将 Ray-Tune 与 sklearn 的 RandomForestClassifier 结合使用

Question

将不同的基础和文档示例放在一起，我设法想出了这个：

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

def objective(config, reporter):
  for i in range(config['iterations']):
    model = RandomForestClassifier(random_state=0, n_jobs=-1, max_depth=None, n_estimators= int(config['n_estimators']), min_samples_split=int(config['min_samples_split']), min_samples_leaf=int(config['min_samples_leaf']))
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
    # Feed the score back to tune?
    reporter(precision=precision_score(y_test, y_pred, average='macro'))

space = {'n_estimators': (100,200),
        'min_samples_split': (2, 10),
        'min_samples_leaf': (1, 5)}

algo = BayesOptSearch(
    space,
    metric="precision",
    mode="max",
    utility_kwargs={
        "kind": "ucb",
        "kappa": 2.5,
        "xi": 0.0
    },
    verbose=3
    )

scheduler = AsyncHyperBandScheduler(metric="precision", mode="max")
config = {
    "num_samples": 1000,
    "config": {
        "iterations": 10,
    }
}
results = run(objective,
    name="my_exp",
    search_alg=algo,
    scheduler=scheduler,
    stop={"training_iteration": 400, "precision": 0.80},
    resources_per_trial={"cpu":2, "gpu":0.5},
    **config)

print(results.dataframe())
print("Best config: ", results.get_best_config(metric="precision"))

它运行，我能够在一切结束时获得最佳配置。但是，我的疑问主要在于objective 函数。我写的正确吗？没有我能找到的样本

跟进问题：

1. 配置对象中的num_samples 是什么？是从每次试验的整体训练数据中提取的样本数量吗？

Answer 1

Tune 现在有原生 sklearn 绑定：https://github.com/ray-project/tune-sklearn

你可以试一试吗？

---

要回答您最初的问题，目标函数看起来不错； num_samples 是你想尝试的超参数配置的总数。

另外，您需要从训练函数中删除 forloop：

def objective(config, reporter):
    model = RandomForestClassifier(random_state=0, n_jobs=-1, max_depth=None, n_estimators= int(config['n_estimators']), min_samples_split=int(config['min_samples_split']), min_samples_leaf=int(config['min_samples_leaf']))
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
    # Feed the score back to tune
    reporter(precision=precision_score(y_test, y_pred, average='macro'))