sklearn代码6 6-KNN癌症诊断

    import numpy as np
    
    import pandas as pd
    
    from pandas import Series,DataFrame
    
    from sklearn.neighbors import KNeighborsClassifier
    
    from sklearn.model_selection import train_test_split
    
    # grid网格 search搜索 cv：cross_validation
    # 搜索算法最合适的参数
    from sklearn.model_selection import GridSearchCV

    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)

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

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

    0    M
    1    M
    2    M
    3    M
    4    M
    Name: Diagnosis, dtype: object

    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)

    GridSearchCV(cv=6, 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=1,
       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, 26, 27, 28, 29], 'weights': ['distance', 'uniform'], 'p': [1, 2]},
       pre_dispatch='2*n_jobs', refit=True, return_train_score='warn',
       scoring='accuracy', verbose=0)

    gcv.best_params_

    {'n_neighbors': 3, 'p': 1, 'weights': 'distance'}

    gcv.best_estimator_

    KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=3, p=1,
           weights='distance')

    gcv.best_score_

94065934065934065