.Rhistory

) %>% print
sat1 <- sat %>%
select(-contains("total")) %>%
gather(part_sex, count, -score_range) %>%
separate(part_sex, c("part", "sex")) %>%
group_by(score_range, sex) %>%
mutate(total = sum(count),
test = mean(count),
prop = count / total
test.prop = median(count)
) %>% print
sat1 <- sat %>%
select(-contains("total")) %>%
gather(part_sex, count, -score_range) %>%
separate(part_sex, c("part", "sex")) %>%
group_by(score_range, sex) %>%
mutate(total = sum(count),
test = mean(count),
prop = count / total,
test.prop = median(count)
) %>% print
swirl()
swirl()
library(swirl)
swirl()
library(tidyr)
students
?gather
gather(students, sex, count, -grade)
students2
res <- gather(students2, sex_class, count)
res <- gather(students2, sex_class, count, -grade)
res
?separate
separate(res, sex_class, c("sex", "class"))
submit()
submit()
students3
submit()
?spread
submit()
extract_numeric("class5")
submit()
submit()
students4
submit()
submit()
submit()
passed
failed
mutate(passed, status = "passed")
passed <- passed %>% mutate(status = "passed")
failed <- failed %>% mutate(status = "failed")
?rbind_list()
rbind_list(passed, failed)
swirl
swirl()
library(swirl)
swirl()
?help
help()
ljadfj
sat
submit()
submit()
exit()
end()
bye()
swirl()
sat
submit()
submit(0)
submit()
submit()
submit()
Sys.getlocale("LC_TIME")
library(lubridate)
help(package = lubridate)
today()
this_day <- today()
this_day
year(this_day)
wday(this_day)
wday(this_day, label = TRUE)
now()
this_moment <- now()
this_moment
seconds(this_moment)
second(this_moment)
ymd("1989-05-17")
my_date <- ymd("1989-05-17")
my_date
class(my_date)
ymd('1989 May 17')
mdy("March 12, 1975")
dmy(25081985)
ymd("192012")
ymd("1920//12")
ymd("1920/1/2")
dt1
ymd_hms(dt1)
hms("03:22:14")
dt2
ymd(dt2)
update(this_moment, hours = 8, minutes = 34, seconds = 55)
this_moment
this_moment <- update(hours = 9, minutes = 50)
this_moment <- update(this_moment, hours = 9, minutes = 50)
this_moe
this_moment
?now()
nyc <- now(tzone = "America/New_York")
nyc
depart <- nyc + days(2)
depart
depart <- update(depart, hours = 17, minutes = 34)
depar
depart
arrive <- nyc + hours(15) + minutes(50)
arrive <- depart + hours(15) + minutes(50)
?with_tz
arrive <- with_tz(arrive, tzone = "Asia/Hong_Kong")
arrive
mdy("June 17, 2008")
mdy("June 17, 2008", tz = "Singapore")
last_time <- mdy("June 17, 2008", tz = "Singapore")
last_time
?new_interval
how_long <- new_interval(arrive, last_time)
how_long <- new_interval(last_time, arrive)
as.period(how_long)
stopwatch()
library('lubridate')
library('ggplot2')
library('dplyr')
Load the following packages. If packages have not been installed, you will need to install them at this point using install.packages().
```{r, results= 'hide'}
library('lubridate')
library('ggplot2')
library('dplyr')
```
#### Load data
``` {r, results='hide'}
data <- read.csv('activity.csv')
```
## Steps per day analysis
```{r, echo=FALSE}
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90))
```
**Rearrange data for calculations**
```{r, results='hide'}
tot.steps.day <- data %>%
group_by(date) %>%
summarise(tot.steps = sum(steps))
```
**Mean and median calculation**
```{r, mean, echo=FALSE}
mean.steps.day <- mean(tot.steps.day$tot.steps, na.rm = TRUE)
median.steps.day <- median(tot.steps.day$tot.steps, na.rm = TRUE)
```
The mean steps per day is **`r mean.steps.day`**.
The median steps per day is **`r median.steps.day`**.
## Average daily pattern analysis
In order to plot the average number of steps taken taken per day, averaged across all days, the data must be rearranged.
```{r, results = 'hide'}
int.mean <- data %>%
group_by(interval) %>%
summarise(mean.steps = mean(steps, na.rm = TRUE))
```
Now data is ready to be plotted with ggplot
```{r}
plot2 <- ggplot(int.mean, aes(x = interval, y = mean.steps)) +
theme(legend.position = 'none') +
geom_line(aes(color = mean.steps), size = 1.4) +
geom_hline(aes(yintercept = mean(int.mean$mean.steps))) +
annotate('text', x = 4, y = 45, label = 'mean') +
labs(title = 'Mean Steps Per Interval')
```
setwd("~/Documents/github_repositories/reproducible_research/project_1")
data <- read.csv('activity.csv')
library('lubridate')
library('ggplot2')
library('dplyr')
## part 1: plot steps per day
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90))
## rearrange data for calculations
tot.steps.day <- data %>%
group_by(date) %>%
summarise(tot.steps = sum(steps))
## mean calculation
mean.steps.day <- mean(tot.steps.day$tot.steps, na.rm = TRUE)
## median calculation
median.steps.day <- median(tot.steps.day$tot.steps, na.rm = TRUE)
int.mean <- data %>%
group_by(interval) %>%
summarise(mean.steps = mean(steps, na.rm = TRUE))
plot2 <- ggplot(int.mean, aes(x = interval, y = mean.steps)) +
theme(legend.position = 'none') +
geom_line(aes(color = mean.steps), size = 1.4) +
geom_hline(aes(yintercept = mean(int.mean$mean.steps))) +
annotate('text', x = 4, y = 45, label = 'mean') +
labs(title = 'Mean Steps Per Interval')
complete.cases(data)
sum(complete.cases(data))
sum(!omplete.cases(data))
sum(!complete.cases(data))
inc.cases <- sum(!complete.cases(data))
?axis
break.vec <- c(min(data$date, median(data$date, max(data$date))))
break.vec <- c(min(data$date), median(data$date), max(data$date))))
break.vec <- c(min(data$date), median(data$date), max(data$date))
class(data$date)
View(data)
break.vec <- c(min(as.Date(data$date), median(as.Date(data$date), max(as.Date(data$date)))
break.vec <- c(min(as.Date(data$date), median(as.Date(data$date)), max(as.Date(data$date))))
break.vec <- c(min(as.Date(data$date)), median(as.Date(data$date)), max(as.Date(data$date))))
break.vec <- c(min(as.Date(data$date)), median(as.Date(data$date)), max(as.Date(data$date)))
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date(breaks = break.vec)
plot1
ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
scale_x_date(breaks = break.vec) +
theme(axis.text.x = element_text(angle = 90))
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date(labels = date_format('%m'))
?scale_x_date
data$date <- as.POSIXct(data$date)
ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date(labels = date_format('%w'))
ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date(labels = date_format('%w'))
ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date(breaks = date_breaks('week'))
library('scales')
ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date(breaks = date_breaks('week'))
?scale_x
?scale_x_date
ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date()
data$date <- as.Date(data$date)
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date()
plot1
detach("package:scales", unload=TRUE)
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date()
plot1
plot2 <- ggplot(int.mean, aes(x = interval, y = mean.steps)) +
theme(legend.position = 'none') +
geom_line(aes(color = mean.steps), size = 1.4) +
geom_hline(aes(yintercept = mean(int.mean$mean.steps))) +
annotate('text', x = 4, y = 45, label = 'mean') +
labs(title = 'Mean Steps Per Interval') +
scale_x_date()
plot2
## rearrange data for calculations
tot.steps.day <- data %>%
group_by(date) %>%
summarise(tot.steps = sum(steps))
## mean calculation
mean.steps.day <- mean(tot.steps.day$tot.steps, na.rm = TRUE)
## median calculation
median.steps.day <- median(tot.steps.day$tot.steps, na.rm = TRUE)
int.mean <- data %>%
group_by(interval) %>%
summarise(mean.steps = mean(steps, na.rm = TRUE))
plot2 <- ggplot(int.mean, aes(x = interval, y = mean.steps)) +
theme(legend.position = 'none') +
geom_line(aes(color = mean.steps), size = 1.4) +
geom_hline(aes(yintercept = mean(int.mean$mean.steps))) +
annotate('text', x = 4, y = 45, label = 'mean') +
labs(title = 'Mean Steps Per Interval') +
scale_x_date()
plot2
data$date <- as.Date(data$date)
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date()
plot1
## rearrange data for calculations
tot.steps.day <- data %>%
group_by(date) %>%
summarise(tot.steps = sum(steps))
## mean calculation
mean.steps.day <- mean(tot.steps.day$tot.steps, na.rm = TRUE)
## median calculation
median.steps.day <- median(tot.steps.day$tot.steps, na.rm = TRUE)
int.mean <- data %>%
group_by(interval) %>%
summarise(mean.steps = mean(steps, na.rm = TRUE))
plot2 <- ggplot(int.mean, aes(x = interval, y = mean.steps)) +
theme(legend.position = 'none') +
geom_line(aes(color = mean.steps), size = 1.4) +
geom_hline(aes(yintercept = mean(int.mean$mean.steps))) +
annotate('text', x = 4, y = 45, label = 'mean') +
labs(title = 'Mean Steps Per Interval') +
scale_x_date()
plot2
data <- read.csv('activity.csv')
library('lubridate')
library('ggplot2')
library('dplyr')
data$date <- as.Date(data$date)
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date()
plot1
## rearrange data for calculations
tot.steps.day <- data %>%
group_by(date) %>%
summarise(tot.steps = sum(steps))
## mean calculation
mean.steps.day <- mean(tot.steps.day$tot.steps, na.rm = TRUE)
## median calculation
median.steps.day <- median(tot.steps.day$tot.steps, na.rm = TRUE)
int.mean <- data %>%
group_by(interval) %>%
summarise(mean.steps = mean(steps, na.rm = TRUE))
plot2 <- ggplot(int.mean, aes(x = interval, y = mean.steps)) +
theme(legend.position = 'none') +
geom_line(aes(color = mean.steps), size = 1.4) +
geom_hline(aes(yintercept = mean(int.mean$mean.steps))) +
annotate('text', x = 4, y = 45, label = 'mean') +
labs(title = 'Mean Steps Per Interval') +
scale_x_date()
plot2
View(tot.steps.day)
tot.steps.day <- data %>%
group_by(date) %>%
summarise(tot.steps = sum(steps))
mean.steps.day <- mean(tot.steps.day$tot.steps, na.rm = TRUE)
median.steps.day <- median(tot.steps.day$tot.steps, na.rm = TRUE)
int.mean <- data %>%
group_by(interval) %>%
summarise(mean.steps = mean(steps, na.rm = TRUE))
plot2 <- ggplot(int.mean, aes(x = interval, y = mean.steps)) +
theme(legend.position = 'none') +
geom_line(aes(color = mean.steps), size = 1.4) +
geom_hline(aes(yintercept = mean(int.mean$mean.steps))) +
annotate('text', x = 4, y = 45, label = 'mean') +
labs(title = 'Mean Steps Per Interval') +
scale_x_date()
plot2
plot2 <- ggplot(int.mean, aes(x = interval, y = mean.steps)) +
theme(legend.position = 'none') +
geom_line(aes(color = mean.steps), size = 1.4) +
geom_hline(aes(yintercept = mean(int.mean$mean.steps))) +
annotate('text', x = 4, y = 45, label = 'mean') +
labs(title = 'Mean Steps Per Interval') +
scale_x_date()
plot2
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date()
plot1
str(data$date)
data$date <- as.POSIXct(data$date)
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_date()
plot1
plot1 <- ggplot(data, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_datetime()
plot1
plot4 <- ggplot(data3, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_datetime()
plot4
plot4 <- ggplot(data3, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_datetime()
int.mean <- data %>%
group_by(interval) %>%
summarise(mean.steps = mean(steps, na.rm = TRUE))
plot2 <- ggplot(int.mean, aes(x = interval, y = mean.steps)) +
theme(legend.position = 'none') +
geom_line(aes(color = mean.steps), size = 1.4) +
geom_hline(aes(yintercept = mean(int.mean$mean.steps))) +
annotate('text', x = 4, y = 45, label = 'mean') +
labs(title = 'Mean Steps Per Interval') +
plot2
## interval with max mean steps per day
max.int.steps <- filter(int.mean, mean.steps == max(mean.steps))
## part 3
inc.cases <- sum(!complete.cases(data))
data3 <- data
data3 <- left_join(data3, int.mean, by = 'interval')
data3$steps[which(is.na(data3$steps))] <- data3$mean.steps[is.na(data3$steps)]
plot4 <- ggplot(data3, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
theme(axis.text.x = element_text(angle = 90)) +
scale_x_datetime()
plot4
plot4 <- ggplot(data3, aes(x = date, y = steps)) +
geom_histogram(stat = 'identity') +
labs(title = "Steps Per Day", x = 'Date', y = 'Number of Steps') +
scale_x_datetime()
plot4
filter(int.mean, mean.steps == max(mean.steps))
max.int.steps <-filter(int.mean, mean.steps == max(mean.steps))
max.int.steps$interval
tot.steps.day.data3 <- data3 %>%
group_by(date) %>%
summarise(tot.steps = sum(steps))
imp.mean <- mean(tot.steps.day.data3$tot.steps)
imp.median <-median(tot.steps.day.data3$tot.steps)
imp.mean
imp.median
## part 4
data4 <- data3
data4$wday <- wday(data4$date)
length(which(data4$wday >5))
length(which(data4$wday <= 5))
data4$week.cat[which(data4$wday > 5)] <- 'weekend'
data4$week.cat[is.na(data4$week.cat)] <- 'weekday'
data4$week.cat <- as.factor(data4$week.cat)
int.data4 <- data4 %>%
group_by(week.cat, interval) %>%
summarise(mean.steps = mean(steps))
data4 <- data3
data4$wday <- wday(data4$date)
length(which(data4$wday >5))
length(which(data4$wday <= 5))
data4$week.cat[which(data4$wday > 5)] <- 'weekend'
str(data4)
rm(data4)
str(data3)
data4$wday <- wday(data4$date)
data4 <- data3
data4$wday <- wday(data4$date)
data4$week.cat[which(data4$wday > 5)] <- 'weekend'
table(data4$wday)
data4$week.cat <- NA
data4$week.cat[which(data4$wday > 5)] <- 'weekend'
data4$week.cat[is.na(data4$week.cat)] <- 'weekday'
data4$week.cat <- as.factor(data4$week.cat)
table(data4$week.cat)
int.data4 <- data4 %>%
group_by(week.cat, interval) %>%
summarise(mean.steps = mean(steps))
View(int.data4)
plot5 <- ggplot(int.data4, aes(x = interval, y = mean.steps, group = week.cat)) +
geom_line() + facet_wrap(~week.cat, ncol = 1)
plot5
plot5 <- ggplot(int.data4, aes(x = interval, y = mean.steps, group = week.cat)) +
geom_line() + facet_wrap(~week.cat, ncol = 1) +
labs(tittle = 'Weekday vs weekend: mean steps per internval', x = 'Interval', y = 'Mean steps')
plot5
plot5 <- ggplot(int.data4, aes(x = interval, y = mean.steps, group = week.cat)) +
geom_line() + facet_wrap(~week.cat, ncol = 1) +
labs(title = 'Weekday vs weekend: mean steps per internval', x = 'Interval', y = 'Mean steps')
plot5
?knitr
library('knitr')
?knit2html
install.packages("markdown")
library("markdown", lib.loc="/Library/Frameworks/R.framework/Versions/3.1/Resources/library")
library("rmarkdown", lib.loc="/Library/Frameworks/R.framework/Versions/3.1/Resources/library")
library('markdown')
detach("package:rmarkdown", unload=TRUE)