load data and have a look at the dataset

url <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2Factivity.zip"
download.file(url, "activity.zip")
unzip("activity.zip")
df <- read.csv("activity.csv")

str(df)
## 'data.frame':    17568 obs. of  3 variables:
##  $ steps   : int  NA NA NA NA NA NA NA NA NA NA ...
##  $ 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 ...
head(df)
##   steps       date interval
## 1    NA 2012-10-01        0
## 2    NA 2012-10-01        5
## 3    NA 2012-10-01       10
## 4    NA 2012-10-01       15
## 5    NA 2012-10-01       20
## 6    NA 2012-10-01       25

Organize data by date and make a histagram of total steps

Most users have total daily steps between 10000 and 15000. The average total steps is 10766 and the median is 10765.

df_date <- df %>% group_by(date)  %>% summarize(total_steps = sum(steps))
head(df_date)
## # A tibble: 6 × 2
##   date       total_steps
##   <chr>            <int>
## 1 2012-10-01          NA
## 2 2012-10-02         126
## 3 2012-10-03       11352
## 4 2012-10-04       12116
## 5 2012-10-05       13294
## 6 2012-10-06       15420
hist(df_date$total_steps)

summary(df_date$total_steps, na.rm=TRUE)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##      41    8841   10765   10766   13294   21194       8

Organize data by interval and explore data pattern

Find out which 5-minute interval contains the maximum number of steps The 835 interval with 206 steps

avg_df <- df %>% group_by(interval)  %>% summarize(avg_steps = mean(steps, na.rm = TRUE))
avg_df[which.max(avg_df$avg_steps),]
## # A tibble: 1 × 2
##   interval avg_steps
##      <int>     <dbl>
## 1      835      206.
ggplot(data = avg_df,
       aes(x = interval, y = avg_steps)) + geom_point(colour = "blue") + geom_line(data = avg_df, 
                                                             aes(x = interval, y = avg_steps), colour = "red")

Deal with missing values

Replace NAs by average value of steps and make a new histagram with new dataset

df_new <- replace(df, is.na(df), "37.38")
sum(is.na(df_new))
## [1] 0
df_new$steps <- as.numeric(df_new$steps)

df_new_by_date <- df_new %>% group_by(date)  %>% summarize(total_steps = sum(steps))

df_new_by_date$total_steps<- as.numeric(df_new_by_date$total_steps)

hist(df_new_by_date$total_steps)

Explore data patterns of steps on weekdays and weekends

Add another filed to define weekday and weekend and plot by two facets to compare patterns

df_new$date <- as.Date(df$date)
weekdays1 <- c('Monday', 'Tuesday','Wedesday','Thursday','Friday')

df_new$wDay <- factor((weekdays(df_new$date) %in% weekdays1), levels = c(FALSE, TRUE), labels = c('weekend','weekday'))

## another method
##library(timeDate)  isWeekday(df1$date, wday=1:5)

ggplot(data = df_new, aes( x = interval, y = steps )) + geom_point()+facet_wrap(~wDay)

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.