机器学习4：逻辑回归
逻辑回归
原理
决策边界
逻辑回归的代价函数
梯度下降法
多分类问题
逻辑回归正则化
正确率、召回率、F1
算法实现
梯度下降—逻辑回归手工实现
import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import classification_report #计算准确率召回率F1
from sklearn import preprocessing
#数据是否需要标准化
scale=False
#载入数据
data=np.genfromtxt("LR-testSet.csv",delimiter=',')
x_data=data[:,:-1]
y_data=data[:,-1]
def plot():
x0=[]
x1=[]
y0=[]
y1=[]
#切分不同类别的数据
for i in range(len(x_data)):
if y_data[i]==0:
x0.append(x_data[i,0])
y0.append(x_data[i,1])
else:
x1.append(x_data[i,0])
y1.append(x_data[i,1])
#画图
scatter0=plt.scatter(x0,y0,c='b',marker='o')
scatter1=plt.scatter(x1,y1,c='r',marker='x')
#画图例
plt.legend(handles=[scatter0,scatter1],labels=['label0','label1'],loc='best')
plot()
plt.show()
#数据处理，添加偏置项
x_data=data[:,:-1]
y_data=data[:,-1,np.newaxis]
print(np.mat(x_data).shape)
print(np.mat(y_data).shape)
#给样本添加偏置项
X_data=np.concatenate((np.ones((100,1)),x_data),axis=1)
print(X_data.shape)
(100, 2)
(100, 1)
(100, 3)
def sigmoid(x):
return 1.0/(1+np.exp(-x))
def cost(xMat,yMat,ws):
left = np.multiply(yMat, np.log(sigmoid(xMat*ws))) #按位相乘
right = np.multiply(1 - yMat, np.log(1 - sigmoid(xMat*ws)))
return np.sum(left + right) / -(len(xMat))
def gradAscent(xArr,yArr):
if scale==True:
xArr=preprocessing.scale(xArr)
xMat=np.mat(xArr)
yMat=np.mat(yArr)
lr=0.001
epochs = 10000
costList = []
# 计算数据行列数
# 行代表数据个数，列代表权值个数
m,n = np.shape(xMat)
# 初始化权值
ws = np.mat(np.ones((n,1)))
for i in range(epochs+1):
# xMat和weights矩阵相乘
h = sigmoid(xMat*ws)
# 计算误差
ws_grad = xMat.T*(h - yMat)/m
ws = ws - lr*ws_grad
if i % 50 == 0:
costList.append(cost(xMat,yMat,ws))
return ws,costList
# 训练模型，得到权值和cost值的变化
ws,costList = gradAscent(X_data, y_data)
print(ws)
[[ 2.05836354]
[ 0.3510579 ]
[-0.36341304]]
if scale == False:
# 画图决策边界
plot()
x_test = [[-4],[3]]
y_test = (-ws[0] - x_test*ws[1])/ws[2]
plt.plot(x_test, y_test, 'k')
plt.show()
# 画图 loss值的变化
x = np.linspace(0,10000,201) #10000/50
plt.plot(x, costList, c='r')
plt.title('Train')
plt.xlabel('Epochs')
plt.ylabel('Cost')
plt.show()
# 预测
def predict(x_data, ws):
if scale == True:
x_data = preprocessing.scale(x_data)
xMat = np.mat(x_data)
ws = np.mat(ws)
return [1 if x >= 0.5 else 0 for x in sigmoid(xMat*ws)]
predictions = predict(X_data, ws)
print(classification_report(y_data, predictions))
逻辑回归-sklearn
import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import classification_report
from sklearn import preprocessing
from sklearn import linear_model
# 数据是否需要标准化
scale = False
# 载入数据
data = np.genfromtxt("LR-testSet.csv", delimiter=",")
x_data = data[:,:-1]
y_data = data[:,-1]
def plot():
x0 = []
x1 = []
y0 = []
y1 = []
# 切分不同类别的数据
for i in range(len(x_data)):
if y_data[i]==0:
x0.append(x_data[i,0])
y0.append(x_data[i,1])
else:
x1.append(x_data[i,0])
y1.append(x_data[i,1])
# 画图
scatter0 = plt.scatter(x0, y0, c='b', marker='o')
scatter1 = plt.scatter(x1, y1, c='r', marker='x')
#画图例
plt.legend(handles=[scatter0,scatter1],labels=['label0','label1'],loc='best')
plot()
plt.show()
logistic = linear_model.LogisticRegression()
logistic.fit(x_data, y_data)
if scale == False:
# 画图决策边界
plot()
x_test = np.array([[-4],[3]])
y_test = (-logistic.intercept_ - x_test*logistic.coef_[0][0])/logistic.coef_[0][1]
plt.plot(x_test, y_test, 'k')
plt.show()
predictions = logistic.predict(x_data)
print(classification_report(y_data, predictions))
梯度下降法-非线性逻辑回归
import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import classification_report
from sklearn import preprocessing
from sklearn.preprocessing import PolynomialFeatures #特征处理
# 数据是否需要标准化
scale = False
# 载入数据
data = np.genfromtxt("LR-testSet2.txt", delimiter=",")
x_data = data[:,:-1]
y_data = data[:,-1,np.newaxis]
def plot():
x0 = []
x1 = []
y0 = []
y1 = []
# 切分不同类别的数据
for i in range(len(x_data)):
if y_data[i]==0:
x0.append(x_data[i,0])
y0.append(x_data[i,1])
else:
x1.append(x_data[i,0])
y1.append(x_data[i,1])
# 画图
scatter0 = plt.scatter(x0, y0, c='b', marker='o')
scatter1 = plt.scatter(x1, y1, c='r', marker='x')
#画图例
plt.legend(handles=[scatter0,scatter1],labels=['label0','label1'],loc='best')
plot()
plt.show()
# 定义多项式回归,degree的值可以调节多项式的特征
poly_reg = PolynomialFeatures(degree=3)
# 特征处理
x_poly = poly_reg.fit_transform(x_data)
def sigmoid(x):
return 1.0/(1+np.exp(-x))
def cost(xMat, yMat, ws):
left = np.multiply(yMat, np.log(sigmoid(xMat*ws)))
right = np.multiply(1 - yMat, np.log(1 - sigmoid(xMat*ws)))
return np.sum(left + right) / -(len(xMat))
def gradAscent(xArr, yArr):
if scale == True:
xArr = preprocessing.scale(xArr)
xMat = np.mat(xArr)
yMat = np.mat(yArr)
lr = 0.03
epochs = 50000
costList = []
# 计算数据列数，有几列就有几个权值
m,n = np.shape(xMat)
# 初始化权值
ws = np.mat(np.ones((n,1)))
for i in range(epochs+1):
# xMat和weights矩阵相乘
h = sigmoid(xMat*ws)
# 计算误差
ws_grad = xMat.T*(h - yMat)/m
ws = ws - lr*ws_grad
if i % 50 == 0:
costList.append(cost(xMat,yMat,ws))
return ws,costList
# 训练模型，得到权值和cost值的变化
ws,costList = gradAscent(x_poly, y_data)
print(ws)
[[ 4.16787292]
[ 2.72213524]
[ 4.55120018]
[-9.76109006]
[-5.34880198]
[-8.51458023]
[-0.55950401]
[-1.55418165]
[-0.75929829]
[-2.88573877]]
# 获取数据值所在的范围
x_min, x_max = x_data[:, 0].min() - 1, x_data[:, 0].max() + 1
y_min, y_max = x_data[:, 1].min() - 1, x_data[:, 1].max() + 1
# 生成网格矩阵
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02),
np.arange(y_min, y_max, 0.02))
# np.r_按row来组合array，
# np.c_按colunm来组合array
# >>> a = np.array([1,2,3])
# >>> b = np.array([5,2,5])
# >>> np.r_[a,b]
# array([1, 2, 3, 5, 2, 5])
# >>> np.c_[a,b]
# array([[1, 5],
# [2, 2],
# [3, 5]])
# >>> np.c_[a,[0,0,0],b]
# array([[1, 0, 5],
# [2, 0, 2],
# [3, 0, 5]])
z = sigmoid(poly_reg.fit_transform(np.c_[xx.ravel(), yy.ravel()]).dot(np.array(ws)))# ravel与flatten类似，多维数据转一维。flatten不会改变原始数据，ravel会改变原始数据
for i in range(len(z)):
if z[i] > 0.5:
z[i] = 1
else:
z[i] = 0
z = z.reshape(xx.shape)
# 等高线图
cs = plt.contourf(xx, yy, z)
plot()
plt.show()
# 预测
def predict(x_data, ws):
# if scale == True:
# x_data = preprocessing.scale(x_data)
xMat = np.mat(x_data)
ws = np.mat(ws)
return [1 if x >= 0.5 else 0 for x in sigmoid(xMat*ws)]
predictions = predict(x_poly, ws)
print(classification_report(y_data, predictions))
sklearn-非线性逻辑回归
import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model
from sklearn.datasets import make_gaussian_quantiles #生成数据
from sklearn.preprocessing import PolynomialFeatures
# 生成2维正态分布，生成的数据按分位数分为两类，500个样本,2个样本特征
# 可以生成两类或多类数据
x_data, y_data = make_gaussian_quantiles(n_samples=500, n_features=2,n_classes=2)
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data) #把分类传到颜色中去,代码简单很多
plt.show()
logistic = linear_model.LogisticRegression()
logistic.fit(x_data, y_data)
# 定义多项式回归,degree的值可以调节多项式的特征
poly_reg = PolynomialFeatures(degree=5)
# 特征处理
x_poly = poly_reg.fit_transform(x_data)
# 定义逻辑回归模型
logistic = linear_model.LogisticRegression()
# 训练模型
logistic.fit(x_poly, y_data)
# 获取数据值所在的范围
x_min, x_max = x_data[:, 0].min() - 1, x_data[:, 0].max() + 1
y_min, y_max = x_data[:, 1].min() - 1, x_data[:, 1].max() + 1
# 生成网格矩阵
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02),
np.arange(y_min, y_max, 0.02))
# np.r_按row来组合array，
# np.c_按colunm来组合array
# >>> a = np.array([1,2,3])
# >>> b = np.array([5,2,5])
# >>> np.r_[a,b]
# array([1, 2, 3, 5, 2, 5])
# >>> np.c_[a,b]
# array([[1, 5],
# [2, 2],
# [3, 5]])
# >>> np.c_[a,[0,0,0],b]
# array([[1, 0, 5],
# [2, 0, 2],
# [3, 0, 5]])
z = logistic.predict(poly_reg.fit_transform(np.c_[xx.ravel(), yy.ravel()]))# ravel与flatten类似，多维数据转一维。flatten不会改变原始数据，ravel会改变原始数据
z = z.reshape(xx.shape)
# 等高线图
cs = plt.contourf(xx, yy, z)
# 样本散点图
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)
plt.show()
print('score:',logistic.score(x_poly,y_data))
100
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
