microsoft / microsoft/WhatTheHack

[Proposal]: What The Hack for Data Science in Microsoft Fabric

Open
#814 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

proposal
Dominant language
C#
Stars
1.9k
Forks
886
PR merge metrics
No merged PRs in 30d

Description

Topic

Hi,

We are planning to create the what the hack for "data science in Microsoft Fabric". This hack will help customers to get an idea how any data scientist can use Microsoft fabric to build end to end data science process.
Below is the fictious use case:-
Contoso hospital has historical, anonymized heart condition data already present in their ADLS Gen 2 as part of their record-keeping solution. They want to leverage this data to create a new app that can help clinicians assess the heart failure risk of their patients, depending on a variety of factors. As an analyst at Contoso, you have been asked to use Microsoft Fabric to train a prediction model and deploy it on Realtime endpoints so that they can build an app on it which will be used by the doctors to predict the patient heart health.

Abstract/Learning Objectives
  1. Bringing data from external source to one lake.
  2. Preprocessing the data using data wrangler as well as copilot
  3. Training the model and registering the model.
  4. Generating batch/real time prediction
  5. Generating report on top of that.
Delivery Date

May 31st,2024.

Authors
juanlldc
Other

No response

Code of Conduct
  • I agree to follow this project's Code of Conduct

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start from the proposal's learning objectives and the Contoso hospital heart-risk scenario. Define the hack's end-to-end material for ingestion, preprocessing, model training and registration, batch or real-time prediction, and reporting; it is done when these objectives are covered for the stated Microsoft Fabric use case.

Written by the indexing model from the issue text.

Assessment

Domain
content, data-engineering, documentation, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.