assignment1

bike_sharing_data <- read.csv("bike_sharing_data.csv")

dim(bike_sharing_data)

## [1] 17379    13

nrow(bike_sharing_data)

## [1] 17379

ncol(bike_sharing_data)

## [1] 13

str(bike_sharing_data)

## 'data.frame':    17379 obs. of  13 variables:
##  $ datetime  : chr  "1/1/2011 0:00" "1/1/2011 1:00" "1/1/2011 2:00" "1/1/2011 3:00" ...
##  $ season    : int  1 1 1 1 1 1 1 1 1 1 ...
##  $ holiday   : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ workingday: int  0 0 0 0 0 0 0 0 0 0 ...
##  $ weather   : int  1 1 1 1 1 2 1 1 1 1 ...
##  $ temp      : num  9.84 9.02 9.02 9.84 9.84 ...
##  $ atemp     : num  14.4 13.6 13.6 14.4 14.4 ...
##  $ humidity  : chr  "81" "80" "80" "75" ...
##  $ windspeed : num  0 0 0 0 0 ...
##  $ casual    : int  3 8 5 3 0 0 2 1 1 8 ...
##  $ registered: int  13 32 27 10 1 1 0 2 7 6 ...
##  $ count     : int  16 40 32 13 1 1 2 3 8 14 ...
##  $ sources   : chr  "ad campaign" "www.yahoo.com" "www.google.fi" "AD campaign" ...

bike_sharing_data[6251, "season"]

## [1] 4

bike_sharing_data[6251, 2]

## [1] 4

table(bike_sharing_data$season)

## 
##    1    2    3    4 
## 4242 4409 4496 4232

sum(bike_sharing_data$season == 1)

## [1] 4242

high_wind_threshold <- 40.23

high_wind_obs <- subset(bike_sharing_data, 
                        season %in% c(1, 2) & windspeed >= high_wind_threshold)

nrow(high_wind_obs)

## [1] 48