【机器学习】突破分类瓶颈：用逻辑回归与Softmax回归解锁多分类世界

from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report

# 生成数据集
X, y = make_classification(n_samples=1000, n_features=20, n_informative=10, random_state=42)

# 数据分割
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 训练模型
model = LogisticRegression()
model.fit(X_train, y_train)

# 预测
y_pred = model.predict(X_test)

# 评估
print(classification_report(y_test, y_pred))

from sklearn.linear_model import LogisticRegression

# 使用Softmax回归处理多分类问题
model = LogisticRegression(multi_class='multinomial', solver='lbfgs')
model.fit(X_train, y_train)

y_pred = model.predict(X_test)
print(classification_report(y_test, y_pred))

from sklearn.ensemble import RandomForestClassifier

# 随机森林分类器
rf = RandomForestClassifier(n_estimators=100)
rf.fit(X_train, y_train)

y_pred = rf.predict(X_test)
print(classification_report(y_test, y_pred))

from imblearn.over_sampling import SMOTE

# 过采样
smote = SMOTE()
X_res, y_res = smote.fit_resample(X_train, y_train)

# 训练模型
model = LogisticRegression()
model.fit(X_res, y_res)

y_pred = model.predict(X_test)
print(classification_report(y_test, y_pred))

# 导入需要的库
import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report, confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt

# 1. 加载Iris数据集
iris = load_iris()
X = iris.data  # 特征
y = iris.target  # 标签

# 2. 数据分割：80%训练数据，20%测试数据
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 3. 数据标准化：逻辑回归对特征的尺度比较敏感
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# 4. 训练逻辑回归模型
logreg = LogisticRegression(max_iter=200)
logreg.fit(X_train, y_train)

# 5. 在测试集上进行预测
y_pred = logreg.predict(X_test)

# 6. 模型评估
print("分类报告：")
print(classification_report(y_test, y_pred))

# 7. 混淆矩阵
cm = confusion_matrix(y_test, y_pred)
print("混淆矩阵：")
print(cm)

# 可视化混淆矩阵
sns.heatmap(cm, annot=True, fmt="d", cmap="Blues", xticklabels=iris.target_names, yticklabels=iris.target_names)
plt.xlabel('Predicted')
plt.ylabel('True')
plt.title('Confusion Matrix')
plt.show()