Python实现线性逻辑回归和非线性逻辑回归

线性逻辑回归

# -*- coding: utf-8 -*-
"""
Created on 2024.2.20

@author: rubyw
"""

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('data.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))

非线性逻辑回归

# -*- coding: utf-8 -*-
"""
Created on 2024.2.20

@author: rubyw
"""

import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model
from sklearn.datasets import make_gaussian_quantiles
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)

logistic = linear_model.LogisticRegression()
logistic.fit(x_data, 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))

z = logistic.predict(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_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))

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))