Stacking思想.rar

from sklearn.datasets import load_iris from sklearn.ensemble import RandomForestClassifier from sklearn.svm import LinearSVC from sklearn.linear_model import LogisticRegression # 分类 from sklearn.preprocessing import StandardScaler from sklearn.pipeline import make_pipeline from sklearn.ensemble import StackingClassifier, GradientBoostingClassifier from sklearn.model_selection import train_test_split import time import matplotlib.pyplot as plt import matplotlib as mpl mpl.rcParams['font.sans-serif'] = [u'simHei'] # 读取数据 X, y = load_iris(return_X_y=True) # 返回值赋给x,y # staking的第一层模型 estimators = [ ('rf', RandomForestClassifier(n_estimators=10, random_state=40)), ('svc', make_pipeline(StandardScaler(), LinearSVC(random_state=40))) # 鸢尾花数据其实不太需要标准化处理，已经在统一量纲下 ] # 构建模型 stacking = StackingClassifier( estimators=estimators, final_estimator=LogisticRegression() ) # 模型对比 softmax = LogisticRegression(C=0.1, solver='lbfgs', multi_class='multinomial', fit_intercept=False) gbdt = GradientBoostingClassifier(learning_rate=0.1, n_estimators=90, max_depth=4) rf = RandomForestClassifier(max_depth=5, n_estimators=100) # stratify=y 表示按照目标向量y的类别进行分层抽样，以确保训练集和测试集中各类别的比例与原始数据集中相同 X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=40) scores_train = [] scores_test = [] models = [] times = [] for clf, modelname in zip([softmax, gbdt, rf, stacking], ['softmax', 'gbdt', 'rf', 'stacking']): print('start:%s' % (modelname)) start = time.time() clf.fit(X_train, y_train) end = time.time() score_train = clf.score(X_train, y_train) score_test = clf.score(X_test, y_test) scores_train.append(score_train) scores_test.append(score_test) models.append(modelname) times.append(end - start) print('scores_train:', scores_train) print('scores_test', scores_test) print('models:', models) # 画图 plt.figure(num=1) plt.plot([0, 1, 2, 3], scores_train, 'r', label=u'训练集') plt.plot([0, 1, 2, 3], scores_test, 'b', label=u'测试集') plt.title(u'鸢尾花数据不同分类器准确率比较', fontsize=16) plt.xticks([0, 1, 2, 3], models, rotation=0) plt.legend(loc='lower left') plt.figure(num=2) plt.plot([0, 1, 2, 3], times) plt.title(u'鸢尾花数据不同分类器训练时间比较', fontsize=16) plt.xticks([0, 1, 2, 3], models, rotation=0) plt.show()