Include mlflow instructions for MM registration in example notebook

Author: smlindauer

examples/pzmmModelImportExampleMLFlow.ipynb

@@ -10,6 +10,65 @@
     "SPDX-License-Identifier: Apache-2.0"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### MLFlow Preamble"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In order to import MLFlow models into SAS Model Manager, there are a few lines that need to be included in the MLFlow script. First of all, include the infer_signature function in the import statements:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from mlflow.models.signature import infer_signature"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Next, adjust any data columns which are not valid Python variable names:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "data = pd.read_csv('data.csv')\n",
+    "data.columns = data.columns.str.replace('\\W|^(?=\\d)', '_', regex=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Include the signature inference after any paramater logging is defined and include a signature argument in the model logging:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import mlflow\n",
+    "signature = infer_signature(data, model.predict(data))\n",
+    "mlflow.sklearn.log_model(model, \"model\", signature=signature)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {