鸢尾花

1.提取数据

  从pandas包中调用read_csv()方法。

import numpy as np
import pandas as pd

names = ['speal-length','speal-width','petal-length','petal-width','Class']
dataset = pd.read_csv('data/iris.csv',names = names)  
x = dataset.iloc[:,:-1].values
y = dataset.iloc[:,4].values

2.数据划分

  将整体数据切割为测试集和样本集

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.5)

3.数据处理

  将数据进行特征缩放，归一化或者标准化。此处进行标准化，将测试/训练数据转换成标准的正态分布

from sklearn.preprocessing import StandardScaler
sclar = StandardScaler()
sclar.fit(x_train)
x_test = sclar.transform(x_test)
x_train = sclar.transform(x_train)

4.训练模型

先将训练集导入训练拟合模型。预测测试集的分类类别。将n_neighbors的参数从1依次提高，收集每一次预测错误的概率，求解最优近邻数。

from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import classification_report, confusion_matrix

#调用fit函数：使用x_train作为训练数据，y_train作为目标值来拟合模型
classifier.fit(x_train,y_train)  #把数据放入到训练模型中
KNeighborsClassifier(algorithm='auto',leaf_size=30,metric='minkowski',
                    metric_params=None,n_jobs=None,n_neighbors=5,
                    p=2,weights='uniform')

#预测标签
y_pred = classifier.predict(x_test)  #预测样本x_test的分类类别
print(confusion_matrix(y_test,y_pred))  #打印混淆矩阵
print(classification_report(y_test,y_pred)) #打印分类报告

error = []   #定义一个error列表
for i in range(1,40):
    knn = KNeighborsClassifier(n_neighbors=i)
    knn.fit(x_train,y_train)
    pred_i = knn.predict(x_test)
    error.append(np.mean(pred_i != y_test))  #添加预测错误的概率

5.绘制K-Error Rate曲线

绘制错误概率曲线图。

import matplotlib.pyplot as plt
plt.figure(figsize=(12,6))
plt.plot(range(1,40),error,color='blue',linestyle='dashed',marker='*',markerfacecolor='red',markersize=10)#marker 点的形状

plt.title('Error Rate K Value')

plt.xlabel('K Value')
plt.ylabel('Mean Error')