《Python机器学习及实践》----无监督学习之特征降维

本片博客是根据《Python机器学习及实践》一书中的实例，所有代码均在本地编译通过。数据为从该书指定的百度网盘上下载的，或者是sklearn自带数据下载到本地使用的。
代码片段：

# coding: utf-8import numpy as npM = np.array([[1, 2], [2, 4]])np.linalg.matrix_rank(M, tol=None)import pandas as pddigits_train = pd.read_csv('D:\Source Code\machinelearn\optdigits.tra', header=None)digits_test = pd.read_csv('D:\Source Code\machinelearn\optdigits.tes', header=None)X_digits = digits_train[np.arange(64)]y_digits = digits_train[64]from sklearn.decomposition import PCAestimator = PCA(n_components=2)X_pca = estimator.fit_transform(X_digits)from matplotlib import pyplot as pltdef plot_pca_scatter():    colors = ['black', 'blue', 'purple', 'yellow', 'white', 'red', 'lime', 'cyan', 'orange', 'gray']    for i in xrange(len(colors)):        px = X_pca[:, 0][y_digits.as_matrix() == i]        py = X_pca[:, 1][y_digits.as_matrix()== i]        plt.scatter(px, py, c=colors[i])    plt.legend(np.arange(0,10).astype(str))    plt.xlabel('First Principal Component')    plt.ylabel('Second Principal Component')    plt.show()plot_pca_scatter()X_train = digits_train[np.arange(64)]y_train = digits_train[64]X_test = digits_test[np.arange(64)]y_test = digits_test[64]from sklearn.svm import LinearSVCsvc = LinearSVC()svc.fit(X_train, y_train)y_predict = svc.predict(X_test)estimator = PCA(n_components=20)pca_X_train = estimator.fit_transform(X_train)pca_X_test = estimator.transform(X_test)pca_svc = LinearSVC()pca_svc.fit(pca_X_train, y_train)pca_y_predict = pca_svc.predict(pca_X_test)from sklearn.metrics import classification_reportprint svc.score(X_test, y_test)print classification_report(y_test, y_predict, target_names=np.arange(10).astype(str))print pca_svc.score(pca_X_test, y_test)print classification_report(y_test, pca_y_predict, target_names=np.arange(10).astype(str))