K近邻算法进行回归预测一般步骤
1 数据的导入与预处理
2 数据的标准化与归一化
3 生成训练集和测试集
4 利用训练集进行训练,导入测试集得出预测值
5 真实值与与测试值进行比较评价
import csv
import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler
#数据导入与预处理
food_info = pd.read_csv("food_info.csv")
food0_info = food_info.dropna()
food1_info = food0_info.drop(["NDB_No","Shrt_Desc"],axis = 1)
#数据标准化或者归一化
colunm = food1_info.columns
food1_info[column] = StandardScaler().fit_transform(food1_info[column])
food1_info.head()
#训练集与测试集
norm_train_df = food1_info.copy().iloc[:2573]
norm_text_df = food1_info.copy().iloc[2573:]
# 导入K近邻算法的回归类
from sklearn.neighbors import KNeighborsRegressor
columns = column[1:]
#实例化
knn = KNeighborsRegressor()
#导入测试集的标签值与属性值,knn.fit(norm_train