docs: update isolation forest doc (#2210)

* update isolation forest doc * formatting * update isolation forest
microsoft · Apr 18, 2024 · 786e59a · 786e59a
1 parent 4487398
commit 786e59a
Showing 1 changed file with 64 additions and 18 deletions.
diff --git a/docs/Explore Algorithms/Anomaly Detection/Quickstart - Isolation Forests.ipynb b/docs/Explore Algorithms/Anomaly Detection/Quickstart - Isolation Forests.ipynb
@@ -24,22 +24,42 @@
    "metadata": {},
    "source": [
     "## Prerequisites\n",
-    " - If you are running it on Synapse, you'll need to [create an AML workspace and set up linked Service](../../../Use%20with%20MLFlow/Overview/).\n"
+    " - If running on Synapse, you'll need to [create an AML workspace and set up linked Service](../../Use%20with%20MLFlow/Overview.md) and add the following installation cell.\n",
+    " - If running on Fabric, you need to add the following installation cell and attach the notebook to a lakehouse. On the left side of your notebook, select Add to add an existing lakehouse or create a new one."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install sqlparse raiwidgets interpret-community mlflow==2.6.0 numpy==1.22.4"
-   ],
+    "# %%configure -f\n",
+    "# {\n",
+    "#   \"name\": \"synapseml\",\n",
+    "#   \"conf\": {\n",
+    "#       \"spark.jars.packages\": \"com.microsoft.azure:synapseml_2.12:<THE_SYNAPSEML_VERSION_YOU_WANT>\",\n",
+    "#       \"spark.jars.repositories\": \"https://mmlspark.azureedge.net/maven\",\n",
+    "#       \"spark.jars.excludes\": \"org.scala-lang:scala-reflect,org.apache.spark:spark-tags_2.12,org.scalactic:scalactic_2.12,org.scalatest:scalatest_2.12,com.fasterxml.jackson.core:jackson-databind\",\n",
+    "#       \"spark.yarn.user.classpath.first\": \"true\",\n",
+    "#       \"spark.sql.parquet.enableVectorizedReader\": \"false\"\n",
+    "#   }\n",
+    "# }"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "collapsed": false,
     "pycharm": {
      "name": "#%%\n"
     }
-   }
+   },
+   "outputs": [],
+   "source": [
+    "%pip install sqlparse raiwidgets interpret-community mlflow==2.6.0 numpy==1.22.4"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -155,8 +175,14 @@
     "\n",
     "# MLFlow experiment\n",
     "artifact_path = \"isolationforest\"\n",
-    "experiment_name = f\"/Shared/isolation_forest_experiment-{str(uuid.uuid1())}/\"\n",
-    "model_name = f\"isolation-forest-model\""
+    "model_name = f\"isolation-forest-model\"\n",
+    "\n",
+    "platform = current_platform()\n",
+    "experiment_name = {\n",
+    "    \"databricks\": f\"/Shared/isolation_forest_experiment-{str(uuid.uuid1())}/\",\n",
+    "    \"synapse\": f\"isolation_forest_experiment-{str(uuid.uuid1())}\",\n",
+    "    \"synapse_internal\": f\"isolation_forest_experiment-{str(uuid.uuid1())}\",  # Fabric\n",
+    "}.get(platform, f\"isolation_forest_experiment\")"
    ]
   },
   {
@@ -365,7 +391,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-synapse-internal"
+    ]
+   },
    "outputs": [],
    "source": [
     "if running_on_synapse():\n",
@@ -374,9 +404,7 @@
     "    tracking_url = find_secret(\n",
     "        secret_name=\"aml-mlflow-tracking-url\", keyvault=\"mmlspark-build-keys\"\n",
     "    )  # check link in prerequisites for more information on mlflow tracking url\n",
-    "    mlflow.set_tracking_uri(tracking_url)\n",
-    "    experiment_name = f\"isolation_forest_experiment\"\n",
-    "    model_name = \"isolation-forest\""
+    "    mlflow.set_tracking_uri(tracking_url)"
    ]
   },
   {
@@ -393,7 +421,7 @@
    "outputs": [],
    "source": [
     "mlflow.set_experiment(experiment_name)\n",
-    "with mlflow.start_run():\n",
+    "with mlflow.start_run() as run:\n",
     "    va = VectorAssembler(inputCols=inputCols, outputCol=\"features\")\n",
     "    pipeline = Pipeline(stages=[va, isolationForest])\n",
     "    model = pipeline.fit(df_train)\n",
@@ -424,7 +452,10 @@
      "nuid": "57cda5af-b090-4b6d-ad07-530519e0300e",
      "showTitle": false,
      "title": ""
-    }
+    },
+    "tags": [
+     "hide-synapse-internal"
+    ]
    },
    "source": [
     "Load the trained Isolation Forest Model"
@@ -439,12 +470,20 @@
      "nuid": "f44b9a1f-c2fe-4b5b-a318-4d6d73370978",
      "showTitle": false,
      "title": ""
-    }
+    },
+    "tags": [
+     "hide-synapse-internal"
+    ]
    },
    "outputs": [],
    "source": [
-    "# model_version = 1\n",
-    "# model_uri = f\"models:/{model_name}/{model_version}\"\n",
+    "# if running_on_databricks():\n",
+    "#     model_version = <your_model_version>\n",
+    "#     model_uri = f\"models:/{model_name}/{model_version}\"\n",
+    "# elif running_on_synapse_internal():\n",
+    "#     model_uri = \"runs:/{run_id}/{artifact_path}\".format(\n",
+    "#         run_id=run.info.run_id, artifact_path=artifact_path\n",
+    "#     )\n",
     "# model = mlflow.spark.load_model(model_uri)"
    ]
   },
@@ -943,12 +982,16 @@
    "source": [
     "When you run the cell above, you will see the following global feature importance plot:\n",
     "\n",
-    "![](https://mmlspark.blob.core.windows.net/graphics/notebooks/global_feature_importance.jpg)"
+    "![](https://mmlspark.blob.core.windows.net/graphics/notebooks/global-feature-importance.jpg)"
    ]
   },
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-synapse-internal"
+    ]
+   },
    "source": [
     "Visualize the explanation in the ExplanationDashboard from https://github.com/microsoft/responsible-ai-widgets."
    ]
@@ -962,7 +1005,10 @@
      "nuid": "140602e6-908e-4b32-ab9c-49dd79705171",
      "showTitle": false,
      "title": ""
-    }
+    },
+    "tags": [
+     "hide-synapse-internal"
+    ]
    },
    "outputs": [],
    "source": [