sklearn笔记10 KNN-癌症诊断

完整代码 sklearn代码6 6-KNN癌症诊断

癌症诊断

导包

import numpy as np

import pandas as pd

from pandas import Series,DataFrame

from sklearn.neighbors import KNeighborsClassifier

导入数据

cancer = pd.read_csv('./cancer.csv',sep='\t')  # 名字中不可以含有汉字符
cancer

cancer.drop('ID',axis = 1,inplace=True)

提取数据

X = cancer.iloc[:,1:]
X.head()

y = cancer['Diagnosis']
y.head()

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2)

knn = KNeighborsClassifier()

params = {'n_neighbors':[i for i in range(1,30)],
         'weights':['distance','uniform'],
         'p':[1,2]}
gcv = GridSearchCV(knn,params,scoring='accuracy',cv = 6)

gcv.fit(X_train,y_train)

gcv.best_params_

gcv.best_estimator_

gcv.best_score_