Question

我需要修改代码，以便可以查看不同批次大小的成本。将每个批次的大小分开绘制，以得出平均成本（y轴）与训练样本数（x轴）的关系。

这是练习

#library
from numpy.random import seed

class AdalineSGD(object):
    def __init__(self, eta=0.01, n_iter=10, shuffle=True, random_state=None):
        self.eta = eta
        self.n_iter = n_iter
        self.w_initialized = False
        self.shuffle = shuffle
        if random_state:
            seed(random_state)

    def fit(self, X, y):
        self._initialize_weights(X.shape[1])
        self.cost_ = []
        for i in range(self.n_iter):
            if self.shuffle:
                X, y = self._shuffle(X, y)
            cost = []
            for xi, target in zip(X, y):
                cost.append(self._update_weights(xi, target))
            avg_cost = sum(cost) / len(y)
            self.cost_.append(avg_cost)
        return self

    def partial_fit(self, X, y):
        #Fit training data without reinitializing the weights
        if not self.w_initialized:
            self._initialize_weights(X.shape[1])
        if y.ravel().shape[0] > 1:
            for xi, target in zip(X, y):
                self._update_weights(xi, target)   
        else:
            self._update_weights(X, y)
        return self

    def _shuffle(self, X, y):
        #Shuffle training data
        r = np.random.permutation(len(y))
        return X[r], y[r]

    def _initialize_weights(self, m):
        """Initialize weights to zeros"""
        self.w_ = np.zeros(1 + m)
        self.w_initialized = True

    def _update_weights(self, xi, target):
        """Apply Adaline learning rule to update the weights"""
        output = self.net_input(xi)
        error = (target - output)
        self.w_[1:] += self.eta * xi.dot(error)
        self.w_[0] += self.eta * error
        cost = 0.5 * error**2
        return cost

    def net_input(self, X):
        """Calculate net input"""
        return np.dot(X, self.w_[1:]) + self.w_[0]

    def activation(self, X):
        """Compute linear activation"""
        return self.net_input(X)

    def predict(self, X):
        """Return class label after unit step"""
        return np.where(self.activation(X) >= 0.0, 1, -1)

X_std = np.copy(X)
X_std[:, 0] = (X[:, 0] - X[:, 0].mean()) / X[:, 0].std()
X_std[:, 1] = (X[:, 1] - X[:, 1].mean()) / X[:, 1].std()

iterations = 15 # i.e. epochs
batch_sizes = [1, 5, 10, 20, 50, 100]

for batch_size in batch_sizes:
    ada = AdalineSGD(n_iter=0, eta=0.01, random_state=1)
    for iteration in range(iterations):
        num_batches = np.ceil(y.ravel().shape[0]/batch_size).astype(int)
        for batch_index in range(num_batches):
            start_index = batch_index*batch_size
            end_index = start_index + batch_size
            ada.partial_fit(X_std[start_index:end_index, :], y[start_index:end_index])
    plt.plot([batch_size * x for x in range(1, len(ada.cost_) + 1)], ada.cost_, label=str(batch_size))

if len(batch_sizes) > 0: 
    plt.xlabel('# trained samples')
    plt.ylabel('Average Cost')
    plt.legend(loc='best')

    plt.tight_layout()
    plt.show()

当我运行代码时，它发生了错误。有什么问题，以及如何修改partial_fit

的代码

如何在随机梯度下降中直观显示具有不同批次大小的成本？代码有什么错误？

0 个答案: