Remove base estimator deprecated name

Signed-off-by: Adam Li <adam2392@gmail.com>

.github/workflows/lint.yml

@@ -7,7 +7,7 @@ on:
   - pull_request_target
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
+  group: ${{ github.workflow }}-${{ github.head_ref }}
   cancel-in-progress: true
 
 jobs:
@@ -62,7 +62,7 @@ jobs:
 
   comment:
     needs: lint
-    if: always()
+    if: ${{ !cancelled() }}
     runs-on: ubuntu-latest
 
     # We need these permissions to be able to post / update comments

README.rst

@@ -80,7 +80,7 @@ scikit-learn 1.0 and later require Python 3.7 or newer.
 scikit-learn 1.1 and later require Python 3.8 or newer.
 
 Scikit-learn plotting capabilities (i.e., functions start with ``plot_`` and
-classes end with "Display") require Matplotlib (>= |MatplotlibMinVersion|).
+classes end with ``Display``) require Matplotlib (>= |MatplotlibMinVersion|).
 For running the examples Matplotlib >= |MatplotlibMinVersion| is required.
 A few examples require scikit-image >= |Scikit-ImageMinVersion|, a few examples
 require pandas >= |PandasMinVersion|, some examples require seaborn >=

asv_benchmarks/benchmarks/datasets.py

@@ -60,9 +60,7 @@ def _20newsgroups_lowdim_dataset(n_components=100, ngrams=(1, 1), dtype=np.float
 
 @M.cache
 def _mnist_dataset(dtype=np.float32):
-    X, y = fetch_openml(
-        "mnist_784", version=1, return_X_y=True, as_frame=False, parser="pandas"
-    )
+    X, y = fetch_openml("mnist_784", version=1, return_X_y=True, as_frame=False)
     X = X.astype(dtype, copy=False)
     X = MaxAbsScaler().fit_transform(X)
 

azure-pipelines.yml

@@ -194,6 +194,7 @@ jobs:
       py38_conda_forge_openblas_ubuntu_2204:
         DISTRIB: 'conda'
         LOCK_FILE: './build_tools/azure/py38_conda_forge_openblas_ubuntu_2204_linux-64_conda.lock'
+        CHECK_WARNINGS: 'true'
         COVERAGE: 'false'
         SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '0'  # non-default seed
 

benchmarks/bench_hist_gradient_boosting_adult.py

@@ -49,7 +49,7 @@ def predict(est, data_test, target_test):
     print(f"predicted in {toc - tic:.3f}s, ROC AUC: {roc_auc:.4f}, ACC: {acc :.4f}")
 
 
-data = fetch_openml(data_id=179, as_frame=True, parser="pandas")  # adult dataset
+data = fetch_openml(data_id=179, as_frame=True)  # adult dataset
 X, y = data.data, data.target
 
 # Ordinal encode the categories to use the native support available in HGBDT

benchmarks/bench_hist_gradient_boosting_higgsboson.py

@@ -25,6 +25,7 @@
 parser.add_argument("--no-predict", action="store_true", default=False)
 parser.add_argument("--cache-loc", type=str, default="/tmp")
 parser.add_argument("--no-interactions", type=bool, default=False)
+parser.add_argument("--max-features", type=float, default=1.0)
 args = parser.parse_args()
 
 HERE = os.path.dirname(__file__)
@@ -36,6 +37,7 @@
 subsample = args.subsample
 lr = args.learning_rate
 max_bins = args.max_bins
+max_features = args.max_features
 
 
 @m.cache
@@ -104,6 +106,7 @@ def predict(est, data_test, target_test):
     random_state=0,
     verbose=1,
     interaction_cst=interaction_cst,
+    max_features=max_features,
 )
 fit(est, data_train, target_train, "sklearn")
 predict(est, data_test, target_test)

benchmarks/bench_isolation_forest.py

@@ -64,7 +64,7 @@ def print_outlier_ratio(y):
         y = dataset.target
 
     if dat == "shuttle":
-        dataset = fetch_openml("shuttle", as_frame=False, parser="pandas")
+        dataset = fetch_openml("shuttle", as_frame=False)
         X = dataset.data
         y = dataset.target.astype(np.int64)
         X, y = sh(X, y, random_state=random_state)

benchmarks/bench_lof.py

@@ -46,7 +46,7 @@
         y = dataset.target
 
     if dataset_name == "shuttle":
-        dataset = fetch_openml("shuttle", as_frame=False, parser="pandas")
+        dataset = fetch_openml("shuttle", as_frame=False)
         X = dataset.data
         y = dataset.target.astype(np.int64)
         # we remove data with label 4

benchmarks/bench_mnist.py

@@ -60,7 +60,7 @@ def load_data(dtype=np.float32, order="F"):
     ######################################################################
     # Load dataset
     print("Loading dataset...")
-    data = fetch_openml("mnist_784", as_frame=True, parser="pandas")
+    data = fetch_openml("mnist_784", as_frame=True)
     X = check_array(data["data"], dtype=dtype, order=order)
     y = data["target"]
 

benchmarks/bench_plot_randomized_svd.py

@@ -192,7 +192,7 @@ def get_data(dataset_name):
         del row
         del col
     else:
-        X = fetch_openml(dataset_name, parser="auto").data
+        X = fetch_openml(dataset_name).data
     return X
 
 

benchmarks/bench_tsne_mnist.py

@@ -36,7 +36,7 @@
 def load_data(dtype=np.float32, order="C", shuffle=True, seed=0):
     """Load the data, then cache and memmap the train/test split"""
     print("Loading dataset...")
-    data = fetch_openml("mnist_784", as_frame=True, parser="pandas")
+    data = fetch_openml("mnist_784", as_frame=True)
 
     X = check_array(data["data"], dtype=dtype, order=order)
     y = data["target"]

build_tools/azure/py38_conda_defaults_openblas_linux-64_conda.lock

@@ -56,7 +56,7 @@ https://repo.anaconda.com/pkgs/main/linux-64/libpq-12.15-hdbd6064_1.conda#218227
 https://repo.anaconda.com/pkgs/main/linux-64/libwebp-1.3.2-h11a3e52_0.conda#9e0d6c9abdd97b076c66d4cf488589ee
 https://repo.anaconda.com/pkgs/main/linux-64/openjpeg-2.4.0-h3ad879b_0.conda#86baecb47ecaa7f7ff2657a1f03b90c9
 https://repo.anaconda.com/pkgs/main/linux-64/python-3.8.18-h955ad1f_0.conda#fa35c1028f48db26df051ee75dd9422f
-https://repo.anaconda.com/pkgs/main/linux-64/certifi-2023.7.22-py38h06a4308_0.conda#59416ad8979a654bb8f5184b62d8a9e7
+https://repo.anaconda.com/pkgs/main/linux-64/certifi-2023.11.17-py38h06a4308_0.conda#3c4c381d8521859fcfde56ef2e3e5c40
 https://repo.anaconda.com/pkgs/main/noarch/cycler-0.11.0-pyhd3eb1b0_0.conda#f5e365d2cdb66d547eb8c3ab93843aab
 https://repo.anaconda.com/pkgs/main/linux-64/cython-0.29.33-py38h6a678d5_0.conda#eb105388ba8bcf5ce82cf4cd5deeb5f9
 https://repo.anaconda.com/pkgs/main/linux-64/exceptiongroup-1.0.4-py38h06a4308_0.conda#db954e73dca6076c64a1004d71b45784