机器学习之k近邻算法教程（代码实战，详解核心算法）

k近邻算法

1.引入依赖

import numpy as np
import pandas as pd

# 这里直接引入sklearn里的数据集，iris鸢尾花
from sklearn.datasets import load_iris 
from sklearn.model_selection import train_test_split  # 切分数据集为训练集和测试集
from sklearn.metrics import accuracy_score # 计算分类预测的准确率

2.数据加载和预处理

iris = load_iris()

df = pd.DataFrame(data = iris.data, columns = iris.feature_names)
df['class'] = iris.target
df['class'] = df['class'].map({
   0: iris.target_names[0], 1: iris.target_names[1], 2: iris.target_names[2]})
df.head(10)
df.describe()

x = iris.data
y = iris.target.reshape(-1,1)
print(x.shape, y.shape)

# 划分训练集和测试集
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=35, stratify=y)

print(x_tr