线性模型——线性判别分析

模型原型

class sklearn.discriminant_analysis.LinearDiscriminantAnalysis(solver=’svd’,
shrinkage=None,priors=None,n_components=None,
store_covariance=False,tol=0.0001)
参数

• solver:指定求解最优化问题的算法

  • ’svd’:奇异值分解(大规模特征的数据)
  • ‘lsqr’:最小平方差算法，可以结合shrinkage参数
  • ‘eigen’:特征值分解算法，可以结合shrinkage参数
• shrinkage:当solver=’lsqr’或’eigen’时才有意义
  
  • ’auto’:根据Ledoit-Wolf引理来自动决定shrinkage参数
  • None:不使用shrinkage参数
  • 浮点数(0~1):指定shrinkage参数
• priors:数组的元素依次指定了每个类别的先验概率(None代表每个类的先验概率都是相等的)
• n_components:指定数据降维后的维度
• store_covariance:是否需要计算每个类别的协方差矩阵
• tol

属性

• coef_
• intercept_
• covariance_:每个类别的协方差矩阵
• means_:每个类别的均值向量
• xbar_:整个样本的均值向量
• niter

方法

• fit(X,y[,sample_weight])
• predict(X)
• predict_log_proba(X)
• predict_proba(X)
• score(X,y[,sample_weight])

import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets,linear_model,discriminant_analysis,cross_validation

加载数据

def load_data():
    iris=datasets.load_iris()
    X_train=iris.data
    y_train=iris.target
    return cross_validation.train_test_split(X_train,y_train,test_size=0.25,random_state=0,stratify=y_train)

使用LinearDiscriminantAnalysis

def test_LinearDiscriminantAnalysis(*data):
    X_train,X_test,y_train,y_test=data
    lda=discriminant_analysis.LinearDiscriminantAnalysis()
    lda.fit(X_train,y_train)
    print('Coefficients:%s,\nintercept %s'%(lda.coef_,lda.intercept_))
    print('Score:%.2f'%lda.score(X_test,y_test))

X_train,X_test,y_train,y_test=load_data()
test_LinearDiscriminantAnalysis(X_train,X_test,y_train,y_test)

LDA降维后数据集分布图

def plot_LDA(converted_X,y):
    from mpl_toolkits.mplot3d import Axes3D
    fig=plt.figure()
    ax=Axes3D(fig)
    colors='rgb'
    markers='o*s'
    for target,color,marker in zip([0,1,2],colors,markers):
        pos=(y==target).ravel()
        X=converted_X[pos,:]
        ax.scatter(X[:,0],X[:,1],X[:,2],color=color,
        marker=marker,label="Label %d"%target)
    ax.legend(loc="best")
    fig.suptitle('Iris After LDA')
    plt.show()

X_train,X_test,y_train,y_test=load_data()
X=np.vstack((X_train,X_test))
Y=np.vstack((y_train.reshape(y_train.size,1),y_test.reshape(y_test.size,1)))
lda=discriminant_analysis.LinearDiscriminantAnalysis()
lda.fit(X,Y)
converted_X=np.dot(X,np.transpose(lda.coef_))+lda.intercept_
plot_LDA(converted_X,Y)

solver对预测能力的影响

def test_LinearDiscriminantAnalysis_solver(*data):
    X_train,X_test,y_train,y_test=data
    solvers=['svd','lsqr','eigen']
    for solver in solvers:
        if(solver=='svd'):
            lda=
            discriminant_analysis.LinearDiscriminantAnalysis(solver=solver)
        else:
            lda=discriminant_analysis.LinearDiscriminantAnalysis
            (solver=solver,shrinkage=None)
        lda.fit(X_train,y_train)
        print('Score at solver=%s:%.2f'%(solver,lda.score(X_test,y_test)))

X_train,X_test,y_train,y_test=load_data()
test_LinearDiscriminantAnalysis_solver(X_train,X_test,y_train,y_test)

shrinkage对预测能力的影响

def test_LinearDiscriminantAnalysis_shrinkage(*data):
    X_train,X_test,y_train,y_test=data
    shrinkages=np.linspace(0.0,1.0,num=20)
    scores=[]
    for shrinkage in shrinkages:
        lda=discriminant_analysis.LinearDiscriminantAnalysis(solver='lsqr',
        shrinkage=shrinkage)
        lda.fit(X_train,y_train)
        scores.append(lda.score(X_train,y_train))
    #绘图
    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    ax.plot(shrinkages,scores)
    ax.set_xlabel(r'shrinkage')
    ax.set_ylabel(r'score')
    ax.set_ylim(0,1.05)
    ax.set_title('LinearDiscriminantAnalysis')
    plt.show()

X_train,X_test,y_train,y_test=load_data()
test_LinearDiscriminantAnalysis_shrinkage(X_train,X_test,y_train,y_test)