bike2012

Data Management

loading all the data from the directory

data = list.files(pattern="*.csv")
list2env(
  lapply(setNames(data, make.names(gsub("*.csv$", "", data))), 
         read.csv), envir = .GlobalEnv)

## <environment: R_GlobalEnv>

Merging sub datasets in to annually

listing all data in the directory

alldata <- mget(ls(pattern="^X\\d+"))

Merge all individual data from 2012

bike2012<- Reduce(smartbind,alldata)

Removing unessccary columns

bike2012<- bike2012 %>% select(Rental.Id, Bike.Id, End.Date,EndStation.Id,Start.Date,StartStation.Id)

Eliminate missing values

sapply(bike2012,function(x) sum(is.na(x)))

##       Rental.Id         Bike.Id        End.Date   EndStation.Id 
##               0              14               0               0 
##      Start.Date StartStation.Id 
##               0               0

bike2012<- na.omit(bike2012)
head(bike2012[1:5,])

##     Rental.Id Bike.Id         End.Date EndStation.Id       Start.Date
## 1:1   9340768     893 04/01/2012 00:20           169 04/01/2012 00:00
## 1:2   9345966    5621 04/01/2012 00:05           319 04/01/2012 00:01
## 1:3   9349921    4365 04/01/2012 00:12           343 04/01/2012 00:01
## 1:4   9341757    2708 04/01/2012 00:08           379 04/01/2012 00:04
## 1:5   9344212      17 04/01/2012 00:20           340 04/01/2012 00:05
##     StartStation.Id
## 1:1             224
## 1:2               3
## 1:3             311
## 1:4             225
## 1:5              88

Saving dataset

#write.table(bike2012,"bike2012.csv", sep = ",")

origin-destination matrix and station’s frquency

od<- function(data){
  odmatrix<-as.data.frame.matrix(table(data$StartStation.Id,data$EndStation.Id))
  frq<-as.data.frame(table(data$StartStation.Id,data$EndStation.Id))
  frq<-frq[with(frq, order(Freq,decreasing = T)),] 
  colnames(frq)<- c("StartStation.Id","EndStation.Id","Freq")
  print(head(odmatrix[c(1:10),c(1:10)]))
  print(head(frq[c(1:10),]))
}

od(bike2012)

##     0   1   2   3   4   5   6  7 8  9
## 1 116 319   0  36  60   4  10  1 2  5
## 2 142   1 400   0   2  15  10  1 1 12
## 3 147  12   0 100  34   2   5  1 0 45
## 4 245  12   0 100 246   1  31 16 0 86
## 5 202   0  10   0   5 437  11  1 5  9
## 6 226   4   3   1  68   3 253 70 7  5
##        StartStation.Id EndStation.Id  Freq
## 189758             191           191 16160
## 305219             307           307 10962
## 301203             303           303  8729
## 402609             406           406  5503
## 403613             407           407  5479
## 400601             404           404  4608