用k最近邻、决策树和朴素贝叶斯比较分类效果

用三种分类方法，分别是k最近邻、决策树和朴素贝叶斯。画出数据点和决策边界，对比其区别。结果在最后的图中
import numpy as np
from numpy import *
import matplotlib.pyplot as plt
from sklearn.naive_bayes import  GaussianNB
from sklearn import metrics
from sklearn.preprocessing import StandardScaler
#from sklearn.cross_validation import train_test_split
from sklearn import datasets
from matplotlib.colors import ListedColormap
from sklearn.datasets import make_moons,make_circles,make_classification
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier

h = 0.02
names = ['Nearest Neighbors','Decision Tree','Naive Bayes']
classifiers = [KNeighborsClassifier(3),DecisionTreeClassifier(max_depth=5),GaussianNB()]

#生成三种形态的数据集
X,y = make_classification(n_features=2,n_informative=2,n_redundant=0,random_state=1,n_clusters_per_class=1)
rng = np.random.RandomState(2)
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= (18,6))
i = 1

for ds in datasets:
    #处理数据，数据标准化后分为测试集和训练集 测试集占30%
    X,y = ds
    X = StandardScaler().fit_transform(X)
    X_train = X[:int(X.shape[0]*0.7)]
    y_train = y[:int(X.shape[0]*0.7)]
    X_test = X[int(X.shape[0]*0.7):]
    y_test = y[int(X.shape[0]*0.7):]
    x_min,x_max = X[:,0].min()-0.5,X[:,0].max()+0.5
    y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5
    xx,yy = np.meshgrid(np.arange(x_min,x_max,h),np.arange(y_min,y_max))

    #画出原始数据点
    cm = plt.cm.RdBu
    cm_bright = ListedColormap(['# FF0000','# 0000FF'])
    ax = plt.subplot(len(datasets),len(classifiers)+1,i)
    #填充训练集中的点
    ax.scatter(X_train[:,0],X_train[:,1],c = y_train)
    #填充测试集中的点
    ax.scatter(X_test[:,0],X_test[:,1],c = y_test,alpha=0.6)
    #设置x轴和y轴的范围
    ax.set_xlim(xx.min(),xx.max())
    ax.set_ylim(yy.min(), yy.max())
    #设置x轴和y轴的刻度
    ax.set_xticks(())
    ax.set_yticks(())
    i += 1
    #画出每个模型的决策点和决策边界
    for name,clf in zip(names,classifiers):
        ax = plt.subplot(len(datasets),len(classifiers)+1,i)
        score = clf.fit(X_train,y_train).score(X_test,y_test)

        #画出决策边界，为此我们需要为网格中的每一个点预测一个颜色（类别）
        Z = clf.predict_proba(np.c_[xx.ravel(),yy.ravel()])[:,1]
        #把结果放进颜色图中
        Z = Z.reshape(xx.shape)
        ax.contourf(xx,yy,Z,cmap = cm,alpha = 0.8)
        #填充训练集中的点
        ax.scatter(X_train[:,0],X_train[:,1],c = y_train)
        #填充测试集中的点
        ax.scatter(X_test[:,0],X_test[:,1],c = y_test,alpha = 0.6)
        ax.set_xlim(xx.min(), xx.max())
        ax.set_ylim(yy.min(), yy.max())
        # 设置x轴和y轴的刻度
        ax.set_xticks(())
        ax.set_yticks(())
        ax.set_title(name)
        #在图的右下角标记模型分数
        ax.text(xx.max()- 0.3,yy.min()+0.3,('%.2f'%score).lstrip('0'),size = 15,horizontalalignment = 'right')
        i = i+1
figure.subplots_adjust(left = 0.02,right = 0.98)
plt.show()
用k最近邻、决策树和朴素贝叶斯比较分类效果

猜你喜欢
