Cleaning pipeline + HPO on training

01_preprocessing/data_preprocessing.ipynb

@@ -81,6 +81,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "%%time\n",
     "import sagemaker\n",
     "from sagemaker import get_execution_role\n",
     "import boto3\n",
@@ -91,7 +92,7 @@
     "role = sagemaker.get_execution_role()\n",
     "\n",
     "default_bucket = sagemaker_session.default_bucket() # or use your own custom bucket name\n",
-    "base_job_prefix = \"preprocess\" # or define your own prefix"
+    "base_job_prefix = \"cv-sagemaker-immersionday\" # or define your own prefix"
    ]
   },
   {
@@ -217,11 +218,8 @@
     "    ProcessingInput,\n",
     "    ProcessingOutput,\n",
     ")\n",
-    "import time \n",
-    "\n",
-    "timpstamp = str(time.time()).split('.')[0]\n",
     "# SKlearnProcessor for preprocessing\n",
-    "output_prefix = f'{base_job_prefix}/outputs/{timpstamp}'\n",
+    "output_prefix = f'{base_job_prefix}/outputs'\n",
     "output_s3_uri = f's3://{default_bucket}/{output_prefix}'\n",
     "\n",
     "class_selection = '13, 17, 35, 36, 47, 68, 73, 87'\n",
@@ -284,14 +282,21 @@
     "    \n",
     "    print(f\"file_name: {file['Key']}, size: {file['Size']}\")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "instance_type": "ml.t3.medium",
   "kernelspec": {
    "display_name": "Python 3 (Data Science)",
    "language": "python",
-   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:eu-west-1:470317259841:image/datascience-1.0"
+   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-east-1:081325390199:image/datascience-1.0"
   },
   "language_info": {
    "codemirror_mode": {