一、K近鄰方法（KNeighborsClassifier）

使用方法同kmeans方法，先構造分類器，再進行擬合。區別是Kmeans聚類是無監督學習，KNN是監督學習，因此需要劃分出訓練集和測試集。

直接貼代碼。

X=[0,1,2,3]#樣本
Y=[0,0,1,1]#標簽
from  sklearn.neighbors import KNeighborsClassifier
neigh = KNeighborsClassifier(n_neighbors=3)#選擇周圍的三個點作為近鄰分析
neigh.fit(X,Y)
neigh.predict(1.1)

K-NN可以看成：有那麽一堆你已經知道分類的數據，然後當一個新數據進入的時候，就開始跟訓練數據裏的每個點求距離，然後挑離這個訓練數據最近的K個點看看這幾個點屬於什麽類型，然後用少數服從多數的原則，給新數據歸類。

2、決策樹（DessionTreeClassifer）

from sklearn.datasets import load_iris
form sklearn.tree import DessionTreeClassifier
from sklearn.model_selection import cross_val_score#交叉驗證
clf = DessionTreeClassifier()#默認參數構造的話，基於基尼系數
iris = iris_load()
cross_val_score(clf,iris.data,iris.target,cv=10)#cv=10代表10折驗證

from
 
 sklearn import tree
X = [[0, 0], [1, 1]]
Y = [0, 1]
clf = tree.DecisionTreeClassifier()
clf = clf.fit(X, Y)
 
clf.predict([[1.2, 1.2]])

三、樸素貝葉斯（naive_bayes.GaussianNB）

對於給定的數據，首先基於特征的條件獨立性假設，學習輸入輸出的聯合分布概率，然後基於此模型對給定的輸入x，應用貝葉斯定力，測試其後驗概率。

在sklearn中實現了高斯樸素貝葉斯，多項式樸素貝葉斯，多元伯努利樸素貝葉斯。

import numpy as np
from
 
 sklearn.naive_bayes import GaussianNB
X=np.array([[-1,-1],[-2,-1],[-3,-2],[1,1],[2,1],[3,2]])
Y=np.array([1,1,1,2,2,2])
clf=GaussianNB()
clf.fit(X,Y)
print(clf.predict([[-0.8,-1]]))

三、人體運動狀態信息評級

    import pandas as pd
    import numpy as np  
     
    from sklearn.preprocessing import Imputer
    from sklearn.cross_validation import train_test_split 
    from sklearn.metrics import classification_report
       
    from sklearn.neighbors import KNeighborsClassifier#K近鄰
    from sklearn.tree import DecisionTreeClassifier#決策樹
    from sklearn.naive_bayes import GaussianNB#樸素貝葉斯
     
    def load_datasets(feature_paths, label_paths):
        feature = np.ndarray(shape=(0,41))
        label = np.ndarray(shape=(0,1))
        for file in feature_paths:
            df = pd.read_table(file, delimiter=‘,‘, na_values=‘?‘, header=None)
            imp = Imputer(missing_values=‘NaN‘, strategy=‘mean‘, axis=0)
            imp.fit(df)
            df = imp.transform(df)
            feature = np.concatenate((feature, df))
         
        for file in label_paths:
            df = pd.read_table(file, header=None)
            label = np.concatenate((label, df))
             
        label = np.ravel(label)
        return feature, label
     
    if __name__ == ‘__main__‘:
        ‘‘‘ 數據路徑 ‘‘‘
        featurePaths = [‘A.feature‘,‘B.feature‘,‘C.feature‘,‘D.feature‘,‘E.feature‘]
        labelPaths = [‘A.label‘,‘B.label‘,‘C.label‘,‘D.label‘,‘E.label‘]
        ‘‘‘ 讀入數據  ‘‘‘
        x_train,y_train = load_datasets(featurePaths[:4],labelPaths[:4])
        x_test,y_test = load_datasets(featurePaths[4:],labelPaths[4:])
        x_train, x_, y_train, y_ = train_test_split(x_train, y_train, test_size = 0.0)
         
        print(‘Start training knn‘)
        knn = KNeighborsClassifier().fit(x_train, y_train)
        print(‘Training done‘)
        answer_knn = knn.predict(x_test)
        print(‘Prediction done‘)
         
        print(‘Start training DT‘)
        dt = DecisionTreeClassifier().fit(x_train, y_train)
        print(‘Training done‘)
        answer_dt = dt.predict(x_test)
        print(‘Prediction done‘)
         
        print(‘Start training Bayes‘)
        gnb = GaussianNB().fit(x_train, y_train)
        print(‘Training done‘)
        answer_gnb = gnb.predict(x_test)
        print(‘Prediction done‘)
         
        print(‘\n\nThe classification report for knn:‘)
        print(classification_report(y_test, answer_knn))
        print(‘\n\nThe classification report for DT:‘)
        print(classification_report(y_test, answer_dt))
        print(‘\n\nThe classification report for Bayes:‘)
        print(classification_report(y_test, answer_gnb))

四、支持向量機（SVM）

    from sklearn import svm  
      
    X = [[0, 0], [1, 1], [1, 0]]  # training samples   
    y = [0, 1, 1]  # training target  
    clf = svm.SVC()  # class   
    clf.fit(X, y)  # training the svc model  
      
    result = clf.predict([[2, 2]]) # predict the target of testing samples   
    print(result)  # target   
      
    print(clf.support_vectors_)  #support vectors  
      
    print(clf.support_)  # indeices of support vectors  
      
    print(clf.n_support_)  # number of support vectors for each class 

以上。

：）

中國mooc北京理工大學機器學習第二周（一）：分類