Analysis of a Personal Activity Monitoring Device

SYNOPSIS

This project makes use of data from a personal activity monitoring device. The 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.

Basic analysis of the data is completed in R and detailed below.

Loading and preprocessing the data

library(ggplot2)
library(plyr)

measured_data <- read.csv("C:/Users/Adam/Documents/School/Coursera/Reproducable research/activity.csv")
measured_data$date <- as.Date(measured_data$date, )
na_index <- !is.na(measured_data$steps)
subset_data <- measured_data[na_index,]

What is mean total number of steps taken per day?

calculating the total number of steps taken per day

summarystat <- aggregate(subset_data$steps, by = list(date=subset_data$date), sum)

A histogram of total number of steps taken per day

qplot(x = summarystat$date, y = summarystat$x, geom = "bar", stat = "identity", xlab = "date", ylab = "count")

The mean and median number of steps taken per day

mean(summarystat$x)

## [1] 10766.19

median(summarystat$x)

## [1] 10765

What is the average daily activity pattern?

A time series plot of interval vs average number of steps taken averaged across all days

mean_steps_inter <- aggregate(subset_data$steps, by = list(interval=subset_data$interval), mean)
qplot(x = mean_steps_inter$interval, y = mean_steps_inter$x, geom = "line", xlab = "interval", ylab = "count")  

The interval and number of steps that contains the maximum number of steps is as follows:

mean_steps_inter[which(mean_steps_inter$x == max(mean_steps_inter$x)),]

##     interval        x
## 104      835 206.1698

Imputing missing values

calculating and reporting the total number of missing values in the dataset

sum(is.na(measured_data$steps))

## [1] 2304

filling in missing data - 8 days of data are missing. Values to be replaced with mean.

for (i in 1:length(measured_data$steps)){
  if (is.na(measured_data$steps[i]) == TRUE) {
    measured_data$steps[i] <- mean_steps_inter$x[which(measured_data$interval[i] == mean_steps_inter$interval)]
  }
}

Making a histogram with replaced data and calculating mean and median

summarystat <- aggregate(measured_data$steps, by = list(date=measured_data$date), sum)
qplot(x = summarystat$date, y = summarystat$x, geom = "bar", stat = "identity", xlab = "date", ylab = "count")

mean(summarystat$x)

## [1] 10766.19

median(summarystat$x)

## [1] 10766.19

Are there differences in activity patterns between weekdays and weekends?

Creating a new factor variable with “weekday and”weekend"

weekday <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
weekday_vec <- NULL
for (i in 1:length(measured_data$date)) {
  if (weekdays(measured_data$date[i]) %in% weekday) {
    weekday_vec[i] <- "Weekday"
  }
  else{
    weekday_vec[i] <- "Weekend"
  }
}
measured_data <- cbind(measured_data, weekday_vec)
summary <- ddply(measured_data, .(weekday_vec,interval), function(measured_data) mean(measured_data$steps, na.rm = TRUE))

Creating a panel time series plot for weekend and weekday

q <- ggplot(summary, aes(x = interval, y= V1)) 
q + geom_line() + facet_grid(.~weekday_vec)