使用Sklearn的SVM接口实现鸢尾花分类

Iris Data Set

Iris Data Set（鸢尾属植物数据集）是历史比较悠久的数据集，它首次出现在著名的英国统计学家和生物学家Ronald Fisher 1936年的论文《The use of multiple measurements in taxonomic problems》中，被用来介绍线性判别式分析。在这个数据集中，包括了三类不同的鸢尾属植物：Iris Setosa，Iris Versicolour，Iris Virginica。每类收集了50个样本，因此这个数据集一共包含了150个样本。
该数据集测量了所有150个样本的4个特征，分别是：sepal length（花萼长度）、sepal width（花萼宽度）、petal length（花瓣长度）、petal width（花瓣宽度），以上四个特征的单位都是厘米。

Sklearn的支持向量机（SVM）算法

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets

# 定义网格函数
def make_meshgrid(x, y, h=.02):
    """Create a mesh of points to plot in
    Parameters
    ----------
    x: data to base x-axis meshgrid on
    y: data to base y-axis meshgrid on
    h: stepsize for meshgrid, optional
    Returns
    -------
    xx, yy : ndarray
    """
    x_min, x_max = x.min() - 1, x.max() + 1
    y_min, y_max = y.min() - 1, y.max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),np.arange(y_min, y_max, h))
    return xx, yy
    
# 绘制填充颜色的二维等高线图_
def plot_contours(ax, clf, xx, yy, **params):
    """Plot the decision boundaries for a classifier.
    Parameters
    ----------
    ax: matplotlib axes object
    clf: a classifier
    xx: meshgrid ndarray
    yy: meshgrid ndarray
    params: dictionary of params to pass to contourf, optional
    """
    # np.c_中的c是column的缩写，是按列叠加两个矩阵的意思，就是把两矩阵左右相加
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    out = ax.contourf(xx, yy, Z, **params)
    return out

# import some data to play with
iris = datasets.load_iris()
# Take the first two features. We could avoid this by using a two-dim dataset
X = iris.data[:, :2]
y = iris.target

# we create an instance of SVM and fit out data. We do not scale our data since we want to plot the support vectors
C = 1.0  # SVM regularization parameter
models = (svm.SVC(kernel='linear', C=C),
          svm.LinearSVC(C=C, max_iter=10000),
          svm.SVC(kernel='rbf', gamma=0.7, C=C),
          svm.SVC(kernel='poly', degree=3, gamma='auto', C=C))
models = (clf.fit(X, y) for clf in models)
# title for the plots
titles = ('SVC with linear kernel',
          'LinearSVC (linear kernel)',
          'SVC with RBF kernel',
          'SVC with polynomial (degree 3) kernel')
# Set-up 2x2 grid for plotting.
fig, sub = plt.subplots(2, 2)
plt.subplots_adjust(wspace=0.4, hspace=0.4)
plt.rcParams['savefig.dpi'] = 600 #图片像素
plt.rcParams['figure.dpi'] = 600 #分辨率

X0, X1 = X[:, 0], X[:, 1]
xx, yy = make_meshgrid(X0, X1)
for clf, title, ax in zip(models, titles, sub.flatten()):
    plot_contours(ax, clf, xx, yy,cmap=plt.cm.coolwarm, alpha=0.8)
    ax.scatter(X0, X1, c=y, cmap=plt.cm.coolwarm, s=20, edgecolors='k')
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xlabel('Sepal length')
    ax.set_ylabel('Sepal width')
    ax.set_xticks(())
    ax.set_yticks(())
    ax.set_title(title)
plt.show()