Scribd
Upload
147 views1 page

Data Science Workflow Guide

This document presents a data science workflow canvas to help structure a data science project. It consists of 6 sections: 1) Problem Statement, 2) Outcomes/Predictions, 3) Data Acquisition, 4) Modeling, 5) Model Evaluation, and 6) Data Preparation. The sections are ordered to first define the problem and desired outcomes, then acquire and prepare the data, select and build models, and finally evaluate the models' performance. This canvas provides a framework to plan and implement a complete data science workflow from start to finish.

Uploaded by

francisco sousa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
147 views1 page

Data Science Workflow Guide

This document presents a data science workflow canvas to help structure a data science project. It consists of 6 sections: 1) Problem Statement, 2) Outcomes/Predictions, 3) Data Acquisition, 4) Modeling, 5) Model Evaluation, and 6) Data Preparation. The sections are ordered to first define the problem and desired outcomes, then acquire and prepare the data, select and build models, and finally evaluate the models' performance. This canvas provides a framework to plan and implement a complete data science workflow from start to finish.

Uploaded by

francisco sousa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Data Science Workflow Canvas*

Conceptualized by Jasmine Vasandani using notes from General Assembly’s Data Science Immersive. Format inspired by Business Model Canvas.
Start here. The sections below are ordered intentionally to make you state your goals first, followed by steps to achieve those goals. You’re allowed to switch orders of these steps!

Title:.
1 Problem Statement 2 Outcomes/Predictions 3 Data Acquisition
What problem are you trying to solve? What prediction(s) are you trying to make? Where are you sourcing your data from?
What larger issues do the problem address? Identify applicable predictor (X) and/or target (y) variables. Is there enough data? Can you work with it?

4 Modeling 5 Model Evaluation 6 Data Preparation


What models are appropriate to use given your outcomes? How can you evaluate your model’s performance? What do you need to do to your data in order to run your
model and achieve your outcomes?

Activation
When you finish filling out the canvas above, now you can begin implementing your data science workflow in roughly this order.
.
.

1 Problem Statement → 2 Data Acquisition → 3 Data Prep → 4 Modeling → 5 Outcomes/Preds → 6 Model Eval

* Note: This canvas is intended to be used as a starting point for your data science projects. Data science workflows are typically nonlinear.

You might also like