用sklearn 实现 kNN算法的流程

1. kNN 分类问题

1.1 获取数据

from sklearn import datasets

iris = datasets.load_iris()

X = iris.data
y = iris.target

1.2 将数据分割成为 训练集 和 测试集

from sklearn.model_selection import train_test_split
 
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size = 0.2 ,random_state = 666 )

1.3 数据归一化

1.3.1 最值归一化

from sklearn.preprocessing import MinMaxScaler

scaler = MinMaxScaler()
scaler.fit(X_train,y_train)
X_train1 = scaler.transform(X_train)
X_test1 = scaler.transform(X_test)

1.3.2 均值方差归一化

from sklearn.preprocessing import StandardScaler

standardScaler = StandardScaler()
standardScaler.fit(X_train,y_train)
X_train2 = standardScaler.transform(X_train)
X_test2 = standardScaler.transform(X_test)

1.4 使用kNN算法分类(采用均值方差归一化为例)

1.4.1 网格搜索 确定最优超参数

from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import GridSearchCV

# 超参数的情况
param_grid = [
    {
        'weights': ['uniform'], 
        'n_neighbors': [i for i in range(1, 11)]
    },
    {
        'weights': ['distance'],
        'n_neighbors': [i for i in range(1, 11)], 
        'p': [i for i in range(1, 6)]
    }
]

knn_clf  = KNeighborsClassifier()
grid_search = GridSearchCV(knn_clf,param_grid)
grid_search.fit(X_train2,y_train)
grid_search.best_params_

1.4.2 开始分类

knn_clf  = KNeighborsClassifier(n_neighbors=7,weights="uniform")
knn_clf.fit(X_train2,y_train)
knn_clf.predict(X_test2)

1.4.3 accuracy_score 准确度

from sklearn.metrics import accuracy_score

y_predict = knn_clf.predict(X_test2)
accuracy_score(y_predict,y_test)

2. kNN 回归问题

2.1 导入数据

import numpy as np
from sklearn import datasets

boston = datasets.load_boston()

X = boston.data
y = boston.target

# 去除边缘值
X = X[y < 50.0]
y = y[y < 50.0]

2.2 将数据分割成为 训练集 和 测试集

from sklearn.model_selection import train_test_split
 
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size = 0.2 ,random_state = 666 )

2.3 数据归一化

from sklearn.preprocessing import StandardScaler

standardScaler = StandardScaler()
standardScaler.fit(X_train,y_train)

X_train_standard = standardScaler.transform(X_train)
X_test_standard = standardScaler.transform(X_test)

2.4 使用回归算法

from sklearn.neighbors import KNeighborsRegressor

knn_reg = KNeighborsRegressor()
knn_reg.fit(X_train_standard,y_train)

# 使用算法默认值的评分
knn_reg.score(X_test_standard,y_test)

2.5 网格搜索

from sklearn.model_selection import GridSearchCV

param_grid = [
    {
        "weights": ["uniform"],
        "n_neighbors": [i for i in range(1, 11)]
    },
    {
        "weights": ["distance"],
        "n_neighbors": [i for i in range(1, 11)],
        "p": [i for i in range(1,6)]
    }
]

grid_search = GridSearchCV(knn_reg, param_grid, n_jobs=-1, verbose=1)
grid_search.fit(X_train_standard, y_train)
grid_search.best_params_

2.6 算法评价

# 经过网格搜索，确定最优参数后评分。
grid_search.best_estimator_.score(X_test_standard, y_test)