#Setting the work space environment#installing and loading all necessary packages for the analysis, including data set files{r loading packages}
install.packages("tidyverse")
library("tidyverse")
install.packages("ggplot2")
library("ggplot2")
install.packages("janitor")
library("janitor")
install.packages("dplyr")
library("dplyr")
library(lubridate)
##Assigning operator###Reading the dailyactivitymerged file and assigning and operator for easy use later{r reading daily_activity}
daily_activity <- read.csv("dailyActivity_merged.csv")
##Viewing the dailyactivity table###Viewing the dailyactivity table to have a glimpse of what we're working with.{r viewing daily_activity}
head(daily_activity)
##Removing duplicates and arranging by Id{r}
daily_activity <- unique(daily_activity)
daily_activity %>%
arrange("Id")
head(daily_activity)
##Changing date format{r}
daily_activity$ActivityDate <- mdy(daily_activity$ActivityDate)
class(daily_activity$ActivityDate)
print(daily_activity)
##Changing column name{r}
names(daily_activity)[names(daily_activity) == "ActivityDate"] <- "Date"
print(daily_activity)
##Create new columns###Creating a new column Total_D1 to confirm the totaldistance , select total distance and TotalD1 to see both columns side by side{r mutate Total_d1}
daily_activity<- daily_activity %>%
mutate(Total_D1=(VeryActiveDistance + ModeratelyActiveDistance + LightActiveDistance + SedentaryActiveDistance))
head(daily_activity)
daily_activity %>%
select(TotalDistance, Total_D1)
###Creating a new yes or no column in da2 to show the activities distance that got logged and ones that did not get logged , this is to be used for a bar char later{r logged activty distance ?}
daily_activity$logged <- cut(daily_activity$LoggedActivitiesDistance,
breaks=c(-1,0,1,2,3,4), labels=c('No', 'No', 'Yes', 'Yes', 'Yes'))
##Calculations###Calculating the minimum and maximum dates of data in the table{r mindat & maxdate}
mindate <- min(daily_activity$Date)
maxdate <- max(daily_activity$Date)
###Counting number of rows in totaldistance that tally with Total_D1, and rows that do not tally{r}
sum(daily_activity$TotalDistance==daily_activity$Total_D1)sum(daily_activity$TotalDistance !=daily_activity$Total_D1)
###Counting the number of rows where activities distance is not logged. UnloggedActivityDistance (ulad), loggedActivityDistance(lad){r unlogged and logged activity distance}
Unlogged_activity_distance <- nrow(daily_activity[daily_activity$LoggedActivitiesDistance == 0, ])
Logged_activity_distance <- (940-908)
#Plots ##totalsteps and totaldistance scattered plot with line{r totalsteps , totaldistance}
ggplot(daily_activity, aes(x=TotalSteps, y= TotalDistance))+
geom_point()+
geom_smooth()+
labs(title="Steps and Distance", subtitle="Plot showing relationship between steps and distance", caption= paste0("Data from: ",mindate, " To ",maxdate))+
theme(axis.text.y = element_text(angle=45),
axis.text.x = element_text(angle=45))
##Totalsteps and calories scattered plot with line{r}
ggplot(daily_activity, aes(x=TotalSteps, y= Calories))+
geom_point()+
geom_smooth()+
labs(title="Relationship between tottalsteps and calories", caption = paste0("Data from: ",mindate," To ", maxdate))+
theme(axis.text.y = element_text(angle=45),
axis.text.x = element_text(angle=45))
##LoggedActivities bar plot###Creating a bar plot to visualized the yes and no column created earlier.{r LoggedActivities}
ggplot(data=subset(daily_activity, !is.na(logged)), aes(x=logged, fill= logged))+
geom_bar()+
theme(axis.text.x = element_text(angle= 45),
axis.text.y = element_text(angle=45))+
labs(title="Comparison of logged and unlogged activities", caption= paste0("Data from: ",mindate, " To ",maxdate),
x= "Logged?")
##Reading weight log info and SleepDay csv files, assigning an operator and using head to check the first 6 rows of the datasets{r weightLogInfo}
weight <- read.csv("weightLogInfo_merged.csv")
sleep <- read.csv("sleepDay_merged.csv")
head(sleep)
##Changing sleepday format to Date only and also creating a weekday column{r}
sleep$SleepDay <- as.Date(mdy_hms(sleep$SleepDay))
print(sleep)
##Changing sleepday calumn name to Date{r}
names(sleep)[names(sleep) == "SleepDay"] <- "Date"
print(sleep)
##Creating weekday column{r}
sleep <- sleep %>%
mutate(Weekday = weekdays(Date))
print(sleep)
# removing dupliates and arranging by Id{r}
sleep <- unique(sleep)
sleep <- sleep %>%
arrange("Id")
print(sleep)
## Counting the number of occurrences for each unique Id{r count Id }
weight %>%
count(Id)
##Checking the number of occurrences for each Totalsleeptime{r SleepDay}
sleep %>%
count(TotalSleepRecords)
##Missing value{r}
num_of_rows_with_zero_sleep <- sum(sleep$TotalMinutesAsleep == 0)
##Creating a new column in sleepday (sd) for TimeNotAsleeep{r}
sleep <- sleep %>%
mutate(TimeNotAsleep=(TotalTimeInBed - TotalMinutesAsleep))
head(sleep)
## Missing values{r}
no_of_rows_with_zero_sleep <- sum(sleep$TotalMinutesAsleep == 0)
##Plotting a bar chart for manual reports to show the counts of manual reports compared to auto{r}
ggplot(weight, aes(x=IsManualReport, fill= IsManualReport))+
geom_bar()+
theme(axis.text.x = element_text(angle=45),
axis.text.y = element_text(angle=45))+
labs(title="Manual report", subtitle="Chart showing counts of manual and auto reports",caption= paste0("Data from: ",mindate," To ", maxdate))
## calculating mnweight and maxweight{r}
minweight <- min(weight$WeightKg)
maxweight <- max(weight$WeightKg)
minweight
maxweight
##Plotting a bar chart showing weight counts and also categorizing how each weight class report , manual or not .{r}
ggplot(weight, aes(x=WeightKg, fill= IsManualReport))+
geom_bar()+
theme(axis.text.x = element_text(angle=45),
axis.text.y = element_text(angle=45))+
labs(title="Weight counts ", subtitle="This plot also shows how each weight class report", caption = paste0("Data from: ",mindate," To ", maxdate))
##Scattered plot to show relationship between TimeAsleep and TimeNotAsleep{r}
ggplot(sleep, aes(y=TimeNotAsleep, x= TotalTimeInBed))+
geom_point()+
geom_smooth()+
labs(title="TimeAsleep and TimeNotAsleep scattered plot",
caption= paste0("Data from: ",mindate," To ", maxdate))+
theme(axis.text.x = element_text(angle=45))
## Loading hourly datasets{r}
hourly_steps <- read.csv("hourlySteps_merged.csv")
hourly_intensities <- read.csv("hourlyIntensities_merged.csv")
hourly_calories <- read.csv("hourlyCalories_merged.csv")
# Creating date and weekday column and changing dat format## Hourly steps{r}
hourly_steps <- hourly_steps %>%
mutate(
ActivityHour = mdy_hms(ActivityHour, tz = "UTC"))
print(hourly_steps)
{r}
hourly_steps <- hourly_steps %>%
mutate(Date = as.Date(ActivityHour),
Weekday = weekdays(ActivityHour))
head(hourly_steps)
## Hourly intensities{r}
hourly_intensities <- hourly_intensities %>%
mutate(
ActivityHour = mdy_hms(ActivityHour, tz = "UTC"),
Date = as.Date(ActivityHour),
Weekday = weekdays(ActivityHour)
)
## Hourly calories{r}
hourly_calories <- hourly_calories %>%
mutate(
ActivityHour = mdy_hms(ActivityHour, tz = "UTC"),
Date = as.Date(ActivityHour),
Weekday = weekdays(ActivityHour))
# Joining dataframes## Daily data{r}
daily <- inner_join(daily_activity, sleep, by = c("Id", "Date"))
## Hourly data{r}
hourly_data <- hourly_steps %>%
left_join(hourly_intensities, by = c("Id", "ActivityHour", "Date", "Weekday")) %>%
left_join(hourly_calories, by = c("Id", "ActivityHour", "Date", "Weekday"))
print(hourly_data)
# Daily average time asleep{r}
daily_avg_sleeptime <- daily %>%
group_by(Weekday) %>%
arrange(Weekday) %>%
summarise(avgsleeptime = mean(TotalMinutesAsleep))
# Average sleep time by weekday bar chart{r}
ggplot(daily_avg_sleeptime, aes(x = Weekday, y = avgsleeptime))+
geom_bar(stat="Identity", fill = "turquoise3", color = "black", alpha = 1)+
theme(axis.text.x = element_text(angle=45))+
labs(title="Average sleeptime destribution by weekday",
caption = paste0("Data from: ", mindate," To ", maxdate))
# Daily average sedentary minutes{r}
daily_avgSedentaryMinutes <- daily %>%
group_by(Weekday) %>%
summarise(avgSedentaryMinutes = mean(SedentaryMinutes))
head(daily_avgSedentaryMinutes)
# Average sedentary minutes bar chart{r}
ggplot(daily_avgSedentaryMinutes, aes(x = Weekday, y = avgSedentaryMinutes))+
geom_bar(stat= "Identity", fill = "turquoise3", color ="black", alpha= 1)+
theme(axis.text.x = element_text(angle=45))+
labs(title="Average dedentary minutes destribution by weekday",
caption = paste0("Data from: ", mindate," To ", maxdate))
## Average totalsteps by weekday{r}
avg_daily_total_steps <- daily %>%
group_by(Weekday) %>%
summarise(avg_daily_total_steps = mean(TotalSteps))
print(avg_daily_total_steps)
## Average total steps by weekday bar chart{r}
ggplot(avg_daily_total_steps, aes(x = Weekday, y = avg_daily_total_steps))+
geom_bar(stat = "Identity", fill="turquoise3", color="black", alpha = 5)+
theme(axis.text.x = element_text(angle=45))+
labs(title = "Average total steps destibutiion by weekday", caption = paste0("Data from: ", mindate," To ", maxdate))