Preprocessing Tabular - Cache Sagemaker version and reinstall in the end (#1578)

* minor fix to persist sagemaker version

Author: paul-cb

preprocessing/tabular_data/preprocessing_tabular_data.ipynb

@@ -46,8 +46,18 @@
     "import subprocess\n",
     "import pkg_resources\n",
     "\n",
+    "def get_sagemaker_version():\n",
+    "    \"Return the version of 'sagemaker' in your kernel or -1 if 'sagemaker' is not installed\"\n",
+    "    for i in pkg_resources.working_set:\n",
+    "        if i.key == \"sagemaker\":\n",
+    "            return \"%s==%s\" % (i.key, i.version)\n",
+    "    return -1\n",
+    "\n",
+    "# Store original 'sagemaker' version\n",
+    "sagemaker_version = get_sagemaker_version()\n",
+    "\n",
     "# Install any missing dependencies\n",
-    "!{sys.executable} -m pip install -qU 'matplotlib' 'numpy' 'pandas' 'plotly' 'sagemaker>=2.0.0' 'sklearn'\n",
+    "!{sys.executable} -m pip install -qU 'plotly' 'sagemaker>=2.0.0'\n",
     "\n",
     "import numpy as np\n",
     "import pandas as pd\n",
@@ -239,12 +249,12 @@
     "%store Y_train\n",
     "%store Y_test\n",
     "%store Y_val\n",
-    "%store choosen_data_set"
+    "%store choosen_data_set\n",
+    "%store sagemaker_version"
    ]
   }
  ],
  "metadata": {
-  "instance_type": "ml.t3.medium",
   "kernelspec": {
    "display_name": "Python 3 (Data Science)",
    "language": "python",

preprocessing/tabular_data/training_model_on_tabular_data.ipynb

@@ -44,6 +44,7 @@
    "outputs": [],
    "source": [
     "import os\n",
+    "import sys\n",
     "import plotly.express as px\n",
     "import plotly.offline as pyo\n",
     "import plotly.graph_objs as go\n",
@@ -92,7 +93,8 @@
     "%store -r Y_train\n",
     "%store -r Y_test\n",
     "%store -r Y_val\n",
-    "%store -r choosen_data_set"
+    "%store -r choosen_data_set\n",
+    "%store -r sagemaker_version"
    ]
   },
   {
@@ -269,10 +271,26 @@
    "source": [
     "sagemaker.s3.S3Downloader.download(s3_uri=list_of_trained_models[-1], local_path='./')"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Below we safe guard your kernel environment by installing your original sagemaker version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not sagemaker_version is None:\n",
+    "    !{sys.executable} -m pip install -qU sagemaker_version"
+   ]
   }
  ],
  "metadata": {
-  "instance_type": "ml.t3.medium",
   "kernelspec": {
    "display_name": "Python 3 (Data Science)",
    "language": "python",