K-近邻算法笔记

机器学习算法分类

开发流程

K-近邻

API

实例

1、处理鸢尾花数据

from sklearn.neighbors import KNeighborsClassifier
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris

#读取数据
path = r'D:\python\2023\机器学习\data\iris.csv'
df = pd.read_csv(path)
df.columns = ['type1','type2','type3','type4','target']
#df = load_iris()
#print(df)
#取出目标值及特征值
y = df['target']
x = df.drop('target',axis=1)
print(x)
#将数据进行分为训练集及测试集
x_train,x_test,y_train,y_test = train_test_split(x,y,train_size=0.25)
#特征工程

#数据建模算法
knn = KNeighborsClassifier(n_neighbors=5)
#fit,predict,score
knn.fit(x_train,y_train)

#数据预测
y_predict = knn.predict(x_test)
print('预测结果：',y_predict)

#评估准确率
print('预测的准确率：',knn.score(x_test,y_test))

2、处理葡萄酒数据

from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler
import pandas as pd

from sklearn.model_selection import train_test_split

path = r'D:\python\2023\机器学习\分类data\winequality-red.csv'

df = pd.read_csv(path)
print(df.isnull().sum())

#取出目标值及特征值
y = df['quality']
x = df.drop('quality',axis=1)
#将数据进行分为训练集及测试集

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.25)

#特征工程
st = StandardScaler()
x_train = st.fit_transform(x_train)
x_test = st.transform(x_test)


#数据建模算法
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(x_train,y_train)
#数据预测
y_predict = knn.predict(x_test)
print('预测结果：',y_predict)

#评估准确率
print('预测的准确率：',knn.score(x_test,y_test))