机器学习_knn算法_2

#target : 目标值，代表着类别，

#得到的不是字典是普通的hash类型

from sklearn import datasets
iris = datasets.load_iris()

#DESCR得到的是英文文档，需要print解析（内有大量的\n,\t）

# print(iris.DESCR)

data = iris.data

target = iris.target

target_names = iris.target_names

from sklearn.model_selection import train_test_split

X_train,X_test,y_train,y_test =  train_test_split(data,target,test_size=0.1)

from sklearn.neighbors import KNeighborsClassifier

knn = KNeighborsClassifier(n_neighbors=5,n_jobs=2)

knn.fit(X_train,y_train)

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=2, n_neighbors=5, p=2,
           weights='uniform')

knn.score(X_train,y_train)

0.9703703703703703

y_pred = knn.predict(X_test)

import pandas as pd

import numpy as np

np.sum(y_test==y_pred)/len(y_test)

0.9333333333333333

import matplotlib.pyplot as plt

plt.scatter(data[:,0],data[:,1],c=target)

<matplotlib.collections.PathCollection at 0x27b0250ae80>

from sklearn.model_selection import GridSearchCV

knn = KNeighborsClassifier()

param_grid = {'n_neighbors':list(range(1,26))}

gc = GridSearchCV(estimator = knn,param_grid = param_grid,cv=3,n_jobs=2)

gc.fit(X_train,y_train)

GridSearchCV(cv=3, error_score='raise',
       estimator=KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=5, p=2,
           weights='uniform'),
       fit_params=None, iid=True, n_jobs=2,
       param_grid={'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25]},
       pre_dispatch='2*n_jobs', refit=True, return_train_score='warn',
       scoring=None, verbose=0)

best_pa = gc.best_params_

best_knn = gc.best_estimator_

gc.best_score_

0.9703703703703703

best_knn.score(X_train,y_train)

0.9703703703703703

best_knn.score(X_test,y_test)

0.9333333333333333