机器学习模型-支持向量机(SVM)

  二.代码实现
  
  import numpy as np
  
  from sklearn import datasets
  
  from sklearn.model_selection import train_test_split
  
  from sklearn.linear_model import LogisticRegression
  
  import warnings
  
  warnings.filterwarnings('ignore')
  
  data = datasets.load_breast_cancer()
  
  x = data.data;y = data.target
  
  y[y==0] = -1
  
  x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=1)
  
  omega = np.zeros(x.shape[1])
  
  b = 0
  
  lr = 0.01
  
  C = 1
  
  maxgen = 500
  
  for L in range(maxgen):
  
      error = 1 - (np.dot(x_train,omega)+b)*y_train
  
      index = np.argmax(error)
  
      if error[index] > 0:
  
          omega = (1-lr)*omega + lr*C*y_train[index]*x_train[index,:]
  
          b = b + lr*C*y_train[index]
  
      else:
  
          break
  
  predict_train = np.sign(np.dot(x_train,omega)+b)
  
  train_acc = len(np.where(predict_train==y_train)[0])/len(y_train)
  
  predict_test = np.sign(np.dot(x_test,omega)+b)
  
  test_acc = len(np.where(predict_test==y_test)[0])/len(y_test)
  
  print('Train acc = ',round(train_acc,4),' Test acc = ',round(test_acc,4))
  
  三.SMO算法实现
  
  import numpy as np
  
  from sklearn import datasets
  
  from sklearn import preprocessing
  
  from sklearn.model_selection import train_test_split
  
  from sklearn.svm import SVC
  
  import warnings
  
  warnings.filterwarnings('ignore')
  
  data = datasets.load_breast_cancer()
  
  x = data.data;x = preprocessing.MinMaxScaler().fit_transform(x)
  
  y = data.target;y[y==0] = -1
  
  x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=1)
  
  alpha = np.zeros(x_train.shape[0])
  
  b = 0
  
  C = 1
  
  p = np.zeros(x_train.shape[0])
  
  maxgen = 100
  
  def gramMat(x):
  
      v = []
  
      for i in x:
  
          for j in x:
  
              k = np.dot(i,j.T)
  
              v.append(k)
  
      gram = np.array(v).reshape(len(x),len(x))
  
      return gram
  
  K = gramMat(x_train)
  
  def selectFirstSample(K,y,p,alpha,b,C):
  
      threshold = 0.001
  
      c = y*p-1
  
      c1 = c.copy();c2=c.copy();c3=c.copy()
  
      c1[(alpha > 0) & (c >= 0)] = 0
  
      c2[((alpha==0) | (alpha==C)) & (c==0)] = 0
  
      c3[(alpha < 0) & (c www.tiaotiaoylzc.com/ <= 0)] = 0
  
      error = c1**2+c2**2+c3**2
  
      index = np.argmax(error)
  
      if error[index] >= threshold:
  
          return index
  
      else:
  
          return None
  
  def selectSecondSample(id1,y_train):
  
      id2 = np.random.randint(www.ysyl157.com len(y_train))
  
      while id1 == id2:
  
          id2 = np.random.randint(len(y_train))
  
      return id2
  
  def boundary(y,id1,id2,C):
  
      if y[id1] =www.xgll521.com= y[id2]:
  
          lb = max(0,alpha[id1]+alpha[id2]-C)
  
          ub = min(C,alpha[id1]+alpha[id2])
  
      else:
  
          lb = max(0,alpha[id2]-alpha[id1])
  
          ub = min(C,C+alpha[id2]-alpha[id1])
  
      return lb,ub
  
  def updateAlpha(K,y,p,id1,id2,lb,ub,C):
  
      old_alpha1 = alpha[id1];old_alpha2 = alpha[id2]
  
      p1 = p[id1];p2 = p[id2]
  
      y1 = y[id1];y2 = y[id2]
  
      E1 = p1 - y1;E2 = p2 - y2
  
      beta = 2*K[id1,id2] - K[id1,id1] - K[id2,id2]
  
      new_alpha2 = old_alpha2 - y2*(E1-E2)/beta
  
      if new_alpha2 > ub:
  
          new_alpha2 = ub
  
      if new_alpha2 < lb:
  
          new_alpha2 www.taohuaqing178.com= lb
  
      alpha[id2] = new_alpha2
  
      new_alpha1 = old_alpha1 - y1*y2*(new_alpha2 - old_alpha2)
  
      alpha[id1] = new_alpha1
  
      deta1 = new_alpha1 - old_alpha1
  
      deta2 = new_alpha2 - old_alpha2
  
      dw = [y1*deta1,y2*deta2]
  
      b1 = -E1 - y1*K[id1,id1]*deta1 - y2*K[id1,id2]*deta2
  
      b2 = -E2 - y1*K[id1,id2]*deta1 - y2*K[id2,id2]*deta2
  
      if new_alpha1 >=0 and new_alpha1 <= C:
  
          db = b1
  
      elif new_alpha2 >www.thd178.com/ =0 and new_alpha2 <= C:
  
          db = b2
  
      else:
  
          db = (b1 + b2)/2
  
      p = p + dw[0]*K[id1,:].T + dw[1]*K[id2,:].T + db
  
      return p
  
  for L in range(maxgen):
  
      id1 = selectFirstSample(K,y_train,p,alpha,b,C)
  
      id2 = selectSecondSample(id1,y_train)
  
      lb,ub = boundary(y_train,id1,id2,C)
  
      p = updateAlpha(K,y,p,id1,id2,lb,ub,C)
  
  index = np.argmax((alpha!=0)&(alpha!=C))
  
  b = y_train[index] - np.sum(alpha*y_train*K[:,index])
  
  predict_train = np.sign(np.sum(alpha*y_train*K,axis=0)+b)
  
  train_acc = len(np.where(predict_train==y_train)[0])/len(y_train)
  
  predict_test = []
  
  for arr in x_test:
  
      v = np.sum(alpha*y_train*np.dot(x_train,arr.T))+b
  
      predict_test.append(np.sign(v))   
  
  test_acc = len(np.where(predict_test==y_test)[0])/len(y_test)
  
  print('self-written ==> Train acc = ',round(train_acc,4),' Test acc = ',round(test_acc,4))
  
  model = SVC()
  
  model.fit(x_train,y_train)
  
  train_acc = model.score(x_train,y_train)
  
  test_acc = model.score(x_test,y_test)
  
  print('sklearn ==> Train acc = ',round(train_acc,4),' Test acc = ',round(test_acc,4))

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值