Question 4
bike4 <- read.delim("bike_sharing_data.txt")
bike3 <- read.csv("bike_sharing_data.csv")
bike1 <- read.table("bike_sharing_data.csv", sep=",", header=TRUE)
bike2 <- read.table("bike_sharing_data.txt", sep="\t", header=TRUE)
Question 6
str(bike1)
## '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" ...
Question 7
bike1[6251,]
## datetime season holiday workingday weather temp atemp humidity
## 6251 9/23/2011 0:00 4 0 1 2 25.42 27.275 94
## windspeed casual registered count sources
## 6251 6.0032 5 23 28 Ad Campaign
Question 8
table(bike1$season)
##
## 1 2 3 4
## 4242 4409 4496 4232
Question 10
sum(bike1$season %in% c(1, 4) & bike1$windspeed >= 40, na.rm = TRUE)
## [1] 46