Get startedGet started for free

Comparing fare distribution by payment type

We have seen that there is no tip for cash payments. Does this mean people who pay with cash don't tip, or does it mean that tips aren't recorded when people pay with cash? For similar routes, we would expect the distributions of total fare to be identical regardless of payment type. In this exercise, we will create a quantile plot comparing the distribution of total fare by payment type and compare that with the original plot in a different facet.

A dataset amount_compare has been created for you that contains variables payment_type, amount, and amount_type. amount_type distinguishes between values that reflect a total payment vs. a payment with no tip.

This exercise is part of the course

Visualizing Big Data with Trelliscope in R

View Course

Exercise instructions

  • Inspect the amount_compare dataset prior to completing the exercise by printing it to the console to understand its structure to help with the plot specification.
  • Use geom_qq() to create a quantile plot of the total fare amount, amount. Be sure to specify distribution = stats::qunif.
  • Make sure separate quantile plots are made for each payment type by coloring by payment type such that each distribution is superposed on the same plot.
  • Show the distribution comparisons for each amount_type by faceting.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

library(ggplot2)
library(dplyr)
library(tidyr)

# Get data ready to plot
amount_compare <- tx_pop %>%
  mutate(total_no_tip = total_amount - tip_amount) %>%
  select(total_amount, total_no_tip, payment_type) %>%
  pivot_longer(!payment_type, names_to = "amount_type", values_to = "amount")

# Quantile plot
ggplot(___, aes(sample = ___, color = ___)) +
  geom_qq(distribution = ___, shape = 21) +
  facet_wrap(~ ___) +
  ylim(c(3, 20))
Edit and Run Code