随机森林学习-2-sklearn

# -*- coding: utf-8 -*-
"""
RandomForestClassifier
skleran的9个模型在3份数据上的使用。
1. 知识点： sklearn自生成分类样本集、标准化、 画等高线图、拆分训练和测试集
2. 结果: 对于2维的线性和非线性的3个分类问题， 都证明了 随机森林可以取得较好效果。
"""

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
# make_classification 随机生成连续自变量和分类因变量
# make_moons 生成二维自变量 和分类自变量，生成半环形图、月亮型
# make_circles 生成二维自变量 和分类自变量，生成半环形图、月亮型

from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA    # 线性判别分析（LDA）
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis as QDA # 二次判别分析（QDA）

h = .02  # step size in the mesh

names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Decision Tree",
         "Random Forest", "AdaBoost", "Naive Bayes", "LDA", "QDA"]
classifiers = [
    KNeighborsClassifier(3),
    SVC(kernel="linear", C=0.025),
    SVC(gamma=2, C=1),
    DecisionTreeClassifier(max_depth=5),
    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
    AdaBoostClassifier(),
    GaussianNB(),
    LDA(),
    QDA()]

# 样本集包含2个自变量， n_classes=2表示因变量类别中包含2类
X, y = make_classification(n_features=2, n_redundant=0, n_informative=2,
                           random_state=1, n_clusters_per_class=1,n_classes=2) #生成样本集
plt.scatter(X[:, 0], X[:, 1], marker='o', c=y)
rng = np.random.RandomState(2)  #每次实例生成后，第n个实例的第i次随机，永远与第m个实例的第i次随机相同。
X += 2 * rng.uniform(size=X.shape)
linearly_separable = (X, y)

datasets = [make_moons(noise=0.3, random_state=0),
            make_circles(noise=0.2, factor=0.5, random_state=1),
            linearly_separable
            ]

figure = plt.figure(figsize=(27, 9))
i = 1
# iterate over datasets
for ds in datasets:
    # preprocess dataset, split into training and test part
    X, y = ds
    X = StandardScaler().fit_transform(X) # 标准化转换
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4) #划分训练和测试集

    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)) # 输出的xx，yy，就是坐标矩阵

    # just plot the dataset first
    cm = plt.cm.RdBu
    cm_bright = ListedColormap(['#FF0000', '#0000FF'])
    ax = plt.subplot(len(datasets), len(classifiers) + 1, i) # 画布
    # Plot the training points
    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
    # and testing points
    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6)
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(()) #清空了坐标轴数字
    ax.set_yticks(()) #清空了坐标轴数字
    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, we will assign a color to each
        # point in the mesh [x_min, m_max]x[y_min, y_max].
        if hasattr(clf, "decision_function"):
            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()]) #np.c_按照行连接两个矩阵[[1,2],[1,2],[1,2]] ,对mesh矩阵中每个样本点输入 经过f(x,y)输出一个预测。
        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, cmap=cm, alpha=.8)   #画 预测函数在坐标系中的登高线图

        # Plot also the training points
        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright) # 画训练数据散点图
        # and testing points
        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
                   alpha=0.6) # 测试数据的散点图

        ax.set_xlim(xx.min(), xx.max()) #设置坐标轴范围
        ax.set_ylim(yy.min(), yy.max())
        ax.set_xticks(())  #清空坐标轴刻度
        ax.set_yticks(())
        ax.set_title(name) #设置正上方的标题
        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),
                size=15, horizontalalignment='right') #在坐标系中指定位置，添加文本
        i += 1

figure.subplots_adjust(left=.02, right=.98) #调整 图像间的空白区域
plt.show()

原始来源网址