It is now possible to collect a large amount of data about personal movement using activity monitoring devices such as a Fitbit, Nike Fuelband, or Jawbone Up. These type of devices are part of the "quantified self" movement - a group of enthusiasts who take measurements about themselves regularly to improve their health, to find patterns in their behavior, or because they are tech geeks. But these data remain under-utilized both because the raw data are hard to obtain and there is a lack of statistical methods and software for processing and interpreting the data.
This report makes use of data from a personal activity monitoring device. This device collects data at 5 minute intervals through out the day. The data consists of two months of data from an anonymous individual collected during the months of October and November, 2012 and include the number of steps taken in 5 minute intervals each day.
The dataset is stored in a comma-separated-value (CSV) file and there are a total of 17,568 observations in this dataset.
The variables included in this dataset are:
##Load packages
library(readr)
library(ggplot2)
library(dplyr)##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union##Get and unzip data
path<-getwd()
url<-"https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2Factivity.zip"
download.file(url,file.path(path,"cp1.zip"))
unzip(zipfile="cp1.zip")
##Read in data
activityData<-read_csv("activity.csv")## Parsed with column specification:
## cols(
## steps = col_double(),
## date = col_date(format = ""),
## interval = col_double()
## )##Condense data
byDate<-as.POSIXct(activityData$date, "%Y-%m-%d")
day <- weekdays(activityData$date)
activity<-cbind(activityData,day)
summary(activity)## steps date interval day
## Min. : 0.00 Min. :2012-10-01 Min. : 0.0 Friday :2592
## 1st Qu.: 0.00 1st Qu.:2012-10-16 1st Qu.: 588.8 Monday :2592
## Median : 0.00 Median :2012-10-31 Median :1177.5 Saturday :2304
## Mean : 37.38 Mean :2012-10-31 Mean :1177.5 Sunday :2304
## 3rd Qu.: 12.00 3rd Qu.:2012-11-15 3rd Qu.:1766.2 Thursday :2592
## Max. :806.00 Max. :2012-11-30 Max. :2355.0 Tuesday :2592
## NA's :2304 Wednesday:2592First, calculate the total number of steps taken per day.
totalSteps_Day<-aggregate(activity$steps,
by=list(activity$date),
FUN=sum,
na.rm=TRUE)
names(totalSteps_Day)<-c("date","steps")
head(totalSteps_Day)## date steps
## 1 2012-10-01 0
## 2 2012-10-02 126
## 3 2012-10-03 11352
## 4 2012-10-04 12116
## 5 2012-10-05 13294
## 6 2012-10-06 15420Now, look at a histogram of these results.
hist(totalSteps_Day$steps,
main="Total Steps per Day",
xlab="Steps",
ylim=c(0,40),
col="turquoise4")
Measures of center for this data so far: This will be the measures of center with a simple removal of any NA values.
meanSteps<-round(mean(totalSteps_Day$steps,na.rm=TRUE),digits=2)
medSteps<-median(totalSteps_Day$steps,NA.RM=TRUE)
print(paste("The mean number of steps taken per day is",meanSteps,sep=" "))## [1] "The mean number of steps taken per day is 9354.23"print(paste("The median number of steps taken per day is",medSteps,sep=" "))## [1] "The median number of steps taken per day is 10395"Time series plot for this dataset to determine any patterns.
##Make a time series plot of the intervals and the average steps taken per day
avgSteps_Int<-aggregate(activity$steps,
by=list(activity$interval),
FUN=mean,
na.rm=TRUE)
names(avgSteps_Int)<-c("interval","mean")
plot(avgSteps_Int$interval,avgSteps_Int$mean,
type="l",
col="turquoise4",
lwd=2,
xlab="5-minute Interval",
ylab="Average Steps Taken",
main="Average Steps Taken per 5-minute Interval")
Which 5-minute interval, on average across all the days in the dataset, contains the maximum number of steps?
maxAvg<-avgSteps_Int[which.max(avgSteps_Int$mean),]$interval
print(paste("The 5-minute interval with the maximum number of steps is",maxAvg,sep=" "))## [1] "The 5-minute interval with the maximum number of steps is 835"Find out how many total missing values (NAs) there are currently in the dataset.
totalNA<-sum(is.na(activity$steps))
print(paste("The total number of NAs in the dataset is",totalNA,sep=" "))## [1] "The total number of NAs in the dataset is 2304"Remove all of the current NA values and replace them with the mean of that interval.
##Create a new dataset that is equal to the original dataset but with the missing data filled in
activityImputed<-activity
activityNA<-is.na(activityImputed$steps)
intervalAvg<-tapply(activity$steps, activity$interval, mean, na.rm=TRUE, simplify=T)
activityImputed$steps[activityNA] <- intervalAvg[as.character(activityImputed$interval[activityNA])]
summary(activityImputed)## steps date interval day
## Min. : 0.00 Min. :2012-10-01 Min. : 0.0 Friday :2592
## 1st Qu.: 0.00 1st Qu.:2012-10-16 1st Qu.: 588.8 Monday :2592
## Median : 0.00 Median :2012-10-31 Median :1177.5 Saturday :2304
## Mean : 37.38 Mean :2012-10-31 Mean :1177.5 Sunday :2304
## 3rd Qu.: 27.00 3rd Qu.:2012-11-15 3rd Qu.:1766.2 Thursday :2592
## Max. :806.00 Max. :2012-11-30 Max. :2355.0 Tuesday :2592
## Wednesday:2592Now that all of the NA values are removed and replaced with the mean of that interval, look at the same histogram as above with the new data. Notice the new mean and median given the new dataset.
##Make a histogram of the total number of steps taken each day
totalSteps_Day_Im<-aggregate(activityImputed$steps,
by=list(activityImputed$date),
FUN=sum,
na.rm=TRUE)
names(totalSteps_Day_Im)<-c("date","steps")
hist(totalSteps_Day_Im$steps,
main="Total Steps per Day",
xlab="Steps",
ylim=c(0,40),
col="turquoise4")
##Calculate and report the mean and median total number of steps taken per day.
meanStepsIm<-round(mean(totalSteps_Day_Im$steps,na.rm=TRUE),digits=2)
medStepsIm<-round(median(totalSteps_Day_Im$steps,NA.RM=TRUE),digits=2)
print(paste("For the imputed dataset,the mean number of steps taken per day is",meanStepsIm,sep=" "))## [1] "For the imputed dataset,the mean number of steps taken per day is 10766.19"print(paste("For the imputed dataset,the median number of steps taken per day is",medStepsIm,sep=" "))## [1] "For the imputed dataset,the median number of steps taken per day is 10766.19"Tthe histogram, while still showing the same trends and distribution as above, has a higher frequency count, which is especially noticeable in the interval from 10,000 to 15,000 steps (where our measures of center lie). Also, notice how both histograms were created with the same y-limit so it is possible to compare the two plots more reasonably. Normally, the first histogram would have a smalled y-limit, but that would allow for a less impactful visual difference between the two.
Aside from the histograms showing a difference between original and imputed data there are differences in the measures of center. The data went from a mean of 9354.23 and a median of 10395 to a new mean and median of the same value, 10766.19.
It can be seen that the NA values were skewing our original data and creating a significant difference between the mean and the median. After imputing the data, it is noted that the mean and median are now exactly the same, which give a nice, symmetrical spread.
To compare the differences between weekday and weekday data, it is first necessary to separate the imputed dataset by day type.
dayType<-sapply(activity$day,function(x)
{if(x=="Saturday"|x=="Sunday")
{y<-"Weekend"} else
{y<-"Weekday"}
y
})From here, two time series plots can be created to show the differences between the Monday-Friday and Saturday-Sunday data.
avgPerInt_dayType<-aggregate(steps~interval + dayType, activity, mean, na.rm = TRUE)
ggplot(avgPerInt_dayType,aes(x = interval , y = steps, color = dayType)) +
geom_line() +
scale_color_manual(values = c("turquoise4", "maroon4")) +
labs(title = "Average steps per Interval by type of day", x = "Interval", y = "Average number of steps") +
facet_wrap(~dayType, ncol = 1, nrow=2)
While it can be seen that there is still a maximum number of steps between interval 500 and 1000, there are clearly more steps taken on average during intervals 1000 to 2000 on the weekend vs. during the week.