# Get the data from my working directory
rep <- read.csv("activity.csv")
# make date column Dates instead of Factor
rep$date <- as.character(rep$date)
rep$dates <- as.Date(rep$date, "%Y-%m-%d")
# remove NAs
data<-na.omit(rep)
# Histogram of the total number of steps taken each day
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
library(knitr)
stepsByDay <- tapply(rep$steps, rep$date, sum, na.rm=TRUE)
barplot(stepsByDay)
#Mean and Median number of steps taken each day
mean(stepsByDay)
## [1] 9354.23
# answer = 9354.23
median(stepsByDay)
## [1] 10395
# answer = 10395
#Time series plot of the average number of steps taken
meanplot <-ggplot(data = data, aes(dates, steps)) +
stat_summary(fun.y = mean, geom = "bar")
meanplot+ggtitle("Mean Steps per Day")
#The 5-minute interval that, on average, contains the maximum number of steps
stepsByInterval <- tapply(data$steps, data$interval, mean, na.rm=TRUE)
summary(stepsByInterval)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 2.486 34.110 37.380 52.830 206.200
sort(stepsByInterval)[length(stepsByInterval)]
## 835
## 206.1698
#answer is interval 835
#Code to describe and show a strategy for imputing missing data
library(zoo)
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
rep$steps<-na.aggregate(rep$steps)
summary(rep)
## steps date interval dates
## Min. : 0.00 Length:17568 Min. : 0.0 Min. :2012-10-01
## 1st Qu.: 0.00 Class :character 1st Qu.: 588.8 1st Qu.:2012-10-16
## Median : 0.00 Mode :character Median :1177.5 Median :2012-10-31
## Mean : 37.38 Mean :1177.5 Mean :2012-10-31
## 3rd Qu.: 37.38 3rd Qu.:1766.2 3rd Qu.:2012-11-15
## Max. :806.00 Max. :2355.0 Max. :2012-11-30
#Histogram of the total number of steps taken each day after missing values are imputed
stepsByDayNA <- tapply(rep$steps, rep$date, sum, na.rm=TRUE)
barplot(stepsByDayNA)
#Panel plot comparing the average number of steps taken per 5-minute interval across weekdays and weekends
rep$week <- weekdays(rep$dates)
rep <- mutate(rep, weekpart = ifelse(week == "Saturday" | week=="Sunday", "weekend", "weekday"))
str(rep)
## 'data.frame': 17568 obs. of 6 variables:
## $ steps : num 37.4 37.4 37.4 37.4 37.4 ...
## $ date : chr "2012-10-01" "2012-10-01" "2012-10-01" "2012-10-01" ...
## $ interval: int 0 5 10 15 20 25 30 35 40 45 ...
## $ dates : Date, format: "2012-10-01" "2012-10-01" ...
## $ week : chr "Monday" "Monday" "Monday" "Monday" ...
## $ weekpart: chr "weekday" "weekday" "weekday" "weekday" ...
rep$weekpart <- as.factor(rep$weekpart)
byDay<-aggregate(steps ~ interval+weekpart, data = rep, mean)
head(byDay)
## interval weekpart steps
## 1 0 weekday 7.006569
## 2 5 weekday 5.384347
## 3 10 weekday 5.139902
## 4 15 weekday 5.162124
## 5 20 weekday 5.073235
## 6 25 weekday 6.295458
ggplot(byDay, aes(interval, steps)) +
geom_line() +
facet_grid(weekpart ~ .) +
xlab("5-minute Interval") +
ylab("Mean Steps")
