python实现abalone数据集分类_使用python+sklearn实现分类器比较

注意：单击此处 https://urlify.cn/jMzu6r 下载完整的示例代码，或通过Binder在浏览器中运行此示例 scikit-learn中的几个分类器在合成数据集上的比较。该示例的目的是为来说明不同分类器的决策边界的性质。应该谨慎对待这些示例，因为这些示例给人的直觉不一定会在实际的数据集中出现一样结果。 特别是在高维空间中，可以更轻松地线性分离数据，简单的分类器(如朴素贝叶斯和线性SVM)可能比其他分类器具有更好的普遍性。 这些图以纯色(solid colors)显示训练点，测试点是半透明的。右下方显示测试集上的分类准确度。

sphx_glr_plot_classifier_comparison_001

print(__doc__)# 源代码: Gaël Varoquaux#              Andreas Müller# 由Jaques Grobler修改过文档# 许可证: BSD 3 clauseimport numpy as npimport matplotlib.pyplot as pltfrom matplotlib.colors import ListedColormapfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import StandardScalerfrom sklearn.datasets import make_moons, make_circles, make_classificationfrom sklearn.neural_network import MLPClassifierfrom sklearn.neighbors import KNeighborsClassifierfrom sklearn.svm import SVCfrom sklearn.gaussian_process import GaussianProcessClassifierfrom sklearn.gaussian_process.kernels import RBFfrom sklearn.tree import DecisionTreeClassifierfrom sklearn.ensemble import RandomForestClassifier, AdaBoostClassifierfrom sklearn.naive_bayes import GaussianNBfrom sklearn.discriminant_analysis import QuadraticDiscriminantAnalysish = .02  # mesh的步长names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Gaussian Process",         "Decision Tree", "Random Forest", "Neural Net", "AdaBoost",         "Naive Bayes", "QDA"]classifiers = [    KNeighborsClassifier(3),    SVC(kernel="linear", C=0.025),    SVC(gamma=2, C=1),    GaussianProcessClassifier(1.0 * RBF(1.0)),    DecisionTreeClassifier(max_depth=5),    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),    MLPClassifier(alpha=1, max_iter=1000),    AdaBoostClassifier(),    GaussianNB(),    QuadraticDiscriminantAnalysis()]X, y = make_classification(n_features=2, n_redundant=0, n_informative=2,                           random_state=1, n_clusters_per_class=1)rng = np.random.RandomState(2)X += 2 * rng.uniform(size=X.shape)linearly_separable = (X, y)datasets = [make_moons(noise=0.3, random_state=0),            make_circles(noise=0.2, factor=0.5, random_state=1),            linearly_separable            ]figure = plt.figure(figsize=(27, 9))i = 1# 遍历数据集for ds_cnt, ds in enumerate(datasets):    # 处理数据集, 把它划分成训练集和测试集    X, y = ds    X = StandardScaler().fit_transform(X)    X_train, X_test, y_train, y_test = \        train_test_split(X, y, test_size=.4, random_state=42)    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),                         np.arange(y_min, y_max, h))    # 先绘制数据集    cm = plt.cm.RdBu    cm_bright = ListedColormap(['#FF0000', '#0000FF'])    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)    if ds_cnt == 0:        ax.set_title("Input data")    # 绘制训练集的点    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,               edgecolors='k')    # 绘制测试集的点    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6,               edgecolors='k')    ax.set_xlim(xx.min(), xx.max())    ax.set_ylim(yy.min(), yy.max())    ax.set_xticks(())    ax.set_yticks(())    i += 1    # 遍历分类器    for name, clf in zip(names, classifiers):        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)        clf.fit(X_train, y_train)        score = clf.score(X_test, y_test)        # 绘制决策边界. 为此，我们把每种颜色分配给        # mesh [x_min, x_max]x[y_min, y_max]中的点        if hasattr(clf, "decision_function"):            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])        else:            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]        # 把结果放入颜色图(color plot)        Z = Z.reshape(xx.shape)        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)        # 绘制训练集的点        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,                   edgecolors='k')        # 绘制测试集的点        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,                   edgecolors='k', alpha=0.6)        ax.set_xlim(xx.min(), xx.max())        ax.set_ylim(yy.min(), yy.max())        ax.set_xticks(())        ax.set_yticks(())        if ds_cnt == 0:            ax.set_title(name)        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),                size=15, horizontalalignment='right')        i += 1plt.tight_layout()plt.show()

脚本的总运行时间：(0分钟4.667秒) 估计的内存使用量： 97 MB 下载Python源代码: plot_classifier_comparison.py 下载Jupyter notebook源代码: plot_classifier_comparison.ipynb 由Sphinx-Gallery生成的画廊

文壹由“伴编辑器”提供技术支持

☆☆☆为方便大家查阅，小编已将scikit-learn学习路线专栏 文章统一整理到公众号底部菜单栏，同步更新中，关注公众号，点击左下方“系列文章”，如图：

欢迎大家和我一起沿着scikit-learn文档这条路线，一起巩固机器学习算法基础。(添加微信：mthler，备注：sklearn学习，一起进【sklearn机器学习进步群】开启打怪升级的学习之旅。)