KNN回归实践
import numpy as np
import matplotlib.pyplot as plt
from sklearn.neighbors import KNeighborsRegressor
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import StandardScaler
import pandas as pd
由于从外部下载的数据集中含有NaN,因此我们选择把这些行删掉
boston = pd.read_csv('boston_housing_data.csv')
boston = boston.dropna()
将最后一列单独拿出来作为y
X = boston.iloc[:, :13]
y = boston.iloc[:, -1]
划分数据集(训练集与测试集)
x_train, x_test, y_train, y_test = train_test_split(X, y, train_size=0.8, random_state=233)
将数据归一化
standardScalar = StandardScaler()
standardScalar.fit(x_train)
x_train = standardScalar.transform(x_train)
x_test = standardScalar.transform(x_test)
超参数搜索
params = {
'n_neighbors':[n for n in range(1, 20)],
'weights':['uniform', 'distance'],
'p':[p for p in range(1, 7)]
}
grid1 = GridSearchCV(
estimator=KNeighborsRegressor(),
param_grid=params,
n_jobs=-1
)
训练模型
grid1.fit(x_train, y_train)
预测
grid1.predict(x_test)
评测
grid1.score(x_test, y_test)