来自sklearn中的一个例子——Classifier comparison

几种分类函数的比较，包括MLP，k近邻，SVC，高斯过程（RBF核），决策树，随机森林，朴素贝叶斯（高斯分布）。

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.neural_network import MLPClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.gaussian_process import GaussianProcessClassifier
from sklearn.gaussian_process.kernels import RBF
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis

h = .02
# 设定步长
names = ['Nearest Neighbors', 'Linear SVM', 'RBF SVM', 'Gaussian Process', 'Decision Tree', 'Random Forest',
         'Neural Net', 'AdaBoost', 'Naive Bayes', 'QVA']

classifiers = [
    KNeighborsClassifier(3),
    # n_neighbors=3, 默认为5， Number of neighbors to use by default for kneighbors queries.
    SVC(kernel='linear', C=0.025),
    # 线性内核，共有linear、poly、rbf、sigmoid、precomputed五种内核
    SVC(gamma=2, C=1),
    # 默认kernel='rbf'，C为惩罚因子
    GaussianProcessClassifier(1.0 * RBF(1.0), warm_start=True),
    DecisionTreeClassifier(max_depth=5),
    RandomForestClassifier(max_depth=5,n_estimators=10, max_features=1),
    # n_estimators default=10 number of trees in the forest
    MLPClassifier(alpha=1),
    AdaBoostClassifier(),
    GaussianNB(),
    QuadraticDiscriminantAnalysis()]

X, y = make_classification(n_features=2, n_redundant=0, n_informative=2, random_state=1, n_clusters_per_class=1)
# n_samples=100, n_feature=The total number of features,
rng = np.random.RandomState(2)
# 梅森扭转伪随机数
X += 2 * rng.uniform(size=X.shape)
# 从均匀分布随机抽样，size 为输出的形状
linearly_separable = (X, y)
# linearly_separable为tuple,其中包含一个（100,2）的矩阵和一个（100）的列向量

datasets = [make_moons(noise=0.3, random_state=0),
            make_circles(noise=0.2, factor=0.5, random_state=1),
            linearly_separable]
#datasets为一个列表，其中的三个对象为tuple
figure = plt.figure(figsize=(27, 9))
#尺寸
i = 1
# iterate over datasets
for ds_cnt, ds in enumerate(datasets):
    # 返回一个带索引的tuple（enumerate object），默认索引号start=0，
    # ds_cnt为dataset的索引号，0,1,2，ds为上面生成的三个数据集
    # preprocess dataset, split into training and test part
    X, y = ds
    X = StandardScaler().fit_transform(X)
    # 标准化特征，计算特征均值和标准差
    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))

    # just plot the dataset first
    cm_bright = ListedColormap(['#FF0000', '#0000FF'])
    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
    # 绘制子图，共有datasets行（3行），classifiers列（
    if ds_cnt ==0:
        ax.set_title('Input data')
    # plot the training points
    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright, edgecolors='k')
    # default:'b'.c can be a sequence of N numbers to be mapped to colors using the cmap and norm specified via kwargs
    # and testing points
    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())
    # set the data limits for the x-axis
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(())
    # 设置x轴的刻度
    ax.set_yticks(())
    i += 1

    # iterate over classifiers
    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)

        # plot the decision boundary. For that, wo will assign a color to each
        # point in the mesh [x_min, x_max]x[y_min, y_max]
        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]

        # put the result into a color plot
        Z = Z.reshape(xx.shape)
        ax.contourf(xx, yy, Z, alpha=.8)

        # plot also the training points
        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright, edgecolors='k')
        # and testing points
        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 += 1

plt.tight_layout()
#Automatically adjust subplot parameters to give specified padding
plt.show()