Introduction

About the company

Bellabeat is a high-tech manufacturer of health-focused products for women. Bellabeat is a successful small company, but they have the potential to become a larger player in the global smart device market. Urška Sršen, cofounder and Chief Creative Officer of Bellabeat, believes that analyzing smart device fitness data could help unlock new growth opport unities for the company.

Characters and products

● Characters

○ Urška Sršen: Bellabeat’s cofounder and Chief Creative Officer

○ Sando Mur: Mathematician and Bellabeat’s cofounder; key member of the Bellabeat executive team

○ Bellabeat marketing analytics team: A team of data analysts responsible for collecting, analyzing, and reporting data that helps guide Bellabeat’s marketing strategy. You joined this team six months ago and have been busy learning about Bellabeat’s mission and business goals — as well as how you, as a junior data analyst, can help Bellabeat achieve them.

● Products

○ Bellabeat app: The Bellabeat app provides users with health data related to their activity, sleep, stress, menstrual cycle, and mindfulness habits. This data can help users bett er understand their current habits and make healthy decisions. The Bellabeat app connects to their line of smart wellness products.

○ Leaf: Bellabeat’s classic wellness tracker can be worn as a bracelet, necklace, or clip. The Leaf tracker connects to the Bellabeat app to track activity, sleep, and stress.

○ Time: This wellness watch combines the timeless look of a classic timepiece with smart technology to track user activity, sleep, and stress. The Time watch connects to the Bellabeat app to provide you with insights into your daily wellness.

○ Spring: This is a water bottle that tracks daily water intake using smart technology to ensure that you are appropriately hydrated throughout the day. The Spring bott le connects to the Bellabeat app to track your hydration levels. ○ Bellabeat membership: Bellabeat also off ers a subscription-based membership program for users. Membership gives users 24/7 access to fully personalized guidance on nutrition, activity, sleep, health and beauty, and mindfulness based on their lifestyle and goals

Ask

Business task/Goals for the analysis

Prepare

Tools to be used: Google Sheets, R Programming, Tableau

For this project, I will use Google Sheets for viewing .cvs files for cleaning purposes. Then I will use R to process the data for data manipulation and visualizations. Tableau will also be used for visualization.

Data sources For this project, I will use FitBit Fitness Tracker Data.

Datasets are downloaded and stored on local storage with .cvs format.

About the Dataset

This dataset generated by respondents to a distributed survey via Amazon Mechanical Turk between 03.12.2016-05.12.2016. Thirty eligible Fitbit users consented to the submission of personal tracker data, including minute-level output for physical activity, heart rate, and sleep monitoring. Individual reports can be parsed by export session ID (column A) or timestamp (column B). Variation between output represents use of different types of Fitbit trackers and individual tracking behaviors / preferences.

Process

In this project, I will use Google Sheets to check the data for data validation and cleaning. Added Two columns for each data sheets named: ActivityDate and Weekday This is done by converting the existing Dates column into custom date and time format to only display “mm/dd/yyyy” format for ActivityDate and “Monday, Tuesday, Wednesday, Thurday, Friday, Saturday, or Sunday” format on Weekday column.

I will be using these datasets for the analysis:

Screenshot-2024-03-01-091050

These are some of the datasets that is cleaned and added with ActivityDate and Weekday column.

Picture1Picture2

Next we’ll be using R to count total participants in each data sets

library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(lubridate)
library(dplyr)
library(ggplot2)
library(tidyr)

sleep <- read.csv("sleepDay_merged.csv")
n_distinct(sleep$Id)
## [1] 24

24

There are total of 24 participants in the dataset that I am processing now.

Data Analysis and Visualization of the total 24 participants in Average sleep per day

sleep$Weekday <- factor(sleep$Weekday, levels = c("Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"))

average_sleep <- aggregate(TotalMinutesAsleep ~ Weekday, data = sleep, FUN = mean)
ggplot(data = average_sleep, aes(x = Weekday, y = TotalMinutesAsleep)) +
  geom_bar(stat = "identity", fill = "skyblue") +
  labs(x = "Weekday", y = "Average Sleep Minutes", title = "Average Sleep Minutes per Day in a Week")

Data Analysis and Visualization of the total 24 participants in Weekday Vs total Minutes Asleep

sleep$Weekday <- factor(sleep$Weekday, levels = c("Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"))

# Plot with sorted x-axis
ggplot(data = sleep, aes(x = Weekday, y = TotalMinutesAsleep)) +
  geom_bar(stat = "identity", width = 0.8, fill = 'darkblue') +
  labs(title = "Bar Plot of Total Sleep Minutes by Weekday") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))  # Rotate x-axis labels for better readability

Next process, I will be merging the steps and calories data sets to analyze and visualize the relationship of the two parameters.

calories <- read.csv("dailyCalories_merged.csv")
steps <- read.csv("dailySteps_merged.csv")

merged_steps_calories <- merge(calories, steps, by = c("Id",    "ActivityDate", "Weekday"), all = FALSE)

head(merged_steps_calories)
##           Id ActivityDate   Weekday Calories StepTotal
## 1 1503960366    4/12/2016   Tuesday     1985     13162
## 2 1503960366    4/13/2016 Wednesday     1797     10735
## 3 1503960366    4/14/2016  Thursday     1776     10460
## 4 1503960366    4/15/2016    Friday     1745      9762
## 5 1503960366    4/16/2016  Saturday     1863     12669
## 6 1503960366    4/17/2016    Sunday     1728      9705

Plotting the Total Steps Vs Calories

ggplot(data=merged_steps_calories) + geom_point() + aes(x=StepTotal,y=Calories) + 
  geom_smooth() + labs(title = "Total Steps vs Calories") 
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

Graphing the relationship of total steps throughout the week

merged_steps_calories$Weekday <- factor(merged_steps_calories$Weekday, levels = c("Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"))
ggplot(data = merged_steps_calories, aes(x = Weekday, y = StepTotal)) +
  geom_bar(stat = "identity", width = 0.9, fill = 'aquamarine3') +
  labs(title = "Total Steps throughout the week") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Total Calories in a week

merged_steps_calories$Weekday <- factor(merged_steps_calories$Weekday, levels = c("Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"))


ggplot(data = merged_steps_calories, aes(x = Weekday, y = Calories)) +
  geom_bar(stat = "identity", width = .9, fill = 'cyan4') +
  labs(title = "Total Calories throughout the week") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Next, I will check the data stored in weightloginfo data set to check participants’ weight info.

weight <- read.csv("weightLogInfo_merged.csv")
str(weight)
## 'data.frame':    67 obs. of  10 variables:
##  $ Id            : num  1.50e+09 1.50e+09 1.93e+09 2.87e+09 2.87e+09 ...
##  $ ActivityDate  : chr  "5/2/2016" "5/3/2016" "5/4/2016" "5/5/2016" ...
##  $ Weekday       : chr  "Monday" "Tuesday" "Wednesday" "Thursday" ...
##  $ Date          : chr  "5/2/2016 11:59:59 PM" "5/3/2016 11:59:59 PM" "4/13/2016 1:08:52 AM" "4/21/2016 11:59:59 PM" ...
##  $ WeightKg      : num  52.6 52.6 133.5 56.7 57.3 ...
##  $ WeightPounds  : num  116 116 294 125 126 ...
##  $ Fat           : int  22 NA NA NA NA 25 NA NA NA NA ...
##  $ BMI           : num  22.6 22.6 47.5 21.5 21.7 ...
##  $ IsManualReport: logi  TRUE TRUE FALSE TRUE TRUE TRUE ...
##  $ LogId         : num  1.46e+12 1.46e+12 1.46e+12 1.46e+12 1.46e+12 ...
n_distinct(weight$Id)
## [1] 8

Total of 8 participants who logged their weight info on the dataset.

Taking the Average weight in Kg of each participants.

weight_average <- weight %>%
  group_by(Id) %>%
  summarise(weight_mean = mean(WeightKg, na.rm = TRUE)) %>%
  arrange(weight_mean)

print(weight_average)
## # A tibble: 8 × 2
##           Id weight_mean
##        <dbl>       <dbl>
## 1 1503960366        52.6
## 2 2873212765        57  
## 3 6962181067        61.6
## 4 4558609924        69.6
## 5 4319703577        72.4
## 6 8877689391        85.1
## 7 5577150313        90.7
## 8 1927972279       134.

With a limited number of participants who logged their weight data,we cannot use this dataset to perform an analysis.

Processing hourly calories and hourly steps data sets.

hourly_calories <- read.csv("hourlyCalories_merged.csv")
hourly_steps <- read.csv("hourlySteps_merged.csv")
colnames(hourly_calories)
## [1] "Id"           "Hour"         "ActivityHour" "Calories"
colnames(hourly_steps)
## [1] "Id"           "Hour"         "ActivityHour" "StepTotal"
merged_hourly_steps_calories <- merge(hourly_calories, hourly_steps, by = c("Id",   "Hour", "ActivityHour"), all = FALSE)
n_distinct(merged_hourly_steps_calories$Id)
## [1] 33
head(merged_hourly_steps_calories)
##           Id  Hour          ActivityHour Calories StepTotal
## 1 1503960366 00:00 4/12/2016 12:00:00 AM       81       373
## 2 1503960366 00:00 4/13/2016 12:00:00 AM       69       144
## 3 1503960366 00:00 4/14/2016 12:00:00 AM       56        81
## 4 1503960366 00:00 4/15/2016 12:00:00 AM       60        83
## 5 1503960366 00:00 4/16/2016 12:00:00 AM       77       459
## 6 1503960366 00:00 4/17/2016 12:00:00 AM       47         0

Plotting Hourly steps vs calories

ggplot(data=merged_hourly_steps_calories) + geom_point() + aes(x=StepTotal,y=Calories) + 
  geom_smooth() + labs(title = "Hourly Total Steps vs Calories") 
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'

Graphing Total steps taken by each participants in a day

ggplot(data = merged_hourly_steps_calories, aes(x = Hour, y = StepTotal)) +
  geom_bar(stat = "identity", width = 0.9, fill = 'azure4') +
  labs(title = "Total Steps throughout the Day") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Graphing Total calories burned by each participants in a day

ggplot(data = merged_hourly_steps_calories, aes(x = Hour, y = Calories)) +
  geom_bar(stat = "identity", width = 0.9, fill = 'cadetblue') +
  labs(title = "Total Calories throughout the Day") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Active Minutes Analysis and Visualization using Tableau

tableau

Analyze

average-sleep total-sleep

In these bar graphs, Sundays have the record of the best average sleep minutes in the whole week. Sleeping for long hours on Sundays help the participants get back the energy they spent during the entire week. We also find a decrease in participants’ sleep frequency and length on Mondays, which could be attributed to participants having to go to work on Monday and/or preparing the family for work or school. Sleep quality improves gradually and peaks on Wednesdays. Sleep quality then worsens until Friday, when we can presume the participants’ party/nightlife activities may influence their sleep patterns, leading to decreased sleep quality compared to earlier in the week.

plot-hour-step-vs-cal steps-vs-calories

In this scatterplots of total steps and calories burned, we see positive correlation between the two variables, which is obvious.

week-calorie week-steps

In the bar graphs depicting Total Steps and Total Calories over the course of the week, a clear trend emerges showing that an increase in steps correlates with a rise in total calories burned. According to the data, both steps and calories reach their highest point on Tuesday. These findings are consistent with the positive correlation observed in the previous scatterplot analysis of steps and calories.

cal-day step-day

This graph depicts total steps and calories per hour throughout the day based on participant averages. Peak step counts were obtained between 6:00 and 7:00 p.m. During this time, the highest number of calories burned were reported. The participants were likely at their most active throughout this period.

tableau

In this Tableau pie chart, we can see the total minutes of all 33 participant in different activities throughout the day where Sedentary minutes tops the chart with a total percentage of 81% total Sedentary minutes.

Share

Sharing Recommendations/Findings for the business

  1. During the data processing phase, we encountered analysis problem involving weight of some of the participants due to not all participants logged their weight. Weight data may help us find useful trends and insights that can be used to improve our analysis. The analytics team should consider other data sources that include weight data for each participants.

  2. In the Total sleep analysis throughout the week, we noticed reduction of good sleep quality during Monday. The Bellabeat App may implement tips and recommendation to improve sleep conditions depending on the day of the week. The app may also notify the users of their sleep quality using the wellness watch to track their sleep duration throughout the night.

  3. In the analysis of steps vs calories scatterplot, we can conclude that more steps is equal to more calories burned. Bellabeat app with the help of wellness tracker and wellness watch, should set daily objectives of the total steps taken by the users by having a reward system if the target is reached, like a discount in membership or being on a top weekly ranking of total calories burned.

  4. The visualization and analysis of the active minutes chart shows that the average number of minutes spent in sedentary activities is the highest. Sedentary behavior typically includes activities such as sitting at a desk, watching television, using a computer, or driving for extended periods without significant movement or physical exertion. Reducing sedentary minutes and increasing physical activity are important for maintaining good health and reducing the risk of chronic diseases. The Bellabeat app can assist users to establish goals and monitor their progress in taking regular breaks from prolonged sitting or sedentary behaviors. It may include features that allow users to set reminders, prompting them to stand up, stretch, or engage in brief walks at hourly intervals.