A.机器学习入门算法（三）：K近邻(k-nearest neighbors)，鸢尾花KNN分类，马绞痛数据--kNN数据预处理+kNN分类pipeline

1 给定测试样本，计算它与训练集中的每一个样本的距离。
2 找出距离近期的K个训练样本。作为测试样本的近邻。
3 依据这K个近邻归属的类别来确定样本的类别。

1. python3.7
2. numpy >= '1.16.4'
3. sklearn >= '0.23.1'

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.neighbors import KNeighborsClassifier
from sklearn import datasets

# 使用莺尾花数据集的前两维数据，便于数据可视化
iris = datasets.load_iris()
X = iris.data[:, :2]
y = iris.target

k_list = [1, 3, 5, 8, 10, 15]
h = .02
# 创建不同颜色的画布
cmap_light = ListedColormap(['orange', 'cyan', 'cornflowerblue'])
cmap_bold = ListedColormap(['darkorange', 'c', 'darkblue'])

plt.figure(figsize=(15,14))
# 根据不同的k值进行可视化
for ind,k in enumerate(k_list):
    clf = KNeighborsClassifier(k)
    clf.fit(X, y)
    # 画出决策边界
    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    # 根据边界填充颜色
    Z = Z.reshape(xx.shape)

    plt.subplot(321+ind)  
    plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
    # 数据点可视化到画布
    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold,
                edgecolor='k', s=20)
    plt.xlim(xx.min(), xx.max())
    plt.ylim(yy.min(), yy.max())
    plt.title("3-Class classification (k = %i)"% k)

plt.show()

import numpy as np
# 加载莺尾花数据集
from sklearn import datasets
# 导入KNN分类器
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
# 导入莺尾花数据集
iris = datasets.load_iris()

X = iris.data
y = iris.target
# 得到训练集合和验证集合, 8: 2
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

# 训练模型
clf = KNeighborsClassifier(n_neighbors=5, p=2, metric="minkowski")
clf.fit(X_train, y_train)

# 预测
X_pred = clf.predict(X_test)
acc = sum(X_pred == y_test) / X_pred.shape[0]
print("预测的准确率ACC: %.3f" % acc)

#Demo来自sklearn官网
import numpy as np
import matplotlib.pyplot as plt
from sklearn.neighbors import KNeighborsRegressor
np.random.seed(0)
# 随机生成40个(0, 1)之前的数，乘以5，再进行升序
X = np.sort(5 * np.random.rand(40, 1), axis=0)
# 创建[0, 5]之间的500个数的等差数列, 作为测试数据
T = np.linspace(0, 5, 500)[:, np.newaxis]
# 使用sin函数得到y值，并拉伸到一维
y = np.sin(X).ravel()
# Add noise to targets[y值增加噪声]
y[::5] += 1 * (0.5 - np.random.rand(8))

# #############################################################################
# Fit regression model
# 设置多个k近邻进行比较
n_neighbors = [1, 3, 5, 8, 10, 40]
# 设置图片大小
plt.figure(figsize=(10,20))
for i, k in enumerate(n_neighbors):
    # 默认使用加权平均进行计算predictor
    clf = KNeighborsRegressor(n_neighbors=k, p=2, metric="minkowski")
    # 训练
    clf.fit(X, y)
    # 预测
    y_ = clf.predict(T)
    plt.subplot(6, 1, i + 1)
    plt.scatter(X, y, color='red', label='data')
    plt.plot(T, y_, color='navy', label='prediction')
    plt.axis('tight')
    plt.legend()
    plt.title("KNeighborsRegressor (k = %i)" % (k))

plt.tight_layout()
plt.show()

# 下载需要用到的数据集
!wget https://tianchi-media.oss-cn-beijing.aliyuncs.com/DSW/3K/horse-colic.csv

# 下载数据集介绍
!wget https://tianchi-media.oss-cn-beijing.aliyuncs.com/DSW/3K/horse-colic.names

import numpy as np
import pandas as pd
# kNN分类器
from sklearn.neighbors import KNeighborsClassifier
# kNN数据空值填充
from sklearn.impute import KNNImputer
# 计算带有空值的欧式距离
from sklearn.metrics.pairwise import nan_euclidean_distances
# 交叉验证
from sklearn.model_selection import cross_val_score
# KFlod的函数
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.pipeline import Pipeline
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split

2,1,530101,38.50,66,28,3,3,?,2,5,4,4,?,?,?,3,5,45.00,8.40,?,?,2,2,11300,00000,00000,2
1,1,534817,39.2,88,20,?,?,4,1,3,4,2,?,?,?,4,2,50,85,2,2,3,2,02208,00000,00000,2
2,1,530334,38.30,40,24,1,1,3,1,3,3,1,?,?,?,1,1,33.00,6.70,?,?,1,2,00000,00000,00000,1
1,9,5290409,39.10,164,84,4,1,6,2,2,4,4,1,2,5.00,3,?,48.00,7.20,3,5.30,2,1,02208,00000,00000,1
2,1,530255,37.30,104,35,?,?,6,2,?,?,?,?,?,?,?,?,74.00,7.40,?,?,2,2,04300,00000,00000,2
......

X = [[1, 2, np.nan], [3, 4, 3], [np.nan, 6, 5], [8, 8, 7]]
imputer = KNNImputer(n_neighbors=2, metric='nan_euclidean')
imputer.fit_transform(X)

nan_euclidean_distances([[np.nan, 6, 5], [3, 4, 3]], [[3, 4, 3], [1, 2, np.nan], [8, 8, 7]])

# load dataset, 将?变成空值
input_file = './horse-colic.csv'
df_data = pd.read_csv(input_file, header=None, na_values='?')

# 得到训练数据和label, 第23列表示是否发生病变, 1: 表示Yes; 2: 表示No. 
data = df_data.values
ix = [i for i in range(data.shape[1]) if i != 23]
X, y = data[:, ix], data[:, 23]

# 查看所有特征的缺失值个数和缺失率
for i in range(df_data.shape[1]):
    n_miss = df_data[[i]].isnull().sum()
    perc = n_miss / df_data.shape[0] * 100
    if n_miss.values[0] > 0:
        print('>Feat: %d, Missing: %d, Missing ratio: (%.2f%%)' % (i, n_miss, perc))

# 查看总的空值个数
print('KNNImputer before Missing: %d' % sum(np.isnan(X).flatten()))
# 定义 knnimputer
imputer = KNNImputer()
# 填充数据集中的空值
imputer.fit(X)
# 转换数据集
Xtrans = imputer.transform(X)
# 打印转化后的数据集的空值
print('KNNImputer after Missing: %d' % sum(np.isnan(Xtrans).flatten()))

results = list()
strategies = [str(i) for i in [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 16, 18, 20, 21]]
for s in strategies:
    # create the modeling pipeline
    pipe = Pipeline(steps=[('imputer', KNNImputer(n_neighbors=int(s))), ('model', KNeighborsClassifier())])
    # 数据多次随机划分取平均得分
    scores = []
    for k in range(20):
        # 得到训练集合和验证集合, 8: 2
        X_train, X_test, y_train, y_test = train_test_split(Xtrans, y, test_size=0.2)
        pipe.fit(X_train, y_train)
        # 验证model
        score = pipe.score(X_test, y_test)
        scores.append(score)
    # 保存results
    results.append(np.array(scores))
    print('>k: %s, Acc Mean: %.3f, Std: %.3f' % (s, np.mean(scores), np.std(scores)))
# print(results)
# plot model performance for comparison
plt.boxplot(results, labels=strategies, showmeans=True)
plt.show()

>k: 1, Acc Mean: 0.800, Std: 0.031
>k: 2, Acc Mean: 0.821, Std: 0.041
>k: 3, Acc Mean: 0.833, Std: 0.053
>k: 4, Acc Mean: 0.824, Std: 0.037
>k: 5, Acc Mean: 0.802, Std: 0.038
>k: 6, Acc Mean: 0.811, Std: 0.030
>k: 7, Acc Mean: 0.797, Std: 0.056
>k: 8, Acc Mean: 0.819, Std: 0.044
>k: 9, Acc Mean: 0.820, Std: 0.032
>k: 10, Acc Mean: 0.815, Std: 0.046
>k: 15, Acc Mean: 0.818, Std: 0.037
>k: 16, Acc Mean: 0.811, Std: 0.048
>k: 18, Acc Mean: 0.809, Std: 0.043
>k: 20, Acc Mean: 0.810, Std: 0.038
>k: 21, Acc Mean: 0.828, Std: 0.038