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
-}