, 2])

# 创建并训练模型
model = SoftmaxRegression(num_classes=3, num_features=2)
model.train(X_train, y_train)

# 准备测试数据
X_test = np.array([[2.0, 1.0], [3.0, 2.0]])

# 预测
predictions = model.predict(X_test)
print(predictions)

希望以上代码能对你有帮助！如有任何疑问，请随时提出。