lookoutequipment 0.1.5

Python SDK for Amazon Lookout for Equipment

Amazon Lookout for Equipment Python Toolbox

The Amazon Lookout for Equipment Python toolbox is an open-source library that allows data scientists and software developers to easily build, train and deploy anomaly detection models for industrial time series data using Amazon Lookout for Equipment. This library is a wrapper on top of the Lookout for Equipment boto3 API and is provided to kick start your journey with this service. Should you have any improvement suggestions or bugs to report, please file an issue against this GitHub repository.

The Amazon Lookout for Equipment Python toolbox enables you to do the following:

• Build dataset schema
• Data upload to the necessary S3 structure
• Train an anomaly detection model using Amazon Lookout for Equipment
• Build beautiful visualization for your model evaluation
• Configure and start an inference scheduler
• Manage schedulers (start, stop, delete) whenever necessary
• Visualize scheduler inferences results

Getting Started With Sample Jupyter Notebooks

The best way to quickly review how the Amazon Lookout for Equipment Python toolbox works is to review the related example notebook.

This notebook provides code and descriptions for creating and running a full project in Amazon Lookout for Equipment using the Amazon Lookout for Equipment Python toolbox.

Example Notebooks in SageMaker

In Amazon SageMaker, upload the Jupyter notebook from the examples/ folder of this repository.

1. To run this example Create a Notebook Instance in SageMaker.
2. Add an inline policy to your Amazon SageMaker role in IAM with the following JSON structure

	{
	    "Version": "2012-10-17",
	    "Statement": [
	        {
	            "Effect": "Allow",
	            "Action": [
	                "lookoutequipment:*"
	            ],
	            "Resource": "*"
	        }
	    ]
	}

3. Upload the Jupyter notebook from examples/ folder.
4. Run the notebook cells

Installing the Amazon Lookout for Equipment Python toolbox

The Amazon Lookout for Equipment Python toolbox is built to PyPI and can be installed with pip as follows:

	pip install lookoutequipment

You can install from source by cloning this repository and running a pip install command in the root directory of the repository:

	git clone https://github.com/aws-samples/amazon-lookout-for-equipment-python-sdk.git
	cd amazon-lookout-for-equipment-python-sdk
	pip install .

Supported Operating Systems

The Amazon Lookout for Equipment Python toolbox supports Unix/Linux and Mac.

Supported Python Versions

The Amazon Lookout for Equipment Python toolbox is tested on:

• Python 3.6

Overview of toolbox

The Amazon Lookout for Equipment Python toolbox provides a Python API that enables you to easily build, train and deploy anomaly detection models for industrial time series data using Amazon Lookout for Equipment, and directly in your python code and Jupyter notebooks.

Using this toolbox you can:

1. Build dataset schema
2. Data upload to the necessary S3 structure
3. Train an anomaly detection model using Amazon Lookout for Equipment
4. Build beautiful visualization for your model evaluation

5. Configure and start an inference scheduler
6. Manage schedulers (start, stop, delete) whenever necessary
7. Visualize scheduler inferences results

For a detailed API reference of the Amazon Lookout for Equipment Python toolbox, be sure to view its documentation hosted on readthedocs.

Amazon Lookout for Equipment

Amazon Lookout for Equipment uses the data from your sensors to detect abnormal equipment behavior, so you can take action before machine failures occur and avoid unplanned downtime.

AWS Permissions

As a managed service, Amazon Lookout for Equipment performs operations on your behalf on AWS hardware that is managed by Amazon Lookout for Equipment. Amazon Lookout for Equipment can perform only operations that the user permits. You can read more about which permissions are necessary in the AWS Documentation.

The Amazon Lookout for Equipment Python toolbox should not require any additional permissions aside from what is required for using boto3 However, if you are using an IAM role with a path in it, you should grant permission for iam:GetRole.

Security

See CONTRIBUTING.md for more information.

Licensing

Amazon Lookout for Equipment Python toolbox is licensed under the Apache 2.0 License. It is copyright 2021 Amazon.com, Inc. or its affiliates. All Rights Reserved. The license is available at: http://aws.amazon.com/apache2.0/.