逻辑回归算法:算法实践
库函数的导入
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.linear_model import LogisticRegression
训练模型
## 构造数据集
x_fearures = np.array([[-1, -2], [-2, -1], [-3, -2], [1, 3], [2, 1], [3, 2]])
y_label = np.array([0, 0, 0, 1, 1, 1])
## 调用逻辑回归模型
lr_clf = LogisticRegression()
## 用逻辑回归模型拟合构造的数据集
lr_clf = lr_clf.fit(x_fearures, y_label) #其拟合方程为 y=w0+w1*x1+w2*x2
模型参数查看
## 查看其对应模型的w
print('the weight of Logistic Regression:',lr_clf.coef_)
## 查看其对应模型的w0
print('the intercept(w0) of Logistic Regression:',lr_clf.intercept_)
the weight of Logistic Regression: [[0.73455784 0.69539712]]
the intercept(w0) of Logistic Regression: [-0.13139986]
数据和模型可视化
plt.figure()
plt.scatter(x_fearures[:,0],x_fearures[:,1], c=y_label, s=50, cmap='viridis')
plt.title('Dataset')
plt.show()
# 可视化决策边界
plt.figure()
plt.scatter(x_fearures[:,0],x_fearures[:,1], c=y_label, s=50, cmap='viridis')
plt.title('Dataset')
nx, ny = 200, 100
x_min, x_max = plt.xlim()
y_min, y_max = plt.ylim()
x_grid, y_grid = np.meshgrid(np.linspace(x_min, x_max, nx),np.linspace(y_min, y_max, ny))
z_proba = lr_clf.predict_proba(np.c_[x_grid.ravel(), y_grid.ravel()])
## np.c_是按行连接两个矩阵,就是把两矩阵左右相加,要求行数相等。
z_proba = z_proba[:, 1].reshape(x_grid.shape)
plt.contour(x_grid, y_grid, z_proba, [0.5], linewidths=2., colors='blue')
plt.show()
代价函数此处判断定义:
成本函数,也称为损失函数,用于定义和测量模型的误差。模型预测的数据与训练数据集中观测到的数据之间的差异称为残差或训练误差。在图中,模型的残差由训练过的实列点和回归超平面之间的一条垂直线表示。
### 可视化预测新样本
plt.figure()
## new point 1
x_fearures_new1 = np.array([[0, -1]])
plt.scatter(x_fearures_new1[:,0],x_fearures_new1[:,1], s=50, cmap='viridis')
plt.annotate(s='New point 1',xy=(0,-1),xytext=(-2,0),color='blue',arrowprops=dict(arrowstyle='-|>',connectionstyle='arc3',color='red'))
## plt.annotate()函数用于标注文字。
## new point 2
x_fearures_new2 = np.array([[1, 2]])
plt.scatter(x_fearures_new2[:,0],x_fearures_new2[:,1], s=50, cmap='viridis')
plt.annotate(s='New point 2',xy=(1,2),xytext=(-1.5,2.5),color='red',arrowprops=dict(arrowstyle='-|>',connectionstyle='arc3',color='red'))
## 训练样本
plt.scatter(x_fearures[:,0],x_fearures[:,1], c=y_label, s=50, cmap='viridis')
plt.title('Dataset')
# 可视化决策边界
plt.contour(x_grid, y_grid, z_proba, [0.5], linewidths=2., colors='blue')
plt.show()
模型预测
## 在训练集和测试集上分布利用训练好的模型进行预测
y_label_new1_predict = lr_clf.predict(x_fearures_new1)
y_label_new2_predict = lr_clf.predict(x_fearures_new2)
print('The New point 1 predict class:\n',y_label_new1_predict)
print('The New point 2 predict class:\n',y_label_new2_predict)
## 由于逻辑回归模型是概率预测模型(前文介绍的 p = p(y=1|x,\theta)),所有我们可以利用 predict_proba 函数预测其概率
y_label_new1_predict_proba = lr_clf.predict_proba(x_fearures_new1)
y_label_new2_predict_proba = lr_clf.predict_proba(x_fearures_new2)
print('The New point 1 predict Probability of each class:\n',y_label_new1_predict_proba)
print('The New point 2 predict Probability of each class:\n',y_label_new2_predict_proba)
The New point 1 predict class:
[0]
The New point 2 predict class:
[1]
The New point 1 predict Probability of each class:
[[0.69567724 0.30432276]]
The New point 2 predict Probability of each class:
[[0.11983936 0.88016064]]