《机器学习》周志华 习题答案 10.1

原题：在西瓜数据集上实现K近邻分类器。

#!/usr/bin/python
# -*- coding:utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt

from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier

file1 = open('c:\quant\watermelon.csv','r')
data = [line.strip('\n').split(',') for line in file1]
data = np.array(data)
#X = [[float(raw[-7]),float(raw[-6]),float(raw[-5]),float(raw[-4]),float(raw[-3]), float(raw[-2])] for raw in data[1:,1:-1]]

X = [[float(raw[-3]), float(raw[-2])] for raw in data[1:]]
y = [1 if raw[-1]=='1' else 0 for raw in data[1:]]
X = np.array(X)
y = np.array(y)

print(__doc__)

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn import neighbors, datasets

n_neighbors = 5

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

h = .02  # step size in the mesh

# Create color maps
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF'])
cmap_bold = ListedColormap(['#FF0000', '#00FF00', '#0000FF'])

for weights in ['uniform', 'distance']:
    # we create an instance of Neighbours Classifier and fit the data.
    clf = neighbors.KNeighborsClassifier(n_neighbors, weights=weights)
    clf.fit(X, y)

    # Plot the decision boundary. For that, we will assign a color to each
    # point in the mesh [x_min, m_max]x[y_min, y_max].
    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])

    # Put the result into a color plot
    Z = Z.reshape(xx.shape)
    plt.figure()
    plt.pcolormesh(xx, yy, Z, cmap=cmap_light)

    # Plot also the training points
    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold)
    plt.xlim(xx.min(), xx.max())
    plt.ylim(yy.min(), yy.max())
    plt.title("3-Class classification (k = %i, weights = '%s')"
              % (n_neighbors, weights))

plt.show()

结果如下：

可以看到不同权重的分布对西瓜数据更加容易分类。

然后我们看决策树的分裂结果如下：

一个很明显的区别就是决策树的分裂边界是垂直于坐标轴的，二聚类的边界是任意形状和规则。