#### Setup ####
# Load packages
library(tidyverse) # All the tidy things
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(jsonlite) # Converting json data into data frames
##
## Attaching package: 'jsonlite'
##
## The following object is masked from 'package:purrr':
##
## flatten
library(magrittr) # Extracting items from list objects using piping grammar
##
## Attaching package: 'magrittr'
##
## The following object is masked from 'package:purrr':
##
## set_names
##
## The following object is masked from 'package:tidyr':
##
## extract
library(httr) # Interacting with HTTP verbs
#### Intro ####
# This API is useful because you can connect to see which events are going on
# in the desired city you are in. As well it provides extra details that the
# ticketmaster website does not give you
# variables needed
# api_key = YOUR api key
# zip = any zip you want to look at
# country = US
# size = 200
# page = 0
# sort = date,asc
tm_api_GET_url <-
function(api_key, country, size, page, sort) {
tm_endpoint <- "https://app.ticketmaster.com/discovery/v2/events.json?"
api_key <- paste("apikey=",api_key, sep = "")
country <- paste("&countryCode=", country, sep = "")
size <- paste("&size=", size, sep = "")
page <- paste("&page=", page, sep = "")
sort <- paste("&sort=", sort, sep = "")
tm_api_GET <-
paste(tm_endpoint, api_key, country, size, page, sort, sep = "")
return(tm_api_GET)
}
#### Calling Data ####
tm_api_GET_url(api_key = "BE6M2fykc97LL2XITU0Q1KJK8Q0GL3BL",
country = "US",
size = 200,
page = 0,
sort = "date,asc") # date.asc
## [1] "https://app.ticketmaster.com/discovery/v2/events.json?apikey=BE6M2fykc97LL2XITU0Q1KJK8Q0GL3BL&countryCode=US&size=200&page=0&sort=date,asc"
#### getting dataframe ####
tm_api_GET_df <-
function(api_key, country, size, page, sort) {
tm_api_url <- tm_api_GET_url(api_key, country, size, page, sort)
ticketmaster_df <-
tm_api_url %>%
GET() %>%
content(as = "text",
encoding = "UTF-8") %>%
fromJSON() %>%
use_series(`_embedded`) %>%
use_series(events)
return(ticketmaster_df)
}
tm_events <-
tm_api_GET_df(api_key = "BE6M2fykc97LL2XITU0Q1KJK8Q0GL3BL",
country = "US",
size = 200,
page = 0,
sort = "date,asc")
#### Looping through Multiple Pages ####
for (i in 2:5) {
tm_events <-
tm_api_GET_df(api_key = "BE6M2fykc97LL2XITU0Q1KJK8Q0GL3BL",
country = "US",
size = 200,
page = i-1,
sort = "date,asc") %>% # Subtract 1 from i to start at page 0!
bind_rows(tm_events)
# Humans love status messages!
# Give the user regular progress updates, otherwise it may look like the
# request has crashed.
paste("Page",i,"of","5","collected", sep = " ") %>%
print()
# Be gentle to the API!
# Add a sleep function at the end of each looping iteration before the last
# request to accommodate any rate limits. If no rate limit is specified in the
# documentation, a good rule is to sleep for a few seconds between requests.
if (i<5) {
Sys.sleep(3)
}
}
## [1] "Page 2 of 5 collected"
## [1] "Page 3 of 5 collected"
## [1] "Page 4 of 5 collected"
## [1] "Page 5 of 5 collected"
#### Visuals ####
# visual that shows how many eevents have safe ticketing enables
# This visual shows the distribution of events that are proteted with a
# changing barcode. This protects people from screenshotting the ticket barcode
# and sending it to someone else
tm_events$ticketing$safeTix %>%
filter(!is.na(enabled)) %>%
ggplot(aes(x = enabled))+
geom_bar()+
labs(title = "Distribution of Events that are Protected with Bar Code Changing data",
x = "TRUE/FALSE",
y = "Count")
# visual that shows how many events have all inclusive pricing like fees
# this visual shows how many events display their pricing and fees upfront.
tm_events$ticketing$allInclusivePricing %>%
filter(!is.na(enabled)) %>%
ggplot(aes(x = enabled))+
geom_bar()+
labs(title = "distribution of Events that contain pricing that displays fees before purchase",
x = "TRUE/FALSE",
y = "Count")
# Average events where safe tickeing, and all inclusive pricing is enabled
# this table shows us how many events show are listed NA under safe ticketing
# fields and allinclusive pricing. This tells us how reliable the data is.
# Right now, there are about 60% NAs in the safe ticketing field and
# 42% NAs in the all inclusive pricing. This is worth flagging because
# ticketmaster does not apply data to all of their events.
# What is worth invesigating are the events flagged with no ticket barcode
# protection.
tm_events %>%
summarise(
safetix_na = mean(is.na(ticketing$safeTix$enabled)),
safetix_yes = mean(ticketing$safeTix$enabled %in% TRUE),
aip_na = mean(is.na(ticketing$allInclusivePricing$enabled)),
aip_yes = mean(ticketing$allInclusivePricing$enabled %in% TRUE))
## safetix_na safetix_yes aip_na aip_yes
## 1 0.626 0.235 0.424 0.491
#### Creating new data frame that pulls events with no ticket protection ####
# This helps look at the events and determine how many events do not have this
# protection help. To further enhance this anaysis, i can add a city field to
# my API URL function to pull the events with no ticket protection by city.
# To ticketmaster this is an internal control issue because a average person
# like me can connect to their API to see which events do not have a ticket
# protection on that event. Someone with unethical prinicples could exploit
# this by screenshotting the bar code on his ticket and sending it to his/her
# friends... Assuming the API is telling the truth.
false_safe_tix <-
tm_events %>%
filter(tm_events$ticketing$safeTix$enabled == FALSE)