02_逻辑回归

逻辑回归

  • [1 逻辑回归代码实现](#1 逻辑回归代码实现)
  • [2 超参数](#2 超参数)
  • [3 多项式逻辑回归](#3 多项式逻辑回归)
  • [4 多分类](#4 多分类)

线性可分数据→逻辑回归
非线性可分数据→多项式逻辑回归
多分类问题→OvO, OvR

1 逻辑回归代码实现

python 复制代码
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression

x, y = make_classification(
    n_samples=200,
    n_features=2,
    n_redundant=0,
    n_classes=2,
    n_clusters_per_class=1,
    random_state=50
)
print(x.shape, y.shape)
x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.7, random_state=0, stratify=y)
plt.scatter(x_train[:, 0], x_train[:, 1], c=y_train)
plt.show()

clf = LogisticRegression()
clf.fit(x_train, y_train)
print(clf.score(x_train, y_train))
print(clf.score(x_test, y_test))
y_predict = clf.predict(x_test)
print(y_predict)
print(clf.predict_proba(x_test)[:3])
print(np.argmax(clf.predict_proba(x_test), axis=1))

(200, 2) (200,)

0.9571428571428572

0.9666666666666667

0 1 0 1 0 0 0 1 1 1 0 1 0 0 0 1 1 0 0 0 1 1 0 1 1 0 1 1 0 1 1 0 0 0 1 0 1 0 0 0 1 1 1 0 1 1 0 1 0 0 1 0 1 0 0 1 1 0 0 0

\[0.9976049 0.0023951

0.00943605 0.99056395

0.99884752 0.00115248\]

0 1 0 1 0 0 0 1 1 1 0 1 0 0 0 1 1 0 0 0 1 1 0 1 1 0 1 1 0 1 1 0 0 0 1 0 1 0 0 0 1 1 1 0 1 1 0 1 0 0 1 0 1 0 0 1 1 0 0 0

2 超参数

python 复制代码
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV

x, y = make_classification(
    n_samples=200,
    n_features=2,
    n_redundant=0,
    n_classes=2,
    n_clusters_per_class=1,
    random_state=50
)
print(x.shape, y.shape)
x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.7, random_state=0, stratify=y)

params = [{
    'penalty': ['l2', 'l1'],
    'C': [0.0001, 0.001, 0.01, 0.1, 1, 10, 100, 1000],
    'solver': ['liblinear']
}, {
    'penalty': ['none'],
    'C': [0.0001, 0.001, 0.01, 0.1, 1, 10, 100, 1000],
    'solver': ['lbfgs']
}, {
    'penalty': ['elasticnet'],
    'C': [0.0001, 0.001, 0.01, 0.1, 1, 10, 100, 1000],
    'l1_ratio': [0, 0.25, 0.5, 0.75, 1],
    'solver': ['saga'],
    'max_iter': [200]
}]
grid = GridSearchCV(
    estimator=LogisticRegression(),
    param_grid=params,
    n_jobs=-1
)
grid.fit(x_train, y_train)
print(grid.best_score_)
print(grid.best_estimator_.score(x_test, y_test))
print(grid.best_params_)

0.9571428571428573

0.9666666666666667

{'C': 1, 'penalty': 'l2', 'solver': 'liblinear'}

3 多项式逻辑回归

python 复制代码
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import PolynomialFeatures

np.random.seed(0)
X = np.random.normal(0, 1, size=(200, 2))
y = np.array((X[:, 0] ** 2) + (X[:, 1] ** 2) < 2, dtype='int')
x_train, x_test, y_train, y_test = train_test_split(X, y, train_size=0.7, random_state=233, stratify=y)
plt.scatter(x_train[:,0], x_train[:,1], c = y_train)
plt.show()

clf = LogisticRegression()
clf.fit(x_train, y_train)
print(clf.score(x_train, y_train))
print(clf.score(x_train, y_train))

# 采用多项式逻辑回归
print('------采用多项式逻辑回归--------')
poly = PolynomialFeatures(degree=2)
poly.fit(x_train)
x2 = poly.transform(x_train)
x2t = poly.transform(x_test)
clf.fit(x2, y_train)
print(clf.score(x2, y_train))
print(clf.score(x2t, y_test))

0.7071428571428572

0.7071428571428572

------采用多项式逻辑回归--------

1.0

0.9666666666666667

4 多分类

python 复制代码
from sklearn import datasets
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.multiclass import OneVsRestClassifier
from sklearn.multiclass import OneVsOneClassifier

iris = datasets.load_iris()
x = iris.data
y = iris.target
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=30)
clf = LogisticRegression()
ovr = OneVsRestClassifier(clf)
ovr.fit(x_train, y_train)
print("ovr.score:")
print(ovr.score(x_test, y_test))

ovr = OneVsOneClassifier(clf)
ovr.fit(x_train, y_train)
print("ovo.score:")
print(ovr.score(x_test, y_test))

ovr.score:

0.9473684210526315

ovo.score:

1.0

相关推荐
xchenhao3 小时前
SciKit-Learn 全面分析分类任务 breast_cancer 数据集
python·机器学习·分类·数据集·scikit-learn·svm
独行soc6 小时前
2025年渗透测试面试题总结-66(题目+回答)
java·网络·python·安全·web安全·adb·渗透测试
先做个垃圾出来………7 小时前
残差连接的概念与作用
人工智能·算法·机器学习·语言模型·自然语言处理
Y学院9 小时前
Python 数据分析:从新手到高手的“摸鱼”指南
python·数据分析
IT学长编程9 小时前
计算机毕业设计 基于大数据技术的医疗数据分析与研究 Python 大数据毕业设计 Hadoop毕业设计选题【附源码+文档报告+安装调试】
大数据·hadoop·机器学习·数据分析·毕业设计·毕业论文·医疗数据分析
Yingjun Mo9 小时前
1. 统计推断-基于神经网络与Langevin扩散的自适应潜变量建模与优化
人工智能·神经网络·算法·机器学习·概率论
深耕AI9 小时前
【PyTorch训练】准确率计算(代码片段拆解)
人工智能·pytorch·python
eqwaak09 小时前
科技信息差(9.12)
开发语言·python·科技·量子计算
AI小白的Python之路9 小时前
机器学习-集成学习
人工智能·机器学习·集成学习