Journey into data

Case Study: Analyzing Fitness Data in Alteryx

Giniya Gupta

Sr. Analyst

What is a case study?

In-depth analysis of a specific real-world situation using data
Answer specific business questions
Prerequisite courses
- Introduction to Alteryx
- Data Preparation in Alteryx
- Data Transformation in Alteryx

Data analysis flow in Alteryx

$$ Case study flow 0

Data analysis flow in Alteryx

Case study flow 1

Understand the business question
- Example: Which days of the week does the usage of smart fitness apps decrease, and how can we prevent it?

Data analysis flow in Alteryx

Case study flow 2

Data quality check:
- Missing values and duplicate rows
- Align with other internal data sources
Build your first Alteryx workflow!

Data analysis flow in Alteryx

Case study flow 3

Removing duplicate rows
Replacing NULL values
Ensuring that the correct data type is assigned to each field

Data analysis flow in Alteryx

Case study flow 4

Reveal patterns and connections
Create calculated fields
Combine data sets

Data analysis flow in Alteryx

Case study flow 5

No visualizations will be created in this course

The scenario

Bellabeat - a company that designs smart fitness-tracking products for women
Seeks to expand its customer base

Lady using app.jpg

The data

Personal fitness tracker data$^1$:
- 30 users over a period of 31 days
Three CSV files
Each dataset contains:
- Common columns, Id and Date
- ID is a unique identifier

Fitness data.JPG

¹ Dataset modified from Kaggle

The data

DailyActivity.csv has 15 columns containing data about daily physical activity tracking:

Column	Description
Id	The unique ID that identifies an app user
ActivityDate	The date activity was recorded
Calories	Calories burnt
Physical activity related metrics	TotalSteps, TotalDistance, ActiveMinutes...

The data

SleepDay.csv contains a daily record of sleep data in five different columns:

Column	Description
Id	The unique identifier for an app user
SleepDay	Date of sleep record
Sleep related metrics	TotalMinutesAsleep, TotalTimeInBed...

WeightLogInfo.csv includes a daily log of weight measurements in seven columns:

Column	Description
Id
Date	Date of recording weight
Weight-related metrics	WeightKg, HeightMeters, Fat...

Business questions

Bellabeat aims to grow its customer base

Is there any pattern in users' activity/exercise schedules?

What are the most tracked activities?

What is the predominant lifestyle based on the lifestyle index?

What are the users' physical activity levels compared to the recommended norms?

Marketing strategy

Let's start analyzing!

Case Study: Analyzing Fitness Data in Alteryx