Scikit-learn之k近邻算法实现

一、导包、导数据

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets

from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

#load the classifying models
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC

iris = datasets.load_iris()
X = iris.data[:, :2]  #load the first two features of the iris data 
y = iris.target #load the target of the iris data

二、划分数据

from sklearn.neighbors import KNeighborsClassifier
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state = 0)

三、交叉验证

from sklearn.model_selection import cross_val_score  #导包
knn_3_clf = KNeighborsClassifier(n_neighbors = 3)   #实例化对象 k取3，最近的三个点
knn_5_clf = KNeighborsClassifier(n_neighbors = 5)

knn_3_scores = cross_val_score(knn_3_clf, X_train, y_train, cv=10) #训练  10折
knn_5_scores = cross_val_score(knn_5_clf, X_train, y_train, cv=10)

print ("knn_3 mean scores: ", knn_3_scores.mean(), "knn_3 std: ",knn_3_scores.std())
print ("knn_5 mean scores: ", knn_5_scores.mean(), " knn_5 std: ",knn_5_scores.std