【统计学习笔记】习题三

1. k值选择与模型复杂度及预测准确率的关系

import numpy as np


class KNN:
    def __init__(self, X_train, y_train, n_neighbors=3, p=2):
        """
        parameter: n_neighbors 临近点个数
        parameter: p 距离度量
        """
        self.n = n_neighbors
        self.p = p
        self.X_train = X_train
        self.y_train = y_train
    
    def predict(self, X):
        # 取出n个点
        knn_list = []
        for i in range(self.n):
            dist = np.linalg.norm(X - self.X_train[i], ord=self.p)
            knn_list.append((dist, self.y_train[i]))
            
        for i in range(self.n, len(self.X_train)):
            max_index = knn_list.index(max(knn_list, key=lambda x: x[0]))
            dist = np.linalg.norm(X - self.X_train[i], ord=self.p)
            if knn_list[max_index][0] > dist:
                knn_list[max_index] = (dist, self.y_train[i])
                
        # 统计
        knn = [k[-1] for k in knn_list]
        count_pairs = Counter(knn)
        max_count = sorted(count_pairs, key=lambda x:x)[-1]
        # print(max_count)
        return max_count
    def segment(self, X):
        # 取出n个点
        knn_list = []
        for i in range(self.n):
            dist = np.linalg.norm(X - self.X_train[i], ord=self.p)
            knn_list.append((dist, self.y_train[i]))
            
        for i in range(self.n, len(self.X_train)):
            max_index = knn_list.index(max(knn_list, key=lambda x: x[0]))
            dist = np.linalg.norm(X - self.X_train[i], ord=self.p)
            if knn_list[max_index][0] > dist:
                knn_list[max_index] = (dist, self.y_train[i])
        
        # 统计
        knn_list = np.array(knn_list)
        sup_class = np.sum(knn_list[:,1]**1.5)
        return sup_class
        
    
    def score(self, X_test, y_test):
        right_count = 0
        n = 10
        for X, y in zip(X_test, y_test):
            label = self.predict(X)
            if label == y:
                right_count += 1
        return right_count / len(X_test)

import matplotlib.pyplot as plt


def plot_decision_boundaries(clusterer, X, resolution=1000,show_xlabels=True, show_ylabels=True):
    mins = X.min(axis=0) - 0.1
    maxs = X.max(axis=0) + 0.1
    xx, yy = np.meshgrid(np.linspace(mins[0], maxs[0], resolution),
                         np.linspace(mins[1], maxs[1], resolution))
    xxx = np.c_[xx.ravel(), yy.ravel()]
    Z = np.array([clusterer.segment(z) for z in xxx])
    Z = Z.reshape(xx.shape)
    plt.contourf(Z, extent=(mins[0], maxs[0], mins[1], maxs[1]),
                cmap="Pastel2")
    plt.contour(Z, extent=(mins[0], maxs[0], mins[1], maxs[1]),
                linewidths=1, colors='k')
    if show_xlabels:
        plt.xlabel("$x_1$", fontsize=14)
    else:
        plt.tick_params(labelbottom=False)
    if show_ylabels:
        plt.ylabel("$x_2$", fontsize=14, rotation=0)
    else:
        plt.tick_params(labelleft=False)

生成训练数据：

X_train = np.random.random((8,2))
Y_train = np.arange(1,10)
plt.plot(X_train[:,0],X_train[:,1],'ko')

1.1 k=1

mod1 = KNN(X_train,Y_train,n_neighbors=1)
plot_decision_boundaries(mod1, X_train,resolution=200)
plt.plot(X_train[:,0],X_train[:,1],'ko')

1.2 k=2

mod2 = KNN(X_train,Y_train,n_neighbors=2)
Z = plot_decision_boundaries(mod2, X_train,resolution=200)
plt.plot(X_train[:,0],X_train[:,1],'ko')

部分区域值其实是不同的，但是不知道为啥没有被划分开…
、正在输入…

。