Pandas使用AdaBoost进行分类的实现

pip install pandas scikit-learn

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris

# 加载 Iris 数据集
iris = load_iris()
df = pd.DataFrame(data=iris.data, columns=iris.feature_names)
df['target'] = iris.target

# 显示前几行数据
print(df.head())

from sklearn.ensemble import AdaBoostClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

# 分割数据集为训练集和测试集
X = df.drop(columns=['target'])
y = df['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 初始化弱分类器（决策树）
weak_classifier = DecisionTreeClassifier(max_depth=1)

# 初始化 AdaBoost 分类器
adaboost = AdaBoostClassifier(base_estimator=weak_classifier, n_estimators=50, learning_rate=1.0, random_state=42)

# 训练模型
adaboost.fit(X_train, y_train)

# 预测
y_pred = adaboost.predict(X_test)

# 评估模型
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy * 100:.2f}%")

from sklearn.metrics import confusion_matrix, classification_report
import seaborn as sns
import matplotlib.pyplot as plt

# 混淆矩阵
cm = confusion_matrix(y_test, y_pred)
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
plt.xlabel('Predicted')
plt.ylabel('True')
plt.title('Confusion Matrix')
plt.show()

# 分类报告
report = classification_report(y_test, y_pred, target_names=iris.target_names)
print(report)