Reproducible Research: Peer Assessment 1

library(lattice)
library(ggplot2)

Load the data for the propossing

getwd()

## [1] "/Users/janakiramsundaraneedi/Activity"

setwd("/Users/janakiramsundaraneedi/Downloads")
data <- read.csv("activity.csv")

Turn the data date into valid date class

dates <- strptime(data$date, "%Y-%m-%d")
data$date <- dates

keep all distinct days

dates_unique <- unique(dates)

Keep all the List of Possible Intervals

unique_intervals <- unique(data$interval)

Histogram of the total number of steps taken each day

Steps_perday <- tapply(data$steps, dates$yday, FUN=sum, na.rm=TRUE)

Plot the data and blue line gives Mean and green line median number of steps taken each day

plot(dates_unique, Steps_perday, main="Histogram of steps taken each day", xlab="Date (October to November 2012)", ylab="Frequency", type="l", lwd=2, col="black")+abline(h = mean(Steps_perday), col = "blue", lwd = 3)+
abline(h = median(Steps_perday), col = "green", lwd = 3)

## numeric(0)

The 5-minute interval that, on average, contains the maximum number of steps

which.max(data$steps)

## [1] 16492

Code to describe and show a strategy for imputing missing data

table(is.na(data))

## 
## FALSE  TRUE 
## 50400  2304

na_value <- which(is.na(data))

Fill in missing values using the average interval value across all days

NA_value <-  which(is.na(data))
Values_Impu<-Steps_perday[as.character(data[NA_value,3])]
names(Values_Impu) <- NA_value
for (i in NA_value) {
    data$steps[i] = Values_Impu[as.character(i)]
}
sum(is.na(data))

## [1] 2248

Are there differences in activity patterns between weekdays and weekends?

wday_wend <- function(date) {
    day <- weekdays(date)
    if (day %in% c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday"))
        return("weekday")
    else if (day %in% c("Saturday", "Sunday"))
        return("weekend")
    else
        stop("invalid date")
}
data$date <- as.Date(data$date)
data$day <- sapply(data$date, FUN=wday_wend)

averages <- aggregate(steps ~ interval + day, data=data, mean)
ggplot(averages, aes(interval, steps)) + geom_line() + facet_grid(day ~ .) +
    xlab("5-minute interval") + ylab("Number of steps")