决策树/随机森林实践

鸢尾花数据决策树图形

决策树画图软件：Graphviz
决策树对鸢尾花数据的两个特征组合的分类结果：

#!/usr/bin/python
# -*- coding:utf-8 -*-

import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier


# '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'

if __name__ == "__main__":
    mpl.rcParams['font.sans-serif'] = ['SimHei']  # 黑体 FangSong/KaiTi
    mpl.rcParams['axes.unicode_minus'] = False

    path = r'D:\ML\iris.data'  # 数据文件路径
    data = pd.read_csv(path, header=None)
    x_prime = data[list(range(4))]
    y = pd.Categorical(data[4]).codes

    feature_pairs = [[0, 1], [0, 2], [0, 3], [1, 2], [1, 3], [2, 3]]
    plt.figure(figsize=(10, 9), facecolor='#FFFFFF')
    for i, pair in enumerate(feature_pairs):
        # 准备数据
        x = x_prime[pair]

        # 决策树学习
        clf = DecisionTreeClassifier(criterion='entropy', min_samples_leaf=3)
        clf.fit(x, y)

        # 画图
        N, M = 500, 500  # 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_test = np.stack((x1.flat, x2.flat), axis=1)  # 测试点

        # 训练集上的预测结果
        y_hat = clf.predict(x)
        y = y.reshape(-1)
        c = np.count_nonzero(y_hat == y)    # 统计预测正确的个数
        print('特征：  ', iris_feature[pair[0]], ' + ', iris_feature[pair[1]], end=' ')
        print('\t预测正确数目：', c, end=' ')
        print('\t准确率: %.2f%%' % (100 * float(c) / float(len(y))))

        # 显示
        cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF'])
        cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
        y_hat = clf.predict(x_test)  # 预测值
        y_hat = y_hat.reshape(x1.shape)  # 使之与输入的形状相同
        plt.subplot(2, 3, i+1)
        plt.pcolormesh(x1, x2, y_hat, cmap=cm_light)  # 预测值
        plt.scatter(x[pair[0]], x[pair[1]], c=y, edgecolors='k', cmap=cm_dark)  # 样本
        plt.xlabel(iris_feature[pair[0]], fontsize=14)
        plt.ylabel(iris_feature[pair[1]], fontsize=14)
        plt.xlim(x1_min, x1_max)
        plt.ylim(x2_min, x2_max)
        plt.grid()
    plt.suptitle('决策树对鸢尾花数据的两特征组合的分类结果', fontsize=18)
    plt.tight_layout(2)
    plt.subplots_adjust(top=0.92)
    plt.show()

随机森林对鸢尾花数据的两特征组合的分类结果：

#!/usr/bin/python
# -*- coding:utf-8 -*-

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn.ensemble import RandomForestClassifier


def iris_type(s):
    it = {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
    return it[s]

# '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'

if __name__ == "__main__":
    mpl.rcParams['font.sans-serif'] = ['SimHei']  # 黑体 FangSong/KaiTi
    mpl.rcParams['axes.unicode_minus'] = False

    path = r'D:\ML\iris.data'  # 数据文件路径
    data = pd.read_csv(path, header=None)
    x_prime = data[list(range(4))]
    y = pd.Categorical(data[4]).codes

    feature_pairs = [[0, 1], [0, 2], [0, 3], [1, 2], [1, 3], [2, 3]]
    plt.figure(figsize=(10, 9), facecolor='#FFFFFF')
    for i, pair in enumerate(feature_pairs):
        # 准备数据
        x = x_prime[pair]

        # 随机森林
        clf = RandomForestClassifier(n_estimators=200, criterion='entropy', max_depth=3)
        clf.fit(x, y.ravel())

        # 画图
        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_test = np.stack((x1.flat, x2.flat), axis=1)  # 测试点

        # 训练集上的预测结果
        y_hat = clf.predict(x)
        y = y.reshape(-1)
        c = np.count_nonzero(y_hat == y)    # 统计预测正确的个数
        print('特征：  ', iris_feature[pair[0]], ' + ', iris_feature[pair[1]], end=' ')
        print('\t预测正确数目：', c, end=' ')
        print('\t准确率: %.2f%%' % (100 * float(c) / float(len(y))))

        # 显示
        cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF'])
        cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
        y_hat = clf.predict(x_test)  # 预测值
        y_hat = y_hat.reshape(x1.shape)  # 使之与输入的形状相同
        plt.subplot(2, 3, i+1)
        plt.pcolormesh(x1, x2, y_hat, cmap=cm_light)  # 预测值
        plt.scatter(x[pair[0]], x[pair[1]], c=y, edgecolors='k', cmap=cm_dark)  # 样本
        plt.xlabel(iris_feature[pair[0]], fontsize=14)
        plt.ylabel(iris_feature[pair[1]], fontsize=14)
        plt.xlim(x1_min, x1_max)
        plt.ylim(x2_min, x2_max)
        plt.grid()
    plt.tight_layout(2.5)
    plt.subplots_adjust(top=0.92)
    plt.suptitle('随机森林对鸢尾花数据的两特征组合的分类结果', fontsize=18)
    plt.show()

决策树用于拟合：

#!/usr/bin/python
# -*- coding:utf-8 -*-

import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeRegressor


if __name__ == "__main__":
    N = 100
    x = np.random.rand(N) * 6 - 3     # [-3,3)
    x.sort()
    y = np.sin(x) + np.random.randn(N) * 0.05
    print(y)
    x = x.reshape(-1, 1)  # 转置后，得到N个样本，每个样本都是1维的
    print(x)

    dt = DecisionTreeRegressor(criterion='mse', max_depth=9)
    dt.fit(x, y)
    x_test = np.linspace(-3, 3, 50).reshape(-1, 1)
    y_hat = dt.predict(x_test)
    plt.plot(x, y, 'r*', ms=10, label='Actual')
    plt.plot(x_test, y_hat, 'g-', linewidth=2, label='Predict')
    plt.legend(loc='upper left')
    plt.grid()
    plt.show()

    # 比较决策树的深度影响
    depth = [2, 4, 6, 8, 10]
    clr = 'rgbmy'
    dtr = DecisionTreeRegressor(criterion='mse')
    plt.plot(x, y, 'ko', ms=6, label='Actual')
    x_test = np.linspace(-3, 3, 50).reshape(-1, 1)
    for d, c in zip(depth, clr):
        dtr.set_params(max_depth=d)
        dtr.fit(x, y)
        y_hat = dtr.predict(x_test)
        plt.plot(x_test, y_hat, '-', color=c, linewidth=2, label='Depth=%d' % d)
    plt.legend(loc='upper left')
    plt.grid(b=True)
    plt.show()

回归曲线拟合：

# /usr/bin/python
# -*- encoding:utf-8 -*-

import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn.linear_model import RidgeCV
from sklearn.ensemble import BaggingRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures


def f(x):
    return 0.5*np.exp(-(x+3) **2) + np.exp(-x**2) + 0.5*np.exp(-(x-3) ** 2)


if __name__ == "__main__":
    np.random.seed(0)
    N = 200
    x = np.random.rand(N) * 10 - 5  # [-5,5)
    x = np.sort(x)
    y = f(x) + 0.05*np.random.randn(N)
    x.shape = -1, 1

    degree = 6
    ridge = RidgeCV(alphas=np.logspace(-3, 2, 20), fit_intercept=False)
    ridged = Pipeline([('poly', PolynomialFeatures(degree=degree)), ('Ridge', ridge)])#岭回归
    bagging_ridged = BaggingRegressor(ridged, n_estimators=100, max_samples=0.2)
    dtr = DecisionTreeRegressor(max_depth=5)
    regs = [
        ('DecisionTree Regressor', dtr),
        ('Ridge Regressor(%d Degree)' % degree, ridged),
        ('Bagging Ridge(%d Degree)' % degree, bagging_ridged),
        ('Bagging DecisionTree Regressor', BaggingRegressor(dtr, n_estimators=100, max_samples=0.2))]
    x_test = np.linspace(1.1*x.min(), 1.1*x.max(), 1000)
    mpl.rcParams['font.sans-serif'] = ['SimHei']
    mpl.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(12, 8), facecolor='w')
    plt.plot(x, y, 'ro', label='训练数据')
    plt.plot(x_test, f(x_test), color='k', lw=3.5, label='真实值')
    clrs = 'bmyg'
    for i, (name, reg) in enumerate(regs):
        reg.fit(x, y)
        y_test = reg.predict(x_test.reshape(-1, 1))
        plt.plot(x_test, y_test.ravel(), color=clrs[i], lw=i+1, label=name, zorder=6-i)
    plt.legend(loc='upper left')
    plt.xlabel('X', fontsize=15)
    plt.ylabel('Y', fontsize=15)
    plt.title('回归曲线拟合', fontsize=21)
    plt.ylim((-0.2, 1.2))
    plt.tight_layout(2)
    plt.grid(True)
    plt.show()