随机梯度下降(Stochastic gradient descent)和 批量梯度下降(Batch gradient descent )

系数比之前多了一个分母m
批量梯度下降法,同上一篇方法,下面看随机梯度法,随机梯度通过一个样本更新所有w,类似笔记一
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt

df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data', header=None)
y = df.iloc[0:100, 4].values
y = np.where(y=='Iris-setosa',1,-1)
x = df.iloc[0:100, [0,2]].values

x_std = np.copy(x)
x_std[:, 0] = (x[:,0]-x[:,0].mean())/x[:,0].std()
x_std[:, 1] = (x[:,1]-x[:,1].mean())/x[:,1].std()

class Perceptron():
    def __init__(self, eta, X, Y, N):
        self.eta = eta
        self.X = X
        self.Y = Y
        self.N = N
        self.w = [0]*len(X[0])
        self.w0 = 0
        self.m = len(X)
        self.n = len(X[0])
    def _shuffle(self, X, y):
        """Shuffle training data"""
        r = np.random.permutation(len(y))
        return X[r], y[r]
    def output_y(self, x):
        z = np.dot(x,self.w)+self.w0
        return z
    def training(self):
        self.errors = []
        for times in xrange(self.N):
            error = 0
            self.X, self.Y = self._shuffle(self.X, self.Y)
            for i in xrange(self.m):
                delta_y = self.Y[i]-self.output_y(self.X[i])
                error += 0.5*delta_y**2
                self.w0 += self.eta*delta_y
                self.w += self.eta*delta_y*self.X[i]
            self.errors.append(error/self.m)
            
per = Perceptron(0.01, x_std, y, 16)

per.training()

print per.w0,per.w

def f(x, y):
    z = per.w0+np.dot(per.w,zip(x,y))
    z = np.where(z>0,1,-1)
    return z

n = 200

mx = np.linspace(-3, 3, n)
my = np.linspace(-2, 2, n)
# 生成网格数据
X, Y = np.meshgrid(mx, my)
fig, axes = plt.subplots(1,2)
axes0, axes1 = axes.flatten()
axes0.plot(per.errors, marker='o')
axes0.set_title('errors')
axes1.contourf(X, Y, f(X, Y), 2, alpha = 0.75, cmap = plt.cm.RdBu)
axes1.scatter(x_std[:,0][0:50], x_std[:, 1][0:50],s=80,edgecolors='r', marker='o')
axes1.scatter(x_std[:,0][50:100], x_std[:, 1][50:100], marker='x', color='g')
axes1.annotate(r'versicolor',xy=(5.5,4.5),xytext=(4.5,5.5),arrowprops=dict(arrowstyle='->', facecolor='blue'))
axes1.annotate(r'setosa',xy=(5.8,2),xytext=(6.5,3),arrowprops=dict(arrowstyle='->', facecolor='blue'))
fig.set_size_inches(12.5, 7.5)

plt.subplots_adjust(left=0.01, right= 0.9, bottom=0.1, top=0.5)
plt.show()
随机梯度下降(Stochastic gradient descent)和 批量梯度下降(Batch gradient descent )_第1张图片

[5]:http://latex.codecogs.com/gif.latex?\mathbf{J(w)}=\frac{1}{2m}\sum{(y{(i)}-\phi(z{(i)}))}^2

你可能感兴趣的:(随机梯度下降(Stochastic gradient descent)和 批量梯度下降(Batch gradient descent ))