Realization of perceptual machine learning algorithm python

Refer to the Hangyuan Li "Statistical learning method" at the beginning of the perceptual Machine chapter, looking at not too complicated to realize ...

1 """2 the original form of perceptual machine learning algorithm3 Example 2.14 """5 ImportNumPy as NP6 7 classPerceptron:8     def __init__(self,w,b,alpha):9SELF.W =WTenSELF.B =b OneSelf.alpha =Alpha A  -     defloss (self,x,y): -         returnNp.sum (y* (Np.dot (x, SELF.W) +self.b)) the      -     defSGD (self,x,y):#Stochastic gradient descent function -SELF.W + = Self.alpha * y *x -self.b + = Self.alpha *y +  -     defTrain (self,x,y): +          while(True): AM = Len (X)#number of error classifications at              forIinchRange (len (X)): -                 ifSelf.loss (X[i],y[i]) <=0: - SELF.SGD (X[i],y[i]) -                     Print "W:", SELF.W,"B:", self.b -                 Else: -M-= 1 in             if  notM: -                 Print "Final Optimal:","W:", SELF.W,"B:", self.b to                  Break +  - classperceptron_dual: the     def __init__(Self,alpha,b,ita): *Self.alpha =Alpha $SELF.B =bPanax NotoginsengSelf.ita =Ita -  the     defgram (self,x): +         returnNp.dot (x,x.t) A  the     defTrain (self,x,y): +g =Self.gram (X) -          $M = Len (X)#number of error classifications $          while(True): -M = Len (X)#number of error classifications -              forJinchRange (len (X)): the                 ifY[J] * (Np.sum (Self.alpha * Y * g[j]) + self.b) <=0: -SELF.ALPHA[J] + =Self.itaWuyiself.b + = Self.ita *Y[j] the                     Print "A:", Self.alpha,"B:", self.b -                 Else: WuM-= 1 -             ifM = =0: About                 Print "Final Optimal:","A:", Self.alpha,"B:", self.b $                  Break -  - if __name__=="__main__": -  AX = Np.array ([[3,3],[4,3],[1,1]]) +      theY = Np.array ([1,1,-1]) -Perc_d = Perceptron_dual (Np.zeros (y.shape), 0,1) $Perc_d.train (X, Y)

Realization of perceptual machine learning algorithm python