DEPRECATION WARNING
This code example was intended for use by the legacy Skafos platform and is no longer being maintained. On 05/29/2019, a new version of Skafos was released, streamlining model delivery to the edge.
Sign-up for an account, join our Slack community, and explore some example models to get started.
The purpose of this example is to highlight the utility of Skafos, Metis Machine's data science operationalization and delivery platform. In this example, we will:
- Build and train a model predicting cell phone churn with data that is available on a public S3 bucket.
- Save this model using the Skafos data engine
- Score new customers using this model and save these scores.
- Access these scores via an API or the data engine.
Note: This tutorial walks you through the standard data science workflow in Skafos. To work through the iOS Quickstart process, go to QuickStart for iOS Developers
The figure below provides a functional architecture for this process.
- Sign up for a Skafos account. If you do not have a Skafos account, you will not be able to complete this tutorial.
- Go through the Skafos Quickstart for Datascientists tutorial to set-up your account. This will take 1-2 minutes.
- Install skafos on your machine
- Authenticate your account via the
skafos authcommand. - A working knowledge of how to use git.
The source data for this example is available in a public S3 bucket provided by Metis Machine. In the steps below, we will describe how to access it. No code modifications are required to access the input data.
This data has been slightly modified from its source, which is freely available and can be found here or here.
In the following step-by-step guide, we will walk you through how to use the code in this repository to run a job on Skafos. Following completion of this tutorial, you should be able to:
- Run the existing code and access its output using the Skafos Data Engine.
- Replace the provided data and model with your own data and model.
- Fork the churn-model-demo from Github. This code is freely available as part of the Skafos organization. Note that the README is a copy of these instructions.
- Clone the forked repo to your machine, and add an upstream remote to connect to the original repo, if desired.
Once in top level of the working directory of this project, type: skafos init on the command line. This will generate a new metis.config.yml file that is tied to your Skafos account and organization. It will look like the metis.config.yml.example file included in this repo.
Open up this config file and edit the job name and entrypoint to match metis.config.yml.example included in the repo. Specifically, the name and entrypoint should look like this:
name: build-churn-model
entrypoint: "build-churn-model.py"Note: Do not edit the project token or job_ids in the .yml file. Otherwise, Skafos will not recognize and run your job.
In metis.config.yml.example, you'll note that there are two jobs: one to build a model, and one to score new users. You will need to add a second job to your Skafos project via the following command on the command line:
skafos create job score-new-users
This will output a job_id on the command line. Copy this job id to your metis.config.yml file, again using metis.config.yml.example as a template, and including the following:
language: python
name: score-new-users
entrypoint: "score-new-users.py"
dependencies: ["<job-id for build-churn-model.py>"]This dependency will ensure that new users are not scored until the churn model has been built. If build-churn-model.py does not complete, then score-new-users.py will not run. Note the quotations that are necessary around the job id on the dependencies line.
Now that your metis.config.yml file has all the necessary components, add it to the repo, commit, and push.
In Steps 3 and 4 above, you initialized a Skafos project so you can run the cloned repo in Skafos. Now, you will need to add the Skafos app to your Github repository.
To do this, navigate to the Settings page for your organization, click on Installed GitHub Apps to add the Skafos app to this repository. Alternatively, if this repo is not part of an organization, navigate to your Settings page, click on Applications, and install the Skafos app.
In order for Skafos to run your job, you will need to make a change to your code. It can be as simple as a sentence to this README.md or adding a comment in one of the Python files. Once these changes are pushed to github, the Skafos app will pick them up and run both the training and scoring jobs.
Navigate to dashboard.metismachine.io to monitor the status of the job you just pushed. Additional documentation about how to use the dashboard can be found here.
Once your job has completed, you can verify that the predictive model itself (in the form of a .pkl file) was written to Cassandra. This can be viewed in the job logs in the dashboard.
In addition to data that has been output to S3, this code uses the Skafos SDK to store scored users in a Cassandra database. Specifically, the save_scores function, will write scored users to a table.
The scored users in Cassandra can be easily accessed via an API call. Navigating to the root project directory on the command line, type skafos fetch --table model_scores. This will return both a list of scores and a cURL command that can be incorporated into applications in the usual fashion to retrieve this data.
Now that you have successfully built a predictive model on Skafos and scored new data, you can adapt this code to build your own models. An example build-churn-model.ipynb has been added to the code repository for this example as a starting point for experimentation and testing.