gsoc: project: Adding Time-Series Forecasting Support in DFFML

[programmer290399]

Project Description

Time-Series Forecasting & Anomaly detection has paramount importance in many real-world problems like infrastructure monitoring, stock exchange, etc. Currently, DFFML has limited integration with time-series data formats and implementation of relevant models. This project aims to add basic support for commonly used datasets, models, and data pre-processing/cleaning methods for time-series data.

This project consists of four phases (Documentation & Testing is required in every phase):

1. Implementation of Common Datasets:
   • Related Issue: #1319
   • Add at least 2 datasets.
2. Implementation/Updation of Operations:
   • Related Issue: #1321
   • Add at least 2 operations.
3. Implementation of Relevant Models:
   • Related Issue: #1320
   • Add at least 3 models.
4. Add documentation and examples showing all the three previous phases in action together. You can use Jupyter notebooks, or rST with python scripts and CLI examples, for the same.

Skills

• Python
• Familiarity with Machine Learning
• Experience with various machine learning frameworks (Pytorch & TensorFlow would be a plus)

Difficulty

Beginner/Easy

Esstimated Time Required

350 hours

Related Readings

• Related readings and links have also been added in the related issues mentioned above.
• https://intel.github.io/dffml/master/examples/data_cleanup/data_cleanup.html
• https://intel.github.io/dffml/master/examples/icecream_sales.html
• https://intel.github.io/dffml/master/examples/or_covid_data_by_county.html
• https://intel.github.io/dffml/master/api/source/dataset/base.html
• https://intel.github.io/dffml/master/api/source/dataset/iris.html

Getting Started

• Read the contributing guidelines
  • https://intel.github.io/dffml/master/contributing/index.html
• Go through the quickstart
  • https://intel.github.io/dffml/master/quickstart/model.html
• Go through the model tutorials
  • https://intel.github.io/dffml/master/tutorials/models/
• Go through the model plugins
  • https://intel.github.io/dffml/master/plugins/dffml_model.html
• Go through Jupyter Notebook Examples (they also have video walkthroughs available)
  • https://intel.github.io/dffml/master/examples/notebooks/index.html
• You don't need to go through all of them. Just get a feel for running a few

Potential Mentors

• John Andersen
• Saahil Ali