26-Nov: Fixes to Issue aws#1800 and SDKv2 corrections (aws#1801)

## Description of Changes 1- Solution to aws#1800 to call serializer in the Predictor constructor 2-SDKv2 updates incorporated (renamed RealTimePredictor, removed content_type from Predictor constructor, renamed image_name in estimator call etc.) 3-Changed inference instance type to m5.large (newer generation, less cost) ## Test Scenario Tested in SageMaker Studio (but with Sagemaker Classic Notebook option) SageMaker SDK version = 2.16.3.post0 See completed notebook here: https://github.com/CloudaYolla/fastai-study-group-DL4coders/blob/main/zoo-smaker-nb/DeepAR-Electricity-StudioNI-PA4.ipynb

Author: CloudaYolla

introduction_to_amazon_algorithms/deepar_electricity/DeepAR-Electricity.ipynb

@@ -16,11 +16,23 @@
  "* Make requests to the deployed model to obtain forecasts interactively\n",
  "* Illustrate advanced features of DeepAR: missing values, additional time features, non-regular frequencies and category information\n",
  "\n",
- "Running this notebook takes around 40 min on a ml.c4.2xlarge for the training, and inference is done on a ml.m4.xlarge (the usage time will depend on how long you leave your served model running).\n",
+ "Running this notebook takes around 40 min on a ml.c4.2xlarge for the training, and inference is done on a ml.m5.large (the usage time will depend on how long you leave your served model running).\n",
+ "\n",
+ "This notebook is tested using SageMaker Studio but using classic Notebook (From the SageMaker Menu, go to Help -> select `Launch Classic Notebook`). \n",
  "\n",
  "For more information see the DeepAR [documentation](https://docs.aws.amazon.com/sagemaker/latest/dg/deepar.html) or [paper](https://arxiv.org/abs/1704.04110), "
  ]
  },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import sys\n",
+ "!{sys.executable} -m pip install s3fs"
+ ]
+ },
  {
  "cell_type": "code",
  "execution_count": null,
@@ -116,7 +128,9 @@
  {
  "cell_type": "code",
  "execution_count": null,
- "metadata": {},
+ "metadata": {
+ "scrolled": false
+ },
  "outputs": [],
  "source": [
  "image_name = sagemaker.amazon.amazon_estimator.get_image_uri(region, \"forecasting-deepar\", \"latest\")"
@@ -424,8 +438,8 @@
  "outputs": [],
  "source": [
  "estimator = sagemaker.estimator.Estimator(\n",
+ " image_uri=image_name,\n",
  " sagemaker_session=sagemaker_session,\n",
- " image_name=image_name,\n",
  " role=role,\n",
  " train_instance_count=1,\n",
  " train_instance_type='ml.c4.2xlarge',\n",
@@ -530,10 +544,22 @@
  "metadata": {},
  "outputs": [],
  "source": [
- "class DeepARPredictor(sagemaker.predictor.RealTimePredictor):\n",
+ "from sagemaker.serializers import IdentitySerializer"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class DeepARPredictor(sagemaker.predictor.Predictor):\n",
  " \n",
  " def __init__(self, *args, **kwargs):\n",
- " super().__init__(*args, content_type=sagemaker.content_types.CONTENT_TYPE_JSON, **kwargs)\n",
+ " super().__init__(*args, \n",
+ " #serializer=JSONSerializer(),\n",
+ " serializer=IdentitySerializer(content_type=\"application/json\"),\n",
+ " **kwargs)\n",
  " \n",
  " def predict(self, ts, cat=None, dynamic_feat=None, \n",
  " num_samples=100, return_samples=False, quantiles=[\"0.1\", \"0.5\", \"0.9\"]):\n",
@@ -556,7 +582,7 @@
  " \n",
  " def __encode_request(self, ts, cat, dynamic_feat, num_samples, return_samples, quantiles):\n",
  " instance = series_to_dict(ts, cat if cat is not None else None, dynamic_feat if dynamic_feat else None)\n",
- "\n",
+ " \n",
  " configuration = {\n",
  " \"num_samples\": num_samples,\n",
  " \"output_types\": [\"quantiles\", \"samples\"] if return_samples else [\"quantiles\"],\n",
@@ -619,7 +645,7 @@
  "source": [
  "predictor = estimator.deploy(\n",
  " initial_instance_count=1,\n",
- " instance_type='ml.m4.xlarge',\n",
+ " instance_type='ml.m5.large',\n",
  " predictor_cls=DeepARPredictor)"
  ]
  },
@@ -984,8 +1010,8 @@
  "source": [
  "%%time\n",
  "estimator_new_features = sagemaker.estimator.Estimator(\n",
+ " image_uri=image_name,\n",
  " sagemaker_session=sagemaker_session,\n",
- " image_name=image_name,\n",
  " role=role,\n",
  " train_instance_count=1,\n",
  " train_instance_type='ml.c4.2xlarge',\n",
@@ -1030,7 +1056,7 @@
  "%%time\n",
  "predictor_new_features = estimator_new_features.deploy(\n",
  " initial_instance_count=1,\n",
- " instance_type='ml.m4.xlarge',\n",
+ " instance_type='ml.m5.large',\n",
  " predictor_cls=DeepARPredictor)"
  ]
  },
@@ -1115,9 +1141,9 @@
  ],
  "metadata": {
  "kernelspec": {
- "display_name": "Python 3",
+ "display_name": "Python 3 (Data Science)",
  "language": "python",
- "name": "python3"
+ "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-east-1:081325390199:image/datascience-1.0"
  },
  "language_info": {
  "codemirror_mode": {