Fix params pop error (#1408)

Bumps [serialize-javascript](https://github.com/yahoo/serialize-javascript) from 6.0.0 to 6.0.2.
- [Release notes](https://github.com/yahoo/serialize-javascript/releases)
- [Commits](https://github.com/yahoo/serialize-javascript/compare/v6.0.0...v6.0.2)

---
updated-dependencies:
- dependency-name: serialize-javascript
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Li Jiang <bnujli@gmail.com>

.github/workflows/python-package.yml

@@ -85,7 +85,7 @@ jobs:
       - name: Test with pytest
         if: matrix.python-version != '3.10'
         run: |
-          pytest test
+          pytest test/
       - name: Coverage
         if: matrix.python-version == '3.10'
         run: |

flaml/automl/model.py

@@ -9,6 +9,7 @@ import os
 import shutil
 import signal
 import sys
+import threading
 import time
 import warnings
 from contextlib import contextmanager
@@ -89,21 +90,25 @@ def limit_resource(memory_limit, time_limit):
             except ValueError:
                 # According to https://bugs.python.org/issue40518, it's a mac-specific error.
                 pass
-    main_thread = False
-    if time_limit is not None:
+    alarm_set = False
+    if time_limit is not None and threading.current_thread() is threading.main_thread():
         try:
             signal.signal(signal.SIGALRM, TimeoutHandler)
             signal.alarm(int(time_limit) or 1)
-            main_thread = True
+            alarm_set = True
         except ValueError:
             pass
+
     try:
         yield
     finally:
-        if main_thread:
+        if alarm_set:
             signal.alarm(0)
         if memory_limit > 0:
-            resource.setrlimit(resource.RLIMIT_AS, (soft, hard))
+            try:
+                resource.setrlimit(resource.RLIMIT_AS, (soft, hard))
+            except ValueError:
+                pass
 
 
 class BaseEstimator:
@@ -130,7 +135,7 @@ class BaseEstimator:
         self._task = task if isinstance(task, Task) else task_factory(task, None, None)
         self.params = self.config2params(config)
         self.estimator_class = self._model = None
-        if "_estimator_type" in config:
+        if "_estimator_type" in self.params:
             self._estimator_type = self.params.pop("_estimator_type")
         else:
             self._estimator_type = "classifier" if self._task.is_classification() else "regressor"
@@ -1691,7 +1696,7 @@ class XGBoostEstimator(SKLearnEstimator):
         # use_label_encoder is deprecated in 1.7.
         if xgboost_version < "1.7.0":
             params["use_label_encoder"] = params.get("use_label_encoder", False)
-        if "n_jobs" in config:
+        if "n_jobs" in params:
             params["nthread"] = params.pop("n_jobs")
         return params
 
@@ -1891,7 +1896,7 @@ class RandomForestEstimator(SKLearnEstimator, LGBMEstimator):
         params = super().config2params(config)
         if "max_leaves" in params:
             params["max_leaf_nodes"] = params.get("max_leaf_nodes", params.pop("max_leaves"))
-        if not self._task.is_classification() and "criterion" in config:
+        if not self._task.is_classification() and "criterion" in params:
             params.pop("criterion")
         if "random_state" not in params:
             params["random_state"] = 12032022
@@ -2344,7 +2349,7 @@ class SGDEstimator(SKLearnEstimator):
         params["loss"] = params.get("loss", None)
         if params["loss"] is None and self._task.is_classification():
             params["loss"] = "log_loss" if SKLEARN_VERSION >= "1.1" else "log"
-        if not self._task.is_classification():
+        if not self._task.is_classification() and "n_jobs" in params:
             params.pop("n_jobs")
 
         if params.get("penalty") != "elasticnet":

flaml/automl/task/generic_task.py

@@ -769,10 +769,10 @@ class GenericTask(Task):
             if not is_spark_dataframe:
                 y_train, y_val = y_train_split[train_index], y_train_split[val_index]
                 if weight is not None:
-                    fit_kwargs["sample_weight"], weight_val = (
-                        weight[train_index],
-                        weight[val_index],
+                    fit_kwargs["sample_weight"] = (
+                        weight[train_index] if isinstance(weight, np.ndarray) else weight.iloc[train_index]
                     )
+                    weight_val = weight[val_index] if isinstance(weight, np.ndarray) else weight.iloc[val_index]
                 if groups is not None:
                     fit_kwargs["groups"] = (
                         groups[train_index] if isinstance(groups, np.ndarray) else groups.iloc[train_index]

flaml/tune/tune.py

@@ -197,9 +197,16 @@ def report(_metric=None, **kwargs):
     global _training_iteration
     if _use_ray:
         try:
-            from ray import tune
+            from ray import __version__ as ray_version
 
-            return tune.report(_metric, **kwargs)
+            if ray_version.startswith("1."):
+                from ray import tune
+
+                return tune.report(_metric, **kwargs)
+            else:  # ray>=2
+                from ray.air import session
+
+                return session.report(metrics={"metric": _metric, **kwargs})
         except ImportError:
             # calling tune.report() outside tune.run()
             return

flaml/version.py

@@ -1 +1 @@
-__version__ = "2.3.3"
+__version__ = "2.3.4"

test/automl/test_model.py

@@ -143,4 +143,5 @@ def test_prep():
 
 
 if __name__ == "__main__":
+    test_lrl2()
     test_prep()

test/automl/test_split.py

@@ -1,4 +1,5 @@
 import numpy as np
+import pandas as pd
 from sklearn.datasets import fetch_openml, load_iris
 from sklearn.metrics import accuracy_score
 from sklearn.model_selection import GroupKFold, KFold, train_test_split
@@ -59,8 +60,6 @@ def test_groups_for_classification_task():
 
         X, y = load_wine(return_X_y=True)
 
-    import numpy as np
-
     automl = AutoML()
     automl_settings = {
         "time_budget": 2,
@@ -118,6 +117,43 @@ def test_groups_for_regression_task():
     automl.fit(X_train, y_train, **automl_settings)
 
 
+def test_groups_with_sample_weights():
+    """Verifies that sample weights can be used with group splits i.e. that https://github.com/microsoft/FLAML/issues/1396 remains fixed"""
+    iris_dict_data = load_iris(as_frame=True)  # numpy arrays
+    iris_data = iris_dict_data["frame"]  # pandas dataframe data + target
+    iris_data["cluster"] = np.random.randint(0, 5, iris_data.shape[0])
+    automl = AutoML()
+
+    X = iris_data[["sepal length (cm)", "sepal width (cm)", "petal length (cm)"]].to_numpy()
+    y = iris_data["petal width (cm)"]
+    sample_weight = pd.Series(np.random.rand(X.shape[0]))
+    (
+        X_train,
+        X_test,
+        y_train,
+        y_test,
+        groups_train,
+        groups_test,
+        sample_weight_train,
+        sample_weight_test,
+    ) = train_test_split(X, y, iris_data["cluster"], sample_weight, random_state=42)
+    automl_settings = {
+        "max_iter": 5,
+        "time_budget": -1,
+        "metric": "r2",
+        "task": "regression",
+        "log_file_name": "error.log",
+        "log_type": "all",
+        "estimator_list": ["lgbm"],
+        "eval_method": "cv",
+        "split_type": "group",
+        "groups": groups_train,
+        "sample_weight": sample_weight_train,
+    }
+    automl.fit(X_train, y_train, **automl_settings)
+    assert automl.model is not None
+
+
 def test_stratified_groupkfold():
     from minio.error import ServerError
     from sklearn.model_selection import StratifiedGroupKFold

test/test_gpu.py

@@ -59,6 +59,17 @@ def _test_hf_data():
     except requests.exceptions.ConnectionError:
         return
 
+    # Tests will only run if there is a GPU available
+    try:
+        import ray
+
+        pg = ray.util.placement_group([{"CPU": 1, "GPU": 1}])
+
+        if not pg.wait(timeout_seconds=10):  # Wait 10 seconds for resources
+            raise RuntimeError("No available node types can fulfill resource request!")
+    except RuntimeError:
+        return
+
     custom_sent_keys = ["sentence1", "sentence2"]
     label_key = "label"
 

website/yarn.lock

@@ -7272,14 +7272,7 @@ send@0.19.0:
     range-parser "~1.2.1"
     statuses "2.0.1"
 
-serialize-javascript@^6.0.0:
-  version "6.0.0"
-  resolved "https://registry.npmmirror.com/serialize-javascript/-/serialize-javascript-6.0.0.tgz#efae5d88f45d7924141da8b5c3a7a7e663fefeb8"
-  integrity sha512-Qr3TosvguFt8ePWqsvRfrKyQXIiW+nGbYpy8XK24NQHE83caxWt+mIymTT19DGFbNWNLfEwsrkSmN64lVWB9ag==
-  dependencies:
-    randombytes "^2.1.0"
-
-serialize-javascript@^6.0.1:
+serialize-javascript@^6.0.0, serialize-javascript@^6.0.1:
   version "6.0.2"
   resolved "https://registry.yarnpkg.com/serialize-javascript/-/serialize-javascript-6.0.2.tgz#defa1e055c83bf6d59ea805d8da862254eb6a6c2"
   integrity sha512-Saa1xPByTTq2gdeFZYLLo+RFE35NHZkAbqZeWNd3BpzppeVisAqpDjcp8dyf6uIvEqJRd46jemmyA4iFIeVk8g==