From c6f12e258982d7af56dbb303a008a368d6cddd51 Mon Sep 17 00:00:00 2001
From: atqy <95724753+atqy@users.noreply.github.com>
Date: Thu, 18 Aug 2022 10:29:41 -0700
Subject: [PATCH 1/4] delete r_examples/r_api_serving_examples (#3564)

---
 .../API Serving Examples.ipynb                | 610 ------------------
 r_examples/r_api_serving_examples/iris.csv    | 151 -----
 r_examples/r_api_serving_examples/launch.sh   |  11 -
 3 files changed, 772 deletions(-)
 delete mode 100644 r_examples/r_api_serving_examples/API Serving Examples.ipynb
 delete mode 100644 r_examples/r_api_serving_examples/iris.csv
 delete mode 100644 r_examples/r_api_serving_examples/launch.sh

diff --git a/r_examples/r_api_serving_examples/API Serving Examples.ipynb b/r_examples/r_api_serving_examples/API Serving Examples.ipynb
deleted file mode 100644
index cb85c5bac6..0000000000
--- a/r_examples/r_api_serving_examples/API Serving Examples.ipynb	
+++ /dev/null
@@ -1,610 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# R API Serving Examples\n",
-    "\n",
-    "In this example, we demonstrate how to quickly compare the runtimes of three methods for serving a model from an R hosted REST API. The following SageMaker examples discuss each method in detail:\n",
-    "\n",
-    "* **Plumber**\n",
-    " * Website: [https://www.rplumber.io/](https://www.rplumber.io)\n",
-    " * SageMaker Example: [r_serving_with_plumber](../r_serving_with_plumber)\n",
-    "* **RestRServe**\n",
-    " * Website: [https://restrserve.org](https://restrserve.org)\n",
-    " * SageMaker Example: [r_serving_with_restrserve](../r_serving_with_restrserve)\n",
-    "* **FastAPI** (reticulated from Python)\n",
-    " * Website: [https://fastapi.tiangolo.com](https://fastapi.tiangolo.com)\n",
-    " * SageMaker Example: [r_serving_with_fastapi](../r_serving_with_fastapi)\n",
-    " \n",
-    "We will reuse the docker images from each of these examples. Each one is configured to serve a small XGBoost model which has already been trained on the classical Iris dataset."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Building Docker Images for Serving\n",
-    "\n",
-    "First, we will build each docker image from the provided SageMaker Examples."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Plumber Serving Image"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "!cd .. && docker build -t r-plumber -f r_serving_with_plumber/Dockerfile r_serving_with_plumber"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### RestRServe Serving Image"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "!cd .. && docker build -t r-restrserve -f r_serving_with_restrserve/Dockerfile r_serving_with_restrserve"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### FastAPI Serving Image"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "!cd .. && docker build -t r-fastapi -f r_serving_with_fastapi/Dockerfile r_serving_with_fastapi"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Launch Serving Containers"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Next, we will launch each search container. The containers will be launch on the following ports to avoid port collisions on your local machine or SageMaker Notebook instance:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "ports = {\n",
-    "    \"plumber\": 5000,\n",
-    "    \"restrserve\": 5001,\n",
-    "    \"fastapi\": 5002,\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!bash launch.sh"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!docker container list"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Define Simple Client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import requests\n",
-    "from tqdm import tqdm\n",
-    "import pandas as pd"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def get_predictions(examples, instance=requests, port=5000):\n",
-    "    payload = {\"features\": examples}\n",
-    "    return instance.post(f\"http://127.0.0.1:{port}/invocations\", json=payload)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def get_health(instance=requests, port=5000):\n",
-    "    instance.get(f\"http://127.0.0.1:{port}/ping\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Define Example Inputs"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Next, we define a example inputs from the classical [Iris](https://archive.ics.uci.edu/ml/datasets/iris) dataset.\n",
-    "* Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "column_names = [\"Sepal.Length\", \"Sepal.Width\", \"Petal.Length\", \"Petal.Width\", \"Label\"]\n",
-    "iris = pd.read_csv(\n",
-    "    \"s3://sagemaker-sample-files/datasets/tabular/iris/iris.data\", names=column_names\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "iris_features = iris[[\"Sepal.Length\", \"Sepal.Width\", \"Petal.Length\", \"Petal.Width\"]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "example = iris_features.values[:1].tolist()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "many_examples = iris_features.values[:100].tolist()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Testing\n",
-    "\n",
-    "Now it's time to test how each API server performs under stress."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We will test two use cases:\n",
-    "* **New Requests**: In this scenario, we test how quickly the server can respond with predictions when each client request establishes a new connection with the server. This simulates the server's ability to handle real-time requests. We could make this more realistic by creating an asynchronous environment that tests the server's ability to fulfill concurrent rather than sequential requests.\n",
-    "* **Keep Alive / Reuse Session**: In this scenario, we test how quickly the server can respond with predictions when each client request uses a session to keep its connection to the server alive between requests. This simulates the server's ability to handle sequential batch requests from the same client."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "For each of the two use cases, we will test the performance on following situations:\n",
-    "\n",
-    "* 1000 requests of a single example\n",
-    "* 1000 requests of 100 examples\n",
-    "* 1000 pings for health status"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## New Requests"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Plumber"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# verify the prediction output\n",
-    "get_predictions(example, port=ports[\"plumber\"]).json()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(example, port=ports[\"plumber\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(many_examples, port=ports[\"plumber\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    get_health(port=ports[\"plumber\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### RestRserve"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# verify the prediction output\n",
-    "get_predictions(example, port=ports[\"restrserve\"]).json()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(example, port=ports[\"restrserve\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(many_examples, port=ports[\"restrserve\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    get_health(port=ports[\"restrserve\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### FastAPI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# verify the prediction output\n",
-    "get_predictions(example, port=ports[\"fastapi\"]).json()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(example, port=ports[\"fastapi\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(many_examples, port=ports[\"fastapi\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    get_health(port=ports[\"fastapi\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Keep Alive (Reuse Session)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now, let's test how each one performs when each request reuses a session connection. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# reuse the session for each post and get request\n",
-    "instance = requests.Session()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Plumber"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(example, instance=instance, port=ports[\"plumber\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(many_examples, instance=instance, port=ports[\"plumber\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    get_health(instance=instance, port=ports[\"plumber\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### RestRserve"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(example, instance=instance, port=ports[\"restrserve\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(many_examples, instance=instance, port=ports[\"restrserve\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    get_health(instance=instance, port=ports[\"restrserve\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### FastAPI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(example, instance=instance, port=ports[\"fastapi\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    _ = get_predictions(many_examples, instance=instance, port=ports[\"fastapi\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in tqdm(range(1000)):\n",
-    "    get_health(instance=instance, port=ports[\"fastapi\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Stop All Serving Containers"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Finally, we will shut down the serving containers we launched for the tests."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!docker kill $(docker ps -q)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Conclusion"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In this example, we demonstrated how to conduct a simple performance benchmark across three R model serving solutions. We leave the choice of serving solution up to the reader since in some cases it might be appropriate to customize the benchmark in the following ways:\n",
-    "\n",
-    "* Update the serving example to serve a specific model\n",
-    "* Perform the tests across multiple instances types\n",
-    "* Modify the serving example and client to test asynchronous requests.\n",
-    "* Deploy the serving examples to SageMaker Endpoints to test within an autoscaling environment.\n",
-    "\n",
-    "For more information on serving your models in custom containers on SageMaker, please see our [support documentation](https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-main.html) for the latest updates and best practices."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "conda_python3",
-   "language": "python",
-   "name": "conda_python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.6.13"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
diff --git a/r_examples/r_api_serving_examples/iris.csv b/r_examples/r_api_serving_examples/iris.csv
deleted file mode 100644
index 8b6393099a..0000000000
--- a/r_examples/r_api_serving_examples/iris.csv
+++ /dev/null
@@ -1,151 +0,0 @@
-Sepal.Length,Sepal.Width,Petal.Length,Petal.Width,Species
-5.1,3.5,1.4,0.2,setosa
-4.9,3,1.4,0.2,setosa
-4.7,3.2,1.3,0.2,setosa
-4.6,3.1,1.5,0.2,setosa
-5,3.6,1.4,0.2,setosa
-5.4,3.9,1.7,0.4,setosa
-4.6,3.4,1.4,0.3,setosa
-5,3.4,1.5,0.2,setosa
-4.4,2.9,1.4,0.2,setosa
-4.9,3.1,1.5,0.1,setosa
-5.4,3.7,1.5,0.2,setosa
-4.8,3.4,1.6,0.2,setosa
-4.8,3,1.4,0.1,setosa
-4.3,3,1.1,0.1,setosa
-5.8,4,1.2,0.2,setosa
-5.7,4.4,1.5,0.4,setosa
-5.4,3.9,1.3,0.4,setosa
-5.1,3.5,1.4,0.3,setosa
-5.7,3.8,1.7,0.3,setosa
-5.1,3.8,1.5,0.3,setosa
-5.4,3.4,1.7,0.2,setosa
-5.1,3.7,1.5,0.4,setosa
-4.6,3.6,1,0.2,setosa
-5.1,3.3,1.7,0.5,setosa
-4.8,3.4,1.9,0.2,setosa
-5,3,1.6,0.2,setosa
-5,3.4,1.6,0.4,setosa
-5.2,3.5,1.5,0.2,setosa
-5.2,3.4,1.4,0.2,setosa
-4.7,3.2,1.6,0.2,setosa
-4.8,3.1,1.6,0.2,setosa
-5.4,3.4,1.5,0.4,setosa
-5.2,4.1,1.5,0.1,setosa
-5.5,4.2,1.4,0.2,setosa
-4.9,3.1,1.5,0.2,setosa
-5,3.2,1.2,0.2,setosa
-5.5,3.5,1.3,0.2,setosa
-4.9,3.6,1.4,0.1,setosa
-4.4,3,1.3,0.2,setosa
-5.1,3.4,1.5,0.2,setosa
-5,3.5,1.3,0.3,setosa
-4.5,2.3,1.3,0.3,setosa
-4.4,3.2,1.3,0.2,setosa
-5,3.5,1.6,0.6,setosa
-5.1,3.8,1.9,0.4,setosa
-4.8,3,1.4,0.3,setosa
-5.1,3.8,1.6,0.2,setosa
-4.6,3.2,1.4,0.2,setosa
-5.3,3.7,1.5,0.2,setosa
-5,3.3,1.4,0.2,setosa
-7,3.2,4.7,1.4,versicolor
-6.4,3.2,4.5,1.5,versicolor
-6.9,3.1,4.9,1.5,versicolor
-5.5,2.3,4,1.3,versicolor
-6.5,2.8,4.6,1.5,versicolor
-5.7,2.8,4.5,1.3,versicolor
-6.3,3.3,4.7,1.6,versicolor
-4.9,2.4,3.3,1,versicolor
-6.6,2.9,4.6,1.3,versicolor
-5.2,2.7,3.9,1.4,versicolor
-5,2,3.5,1,versicolor
-5.9,3,4.2,1.5,versicolor
-6,2.2,4,1,versicolor
-6.1,2.9,4.7,1.4,versicolor
-5.6,2.9,3.6,1.3,versicolor
-6.7,3.1,4.4,1.4,versicolor
-5.6,3,4.5,1.5,versicolor
-5.8,2.7,4.1,1,versicolor
-6.2,2.2,4.5,1.5,versicolor
-5.6,2.5,3.9,1.1,versicolor
-5.9,3.2,4.8,1.8,versicolor
-6.1,2.8,4,1.3,versicolor
-6.3,2.5,4.9,1.5,versicolor
-6.1,2.8,4.7,1.2,versicolor
-6.4,2.9,4.3,1.3,versicolor
-6.6,3,4.4,1.4,versicolor
-6.8,2.8,4.8,1.4,versicolor
-6.7,3,5,1.7,versicolor
-6,2.9,4.5,1.5,versicolor
-5.7,2.6,3.5,1,versicolor
-5.5,2.4,3.8,1.1,versicolor
-5.5,2.4,3.7,1,versicolor
-5.8,2.7,3.9,1.2,versicolor
-6,2.7,5.1,1.6,versicolor
-5.4,3,4.5,1.5,versicolor
-6,3.4,4.5,1.6,versicolor
-6.7,3.1,4.7,1.5,versicolor
-6.3,2.3,4.4,1.3,versicolor
-5.6,3,4.1,1.3,versicolor
-5.5,2.5,4,1.3,versicolor
-5.5,2.6,4.4,1.2,versicolor
-6.1,3,4.6,1.4,versicolor
-5.8,2.6,4,1.2,versicolor
-5,2.3,3.3,1,versicolor
-5.6,2.7,4.2,1.3,versicolor
-5.7,3,4.2,1.2,versicolor
-5.7,2.9,4.2,1.3,versicolor
-6.2,2.9,4.3,1.3,versicolor
-5.1,2.5,3,1.1,versicolor
-5.7,2.8,4.1,1.3,versicolor
-6.3,3.3,6,2.5,virginica
-5.8,2.7,5.1,1.9,virginica
-7.1,3,5.9,2.1,virginica
-6.3,2.9,5.6,1.8,virginica
-6.5,3,5.8,2.2,virginica
-7.6,3,6.6,2.1,virginica
-4.9,2.5,4.5,1.7,virginica
-7.3,2.9,6.3,1.8,virginica
-6.7,2.5,5.8,1.8,virginica
-7.2,3.6,6.1,2.5,virginica
-6.5,3.2,5.1,2,virginica
-6.4,2.7,5.3,1.9,virginica
-6.8,3,5.5,2.1,virginica
-5.7,2.5,5,2,virginica
-5.8,2.8,5.1,2.4,virginica
-6.4,3.2,5.3,2.3,virginica
-6.5,3,5.5,1.8,virginica
-7.7,3.8,6.7,2.2,virginica
-7.7,2.6,6.9,2.3,virginica
-6,2.2,5,1.5,virginica
-6.9,3.2,5.7,2.3,virginica
-5.6,2.8,4.9,2,virginica
-7.7,2.8,6.7,2,virginica
-6.3,2.7,4.9,1.8,virginica
-6.7,3.3,5.7,2.1,virginica
-7.2,3.2,6,1.8,virginica
-6.2,2.8,4.8,1.8,virginica
-6.1,3,4.9,1.8,virginica
-6.4,2.8,5.6,2.1,virginica
-7.2,3,5.8,1.6,virginica
-7.4,2.8,6.1,1.9,virginica
-7.9,3.8,6.4,2,virginica
-6.4,2.8,5.6,2.2,virginica
-6.3,2.8,5.1,1.5,virginica
-6.1,2.6,5.6,1.4,virginica
-7.7,3,6.1,2.3,virginica
-6.3,3.4,5.6,2.4,virginica
-6.4,3.1,5.5,1.8,virginica
-6,3,4.8,1.8,virginica
-6.9,3.1,5.4,2.1,virginica
-6.7,3.1,5.6,2.4,virginica
-6.9,3.1,5.1,2.3,virginica
-5.8,2.7,5.1,1.9,virginica
-6.8,3.2,5.9,2.3,virginica
-6.7,3.3,5.7,2.5,virginica
-6.7,3,5.2,2.3,virginica
-6.3,2.5,5,1.9,virginica
-6.5,3,5.2,2,virginica
-6.2,3.4,5.4,2.3,virginica
-5.9,3,5.1,1.8,virginica
diff --git a/r_examples/r_api_serving_examples/launch.sh b/r_examples/r_api_serving_examples/launch.sh
deleted file mode 100644
index e456602d35..0000000000
--- a/r_examples/r_api_serving_examples/launch.sh
+++ /dev/null
@@ -1,11 +0,0 @@
-#!/bin/bash
-
-echo "Launching Plumber"
-docker run -d --rm -p 5000:8080 r-plumber 
-
-echo "Launching RestRServer"
-docker run -d  --rm -p 5001:8080 r-restrserve 
-
-echo "Launching FastAPI"
-docker run -d  --rm -p 5002:8080 r-fastapi 
-

From d027120df4b23186a57eab2f355a2b20b32d4dfe Mon Sep 17 00:00:00 2001
From: atqy <95724753+atqy@users.noreply.github.com>
Date: Thu, 18 Aug 2022 10:29:53 -0700
Subject: [PATCH 2/4] delete paddlepaddle_sentiment_analysis_byo_mms (#3565)

---
 ...r Apache MXNet's (MMS) BYO container.ipynb | 539 ------------------
 1 file changed, 539 deletions(-)
 delete mode 100644 sagemaker-python-sdk/paddlepaddle_sentiment_analysis_byo_mms/Bring Your Own DL Framework to Amazon Sagemaker with Model Server for Apache MXNet's (MMS) BYO container.ipynb

diff --git a/sagemaker-python-sdk/paddlepaddle_sentiment_analysis_byo_mms/Bring Your Own DL Framework to Amazon Sagemaker with Model Server for Apache MXNet's (MMS) BYO container.ipynb b/sagemaker-python-sdk/paddlepaddle_sentiment_analysis_byo_mms/Bring Your Own DL Framework to Amazon Sagemaker with Model Server for Apache MXNet's (MMS) BYO container.ipynb
deleted file mode 100644
index ab9f3d330b..0000000000
--- a/sagemaker-python-sdk/paddlepaddle_sentiment_analysis_byo_mms/Bring Your Own DL Framework to Amazon Sagemaker with Model Server for Apache MXNet's (MMS) BYO container.ipynb	
+++ /dev/null
@@ -1,539 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {
-    "image.png": {
-     "image/png": "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"
-    }
-   },
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Introduction\n",
-    "\n",
-    "Deep Learning frameworks enable Machine Learning (ML) practitioners to build and train ML models. However, the process of deploying ML models in production to serve predictions (also known as inferences) in real time is more complex. It requires that ML practitioners build a scalable and performant model server, which can host these models and handle inference requests at scale. Model Server for Apache MXNet (MMS), was developed to address this hurdle. MMS is a highly scalable, production ready inference server. MMS was designed in a ML/DL framework agnostic way to host models trained in any ML/DL framework.\n",
-    "\n",
-    "In this blog post, we will showcase how anyone could use Model Server for Apache MXNet (MMS) to host their model trained using any Machine Learning/Deep Learning (ML/DL) framework or tool kit in production. We chose Amazon Sagemaker service for production hosting - this PaaS solution does a lot of heavy lifting to provide infrastructure and allows users to focus on their use cases. We will be using 'Bring your own Inference code with Amazon Sagemaker hosting'  approach, where users could bring their models together with all necessary dependencies, libraries, frameworks and other components compiled inside of a single custom-built docker container and host it on Sagemaker. \n",
-    "\n",
-    "To showcase the true 'ML/DL framework agnostic architecture' of MMS, we chose to launch a model trained with 'PaddlePaddle' framework into production.\n",
-    "\n",
-    "The overall picture of steps involved to take a model trained on any ML/DL framework to Amazon Sagemaker using MMS BYO container looks as follows:\n",
-    "\n",
-    "![image.png](attachment:image.png)\n",
-    "\n",
-    "As shown in the picture above, in order to bring your own ML/DL framework to Amazon Sagemaker using MMS Bring Your Own (BYO) container, we need two main components\n",
-    "\n",
-    "1. **Model artifacts/Model Archive**: These are all the artifacts required to run your model on a given host. This contains the following:\n",
-    "  1. **Model files**, which are usually symbols and weights. These are the artifacts of training a model.\n",
-    "  2. **Custom Service File**: This file contains the entry-point which gets called every time when inference request is received and served by MMS. This file generally contains the logic to initialize the model in a particular ML/DL framework, preprocess the incoming request, run inference in a particular ML/DL framework and post-process logic which takes the data coming out of framework's inference method and converts it to end-user consumable data.\n",
-    "  3. **MANIFEST File**: This is the interface between custom service file and the MMS. This file is generated by running a tool that comes as part of MMS distribution, called 'model-archiver'.\n",
-    "2. **Container artifact**: To load and run a model written in a custom DL framework on Sagemaker, you need to bring a container that will be run on Sagemaker service. In this document we will show how to use MMS base container and extend it to support custom DL frameworks and other model dependencies. The MMS base container is a docker container that comes with a highly scalable and performant model-server which is readily launchable onto Sagemaker service.\n",
-    "In the following sections, we will see each of the above components in detail.\n",
-    "\n",
-    "## Preparing a Model\n",
-    "MMS container is completely ML/DL framework agnostic. Users can write models in a ML/DL framework of their choice and bring it to Sagemaker with MMS BYO container to get the features of scalability and performance. In this blogpost, we chose to showcase this by bringing in a model written for PaddlePaddle framework. Lets look at how to prepare a PaddlePaddle model in the following sections. The model artifact is readily available at <*TODO: Update this with the S3 link with model.tar.gz*>.\n",
-    "\n",
-    "### Preparing Model Artifacts\n",
-    "We are going to use [Understand Sentiment](https://github.com/PaddlePaddle/book/tree/develop/06.understand_sentiment) example that is available and published in examples section of PaddlePaddle repository. First of all we need to create a model. In order to do that we followed instructions provided in [PaddlePaddle/book](https://github.com/PaddlePaddle/book) repository: downloaded  container and ran training by the notebook that is provided as part of the example. We used 'Stacked Bidirectional LSTM' network for our training and trained the model for 100 epochs. At the end of this training exercise, we get the following list of trained model artifacts.\n",
-    "\n",
-    "```bash\n",
-    "!ls\n",
-    "embedding_0.w_0    fc_2.w_0    fc_5.w_0    learning_rate_0    lstm_3.b_0    moment_10    moment_18    moment_25    moment_32    moment_8\n",
-    "embedding_1.w_0    fc_2.w_1    fc_5.w_1    learning_rate_1    lstm_3.w_0    moment_11    moment_19    moment_26    moment_33    moment_9\n",
-    "fc_0.b_0    fc_3.b_0    fc_6.b_0    lstm_0.b_0    lstm_4.b_0    moment_12    moment_2    moment_27    moment_34\n",
-    "fc_0.w_0    fc_3.w_0    fc_6.w_0    lstm_0.w_0    lstm_4.w_0    moment_13    moment_20    moment_28    moment_35\n",
-    "fc_1.b_0    fc_3.w_1    fc_6.w_1    lstm_1.b_0    lstm_5.b_0    moment_14    moment_21    moment_29    moment_4\n",
-    "fc_1.w_0    fc_4.b_0    fc_7.b_0    lstm_1.w_0    lstm_5.w_0    moment_15    moment_22    moment_3    moment_5\n",
-    "fc_1.w_1    fc_4.w_0    fc_7.w_0    lstm_2.b_0    moment_0    moment_16    moment_23    moment_30    moment_6\n",
-    "fc_2.b_0    fc_5.b_0    fc_7.w_1    lstm_2.w_0    moment_1    moment_17    moment_24    moment_31    moment_7\n",
-    "```\n",
-    "\n",
-    "These artifacts constitute a PaddlePaddle model. We copy these artifacts from within training container to localhost so that it will be easier to begin preparation of the model for production hosting. To learn more on how to copy files from inside a docker container to location outside of it please refer to [Docker CLI](https://docs.docker.com/engine/reference/commandline/cp/).\n",
-    "\n",
-    "### Writing Custom Service Code\n",
-    "We now have model files required to host the model in production. We can now define a custom service file which knows how to use these files and also knows how to 'preprocess' the raw request coming into the server and how to 'postprocess' the responses coming out of the PaddlePaddle framework's 'infer' method. For this, we modified the notebook example written to test the trained model *<TODO: supply link to what was the source of the example notebook>*. Let's look at some code. \n",
-    "\n",
-    "We created a custom service file called 'paddle_sentiment_analysis.py'. Here, we first define a class called 'PaddleSentimentAnalysis' which contains methods to initialize the model and also defines pre-processing, post-processing and inference methods. Refer [Custom Service Code](https://github.com/awslabs/mxnet-model-server/blob/master/docs/custom_service.md) document to learn how to write your custom-service code. The skeleton of this file is as follows:\n",
-    "\n",
-    "```bash\n",
-    "$ cat paddle_sentiment_analysis.py\n",
-    "```\n",
-    "```python\n",
-    "\n",
-    "from __future__ import print_function\n",
-    "import paddle\n",
-    "import paddle.fluid as fluid\n",
-    "import paddle.dataset as dataset\n",
-    "from functools import partial\n",
-    "\n",
-    "  \n",
-    "class PaddleSentimentAnalysis(object):\n",
-    "    def __init__(self):\n",
-    "    ...\n",
-    "\n",
-    "    def initialize(self, context):\n",
-    "    \"\"\"\n",
-    "    This method is used to initialize the network and read other artifacts.\n",
-    "    \"\"\"\n",
-    "    ...\n",
-    "    \n",
-    "    def preprocess(self, data):\n",
-    "    \"\"\"\n",
-    "    This method is used to convert the string requests coming from client \n",
-    "    into tensors. \n",
-    "    \"\"\"\n",
-    "    ...\n",
-    "\n",
-    "    def inference(self, input):\n",
-    "    \"\"\"\n",
-    "    This method runs the tensors created in preprocess method through the \n",
-    "    DL framework's infer method.\n",
-    "    \"\"\"\n",
-    "    ...\n",
-    "\n",
-    "    def postprocess(self, output, data):\n",
-    "    \"\"\"\n",
-    "    Here the values returned from the inference method is converted to a \n",
-    "    human understandable response.\n",
-    "    \"\"\"\n",
-    "    ...\n",
-    "    \n",
-    "\n",
-    "_service = PaddleSentimentAnalysis()\n",
-    "\n",
-    "\n",
-    "def handle(data, context):\n",
-    "\"\"\"\n",
-    "This method is the entrypoint \\\"handler\\\" method that is used by MMS.\n",
-    "Any request coming in for this model will be sent to this method.\n",
-    "\"\"\"\n",
-    "    if not _service.initialized:\n",
-    "        _service.initialize(context)\n",
-    "\n",
-    "    if data is None:\n",
-    "        return None\n",
-    "\n",
-    "    pre = _service.preprocess(data)\n",
-    "    inf = _service.inference(pre)\n",
-    "    ret = _service.postprocess(inf, data)\n",
-    "    return ret\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Note about Permissions\n",
-    "Running this notebook requires permissions in addition to the normal **SageMakerFullAccess** permissions. This is because we'll creating new repositories in Amazon ECR. The easiest way to add these permissions is simply to add the managed policy **AmazonEC2ContainerRegistryFullAccess** to the role that you used to start your notebook instance. There's no need to restart your notebook instance when you do this, the new permissions will be available immediately."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Creating Model artifact file to be hosted on sagemaker\n",
-    "In order to load this model onto Sagemaker platform with MMS BYO container, we need to do the following:\n",
-    "\n",
-    "1. Create a MANIFEST file, which is used by MMS as a model's metadata to load and run the model.\n",
-    "2. Add the above custom-service file and the trained model-artifacts, along with the MANIFEST file, to a .tar.gz file.\n",
-    "\n",
-    "Let's use 'model-archiver' tool, to accomplish the above points. Before we use the tool to create a ''.tar.gz' artifact, we need to collect all the model artifacts, including the custom-service-file mentioned above, into a separate folder. For ease of getting started, we have uploaded all the model artifacts onto an [S3 bucket](https://s3.amazonaws.com/model-server/blog_artifacts/PaddlePaddle_blog/sentiment.tar.gz). Lets run the following commands to get this artifact onto your host:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!(curl https://s3.amazonaws.com/model-server/blog_artifacts/PaddlePaddle_blog/artifacts.tgz | tar zxvf -) 2>/dev/null"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!ls -R artifacts/sentiment"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now that we have the model artifacts, let's convert this to a model artifact that can be hosted on Sagemaker. \n",
-    "\n",
-    "### Prerequisites\n",
-    "Before we proceed with preparing a Sagemaker model-artifact and endpoint, we need the following:\n",
-    "#### Software packages and tools\n",
-    "1. pip\n",
-    "1. Docker\n",
-    "1. Model-archiver tool\n",
-    "1. Sagemaker SDK\n",
-    "1. Boto3 \n",
-    "\n",
-    "#### AWS user account with following permissions\n",
-    "We will need AWS account user with permissions to \n",
-    "1. Create roles (or access to an already existing Sagemaker role)\n",
-    "2. Create Sagemaker Endpoint\n",
-    "3. Create an ECR repository and upload a container to the repository\n",
-    "4. Create an S3 bucket and upload an artifact to S3 bucket"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We are now ready to create a sagemaker model artifact. For this, we use the \"model-archiver\" tool to create a Sagemaker model artifact. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install -U mxnet-model-server"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!model-archiver -f --model-name paddle_sentiment \\\n",
-    "--handler paddle_sentiment_analysis:handle \\\n",
-    "--model-path artifacts/sentiment --export-path . --archive-format tgz"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The above command would create an model artifact called `paddle_sentiment.tar.gz`, which we will use to host our endpoint. Let's verify if this model artifact is created."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!ls"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Next let's take a look at how to build a container with it and bring it into Sagemaker.\n",
-    "\n",
-    "### Building your own BYO container with MMS\n",
-    "\n",
-    "In this section, we build our own MMS based container which can be brought onto Sagemaker (also known as BYO Container).\n",
-    "\n",
-    "To help with this process, every released version of MMS comes with a corresponding MMS base container, hosted on [DockerHub](https://hub.docker.com/r/awsdeeplearningteam/mxnet-model-server/tags) which can be hosted on the Sagemaker platform.\n",
-    "\n",
-    "For this example, we will use container tagged *awsdeeplearningteam/mxnet-model-server:base_cpu_py3.6*. To host the model created in the above section, we need to install 'PaddlePaddle' and 'numpy' packages in the container. This can be done by creating a Dockerfile which extends from the base MMS image and installs the above python packages. Here is how its content should look like:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!cat artifacts/Dockerfile.paddle.mms"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now that we have Dockerfile that describes our BYO container let's build it:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!cd artifacts && docker build -t paddle-mms -f Dockerfile.paddle.mms ."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Creating Sagemaker endpoint with PaddlePaddle model\n",
-    "Before we go on and create a Sagemaker endpoint for our model, we need to do some preparations:\n",
-    "\n",
-    "### Upload the Sagemaker model artifact to a S3 bucket\n",
-    "Upload the model archive **sentiment.tar.gz** created above to a S3 bucket. Here we uploaded it to the S3 bucket called paddle_paddle. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import boto3, os, uuid\n",
-    "\n",
-    "s3 = boto3.resource(\"s3\")\n",
-    "s3_bucket_name = \"paddle-sentiment-model-\" + str(uuid.uuid1())\n",
-    "local_model_artifact = s3_model_artifact = \"paddle_sentiment.tar.gz\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now lets create a bucket called **paddle-sentiment-model**. Here is where we will copy the model, **paddle_sentiment.tar.gz**, that we had created above."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import sagemaker\n",
-    "from sagemaker import get_execution_role\n",
-    "import boto3\n",
-    "from botocore.exceptions import ClientError\n",
-    "import json\n",
-    "\n",
-    "sess = sagemaker.Session()\n",
-    "account = sess.boto_session.client(\"sts\").get_caller_identity()[\"Account\"]\n",
-    "region = sess.boto_session.region_name\n",
-    "\n",
-    "s3.create_bucket(Bucket=s3_bucket_name, CreateBucketConfiguration={\"LocationConstraint\": region})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "s3.meta.client.upload_file(local_model_artifact, s3_bucket_name, s3_model_artifact)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We now have **paddle_sentiment.tar.gz** on S3 in our account. Now let's look at having the container that we built on ECR, so that we can go ahead and set up our Sagemaker Endpoint."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Upload the container image to ECR\n",
-    "We had built an image called **paddle-mms** above. We need to upload this to a Amazon ECR in our account."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%%sh\n",
-    "\n",
-    "# The name of our algorithm\n",
-    "algorithm_name=paddle-mms\n",
-    "\n",
-    "account=$(aws sts get-caller-identity --query Account --output text)\n",
-    "\n",
-    "# Get the region defined in the current configuration (default to us-west-2 if none defined)\n",
-    "region=$(aws configure get region)\n",
-    "# specifically setting to us-east-1 since during the pre-release period, we support only that region.\n",
-    "region=${region:-us-east-1}\n",
-    "\n",
-    "echo \"region is \" $region\n",
-    "\n",
-    "fullname=\"${account}.dkr.ecr.${region}.amazonaws.com/${algorithm_name}:latest\"\n",
-    "\n",
-    "echo $fullname\n",
-    "# If the repository doesn't exist in ECR, create it.\n",
-    "\n",
-    "aws ecr describe-repositories --repository-names \"${algorithm_name}\" > /dev/null 2>&1\n",
-    "\n",
-    "if [ $? -ne 0 ]\n",
-    "then\n",
-    "    aws ecr create-repository --repository-name \"${algorithm_name}\" > /dev/null\n",
-    "fi\n",
-    "\n",
-    "# Get the login command from ECR and execute it directly\n",
-    "$(aws ecr get-login --region ${region} --no-include-email)\n",
-    "\n",
-    "# Build the docker image locally with the image name and then push it to ECR\n",
-    "# with the full name.\n",
-    "\n",
-    "docker tag ${algorithm_name}:latest ${fullname}\n",
-    "\n",
-    "docker push ${fullname}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This pushes the \"paddle-mms\" container to Amazon ECR in your account."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Creating Sagemaker Endpoint\n",
-    "Now that the model and container artifacts are uploaded onto S3 and ECR respectively, we can go ahead and create Sagemaker endpoint. To do that we need to complete following steps\n",
-    "\n",
-    "\n",
-    "#### Sagemaker role\n",
-    "\n",
-    "Before we go onto create an Sagemaker endpoint, we need to setup an IAM role which has **AmazonSageMakerFullAccess** and **AmazonS3FullAccess** and **AmazonEC2ContainerRegistryFullAccess** policy attached to it. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import sagemaker\n",
-    "from sagemaker import get_execution_role\n",
-    "import boto3\n",
-    "from botocore.exceptions import ClientError\n",
-    "import json\n",
-    "\n",
-    "sess = sagemaker.Session()\n",
-    "account = sess.boto_session.client(\"sts\").get_caller_identity()[\"Account\"]\n",
-    "region = sess.boto_session.region_name\n",
-    "# NOTE: If you already have a sagemaker execution role created with above attached policies, use it instead of calling get_execution_role()\n",
-    "sm_role = get_execution_role()\n",
-    "inference_image = \"{}.dkr.ecr.{}.amazonaws.com/paddle-mms:latest\".format(account, region)\n",
-    "s3_url = \"s3://{}/{}\".format(s3_bucket_name, s3_model_artifact)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We created the role required to launch our Sagemaker endpoint above. Now let's use the Sagemaker SDK to launch an endpoint."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "inf_handler = None"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from sagemaker.model import Model\n",
-    "\n",
-    "endpoint = \"PaddleSentiment\"\n",
-    "paddle_model = Model(model_data=s3_url, image=inference_image, role=sm_role)\n",
-    "try:\n",
-    "    inf_handler = paddle_model.deploy(1, \"ml.m4.xlarge\", endpoint_name=endpoint)\n",
-    "except ClientError as e:\n",
-    "    if \"ValidationException\" == e.response[\"Error\"][\"Code\"]:\n",
-    "        print('The endpoint \"{}\"already exists'.format(endpoint))\n",
-    "        pass\n",
-    "    else:\n",
-    "        raise"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This creats an sagemaker endpoint using the model artifact \"paddle_sentiment.tar.gz\".\n",
-    "\n",
-    "### Testing the endpoint\n",
-    "Let's test the endpoint. To do this, we will send a movie review to the endpoint \"paddle-sentiment\"."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from sagemaker.predictor import (\n",
-    "    json_serializer,\n",
-    "    csv_serializer,\n",
-    "    json_deserializer,\n",
-    "    RealTimePredictor,\n",
-    ")\n",
-    "\n",
-    "predictor = RealTimePredictor(endpoint=endpoint, sagemaker_session=sess)\n",
-    "\n",
-    "message = \"This is an amazing movie.\"\n",
-    "print(predictor.predict(message).decode(\"utf-8\"))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You would get a response showing that the review was positive.\n",
-    "### Delete Endpoint\n",
-    "After testing your endpoint, you could delete the endpoint you created as follows."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "sess.delete_endpoint(endpoint)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Conclusion\n",
-    "We have just shown how to build and host PaddlePaddle model on Sagemaker using MMS BYO container. This flow can be reused with minor modifications in order to build BYO containers serving inference traffic on Sagemaker endpoints with MMS for models built using many ML/DL frameworks, not just PaddlePaddle."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "conda_python3",
-   "language": "python",
-   "name": "conda_python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.6.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

From 30a7652219168bc965fa43fb574e0b22d2304cdb Mon Sep 17 00:00:00 2001
From: Julia Kroll <75504951+jkroll-aws@users.noreply.github.com>
Date: Thu, 18 Aug 2022 12:33:29 -0500
Subject: [PATCH 3/4] Fix 'JSONLines' -> 'JSON Lines' (#3558)

Co-authored-by: atqy <95724753+atqy@users.noreply.github.com>
---
 .../tensorflow-serving-tfrecord.cli.ipynb                       | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sagemaker_batch_transform/tensorflow_open-images_tfrecord/tensorflow-serving-tfrecord.cli.ipynb b/sagemaker_batch_transform/tensorflow_open-images_tfrecord/tensorflow-serving-tfrecord.cli.ipynb
index 48f7427362..678a38c58c 100644
--- a/sagemaker_batch_transform/tensorflow_open-images_tfrecord/tensorflow-serving-tfrecord.cli.ipynb
+++ b/sagemaker_batch_transform/tensorflow_open-images_tfrecord/tensorflow-serving-tfrecord.cli.ipynb
@@ -270,7 +270,7 @@
     "SPLIT_TYPE=\"TFRecord\"\n",
     "BATCH_STRATEGY=\"SingleRecord\"\n",
     "\n",
-    "# Join outputs by newline characters. This will make JSONLines output, since each output is JSON.\n",
+    "# Join outputs by newline characters. This will make JSON Lines output, since each output is JSON.\n",
     "ASSEMBLE_WITH=\"Line\"\n",
     "\n",
     "# The Data Source tells Batch to get all objects under the S3 prefix.\n",

From c68ba41a7b11d38350450c9c5ebaace5f678a82a Mon Sep 17 00:00:00 2001
From: Julia Kroll <75504951+jkroll-aws@users.noreply.github.com>
Date: Thu, 18 Aug 2022 12:33:40 -0500
Subject: [PATCH 4/4] Fix 'JSONLines' -> 'JSON Lines' (#3555)

Co-authored-by: atqy <95724753+atqy@users.noreply.github.com>
---
 .../fairness_and_explainability.ipynb                           | 2 +-
 .../fairness_and_explainability_outputs.ipynb                   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/sagemaker_processing/fairness_and_explainability/fairness_and_explainability.ipynb b/sagemaker_processing/fairness_and_explainability/fairness_and_explainability.ipynb
index 7831728e60..99fa1fe0bc 100644
--- a/sagemaker_processing/fairness_and_explainability/fairness_and_explainability.ipynb
+++ b/sagemaker_processing/fairness_and_explainability/fairness_and_explainability.ipynb
@@ -50,7 +50,7 @@
     "1. Explaining the importance of the various input features on the model's decision\n",
     "1. Accessing the reports through SageMaker Studio if you have an instance set up.\n",
     "\n",
-    "In doing so, the notebook first trains a [SageMaker XGBoost](https://docs.aws.amazon.com/sagemaker/latest/dg/xgboost.html) model using training dataset, then use SageMaker Clarify to analyze a testing dataset in CSV format. SageMaker Clarify also supports analyzing dataset in [SageMaker JSONLines dense format](https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html#common-in-formats), which is illustrated in [another notebook](https://github.com/aws/amazon-sagemaker-examples/blob/master/sagemaker_processing/fairness_and_explainability/fairness_and_explainability_jsonlines_format.ipynb)."
+    "In doing so, the notebook first trains a [SageMaker XGBoost](https://docs.aws.amazon.com/sagemaker/latest/dg/xgboost.html) model using training dataset, then use SageMaker Clarify to analyze a testing dataset in CSV format. SageMaker Clarify also supports analyzing dataset in [SageMaker JSON Lines dense format](https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html#common-in-formats), which is illustrated in [another notebook](https://github.com/aws/amazon-sagemaker-examples/blob/master/sagemaker_processing/fairness_and_explainability/fairness_and_explainability_jsonlines_format.ipynb)."
    ]
   },
   {
diff --git a/sagemaker_processing/fairness_and_explainability/fairness_and_explainability_outputs.ipynb b/sagemaker_processing/fairness_and_explainability/fairness_and_explainability_outputs.ipynb
index 289d3b8e5b..ca4cd45863 100644
--- a/sagemaker_processing/fairness_and_explainability/fairness_and_explainability_outputs.ipynb
+++ b/sagemaker_processing/fairness_and_explainability/fairness_and_explainability_outputs.ipynb
@@ -70,7 +70,7 @@
     "1. Explaining the importance of the various input features on the model's decision\n",
     "1. Accessing the reports through SageMaker Studio if you have an instance set up.\n",
     "\n",
-    "In doing so, the notebook first trains a [SageMaker XGBoost](https://docs.aws.amazon.com/sagemaker/latest/dg/xgboost.html) model using training dataset, then use SageMaker Clarify to analyze a testing dataset in CSV format. SageMaker Clarify also supports analyzing dataset in [SageMaker JSONLines dense format](https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html#common-in-formats), which is illustrated in [another notebook](https://github.com/aws/amazon-sagemaker-examples/blob/master/sagemaker_processing/fairness_and_explainability/fairness_and_explainability_jsonlines_format.ipynb)."
+    "In doing so, the notebook first trains a [SageMaker XGBoost](https://docs.aws.amazon.com/sagemaker/latest/dg/xgboost.html) model using training dataset, then use SageMaker Clarify to analyze a testing dataset in CSV format. SageMaker Clarify also supports analyzing dataset in [SageMaker JSON Lines dense format](https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html#common-in-formats), which is illustrated in [another notebook](https://github.com/aws/amazon-sagemaker-examples/blob/master/sagemaker_processing/fairness_and_explainability/fairness_and_explainability_jsonlines_format.ipynb)."
    ]
   },
   {