In dtkaplan/statPREPpackage: Calculations to support the statPREP tutorials

knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
library(lubridate)

Taxi_trips (from the statPREP package) is a subset of a much larger data set from the New York City Taxi and Limosine Commission about taxicab trips in New York City.

The unit of observation is a single trip by taxi. The recorded variables are pickup and dropoff date-times, distance of the trip (in miles), the fare amount (in dollars), and the number of passengers. From these have been derived the duration of the trip (in minutes), the hour_of_day of the start of the trip (with, e.g. 16.5 meaning 4:30pm), and the day_of_week of the trip. Also added is the fare_distance, which is the distance rounded up to the nearest 5th of a mile.

Some possible questions:

How much slower is a trip during rush hour than during the off hours?
Can you determine what the rush hours are from the data?
Are the fares being determined according to the official policy stated at the Taxi and Limosine Commission?

load("Taxi_trips.rda")
names(Taxi_trips) <- c("distance", "fare", "passengers", "pickup", "dropoff")
Taxi_trips <- Taxi_trips %>%
  mutate(duration = as.numeric(dropoff - pickup) /60,
         day_of_week = lubridate::wday(pickup, label = TRUE),
         hour_of_day = lubridate::hour(pickup) + 
           lubridate::minute(pickup) / 60,
         fare_distance = ceiling(distance * 5) / 5)
save(Taxi_trips, file = "../../data/Taxi_trips.rda")