NYC Citi Bike System Data Analysis

NYC Citi Bike is a public bicycle sharing system that serves parts of Manhattan and Brooklyn, two of the most populous boroughs of New York City. The New York Citi Bike System Data is publicly available here. The data is available for past 12 months from the current date.

Citi Bike Trip data include:

• Trip Duration (seconds)
• Start Time and Date
• Stop Time and Date
• Start Station Name
• End Station Name
• Station ID
• Station Latitude/Longitude
• Bike ID
• User Type (Customer = 24-hour pass or 7-day pass user; Subscriber = Annual Member)
• Gender (0 = unknown; 1 = male; 2 = female)
• Year of Birth

Since the location of Citi Bike Station is important variable and it was not available here, I then used Google to find out the location of Citi Bike Station in NYC. Citi Bike Station location data is available here.

I am using R to analyze 3 months (December 2013 to February 2014) of Citi Bike Trip data. The R code is stated below.

#############################################################################################
# Set working directory
setwd("/Users/Ankoor/Desktop/NYCBS")

# Read data
dec <- read.csv("2013-12 - Citi Bike trip data.csv", stringsAsFactors = FALSE)
jan <- read.csv("2014-01 - Citi Bike trip data.csv", stringsAsFactors = FALSE)
feb <- read.csv("2014-02 - Citi Bike trip data.csv", stringsAsFactors = FALSE)


# Merge data (Adding rows)
trip <- rbind(dec, jan, feb)
rm(dec, jan, feb)

# Bike station data
bikeStn <- read.csv("citibike.csv", stringsAsFactor = FALSE)

# Drop unnecessary columns from bikeStn
names(bikeStn) # Get column names in bikeStn
drop <- c("name", "streetAddress", "streetAddress.address2", "latitude", "longitude",
          "loc", "entityTitle", "X.context", "X.type", "X.id")
bikeStn <- bikeStn[, !(names(bikeStn) %in% drop)]

# Change column names in BikeStn to merge start
names(bikeStn) <- c("start.station.id", "start.totDocks", "start.hood", "start.zip")

# Merge data for start station (many to one)
trip <- merge(trip, bikeStn, by = c("start.station.id"))

# Change column names in BikeStn to merge start
names(bikeStn) <- c("end.station.id", "end.totDocks", "end.hood", "end.zip")

# Merge data for end station (many to one)
trip <- merge(trip, bikeStn, by = c("end.station.id"))
rm(bikeStn, drop)

# Plot - 1: NYC Citi Bike Route Popularity 

hood.trips <- table(trip$start.hood, trip$end.hood)
temp <- data.frame(hood.trips)
names(temp) <- c("startHood", "endHood", "Popularity")
temp <- temp[,c(2,1,3)]
names(temp) <- c("startHood", "endHood", "Popularity")

# ggplot2 library
library(ggplot2)

# Plot
pdf("NYC Citi Bike Route Popularity.pdf", width = 11, height = 11)
ggplot(temp, aes(startHood, endHood)) + geom_tile(aes(fill = Popularity), color = "black") + 
        scale_fill_gradient(low = 'white', high = 'blue') + theme(axis.text.x = element_text(
                angle = 90)) + xlab("Starting Neighborhood") + ylab("Ending Neighborhood") +
        ggtitle("NYC Citi Bike Route Popularity")
dev.off()

#############################################################################################

The above R code produces this plot. Here is the screen shot of the plot: