机器学习之决策树（下）

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn import tree
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_iris
import pydotplus
mpl.rcParams['font.sans-serif'] = ['simHei']
mpl.rcParams['axes.unicode_minus'] = False

iris_feature_E = 'sepal length', 'sepal width', 'petal length', 'petal width'
iris_feature = '花萼长度', '花萼宽度', '花瓣长度', '花瓣宽度'
iris_class = 'Iris-setosa', 'Iris-versicolor', 'Iris-virginica'
# 加载数据
x = pd.DataFrame(load_iris().data)
y = load_iris().target

# 为了可视化，仅使用前两列特征
x = x[[0,1]]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=1)
model = DecisionTreeClassifier(criterion='entropy')
model.fit(x_train, y_train)
y_train_pred = model.predict(x_train)
print('训练集正确率：', accuracy_score(y_train, y_train_pred))
y_test_hat = model.predict(x_test)      # 测试数据
print('测试集正确率：', accuracy_score(y_test, y_test_hat))

训练集正确率： 0.9523809523809523
测试集正确率： 0.6222222222222222

dot_data = tree.export_graphviz(model, out_file=None, feature_names=iris_feature_E[0:2], class_names=iris_class,
                                    filled=True, rounded=True, special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data)
graph.write_pdf('iris.pdf')
f = open('iris.png', 'wb')
f.write(graph.create_png())
f.close()

depth = np.arange(1, 15)
err_train_list = []
err_test_list = []
clf = DecisionTreeClassifier(criterion='entropy')
for d in depth:
    clf.set_params(max_depth=d)
    clf.fit(x_train, y_train)
    y_train_pred = clf.predict(x_train)
    err_train = 1 - accuracy_score(y_train, y_train_pred)
    err_train_list.append(err_train)
    y_test_pred = clf.predict(x_test)
    err_test = 1 - accuracy_score(y_test, y_test_pred)
    err_test_list.append(err_test)
    print(d, ' 测试集错误率: %.2f%%' % (100 * err_test))
plt.figure(facecolor='w')
plt.plot(depth, err_test_list, 'ro-', markeredgecolor='k', lw=2, label='测试集错误率')
plt.plot(depth, err_train_list, 'go-', markeredgecolor='k', lw=2, label='训练集错误率')
plt.xlabel('决策树深度', fontsize=13)
plt.ylabel('错误率', fontsize=13)
plt.legend(loc='lower left', fontsize=13)
plt.title('决策树深度与过拟合', fontsize=15)
plt.grid(b=True, ls=':', color='#606060')
plt.show()

N, M = 50, 50  # 横纵各采样多少个值
x1_min, x2_min = x.min()
x1_max, x2_max = x.max()
t1 = np.linspace(x1_min, x1_max, N)
t2 = np.linspace(x2_min, x2_max, M)
x1, x2 = np.meshgrid(t1, t2)  # 生成网格采样点
x_show = np.stack((x1.flat, x2.flat), axis=1)  # 测试点
print(x_show.shape)
print('x_show = \n', x_show)

cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF'])
cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
y_show_hat = model.predict(x_show)  # 预测值
print(y_show_hat.shape)
print(y_show_hat)
y_show_hat = y_show_hat.reshape(x1.shape)  # 使之与输入的形状相同
print(y_show_hat)
plt.figure(facecolor='w')
plt.pcolormesh(x1, x2, y_show_hat, cmap=cm_light)  # 预测值的显示
plt.scatter(x_test[0], x_test[1], c=y_test.ravel(), edgecolors='k', s=100, zorder=10, cmap=cm_dark, marker='*')  # 测试数据
plt.scatter(x[0], x[1], c=y.ravel(), edgecolors='k', s=20, cmap=cm_dark)  # 全部数据
plt.xlabel(iris_feature[0], fontsize=13)
plt.ylabel(iris_feature[1], fontsize=13)
plt.xlim(x1_min, x1_max)
plt.ylim(x2_min, x2_max)
plt.grid(b=True, ls=':', color='#606060')
plt.title('鸢尾花数据的决策树分类', fontsize=15)
plt.show()

from sklearn.ensemble import RandomForestClassifier
x_prime = pd.DataFrame(load_iris().data)
y = load_iris().target
x_prime_train, x_prime_test, y_train, y_test = train_test_split(x_prime, y, test_size=0.3, random_state=0)
feature_pairs = [[0, 1], [0, 2], [0, 3], [1, 2], [1, 3], [2, 3]]
plt.figure(figsize=(8, 6))
for i, pair in enumerate(feature_pairs):
    # 准备数据
    x_train = x_prime_train[pair]
    x_test = x_prime_test[pair]

    # 决策树学习
    model = RandomForestClassifier(n_estimators=100, criterion='entropy', max_depth=5, oob_score=True)
    model.fit(x_train, y_train)

    # 画图
    N, M = 500, 500  # 横纵各采样多少个值
    x1_min, x2_min = x_train.min()
    x1_max, x2_max = x_train.max()
    t1 = np.linspace(x1_min, x1_max, N)
    t2 = np.linspace(x2_min, x2_max, M)
    x1, x2 = np.meshgrid(t1, t2)  # 生成网格采样点
    x_show = np.stack((x1.flat, x2.flat), axis=1)  # 测试点

    # 训练集上的预测结果
    y_train_pred = model.predict(x_train)
    acc_train = accuracy_score(y_train, y_train_pred)
    y_test_pred = model.predict(x_test)
    acc_test = accuracy_score(y_test, y_test_pred)
    print('特征：', iris_feature[pair[0]], ' + ', iris_feature[pair[1]])
    print('Score:', model.oob_score_)
    print('\t训练集准确率: %.4f%%' % (100*acc_train))
    print('\t测试集准确率: %.4f%%\n' % (100*acc_test))

    cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF'])
    cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
    y_hat = model.predict(x_show)
    y_hat = y_hat.reshape(x1.shape)
    plt.subplot(2, 3, i+1)
    plt.contour(x1, x2, y_hat, colors='k', levels=[0, 1], antialiased=True, linestyles='--', linewidths=1)
    plt.pcolormesh(x1, x2, y_hat, cmap=cm_light)  # 预测值
    plt.scatter(x_train[pair[0]], x_train[pair[1]], c=y_train, s=20, edgecolors='k', cmap=cm_dark, label='训练集')
    plt.scatter(x_test[pair[0]], x_test[pair[1]], c=y_test, s=100, marker='*', edgecolors='k', cmap=cm_dark, label='测试集')
    plt.xlabel(iris_feature[pair[0]], fontsize=12)
    plt.ylabel(iris_feature[pair[1]], fontsize=12)

    plt.xlim(x1_min, x1_max)
    plt.ylim(x2_min, x2_max)
    plt.grid(b=True, ls=':', color='#606060')
plt.suptitle('随机森林对鸢尾花数据两特征组合的分类结果', fontsize=15)
plt.tight_layout(1, rect=(0, 0, 1, 0.95))    # (left, bottom, right, top)
plt.show()