python-base--/tmp.py

# 导入必要的库
import pandas as pd
from catboost import CatBoostClassifier, Pool
from sklearn.model_selection import train_test_split

# 加载示例数据集
data = pd.read_csv('/Users/alvin/Downloads/mushrooms.csv')
X = pd.get_dummies(data.drop('class', axis=1))
y = data['class']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 定义CatBoost分类器并训练模型
model = CatBoostClassifier(iterations=100, depth=2, learning_rate=0.1, loss_function='Logloss')
model.fit(X_train, y_train, verbose=False)

# 评估模型性能
print('Train accuracy:', model.score(X_train, y_train))
print('Test accuracy:', model.score(X_test, y_test))

# 保存模型
model.save_model('catboost_model.bin')

# 加载模型
loaded_model = CatBoostClassifier()
loaded_model.load_model('catboost_model.bin')

# 使用模型进行预测
preds_class = loaded_model.predict(X_test)
preds_proba = loaded_model.predict_proba(X_test)

# 输出预测结果
print('Predicted classes:', preds_class)
print('Predicted probabilities:', preds_proba)