example update (#359)

update some examples for consistencies with others.

test/automl/test_classification.py

@@ -2,6 +2,7 @@ import unittest
 import numpy as np
 import scipy.sparse
 from sklearn.datasets import load_breast_cancer
+from sklearn.model_selection import train_test_split
 import pandas as pd
 from datetime import datetime
 from flaml import AutoML
@@ -221,14 +222,28 @@ class TestClassification(unittest.TestCase):
         print(automl_experiment.best_estimator)
 
     def test_ray_classification(self):
-        from sklearn.datasets import make_classification
+        X, y = load_breast_cancer(return_X_y=True)
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)
 
-        X, y = make_classification(1000, 10)
         automl = AutoML()
         try:
-            automl.fit(X, y, time_budget=10, task="classification", use_ray=True)
             automl.fit(
-                X, y, time_budget=10, task="classification", n_concurrent_trials=2
+                X_train,
+                y_train,
+                X_val=X_test,
+                y_val=y_test,
+                time_budget=10,
+                task="classification",
+                use_ray=True,
+            )
+            automl.fit(
+                X_train,
+                y_train,
+                X_val=X_test,
+                y_val=y_test,
+                time_budget=10,
+                task="classification",
+                n_concurrent_trials=2,
             )
         except ImportError:
             return

test/ray/distribute_tune.py

@@ -1,30 +1,28 @@
 import ray
 import lightgbm as lgb
 import numpy as np
-import sklearn.datasets
-import sklearn.metrics
+from sklearn.datasets import load_breast_cancer
+from sklearn.metrics import accuracy_score
 from sklearn.model_selection import train_test_split
 from flaml import tune
 from flaml.model import LGBMEstimator
 
-data, target = sklearn.datasets.load_breast_cancer(return_X_y=True)
-train_x, test_x, train_y, test_y = train_test_split(data, target, test_size=0.25)
+X, y = load_breast_cancer(return_X_y=True)
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)
 
 
 def train_breast_cancer(config):
     params = LGBMEstimator(**config).params
-    train_set = lgb.Dataset(train_x, label=train_y)
+    train_set = lgb.Dataset(X_train, label=y_train)
     gbm = lgb.train(params, train_set)
-    preds = gbm.predict(test_x)
+    preds = gbm.predict(X_test)
     pred_labels = np.rint(preds)
-    tune.report(
-        mean_accuracy=sklearn.metrics.accuracy_score(test_y, pred_labels), done=True
-    )
+    tune.report(mean_accuracy=accuracy_score(y_test, pred_labels), done=True)
 
 
 if __name__ == "__main__":
     ray.init(address="auto")
-    flaml_lgbm_search_space = LGBMEstimator.search_space(train_x.shape)
+    flaml_lgbm_search_space = LGBMEstimator.search_space(X_train.shape)
     config_search_space = {
         hp: space["domain"] for hp, space in flaml_lgbm_search_space.items()
     }

test/tune_example.py

@@ -36,6 +36,14 @@ low_cost_partial_config = {
     for hp, space in flaml_lgbm_search_space.items()
     if "low_cost_init_value" in space
 }
+# initial points to evaluate
+points_to_evaluate = [
+    {
+        hp: space["init_value"]
+        for hp, space in flaml_lgbm_search_space.items()
+        if "init_value" in space
+    }
+]
 # run the tuning, minimizing mse, with total time budget 3 seconds
 analysis = tune.run(
     train_lgbm,
@@ -43,6 +51,7 @@ analysis = tune.run(
     mode="min",
     config=config_search_space,
     low_cost_partial_config=low_cost_partial_config,
+    points_to_evaluate=points_to_evaluate,
     time_budget_s=3,
     num_samples=-1,
 )