migrate notebooks to use openml (#3121)

* migrate notebooks to use openml

* remove multiclass flag due to dropped sklearn support

* load svc dataset as dense

* nan/inf fixes in svc

Author: ethanglaser

.ci/pipeline/nightly.yml

@@ -75,7 +75,7 @@ jobs:
       pip install -r dependencies-dev
       pip install -r requirements-doc.txt
       pip install -r requirements-test.txt
-      pip install jupyter matplotlib requests
+      pip install jupyter matplotlib requests openml
     displayName: 'Install requirements'
   - script: |
       . /usr/share/miniconda/etc/profile.d/conda.sh

examples/notebooks/ElasticNet.ipynb

@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "b1b922d1",
    "metadata": {},
    "outputs": [],
@@ -19,7 +19,7 @@
     "from sklearn import metrics\n",
     "from sklearn.model_selection import train_test_split\n",
     "import warnings\n",
-    "from sklearn.datasets import fetch_openml\n",
+    "import openml\n",
     "from sklearn.preprocessing import LabelEncoder\n",
     "from IPython.display import HTML\n",
     "\n",
@@ -36,12 +36,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "00c2277b",
    "metadata": {},
    "outputs": [],
    "source": [
-    "x, y = fetch_openml(name=\"Airlines_DepDelay_10M\", return_X_y=True)"
+    "dataset = openml.datasets.get_dataset(\n",
+    "    \"Airlines_DepDelay_10M\",\n",
+    "    download_data=True,\n",
+    "    download_qualities=False,\n",
+    "    download_features_meta_data=False,\n",
+    ")\n",
+    "x, y, _, _ = dataset.get_data(\n",
+    "    dataset_format=\"dataframe\", target=dataset.default_target_attribute\n",
+    ")"
    ]
   },
   {

examples/notebooks/dbscan.ipynb

@@ -10,15 +10,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "b1b922d1",
    "metadata": {},
    "outputs": [],
    "source": [
     "from timeit import default_timer as timer\n",
     "from sklearn.model_selection import train_test_split\n",
     "from sklearn.metrics import davies_bouldin_score\n",
-    "from sklearn.datasets import fetch_openml\n",
+    "import openml\n",
     "from IPython.display import HTML\n",
     "import warnings\n",
     "\n",
@@ -35,12 +35,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "7e73dc65",
    "metadata": {},
    "outputs": [],
    "source": [
-    "x, y = fetch_openml(name=\"spoken-arabic-digit\", return_X_y=True)"
+    "dataset = openml.datasets.get_dataset(\n",
+    "    \"spoken-arabic-digit\",\n",
+    "    download_data=True,\n",
+    "    download_qualities=False,\n",
+    "    download_features_meta_data=False,\n",
+    ")\n",
+    "x, y, _, _ = dataset.get_data(\n",
+    "    dataset_format=\"dataframe\", target=dataset.default_target_attribute\n",
+    ")"
    ]
   },
   {

examples/notebooks/kmeans.ipynb

@@ -10,14 +10,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "b1b922d1",
    "metadata": {},
    "outputs": [],
    "source": [
     "from timeit import default_timer as timer\n",
     "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.datasets import fetch_openml\n",
+    "import openml\n",
     "from IPython.display import HTML\n",
     "import warnings\n",
     "\n",
@@ -34,12 +34,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "7e73dc65",
    "metadata": {},
    "outputs": [],
    "source": [
-    "x, y = fetch_openml(name=\"spoken-arabic-digit\", return_X_y=True)"
+    "dataset = openml.datasets.get_dataset(\n",
+    "    \"spoken-arabic-digit\",\n",
+    "    download_data=True,\n",
+    "    download_qualities=False,\n",
+    "    download_features_meta_data=False,\n",
+    ")\n",
+    "x, y, _, _ = dataset.get_data(\n",
+    "    dataset_format=\"dataframe\", target=dataset.default_target_attribute\n",
+    ")"
    ]
   },
   {

examples/notebooks/knn_mnist.ipynb

@@ -10,15 +10,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "23512089",
    "metadata": {},
    "outputs": [],
    "source": [
     "from timeit import default_timer as timer\n",
     "from IPython.display import HTML\n",
     "from sklearn import metrics\n",
-    "from sklearn.datasets import fetch_openml\n",
+    "import openml\n",
     "from sklearn.model_selection import train_test_split"
    ]
   },
@@ -32,12 +32,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "27b99b44",
    "metadata": {},
    "outputs": [],
    "source": [
-    "x, y = fetch_openml(name=\"mnist_784\", return_X_y=True)"
+    "dataset = openml.datasets.get_dataset(\n",
+    "    \"mnist_784\",\n",
+    "    download_data=True,\n",
+    "    download_qualities=False,\n",
+    "    download_features_meta_data=False,\n",
+    ")\n",
+    "x, y, _, _ = dataset.get_data(\n",
+    "    dataset_format=\"dataframe\", target=dataset.default_target_attribute\n",
+    ")"
    ]
   },
   {

examples/notebooks/logistictic_regression_cifar.ipynb

@@ -34,14 +34,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "27b99b44",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sklearn.datasets import fetch_openml\n",
+    "import openml\n",
     "\n",
-    "x, y = fetch_openml(name=\"CIFAR-100\", return_X_y=True)"
+    "dataset = openml.datasets.get_dataset(\n",
+    "    \"CIFAR-100\",\n",
+    "    download_data=True,\n",
+    "    download_qualities=False,\n",
+    "    download_features_meta_data=False,\n",
+    ")\n",
+    "x, y, _, _ = dataset.get_data(\n",
+    "    dataset_format=\"dataframe\", target=dataset.default_target_attribute\n",
+    ")"
    ]
   },
   {
@@ -121,28 +129,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "e9b8f06b",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Extension for Scikit-learn time: 24.82 s'"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from sklearn.linear_model import LogisticRegression\n",
     "\n",
     "params = {\n",
     "    \"C\": 0.1,\n",
     "    \"solver\": \"lbfgs\",\n",
-    "    \"multi_class\": \"multinomial\",\n",
     "    \"n_jobs\": -1,\n",
     "}\n",
     "start = timer()\n",

examples/notebooks/nusvr_medical_charges.ipynb

@@ -10,13 +10,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "27b99b44",
    "metadata": {},
    "outputs": [],
    "source": [
     "from timeit import default_timer as timer\n",
-    "from sklearn.datasets import fetch_openml\n",
+    "import openml\n",
     "from sklearn.model_selection import train_test_split\n",
     "from IPython.display import HTML\n",
     "import warnings\n",
@@ -34,12 +34,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "a9b315cc",
    "metadata": {},
    "outputs": [],
    "source": [
-    "x, y = fetch_openml(name=\"medical_charges_nominal\", return_X_y=True)"
+    "dataset = openml.datasets.get_dataset(\n",
+    "    \"medical_charges_nominal\",\n",
+    "    download_data=True,\n",
+    "    download_qualities=False,\n",
+    "    download_features_meta_data=False,\n",
+    ")\n",
+    "x, y, _, _ = dataset.get_data(\n",
+    "    dataset_format=\"dataframe\", target=dataset.default_target_attribute\n",
+    ")"
    ]
   },
   {