Question 4: Extract the bike sharing datasets

bike1 <- read.table("bike_sharing_data.csv", sep=",", header=TRUE)
bike2 <- read.table("bike_sharing_data.txt", sep="\t", header=TRUE)
bike3 <- read.csv("bike_sharing_data.csv")
bike4 <- read.delim("bike_sharing_data.txt")

Question 5: What is the total number of observations and variables?

dim(bike1)[1]
## [1] 17379
dim(bike1)[2]
## [1] 13

Question 6: What is data type of humidity perceived by R?

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: What is the value of season in row 6251?

bike1$season[6251]
## [1] 4

Question 8: How many observations have the season as winter?

table(bike1$season)[4]
##    4 
## 4232

Question 10: How many observations having “High” wind thread condition or above during winter or spring?

subset_season <- bike1$season %in% c(1,4)
subset_wind <- bike1$wind >= 40
subset_combined <- subset_season & subset_wind
num_obs <- sum(subset_combined)
num_obs
## [1] 46