#利用Python實(shí)現(xiàn)感知機(jī)算法的原始形式
# -*- encoding:utf-8 -*-

"""
Created on 2017.6.7

@author: Ada
"""

import numpy as np
import matplotlib.pyplot as plt

#1、創(chuàng)建數(shù)據(jù)集
def createdata():
 samples=np.array([[3,-3],[4,-3],[1,1],[1,2]])
 labels=[-1,-1,1,1]
 return samples,labels

#訓(xùn)練感知機(jī)模型
class Perceptron:
 def __init__(self,x,y,a=1):
  self.x=x
  self.y=y
  self.w=np.zeros((x.shape[1],1))#初始化權(quán)重，w1,w2均為0
  self.b=0
  self.a=1#學(xué)習(xí)率
  self.numsamples=self.x.shape[0]
  self.numfeatures=self.x.shape[1]

 def sign(self,w,b,x):
  y=np.dot(x,w)+b
  return int(y)

 def update(self,label_i,data_i):
  tmp=label_i*self.a*data_i
  tmp=tmp.reshape(self.w.shape)
  #更新w和b
  self.w=tmp+self.w
  self.b=self.b+label_i*self.a

 def train(self):
  isFind=False
  while not isFind:
   count=0
   for i in range(self.numsamples):
    tmpY=self.sign(self.w,self.b,self.x[i,:])
    if tmpY*self.y[i]<=0:#如果是一個(gè)誤分類實(shí)例點(diǎn)
     print '誤分類點(diǎn)為：',self.x[i,:],'此時(shí)的w和b為：',self.w,self.b
     count+=1
     self.update(self.y[i],self.x[i,:])
   if count==0:
    print '最終訓(xùn)練得到的w和b為：',self.w,self.b
    isFind=True
  return self.w,self.b

#畫圖描繪
class Picture:
 def __init__(self,data,w,b):
  self.b=b
  self.w=w
  plt.figure(1)
  plt.title('Perceptron Learning Algorithm',size=14)
  plt.xlabel('x0-axis',size=14)
  plt.ylabel('x1-axis',size=14)

  xData=np.linspace(0,5,100)
  yData=self.expression(xData)
  plt.plot(xData,yData,color='r',label='sample data')

  plt.scatter(data[0][0],data[0][1],s=50)
  plt.scatter(data[1][0],data[1][1],s=50)
  plt.scatter(data[2][0],data[2][1],s=50,marker='x')
  plt.scatter(data[3][0],data[3][1],s=50,marker='x')
  plt.savefig('2d.png',dpi=75)

 def expression(self,x):
  y=(-self.b-self.w[0]*x)/self.w[1]#注意在此，把x0，x1當(dāng)做兩個(gè)坐標(biāo)軸，把x1當(dāng)做自變量，x2為因變量
  return y

 def Show(self):
  plt.show()


if __name__ == '__main__':
 samples,labels=createdata()
 myperceptron=Perceptron(x=samples,y=labels)
 weights,bias=myperceptron.train()
 Picture=Picture(samples,weights,bias)
 Picture.Show()

#利用Python實(shí)現(xiàn)感知機(jī)算法的對(duì)偶形式
# -*- encoding:utf-8 -*-

"""
Created on 2017.6.7

@author: Ada
"""

import numpy as np
import matplotlib.pyplot as plt

#1、創(chuàng)建數(shù)據(jù)集
def createdata():
 samples=np.array([[3,-3],[4,-3],[1,1],[1,2]])
 labels=np.array([-1,-1,1,1])
 return samples,labels

#訓(xùn)練感知機(jī)模型
class Perceptron:
 def __init__(self,x,y,a=1):
  self.x=x
  self.y=y
  self.w=np.zeros((1,x.shape[0]))
  self.b=0
  self.a=1#學(xué)習(xí)率
  self.numsamples=self.x.shape[0]
  self.numfeatures=self.x.shape[1]
  self.gMatrix=self.cal_gram(self.x)

 def cal_gram(self,x):
  gMatrix=np.zeros((self.numsamples,self.numsamples))
  for i in xrange(self.numsamples):
   for j in xrange(self.numsamples):
    gMatrix[i][j]=np.dot(self.x[i,:],self.x[j,:])
  return gMatrix

 def sign(self,w,b,key):
  y=np.dot(w*self.y,self.gMatrix[:,key])+b
  return int(y)

 def update(self,i):
  self.w[i,]=self.w[i,]+self.a
  self.b=self.b+self.y[i]*self.a

 def cal_w(self):
  w=np.dot(self.w*self.y,self.x)
  return w

 def train(self):
  isFind=False
  while not isFind:
   count=0
   for i in range(self.numsamples):
    tmpY=self.sign(self.w,self.b,i)
    if tmpY*self.y[i]<=0:#如果是一個(gè)誤分類實(shí)例點(diǎn)
     print '誤分類點(diǎn)為：',self.x[i,:],'此時(shí)的w和b為：',self.cal_w(),',',self.b
     count+=1
     self.update(i)
   if count==0:
    print '最終訓(xùn)練得到的w和b為：',self.cal_w(),',',self.b
    isFind=True
  weights=self.cal_w()
  return weights,self.b

#畫圖描繪
class Picture:
 def __init__(self,data,w,b):
  self.b=b
  self.w=w
  plt.figure(1)
  plt.title('Perceptron Learning Algorithm',size=14)
  plt.xlabel('x0-axis',size=14)
  plt.ylabel('x1-axis',size=14)

  xData=np.linspace(0,5,100)
  yData=self.expression(xData)
  plt.plot(xData,yData,color='r',label='sample data')

  plt.scatter(data[0][0],data[0][1],s=50)
  plt.scatter(data[1][0],data[1][1],s=50)
  plt.scatter(data[2][0],data[2][1],s=50,marker='x')
  plt.scatter(data[3][0],data[3][1],s=50,marker='x')
  plt.savefig('2d.png',dpi=75)

 def expression(self,x):
  y=(-self.b-self.w[:,0]*x)/self.w[:,1]
  return y

 def Show(self):
  plt.show()


if __name__ == '__main__':

 samples,labels=createdata()
 myperceptron=Perceptron(x=samples,y=labels)
 weights,bias=myperceptron.train()
 Picture=Picture(samples,weights,bias)
 Picture.Show()

# -*- encoding:utf-8 -*-

"""
利用sklearn中的感知機(jī)學(xué)習(xí)算法進(jìn)行實(shí)驗(yàn)
Created on 2017.6.7

@author: Ada
"""

import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import Perceptron

#創(chuàng)建數(shù)據(jù),直接定義數(shù)據(jù)列表
def creatdata1():
 samples=np.array([[3,-3],[4,-3],[1,1],[1,2]])
 labels=np.array([-1,-1,1,1])
 return samples,labels

def MyPerceptron(samples,labels):
 #定義感知機(jī)
 clf=Perceptron(fit_intercept=True,n_iter=30,shuffle=False)
 #訓(xùn)練感知機(jī)
 clf.fit(samples,labels)
 #得到權(quán)重矩陣
 weigths=clf.coef_

 #得到截距bisa
 bias=clf.intercept_

 return weigths,bias

#畫圖描繪
class Picture:
 def __init__(self,data,w,b):
  self.b=b
  self.w=w
  plt.figure(1)
  plt.title('Perceptron Learning Algorithm',size=14)
  plt.xlabel('x0-axis',size=14)
  plt.ylabel('x1-axis',size=14)

  xData=np.linspace(0,5,100)
  yData=self.expression(xData)
  plt.plot(xData,yData,color='r',label='sample data')

  plt.scatter(data[0][0],data[0][1],s=50)
  plt.scatter(data[1][0],data[1][1],s=50)
  plt.scatter(data[2][0],data[2][1],s=50,marker='x')
  plt.scatter(data[3][0],data[3][1],s=50,marker='x')
  plt.savefig('3d.png',dpi=75)

 def expression(self,x):
  y=(-self.b-self.w[:,0]*x)/self.w[:,1]
  return y

 def Show(self):
  plt.show()




if __name__ == '__main__':
 samples,labels=creatdata1()
 weights,bias=MyPerceptron(samples,labels)
 print '最終訓(xùn)練得到的w和b為：',weights,',',bias
 Picture=Picture(samples,weights,bias)
 Picture.Show()

# -*- encoding:utf-8 -*-
'''
利用sklearn中的的Perceptron進(jìn)行實(shí)驗(yàn)，并進(jìn)行測(cè)試
'''
from sklearn.datasets import make_classification
from sklearn.linear_model import Perceptron
from sklearn.cross_validation import train_test_split
from matplotlib import pyplot as plt
import numpy as np
#利用算法進(jìn)行創(chuàng)建數(shù)據(jù)集
def creatdata():

 x,y = make_classification(n_samples=1000, n_features=2,n_redundant=0,n_informative=1,n_clusters_per_class=1)
 '''
 #n_samples:生成樣本的數(shù)量

 #n_features=2:生成樣本的特征數(shù)，特征數(shù)=n_informative（） + n_redundant + n_repeated

 #n_informative：多信息特征的個(gè)數(shù)

 #n_redundant：冗余信息，informative特征的隨機(jī)線性組合

 #n_clusters_per_class ：某一個(gè)類別是由幾個(gè)cluster構(gòu)成的

 make_calssification默認(rèn)生成二分類的樣本，上面的代碼中，x代表生成的樣本空間（特征空間）
 y代表了生成的樣本類別，使用1和0分別表示正例和反例

 y=[0 0 0 1 0 1 1 1... 1 0 0 1 1 0]
 '''
 return x,y

if __name__ == '__main__':
 x,y=creatdata()

 #將生成的樣本分為訓(xùn)練數(shù)據(jù)和測(cè)試數(shù)據(jù)，并將其中的正例和反例分開
 x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)

 #正例和反例
 positive_x1=[x[i,0]for i in range(len(y)) if y[i]==1]
 positive_x2=[x[i,1]for i in range(len(y)) if y[i]==1]
 negetive_x1=[x[i,0]for i in range(len(y)) if y[i]==0]
 negetive_x2=[x[i,1]for i in range(len(y)) if y[i]==0]

 #定義感知機(jī)
 clf=Perceptron(fit_intercept=True,n_iter=50,shuffle=False)
 # 使用訓(xùn)練數(shù)據(jù)進(jìn)行訓(xùn)練
 clf.fit(x_train,y_train)
 #得到訓(xùn)練結(jié)果，權(quán)重矩陣
 weights=clf.coef_
 #得到截距
 bias=clf.intercept_

 #到此時(shí)，我們已經(jīng)得到了訓(xùn)練出的感知機(jī)模型參數(shù)，下面用測(cè)試數(shù)據(jù)對(duì)其進(jìn)行驗(yàn)證
 acc=clf.score(x_test,y_test)#Returns the mean accuracy on the given test data and labels.
 print '平均精確度為：%.2f'%(acc*100.0)

 #最后，我們將結(jié)果用圖像顯示出來，直觀的看一下感知機(jī)的結(jié)果
 #畫出正例和反例的散點(diǎn)圖
 plt.scatter(positive_x1,positive_x2,c='red')
 plt.scatter(negetive_x1,negetive_x2,c='blue')

 #畫出超平面（在本例中即是一條直線）
 line_x=np.arange(-4,4)
 line_y=line_x*(-weights[0][0]/weights[0][1])-bias
 plt.plot(line_x,line_y)
 plt.show()

# -*- encoding:utf-8 -*-
import numpy as np


'''
以scikit-learn 中的perceptron為例介紹分類算法

應(yīng)用及其學(xué)習(xí)分類算法的五個(gè)步驟
（1）選擇特征
（2）選擇一個(gè)性能指標(biāo)
（3）選擇一個(gè)分類器和一個(gè)優(yōu)化算法
（4）評(píng)價(jià)模型的性能
（5）優(yōu)化算法

以scikit-learn 中的perceptron為例介紹分類算法
1 讀取數(shù)據(jù)-iris
2 分配訓(xùn)練集和測(cè)試集
3 標(biāo)準(zhǔn)化特征值
4 訓(xùn)練感知器模型
5 用訓(xùn)練好的模型進(jìn)行預(yù)測(cè)
6 計(jì)算性能指標(biāo)
7 描繪分類界面

'''

from sklearn import datasets
import numpy as np
import matplotlib.pyplot as plt

iris=datasets.load_iris()
X=iris.data[:,[2,3]]
y=iris.target

#訓(xùn)練數(shù)據(jù)和測(cè)試數(shù)據(jù)分為7:3
from sklearn.cross_validation import train_test_split
x_train,x_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0)

#標(biāo)準(zhǔn)化數(shù)據(jù)
from sklearn.preprocessing import StandardScaler
sc=StandardScaler()
sc.fit(x_train)
x_train_std=sc.transform(x_train)
x_test_std=sc.transform(x_test)

#引入skleran 的Perceptron并進(jìn)行訓(xùn)練
from sklearn.linear_model import Perceptron
ppn=Perceptron(n_iter=40,eta0=0.01,random_state=0)
ppn.fit(x_train_std,y_train)

y_pred=ppn.predict(x_test_std)
print '錯(cuò)誤分類數(shù)：%d'%(y_test!=y_pred).sum()

from sklearn.metrics import accuracy_score
print '準(zhǔn)確率為:%.2f'%accuracy_score(y_test,y_pred)

#繪制決策邊界
from matplotlib.colors import ListedColormap
import warnings

def versiontuple(v):
 return tuple(map(int,(v.split('.'))))

def plot_decision_regions(X,y,classifier,test_idx=None,resolution=0.02):
 #設(shè)置標(biāo)記點(diǎn)和顏色
 markers=('s','x','o','^','v')
 colors=('red','blue','lightgreen','gray','cyan')
 cmap=ListedColormap(colors[:len(np.unique(y))])

 # 繪制決策面
 x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
 x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
 xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
       np.arange(x2_min, x2_max, resolution))
 Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
 Z = Z.reshape(xx1.shape)
 plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
 plt.xlim(xx1.min(), xx1.max())
 plt.ylim(xx2.min(), xx2.max())

 for idx, cl in enumerate(np.unique(y)):
  plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1],
     alpha=0.8, c=cmap(idx),
     marker=markers[idx], label=cl)

 if test_idx:
  # 繪制所有數(shù)據(jù)點(diǎn)
  if not versiontuple(np.__version__) >= versiontuple('1.9.0'):
   X_test, y_test = X[list(test_idx), :], y[list(test_idx)]
   warnings.warn('Please update to NumPy 1.9.0 or newer')
  else:
   X_test, y_test = X[test_idx, :], y[test_idx]
  plt.scatter(X_test[:, 0], X_test[:, 1], c='',
    alpha=1.0, linewidth=1, marker='o',
    s=55, label='test set')

def plot_result():
 X_combined_std = np.vstack((x_train_std, x_test_std))
 y_combined = np.hstack((y_train, y_test))

 plot_decision_regions(X=X_combined_std, y=y_combined,
      classifier=ppn, test_idx=range(105,150))
 plt.xlabel('petal length [standardized]')
 plt.ylabel('petal width [standardized]')
 plt.legend(loc='upper left')

 plt.tight_layout()
 plt.show()

plot_result()