☆ 自动机器学习框架

★ 几种自动机器学习的框架

Tpot

import pandas as pd# X_py,y_pypython_X = ......
python_y = ......from tpot import TPOTClassifier,TPOTRegressor
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from scipy.stats import pearsonr
# 加载数据集
digits = load_digits()
X_train, X_test, y_train, y_test = train_test_split(python_X, python_y, train_size=0.75, test_size=0.25)# 定义并训练TPOT分类器
tpot = TPOTRegressor(generations=3, population_size=20, verbosity=2, random_state=42)
tpot.fit(X_train, y_train)# 在测试集上评估模型
y_pred = tpot.predict(X_test)# 输出最优模型
print(tpot.fitted_pipeline_)# 输出模型评估报告
print(tpot.evaluated_individuals_)from sklearn.metrics import mean_absolute_error
from sklearn.metrics import mean_squared_error
from sklearn.metrics import r2_scoreprint("Pearson's r:", pearsonr(y_test.reshape(-1), y_pred.reshape(-1))[0])
print("MAE:", mean_absolute_error(y_test, y_pred))
print("RMSE:", mean_squared_error(y_test, y_pred)**0.5)
print("R-squared:", r2_score(y_test, y_pred))# 保存模型
joblib.dump(tpot.fitted_pipeline_, 'tpot_best_model.pkl')# 加载模型
loaded_model = joblib.load('tpot_best_model.pkl')# 在测试集上评估加载的模型
y_pred = loaded_model.predict(X_test)

✅ 总结