Merge pull request #349 from oracle-samples/update_uploading_larger_artifact_oracle_ads

[ODSC-49121]update with the latest module

Author: qiuosier

model_catalog_examples/notebook_examples/uploading_larger_artifact_oracle_ads.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "<font color=gray>Oracle Cloud Infrastructure Data Science Sample Notebook\n",
     "\n",
-    "Copyright (c) 2021 Oracle, Inc.  All rights reserved. <br>\n",
+    "Copyright (c) 2021, 2023 Oracle, Inc.  All rights reserved. <br>\n",
     "Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl.\n",
     "</font>"
    ]
@@ -35,16 +35,7 @@
    "id": "9325ef67",
    "metadata": {},
    "source": [
-    "* We recommend that you run this notebook in a notebook session using a conda environment that has ADS version 2.3.1 installed\n",
-    "* You need access to the public internet\n",
-    "\n",
-    "***\n",
-    " \n",
-    "<font color=gray>Datasets are provided as a convenience. Datasets are considered Third Party Content and are not considered Materials under your agreement with Oracle applicable to the Services.\n",
-    " \n",
-    "The dataset `oracle_classification_dataset1` is distributed under the [UPL license](oracle_data/UPL.txt). \n",
-    "</font>\n",
-    "***"
+    "* We recommend that you run this notebook in a notebook session using a conda environment that has ADS version 2.8.10 installed"
    ]
   },
   {
@@ -54,31 +45,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import ads\n",
-    "import logging\n",
-    "import os\n",
-    "import tempfile\n",
-    "import warnings\n",
-    "\n",
-    "from ads.catalog.model import ModelCatalog\n",
-    "from ads.common.model import ADSModel\n",
-    "from ads.common.model_export_util import prepare_generic_model\n",
-    "from ads.common.model_metadata import (MetadataCustomCategory,\n",
-    "                                       UseCaseType,\n",
-    "                                       Framework)\n",
-    "from ads.dataset.factory import DatasetFactory\n",
-    "from ads.feature_engineering.schema import Expression, Schema\n",
-    "from os import path\n",
     "from sklearn.ensemble import RandomForestClassifier\n",
-    "\n",
-    "logging.basicConfig(format='%(levelname)s:%(message)s', level=logging.ERROR)\n",
-    "warnings.filterwarnings('ignore')\n",
-    "ads.set_documentation_mode(False)"
+    "from sklearn.datasets import make_classification\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import ads\n",
+    "import os"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "e49fd60d",
    "metadata": {},
    "outputs": [],
@@ -95,19 +71,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Load the dataset\n",
-    "ds_path = path.join(\"/\", \"opt\", \"notebooks\", \"ads-examples\", \"oracle_data\", \"oracle_classification_dataset1_150K.csv\")\n",
-    "\n",
-    "ds = DatasetFactory.open(ds_path, target=\"class\")\n",
-    "\n",
-    "ds\n",
-    "# Data preprocessing\n",
-    "transformed_ds = ds.auto_transform(fix_imbalance=False)\n",
-    "train, test = transformed_ds.train_test_split(test_size=0.15)\n",
-    "\n",
-    "# Build the model and convert it to an ADSModel object\n",
-    "rf_clf = RandomForestClassifier(n_estimators=10).fit(train.X.values, train.y.values)\n",
-    "rf_model = ADSModel.from_estimator(rf_clf)"
+    "seed = 42\n",
+    "# make some classification data\n",
+    "X, y = make_classification(n_samples=10000, n_features=15, n_classes=2, flip_y=0.05)\n",
+    "trainx, testx, trainy, testy = train_test_split(X, y, test_size=30, random_state=seed)\n",
+    "model = RandomForestClassifier(\n",
+    "        n_estimators=100, random_state=42\n",
+    "    )\n",
+    "# train a random forest classifier\n",
+    "model.fit(\n",
+    "        trainx,\n",
+    "        trainy,\n",
+    "    )"
    ]
   },
   {
@@ -118,11 +93,17 @@
    "outputs": [],
    "source": [
     "# Prepare the model artifacts\n",
-    "path_to_ADS_model_artifact = tempfile.mkdtemp()\n",
+    "from ads.model.framework.sklearn_model import SklearnModel\n",
+    "from ads.common.model_metadata import UseCaseType\n",
     "\n",
-    "rf_model_artifact = rf_model.prepare(path_to_ADS_model_artifact, use_case_type=UseCaseType.BINARY_CLASSIFICATION,\n",
-    "                                     force_overwrite=True, data_sample=test, data_science_env=True,\n",
-    "                                     fn_artifact_files_included=False)"
+    "sklearn_model = SklearnModel(estimator=model, artifact_dir=\"~/sklearn_artifact_dir\")\n",
+    "sklearn_model.prepare(\n",
+    "    inference_conda_env=\"generalml_p38_cpu_v1\",\n",
+    "    training_conda_env=\"generalml_p38_cpu_v1\",\n",
+    "    X_sample=trainx,\n",
+    "    y_sample=trainy,\n",
+    "    use_case_type=UseCaseType.BINARY_CLASSIFICATION,\n",
+    ")"
    ]
   },
   {
@@ -133,14 +114,14 @@
    "outputs": [],
    "source": [
     "# Saving the model artifact to the model catalog:\n",
-    "mc_model = rf_model_artifact.save(project_id=os.environ['PROJECT_OCID'],\n",
+    "mc_model = sklearn_model.save(project_id=os.environ['PROJECT_OCID'],\n",
     "                                  compartment_id=os.environ['NB_SESSION_COMPARTMENT_OCID'],\n",
     "                                  training_id=os.environ['NB_SESSION_OCID'],\n",
     "                                  display_name=\"<replace-with-your-display-name>\",\n",
     "                                  description=\"<replace-with-description>\",\n",
     "                                  ignore_pending_changes=True,\n",
-    "                                  timeout=1800,\n",
     "                                  ignore_introspection=True,\n",
+    "                                  bucket_uri=\"oci://<replace-with-your-bucket-name>\",\n",
     "                                 )\n",
     "mc_model"
    ]
@@ -156,9 +137,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python [conda env:dataexpl_p37_cpu_v2]",
+   "display_name": "ads_testing",
    "language": "python",
-   "name": "conda-env-dataexpl_p37_cpu_v2-py"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -170,7 +151,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.10"
+   "version": "3.8.18"
   }
  },
  "nbformat": 4,