linear SVM
import numpy as np from sklearn import datasets iris = datasets.load_iris() X = iris.data[:, [2, 3]] y = iris.target from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1, stratify=y) from sklearn.preprocessing import StandardScaler from sklearn.svm import SVC sc = StandardScaler() sc.fit(X_train) X_train_std = sc.transform(X_train) X_test_std = sc.transform(X_test) svm = SVC(kernel='linear', C=1, random_state=1) svm.fit(X_train_std, y_train) y_pred = svm.predict(X_train_std) print('Misclassified training samples:',(y_train!=y_pred).sum()) y_pred = svm.predict(X_test_std) print('Misclassified samples:', (y_test != y_pred).sum()) from sklearn.metrics import accuracy_score print('Accuracy: %.3f' % accuracy_score(y_test, y_pred)) #下面就是可视化的部分 X_combined_std = np.vstack((X_train_std, X_test_std)) y_combined = np.hstack((y_train, y_test)) import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02): 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') if test_idx: X_test, y_test = X[test_idx, :], y[test_idx] plt.scatter(X_test[:, 0], X_test[:, 1], c='none', edgecolor='black', alpha=1.0, linewidth=1, marker='o', s=100, label='test set') from sklearn.svm import SVC svm = SVC(kernel='linear', C=1, random_state=1) svm.fit(X_train_std, y_train) plot_decision_regions(X_combined_std, y_combined, classifier=svm, test_idx=range(105, 150)) plt.xlabel('petal length (standardized)') plt.ylabel('petal width (standardized)') plt.legend(loc='upper left') plt.show()
import pandas as pd import numpy as py from sklearn import datasets from sklearn.preprocessing import StandardScaler from sklearn.model_selection import train_test_split from sklearn.svm import SVC from sklearn.metrics import accuracy_score iris = datasets.load_iris() X = iris.data[:,[2,3]] #X是numpy array #这是只用花瓣长度和花瓣宽度来预测 y = iris.target #y是numpy array X_train, X_test, y_train,y_test = train_test_split(X,y,test_size=0.3, random_state=1, stratify=y) sc = StandardScaler() sc.fit(X_train) X_train_std = sc.transform(X_train) X_test_std = sc.transform(X_test) svm = SVC(kernel='linear', C=1, random_state=1) svm.fit(X_train_std, y_train) y_pred = svm.predict(X_train_std) print('misclassified training samples: ', (y_pred != y_train).sum()) y_pred = svm.predict(X_test_std) print('misclassified testing samples: ', (y_pred != y_test).sum()) print('Accuracy: %.3f' % (accuracy_score(y_pred, y_test)))
non-linear kernel
不同的核
- 线性核函数kernel=‘linear’
- 多项式核函数kernel=‘poly’
- 径向基核函数kernel=‘rbf’
- sigmod核函数kernel=‘sigmod’
import numpy as np from sklearn import datasets iris = datasets.load_iris() X = iris.data[:, [2, 3]] y = iris.target from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1, stratify=y) from sklearn.preprocessing import StandardScaler sc = StandardScaler() sc.fit(X_train) X_train_std = sc.transform(X_train) X_test_std = sc.transform(X_test) from sklearn.svm import SVC svm = SVC(kernel='rbf', C=20.0, gamma = 1, random_state=1) svm.fit(X_train_std, y_train) y_pred = svm.predict(X_train_std) print('Misclassified training samples:',(y_train!=y_pred).sum()) y_pred = svm.predict(X_test_std) print('Misclassified samples:', (y_test != y_pred).sum()) from sklearn.metrics import accuracy_score print('Accuracy: %.3f' % accuracy_score(y_test, y_pred)) X_combined_std = np.vstack((X_train_std, X_test_std)) y_combined = np.hstack((y_train, y_test)) import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02): 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') if test_idx: X_test, y_test = X[test_idx, :], y[test_idx] plt.scatter(X_test[:, 0], X_test[:, 1], c='none', edgecolor='black', alpha=1.0, linewidth=1, marker='o', s=100, label='test set') #create linear inseperable data import matplotlib.pyplot as plt import numpy as np np.random.seed(1) X_xor = np.random.randn(200, 2) y_xor = np.logical_xor(X_xor[:,0] > 0, X_xor[:, 1] > 0) y_xor = np.where(y_xor, 1, -1) plt.scatter(X_xor[y_xor == 1, 0], X_xor[y_xor == 1, 1]) plt.scatter(X_xor[y_xor == -1, 0], X_xor[y_xor == -1, 1]) plt.xlim([-3, 3]) plt.ylim([-3, 3]) plt.show() from sklearn.svm import SVC svm = SVC(kernel='rbf', C=20.0, gamma = 1, random_state=1) svm.fit(X_xor, y_xor) plot_decision_regions(X_xor, y_xor, classifier=svm) plt.legend(loc='upper left') plt.show()
import pandas as pd import numpy as py from sklearn import datasets from sklearn.preprocessing import StandardScaler from sklearn.model_selection import train_test_split from sklearn.svm import SVC from sklearn.metrics import accuracy_score iris = datasets.load_iris() X = iris.data[:,[2,3]] #X是numpy array #这是只用花瓣长度和花瓣宽度来预测 y = iris.target #y是numpy array X_train, X_test, y_train,y_test = train_test_split(X,y,test_size=0.3, random_state=1, stratify=y) sc = StandardScaler() sc.fit(X_train) X_train_std = sc.transform(X_train) X_test_std = sc.transform(X_test) svm = SVC(kernel='rbf', C=20, gamma=1, random_state=1) svm.fit(X_train_std, y_train) y_pred = svm.predict(X_train_std) print('misclassified training samples: ', (y_pred != y_train).sum()) y_pred = svm.predict(X_test_std) print('misclassified testing samples: ', (y_pred != y_test).sum()) print('Accuracy: %.3f' % (accuracy_score(y_pred, y_test)))
different parameters
import numpy as np from sklearn import datasets iris = datasets.load_iris() X = iris.data[:, [2, 3]] y = iris.target from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1, stratify=y) from sklearn.preprocessing import StandardScaler sc = StandardScaler() sc.fit(X_train) X_train_std = sc.transform(X_train) X_test_std = sc.transform(X_test) X_combined_std = np.vstack((X_train_std, X_test_std)) y_combined = np.hstack((y_train, y_test)) import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02): 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') if test_idx: X_test, y_test = X[test_idx, :], y[test_idx] plt.scatter(X_test[:, 0], X_test[:, 1], c='none', edgecolor='black', alpha=1.0, linewidth=1, marker='o', s=100, label='test set') #create linear inseperable data import matplotlib.pyplot as plt import numpy as np np.random.seed(1) X_xor = np.random.randn(200, 2) y_xor = np.logical_xor(X_xor[:,0] > 0, X_xor[:, 1] > 0) y_xor = np.where(y_xor, 1, -1) plt.scatter(X_xor[y_xor == 1, 0], X_xor[y_xor == 1, 1]) plt.scatter(X_xor[y_xor == -1, 0], X_xor[y_xor == -1, 1]) plt.xlim([-3, 3]) plt.ylim([-3, 3]) plt.show() from sklearn.svm import SVC svm = SVC(kernel='rbf', random_state=1, gamma=0.2, C=1.0) svm.fit(X_train_std, y_train) plot_decision_regions(X_combined_std, y_combined,classifier=svm, test_idx=range(105, 150)) plt.xlabel('petal length [standardized]') plt.ylabel('petal width [standardized]') plt.legend(loc='upper left') plt.tight_layout() plt.show()
different parameters
import numpy as np from sklearn import datasets iris = datasets.load_iris() X = iris.data[:, [2, 3]] y = iris.target from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1, stratify=y) from sklearn.preprocessing import StandardScaler sc = StandardScaler() sc.fit(X_train) X_train_std = sc.transform(X_train) X_test_std = sc.transform(X_test) X_combined_std = np.vstack((X_train_std, X_test_std)) y_combined = np.hstack((y_train, y_test)) import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02): 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') if test_idx: X_test, y_test = X[test_idx, :], y[test_idx] plt.scatter(X_test[:, 0], X_test[:, 1], c='none', edgecolor='black', alpha=1.0, linewidth=1, marker='o', s=100, label='test set') #create linear inseperable data import matplotlib.pyplot as plt import numpy as np np.random.seed(1) X_xor = np.random.randn(200, 2) y_xor = np.logical_xor(X_xor[:,0] > 0, X_xor[:, 1] > 0) y_xor = np.where(y_xor, 1, -1) plt.scatter(X_xor[y_xor == 1, 0], X_xor[y_xor == 1, 1]) plt.scatter(X_xor[y_xor == -1, 0], X_xor[y_xor == -1, 1]) plt.xlim([-3, 3]) plt.ylim([-3, 3]) plt.show() from sklearn.svm import SVC svm = SVC(kernel='rbf', random_state=1, gamma=100.0, C=1.0) svm.fit(X_train_std, y_train) plot_decision_regions(X_combined_std, y_combined, classifier=svm, test_idx=range(105, 150)) plt.xlabel('petal length [standardized]') plt.ylabel('petal width [standardized]') plt.legend(loc='upper left') plt.tight_layout() plt.show()
COMP7404 Machine Learing——SVM
最新推荐文章于 2023-11-09 15:20:25 发布