import pandas as pd import numpy as np import matplotlib.pyplot as plt df = pd.read_csv('https://www.dropbox.com/s/mqyxvm8z2v1a20g/iris.data?dl=1', header=None) y = df.iloc[0:100, 4] y = np.where(y == 'Iris-setosa', -1, 1) X = df.iloc[0:100, [0, 2]].values class AdalineGD(object): def __init__(self, eta=0.01, n_iter=50, random_state=1): self.eta = eta self.n_iter = n_iter self.random_state = random_state def fit(self, X, y): #initiate weights rgen = np.random.RandomState(self.random_state) self.w_ = rgen.normal(loc=0.0, scale=0.01, size=1 + X.shape[1]) self.cost_ = [] for i in range(self.n_iter): net_input = self.net_input(X) output = self.activation(net_input) errors = (y - output) self.w_[1:] += self.eta * X.T.dot(errors) self.w_[0] += self.eta * errors.sum() cost = (errors**2).sum() / 2.0 self.cost_.append(cost) return self def net_input(self, X): return np.dot(X, self.w_[1:]) + self.w_[0] def activation(self, X): return X def predict(self, X): return np.where(self.activation(self.net_input(X)) >= 0.0, 1, -1) ada = AdalineGD(n_iter=30, eta=0.0001).fit(X, y) print(ada.cost_)
import pandas as pd import numpy as np import matplotlib.pyplot as plt df = pd.read_csv('https://www.dropbox.com/s/mqyxvm8z2v1a20g/iris.data?dl=1', header=None) y = df.iloc[0:100, 4] y = np.where(y == 'Iris-setosa', -1, 1) X = df.iloc[0:100, [0, 2]].values class AdalineGD(object): def __init__(self, eta=0.01, n_iter=50, random_state=1): self.eta = eta self.n_iter = n_iter self.random_state = random_state def fit(self, X, y): #initiate weights rgen = np.random.RandomState(self.random_state) self.w_ = rgen.normal(loc=0.0, scale=0.01, size=1 + X.shape[1]) self.cost_ = [] for i in range(self.n_iter): net_input = self.net_input(X) output = self.activation(net_input) errors = (y - output) self.w_[1:] += self.eta * X.T.dot(errors) self.w_[0] += self.eta * errors.sum() cost = (errors**2).sum() / 2.0 self.cost_.append(cost) return self def net_input(self, X): return np.dot(X, self.w_[1:]) + self.w_[0] def activation(self, X): return X def predict(self, X): return np.where(self.activation(self.net_input(X)) >= 0.0, 1, -1) ada = AdalineGD(n_iter=30, eta=0.0001).fit(X, y) print(ada.cost_) fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(10, 4)) ada1 = AdalineGD(n_iter=10, eta=0.01).fit(X, y) ax[0].plot(range(1, len(ada1.cost_) + 1), np.log10(ada1.cost_), marker='o') ax[0].set_xlabel('Epochs') ax[0].set_ylabel('log(Sum-squared-error)') ax[0].set_title('Adaline - Learning rate 0.01') ada2 = AdalineGD(n_iter=10, eta=0.0001).fit(X, y) ax[1].plot(range(1, len(ada2.cost_) + 1), ada2.cost_, marker='o') ax[1].set_xlabel('Epochs') ax[1].set_ylabel('Sum-squared-error') ax[1].set_title('Adaline - Learning rate 0.0001') plt.show()
Improving gradient descent through feature scaling
import pandas as pd import numpy as np import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap df = pd.read_csv('https://www.dropbox.com/s/mqyxvm8z2v1a20g/iris.data?dl=1', header=None) y = df.iloc[0:100, 4] y = np.where(y == 'Iris-setosa', -1, 1) X = df.iloc[0:100, [0, 2]].values class AdalineGD(object): def __init__(self, eta=0.01, n_iter=50, random_state=1): self.eta = eta self.n_iter = n_iter self.random_state = random_state def fit(self, X, y): #initiate weights rgen = np.random.RandomState(self.random_state) self.w_ = rgen.normal(loc=0.0, scale=0.01, size=1 + X.shape[1]) self.cost_ = [] for i in range(self.n_iter): net_input = self.net_input(X) output = self.activation(net_input) errors = (y - output) self.w_[1:] += self.eta * X.T.dot(errors) self.w_[0] += self.eta * errors.sum() cost = (errors**2).sum() / 2.0 self.cost_.append(cost) return self def net_input(self, X): return np.dot(X, self.w_[1:]) + self.w_[0] def activation(self, X): return X def predict(self, X): return np.where(self.activation(self.net_input(X)) >= 0.0, 1, -1) ada = AdalineGD(n_iter=30, eta=0.0001).fit(X, y) print(ada.cost_) fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(10, 4)) ada1 = AdalineGD(n_iter=10, eta=0.01).fit(X, y) ax[0].plot(range(1, len(ada1.cost_) + 1), np.log10(ada1.cost_), marker='o') ax[0].set_xlabel('Epochs') ax[0].set_ylabel('log(Sum-squared-error)') ax[0].set_title('Adaline - Learning rate 0.01') ada2 = AdalineGD(n_iter=10, eta=0.0001).fit(X, y) ax[1].plot(range(1, len(ada2.cost_) + 1), ada2.cost_, marker='o') ax[1].set_xlabel('Epochs') ax[1].set_ylabel('Sum-squared-error') ax[1].set_title('Adaline - Learning rate 0.0001') plt.show() 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() def plot_decision_regions(X, y, classifier, resolution=0.01): markers = ('s', 'x', 'o', '^', 'v') colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan') cmap = ListedColormap(colors[:len(np.unique(y))]) x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1 x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1 xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution), np.arange(x2_min, x2_max, resolution)) Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T) Z = Z.reshape(xx1.shape) plt.contourf(xx1, xx2, Z, alpha=0.3, cmap=cmap) plt.xlim(xx1.min(), xx1.max()) plt.ylim(xx2.min(), xx2.max()) for idx, cl in enumerate(np.unique(y)): plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha=0.8, c=colors[idx], marker=markers[idx], label=cl, edgecolor='black') ada = AdalineGD(n_iter=15, eta=0.01) ada.fit(X_std, y) plot_decision_regions(X_std, y, classifier=ada) plt.title('Adaline - Gradient Descent') plt.xlabel('sepal length [standardized]') plt.ylabel('petal length [standardized]') plt.legend(loc='upper left') plt.tight_layout() plt.show() plt.plot(range(1, len(ada.cost_) + 1), ada.cost_, marker='o') plt.xlabel('Epochs') plt.ylabel('Sum-squared-error') plt.tight_layout() plt.show() print(ada.cost_)
与之前的图对比可以发现，收敛地更快了
stochastic gradient descent
import pandas as pd import numpy as np import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap df = pd.read_csv('https://www.dropbox.com/s/mqyxvm8z2v1a20g/iris.data?dl=1', header=None) y = df.iloc[0:100, 4] y = np.where(y == 'Iris-setosa', -1, 1) X = df.iloc[0:100, [0, 2]].values 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() 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 self.random_state = 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): 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): r = self.rgen.permutation(len(y)) return X[r], y[r] def _initialize_weights(self, m): self.rgen = np.random.RandomState(self.random_state) self.w_ = self.rgen.normal(loc=0.0, scale=0.01, size=1 + m) self.w_initialized = True def _update_weights(self, xi, target): output = self.activation(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): return np.dot(X, self.w_[1:]) + self.w_[0] def activation(self, X): return X def predict(self, X): return np.where(self.activation(self.net_input(X)) >= 0.0, 1, -1) def plot_decision_regions(X, y, classifier, resolution=0.01): markers = ('s', 'x', 'o', '^', 'v') colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan') cmap = ListedColormap(colors[:len(np.unique(y))]) x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1 x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1 xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution), np.arange(x2_min, x2_max, resolution)) Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T) Z = Z.reshape(xx1.shape) plt.contourf(xx1, xx2, Z, alpha=0.3, cmap=cmap) plt.xlim(xx1.min(), xx1.max()) plt.ylim(xx2.min(), xx2.max()) for idx, cl in enumerate(np.unique(y)): plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha=0.8, c=colors[idx], marker=markers[idx], label=cl, edgecolor='black') ada = AdalineSGD(n_iter=15, eta=0.01, random_state=1) ada.fit(X_std, y) plot_decision_regions(X_std, y, classifier=ada) plt.title('Adaline - Stochastic Gradient Descent') plt.xlabel('sepal length [standardized]') plt.ylabel('petal length [standardized]') plt.legend(loc='upper left') plt.tight_layout() plt.show() plt.plot(range(1, len(ada.cost_) + 1), ada.cost_, marker='o') plt.xlabel('Epochs') plt.ylabel('Average Cost') plt.tight_layout() plt.show()
扫一扫
11-25
557
557
07-24
8万+
8万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
