欢迎访问集智主站：
注意!
本文所有代码均可在集智原贴中运行调试（无需安装环境），请前往原贴
管道
已知有的预测器可以变换数据，有的预测器可以预测变量。我们可以创造组合预测器：
%matplotlib inlineimport numpy as npimport matplotlib.pyplot as pltfrom sklearn import linear_model, decomposition, datasetsfrom sklearn.pipeline import Pipelinefrom sklearn.grid_search import GridSearchCV# 创建和预测器对象：逻辑回归、主成分分析、管道logistic = linear_model.LogisticRegression()pca = decomposition.PCA()pipe = Pipeline(steps=[('pca', pca), ('logistic', logistic)])# 导入数字数据集digits = datasets.load_digits()X_digits = digits.datay_digits = digits.target# 绘制并输出PCA频谱pca.fit(X_digits)plt.figure(1, figsize=(4, 3))plt.clf()plt.axes([.2, .2, .7, .7])plt.plot(pca.explained_variance_, linewidth=2)plt.axis('tight')plt.xlabel('n_components')plt.ylabel('explained_variance_')# 预测n_components = [20, 40, 64]Cs = np.logspace(-4, 4, 3)# 管道的参数通过用'__'分隔的参数名来设置estimator = GridSearchCV(pipe, dict(pca__n_components=n_components, logistic__C=Cs))estimator.fit(X_digits, y_digits)plt.axvline(estimator.best_estimator_.named_steps['pca'].n_components, linestyle=':', label='n_components chosen')plt.legend(prop=dict(size=12))[/amalthea_sample_code][amalthea_solution]from sklearn import linear_model, decomposition, datasetsfrom sklearn.pipeline import Pipelinefrom sklearn.grid_search import GridSearchCV# 创建和预测器对象：逻辑回归、主成分分析、管道logistic = linear_model.LogisticRegression()pca = decomposition.PCA()pipe = Pipeline(steps=[('pca', pca), ('logistic', logistic)])# 导入数字数据集digits = datasets.load_digits()X_digits = digits.datay_digits = digits.target################################################################################ 绘制并输出PCA频谱pca.fit(X_digits)plt.figure(1, figsize=(4, 3))plt.clf()plt.axes([.2, .2, .7, .7])plt.plot(pca.explained_variance_, linewidth=2)plt.axis('tight')plt.xlabel('n_components')plt.ylabel('explained_variance_')################################################################################ 预测n_components = [20, 40, 64]Cs = np.logspace(-4, 4, 3)# 管道的参数通过用'__'分隔的参数名来设置estimator = GridSearchCV(pipe, dict(pca__n_components=n_components, logistic__C=Cs))estimator.fit(X_digits, y_digits)plt.axvline(estimator.best_estimator_.named_steps['pca'].n_components, linestyle=':', label='n_components chosen')plt.legend(prop=dict(size=12))# 创建和预测器对象：逻辑回归、主成分分析、管道logistic = linear_model.LogisticRegression()pca = decomposition.PCA()pipe = Pipeline(steps=[('pca', pca), ('logistic', logistic)])复制代码 人脸识别之特征脸(eigenface)
本例所用的数据集是"Labeled Faces in the Wild"()的预处理摘录。
%matplotlib inline"""===================================================Faces recognition example using eigenfaces and SVMs===================================================The dataset used in this example is a preprocessed excerpt of the"Labeled Faces in the Wild", aka LFW_: http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz (233MB).. _LFW: http://vis-www.cs.umass.edu/lfw/Expected results for the top 5 most represented people in the dataset:================== ============ ======= ========== ======= precision recall f1-score support================== ============ ======= ========== ======= Ariel Sharon 0.67 0.92 0.77 13 Colin Powell 0.75 0.78 0.76 60 Donald Rumsfeld 0.78 0.67 0.72 27 George W Bush 0.86 0.86 0.86 146Gerhard Schroeder 0.76 0.76 0.76 25 Hugo Chavez 0.67 0.67 0.67 15 Tony Blair 0.81 0.69 0.75 36 avg / total 0.80 0.80 0.80 322================== ============ ======= ========== ======="""from __future__ import print_functionfrom time import timeimport loggingimport matplotlib.pyplot as pltfrom sklearn.model_selection import train_test_splitfrom sklearn.model_selection import GridSearchCVfrom sklearn.datasets import fetch_lfw_peoplefrom sklearn.metrics import classification_reportfrom sklearn.metrics import confusion_matrixfrom sklearn.decomposition import PCAfrom sklearn.svm import SVCprint(__doc__)# 在stdout中输出过程日志logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')# 如果本地还没有Numpy数组格式的数据，则从网上下载。lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)# 图像数组的规模n_samples, h, w = lfw_people.images.shape# 对于机器学习我们只直接使用两个数据（忽略相对像素位置信息）X = lfw_people.datan_features = X.shape[1]# 人物id是预测目的标签y = lfw_people.targettarget_names = lfw_people.target_namesn_classes = target_names.shape[0]print("Total dataset size:")print("n_samples: %d" % n_samples)print("n_features: %d" % n_features)print("n_classes: %d" % n_classes)# 用分层K-Fold方法划分训练集和测试集X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.25, random_state=42)# 在人脸数据集上计算PCA（当作无标签数据集）：无监督特征提取/维数压缩n_components = 150print("Extracting the top %d eigenfaces from %d faces" % (n_components, X_train.shape[0]))t0 = time()pca = PCA(n_components=n_components, svd_solver='randomized', whiten=True).fit(X_train)print("done in %0.3fs" % (time() - t0))eigenfaces = pca.components_.reshape((n_components, h, w))print("Projecting the input data on the eigenfaces orthonormal basis")t0 = time()X_train_pca = pca.transform(X_train)X_test_pca = pca.transform(X_test)print("done in %0.3fs" % (time() - t0))# 训练SVM分类模型print("Fitting the classifier to the training set")t0 = time()param_grid = { 'C': [1e3, 5e3, 1e4, 5e4, 1e5], 'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid)clf = clf.fit(X_train_pca, y_train)print("done in %0.3fs" % (time() - t0))print("Best estimator found by grid search:")print(clf.best_estimator_)# 在测试集上定量评估模型质量print("Predicting people's names on the test set")t0 = time()y_pred = clf.predict(X_test_pca)print("done in %0.3fs" % (time() - t0))print(classification_report(y_test, y_pred, target_names=target_names))print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))# 用matplotlib定量绘制预测器的评估def plot_gallery(images, titles, h, w, n_row=3, n_col=4): """Helper function to plot a gallery of portraits""" plt.figure(figsize=(1.8 * n_col, 2.4 * n_row)) plt.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35) for i in range(n_row * n_col): plt.subplot(n_row, n_col, i + 1) plt.imshow(images[i].reshape((h, w)), cmap=plt.cm.gray) plt.title(titles[i], size=12) plt.xticks(()) plt.yticks(())# 在测试集的一部分上绘制预测结果图象def title(y_pred, y_test, target_names, i): pred_name = target_names[y_pred[i]].rsplit(' ', 1)[-1] true_name = target_names[y_test[i]].rsplit(' ', 1)[-1] return 'predicted: %s\ntrue: %s' % (pred_name, true_name)prediction_titles = [title(y_pred, y_test, target_names, i) for i in range(y_pred.shape[0])]plot_gallery(X_test, prediction_titles, h, w)# 画出辨识度最高的特征脸eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]plot_gallery(eigenfaces, eigenface_titles, h, w)plt.show()"""===================================================Faces recognition example using eigenfaces and SVMs===================================================The dataset used in this example is a preprocessed excerpt of the"Labeled Faces in the Wild", aka LFW_: http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz (233MB).. _LFW: http://vis-www.cs.umass.edu/lfw/Expected results for the top 5 most represented people in the dataset:================== ============ ======= ========== ======= precision recall f1-score support================== ============ ======= ========== ======= Ariel Sharon 0.67 0.92 0.77 13 Colin Powell 0.75 0.78 0.76 60 Donald Rumsfeld 0.78 0.67 0.72 27 George W Bush 0.86 0.86 0.86 146Gerhard Schroeder 0.76 0.76 0.76 25 Hugo Chavez 0.67 0.67 0.67 15 Tony Blair 0.81 0.69 0.75 36 avg / total 0.80 0.80 0.80 322================== ============ ======= ========== ======="""from __future__ import print_functionfrom time import timeimport loggingimport matplotlib.pyplot as pltfrom sklearn.model_selection import train_test_splitfrom sklearn.model_selection import GridSearchCVfrom sklearn.datasets import fetch_lfw_peoplefrom sklearn.metrics import classification_reportfrom sklearn.metrics import confusion_matrixfrom sklearn.decomposition import PCAfrom sklearn.svm import SVCprint(__doc__)# 在stdout中输出过程日志logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')# 如果本地还没有Numpy数组格式的数据，则从网上下载。lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)# 图像数组的规模n_samples, h, w = lfw_people.images.shape# 对于机器学习我们只直接使用两个数据（忽略相对像素位置信息）X = lfw_people.datan_features = X.shape[1]# 人物id是预测目的标签y = lfw_people.targettarget_names = lfw_people.target_namesn_classes = target_names.shape[0]print("Total dataset size:")print("n_samples: %d" % n_samples)print("n_features: %d" % n_features)print("n_classes: %d" % n_classes)# 用分层K-Fold方法划分训练集和测试集X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.25, random_state=42)# 在人脸数据集上计算PCA（当作无标签数据集）：无监督特征提取/维数压缩n_components = 150print("Extracting the top %d eigenfaces from %d faces" % (n_components, X_train.shape[0]))t0 = time()pca = PCA(n_components=n_components, svd_solver='randomized', whiten=True).fit(X_train)print("done in %0.3fs" % (time() - t0))eigenfaces = pca.components_.reshape((n_components, h, w))print("Projecting the input data on the eigenfaces orthonormal basis")t0 = time()X_train_pca = pca.transform(X_train)X_test_pca = pca.transform(X_test)print("done in %0.3fs" % (time() - t0))# 训练SVM分类模型print("Fitting the classifier to the training set")t0 = time()param_grid = { 'C': [1e3, 5e3, 1e4, 5e4, 1e5], 'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid)clf = clf.fit(X_train_pca, y_train)print("done in %0.3fs" % (time() - t0))print("Best estimator found by grid search:")print(clf.best_estimator_)# 在测试集上定量评估模型质量print("Predicting people's names on the test set")t0 = time()y_pred = clf.predict(X_test_pca)print("done in %0.3fs" % (time() - t0))print(classification_report(y_test, y_pred, target_names=target_names))print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))# 用matplotlib定量绘制预测器的评估def plot_gallery(images, titles, h, w, n_row=3, n_col=4): """Helper function to plot a gallery of portraits""" plt.figure(figsize=(1.8 * n_col, 2.4 * n_row)) plt.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35) for i in range(n_row * n_col): plt.subplot(n_row, n_col, i + 1) plt.imshow(images[i].reshape((h, w)), cmap=plt.cm.gray) plt.title(titles[i], size=12) plt.xticks(()) plt.yticks(())# 在测试集的一部分上绘制预测结果图象def title(y_pred, y_test, target_names, i): pred_name = target_names[y_pred[i]].rsplit(' ', 1)[-1] true_name = target_names[y_test[i]].rsplit(' ', 1)[-1] return 'predicted: %s\ntrue: %s' % (pred_name, true_name)prediction_titles = [title(y_pred, y_test, target_names, i) for i in range(y_pred.shape[0])]plot_gallery(X_test, prediction_titles, h, w)# 画出辨识度最高的特征脸eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]plot_gallery(eigenfaces, eigenface_titles, h, w)plt.show()# 该程序较大，若在线执行失败，请尝试本地运行。# 注：Scikit-learn版本为0.17复制代码