【sklearn库中KNN实现多分类任务】

多分类KNN学习记录

转载于：https://blog.csdn.net/pengjunlee/article/details/82713047

import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import make_blobs
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split

data = make_blobs(n_samples=500, n_features=2, centers=5, cluster_std=1.0, random_state=8)  # 此处data为一个元组
X, Y = data  # X为500×2的数据，Y为标签

# 将生成的数据集进行可视化
# plt.scatter(X[:, 0], X[:, 1], s=50, c=Y,  cmap=plt.cm.spring, edgecolors='k')
# plt.show()

clf = KNeighborsClassifier(n_neighbors=7)
clf.fit(X, Y)

# 绘制图形
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, .02), np.arange(y_min, y_max, .02))
z = clf.predict(np.c_[xx.ravel(), yy.ravel()])  # 对所有网格点进行预测
z = z.reshape(xx.shape)

plt.pcolormesh(xx, yy, z, shading='auto', cmap='Greens')
plt.scatter(X[:, 0], X[:, 1], s=50, c=Y, cmap=plt.cm.spring, edgecolors='k')
plt.grid(True)
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.title("Classifier:KNN")

# 把待分类的数据点用五星表示出来
plt.scatter(0, 5, marker='*', c='red', s=200)

# 对待分类的数据点的分类进行判断
res = clf.predict([[0, 5]])
plt.text(0.2, 4.6, 'Classification flag: ' + str(res))
plt.text(3.75, -13, 'Model accuracy: {:.2f}'.format(clf.score(X, Y)))
plt.show()

示例二，自定义函数实现KNN二分类

import math
import csv
import operator
import random
# import numpy as np
# from sklearn.datasets import make_blobs

# 生成样本数据集 samples(样本数量) features(特征向量的维度) centers(类别个数)
# def createDataSet(samples=100, features=2, centers=2):
#     return make_blobs(n_samples=samples, n_features=features, centers=centers, cluster_std=1.0, random_state=8)

# 加载鸢尾花卉数据集 filename(数据集文件存放路径)，作出初步处理
def loadIrisDataset(filename):
    with open(filename, 'r') as csvfile:
        lines = csv.reader(csvfile)
        dataset = list(lines)
        dataset.pop()
        for x in range(len(dataset)):  # 读出来的数据始终是字符串的形式，需要转成float
            for y in range(4):
                dataset[x][y] = float(dataset[x][y])
        return dataset

# 拆分数据集 dataset(要拆分的数据集) split(训练集所占比例) trainingSet(训练集) testSet(测试集)
def splitDataSet(dataSet, split, trainingSet=[], testSet=[]):
    for x in range(len(dataSet)):
        if random.random() <= split:
            trainingSet.append(dataSet[x])
        else:
            testSet.append(dataSet[x])

# 计算欧氏距离
def euclideanDistance(instance1, instance2, length):
    distance = 0
    for x in range(length):
        distance += pow((instance1[x] - instance2[x]), 2)
    return math.sqrt(distance)

# 选取距离最近的K个实例
def getNeighbors(trainingSet, testInstance, k):
    distances = []
    length = len(testInstance) - 1
    for x in range(len(trainingSet)):
        dist = euclideanDistance(testInstance, trainingSet[x], length)
        distances.append((trainingSet[x], dist))  # 对该列表按照第二个维度进行排序，即对到每个训练集的距离排序
    distances.sort(key=operator.itemgetter(1))

    neighbors = []
    for x in range(k):
        neighbors.append(distances[x][0])
    return neighbors  # 返回最近的k个训练集实例

#  获取距离最近的K个实例中占比例较大的分类
def getResponse(neighbors):
    classVotes = {}
    for x in range(len(neighbors)):
        response = neighbors[x][-1]
        if response in classVotes:
            classVotes[response] += 1
        else:
            classVotes[response] = 1
    sortedVotes = sorted(classVotes.items(), key=operator.itemgetter(1), reverse=True)
    return sortedVotes[0][0]

# 计算准确率
def getAccuracy(testSet, predictions):
    correct = 0
    for x in range(len(testSet)):
        if testSet[x][-1] == predictions[x]:
            correct += 1
    return (correct / float(len(testSet))) * 100.0

def main():
    # 使用自定义创建的数据集进行分类
    # x,y = createDataSet(features=2)
    # dataSet= np.c_[x,y]
    # 使用鸢尾花卉数据集进行分类
    dataSet = loadIrisDataset('D:/pycharm/dataset/iris/iris.data.csv')

    print(dataSet)
    trainingSet = []
    testSet = []
    splitDataSet(dataSet, 0.75, trainingSet, testSet)
    print('Train set:' + repr(len(trainingSet)))
    print('Test set:' + repr(len(testSet)))
    predictions = []
    k = 7
    for x in range(len(testSet)):
        neighbors = getNeighbors(trainingSet, testSet[x], k)
        result = getResponse(neighbors)
        predictions.append(result)
        print('>predicted=' + repr(result) + ',actual=' + repr(testSet[x][-1]))
    accuracy = getAccuracy(testSet, predictions)
    print('Accuracy: ' + repr(accuracy) + '%')

main()