The Visual Analytics Alphabet Series – The Data

[#1]

Because the Visual Analytics Alphabet Series was inspired at the screening of a horror movie (see A is for Aggregated Data), most of the data used in this series is horror based.

HORROR_MOVIES

HORROR_MOVIES from Kaggle, a data set of horror films from 1950 – 2022, was extracted from The Movie Database (TMDB) using the TMDB API. The Movie Database is a community built movie and TV database that contains information about movies, TV shows, cast, and community reviews.

If you would like to use the TMDB API for your own data adventures, check out the documentation.

Name	Label	Description	Unique Count	Range
id	Movie ID	Unique ID for TMDB, used to construct link to movie page	32,540
original_title	Original Title	Original movie title	30,294
title	Movie Title	Movie title	29,563
original_language	Original Lanugage	Language in which the movie was made (for example, en for English, no for Norwegian, de for German)	97
overview	Description	Description of movie	31,021
tagline	Tagline	Tagline of movie	12, 514
release_date	Release Date	Release date (mm/dd/yyyy)	10,999
poster_path	Poster Image	Unique name of the movie poster. This can be used to generate a link to the poster image.	28,049
popularity	Popularity Score	Lifetime popularity score generated by the community. For movies, this is based on daily metrics (like number of votes, number of views, times favorited, times watchlisted), release date, total votes, and the previous day’s score.		0 - 5,088.584
vote_count	# User Ratings	Number of user ratings for movie		0 - 16,900
vote_average	User Score (1-1)	Average rating for movie. Ratings range from 1 to 10 stars.		0.5 - 10
budget	Budget (in $)	Budget of movie in US dollars		$1 - $200,000,000
revenue	Revenue (in $)	Revenue made from movie in US dollars		$1 -$701.842,551
runtime	Movie Runtime (min)	Official runtime of movie (in minutes)		1 - 683
status	Movie Status	Status of movie (Released, In Production, Post Production, Planned) at time of extract (late 2022)	4
adult	<not used>	<not used>	<not used>
backdrop_path	Backdrop Image	Unique name of movie backdrop image. This can be used to generate a link to the poster image.	13,537
genre_name	Genre(s)	List of movie genres	772
collection	Collection ID	ID of the collection, used to construct link to collection page.	816
collection_name	Collection Name	Name of collection	816

A few data cleansing techniques needed to be applied to the HORROR_MOVIES table to get the data report ready:

• Several measures were set to zero when data was not available for those movies (for example, vote_average, budget, revenue, and runtime). These zeros were replaced with missing values.
• Year had to be created from release_year to join the table with KILLCOUNTS
• Some of the titles had to be modified to match the title with KILLCOUNTS 

KILLCOUNTS

KILLCOUNTS from Github, a data set of horror films from 1922-2025, was sourced from community projects (like Dead Meat, MovieBodyCounts, List of Deaths Wiki, and work done by Randal Olson.

Name	Label	Description	Unique Count	Range
title	Movie Title	Movie Title	469
year	Release Year	Release year	63
count	Kill Count	Total confirmed kills		1 - 4,295
tmdb_id	TMDB ID	The Movie Database (TMDB) unique ID	482

A few data cleansing techniques needed to be applied to the KILLCOUNTS table to get the data report ready:

• In the original table, year is stored as a category. It was converted to a date in Visual Analytics using the DateFromMDY and TreatAs functions.
  

HAUNTED_PLACES

HAUNTED_PLACES from Kaggle, a data set of haunted places in the United States was compiled by Tim Renner using The Shadowlands Haunted Places Index.

Name	Label	Description	Unique Count	Range
city	City	City where the haunted place is located	4,285
country	Country	Country where the haunted place is located (all United States)	1
description	Description	Description of the haunted place	10,979
location	Location	Name of the haunted place	9,691
state	State	US state where the haunted place is located	51
state_abbrev	state_abbrev	US two-letter state abbreviation where the haunted place is located	51
longitude	Location Longitude	Longitude of the haunted place		-164.7224104 - -66.6667528
latitude	Location Latitutde	Latitude of the haunted place		19.632069 - 66.8925886
city_longitude	City Longitude	Longitude of the city center		-164.7238888 - -67.8402316
city_latitude	City Latitude	Latitude of the city center		19.5756191 - 66.8983333

A few data cleansing techniques needed to be applied to the HAUNTED_PLACES table to get the data report ready:

• Location values were modified to ensure consistency. For example, Saint Peters Catholic Church was standardized to St Peters Catholic Church.
• Unique ID was created when importing the Microsoft Excel file by selecting Create unique ID column in the Import Data window. This creates a column that has a unique value for each row, which can be used for text analytics.
• AI was used to group locations into 9 distinct Haunting Locations:
  • Cemeteries & Graveyards
  • Homes & Residences
  • Hospitals & Asylums
  • Hotels & Lodging
  • Parks & Natural Areas
  • Roads, Bridges & Paths
  • Schools & Universities
  • Theatres & Entertainment
  • Other Buildings/Places
• AI was used to group descriptions of hauntings into 8 distinct Haunting Categories:
  • Auditory Phenomena
  • Entity-Based
  • Environmental Effects
  • Experiential States
  • Narrative/Historical
  • Physical Interactions
  • Visual Manifestations
  • Mixed/Unclassified
• AI was used to group descriptions of hauntings into 14 distinct Haunting Types:
  • Animal Spirit
  • Apparitions & Full-Body Ghosts
  • Child Spirit
  • Demonic or Malevolent Entity
  • Disembodied Sounds & Voices
  • Environmental & Emotional Sensations
  • Lights, Orbs & Shadow Phenomena
  • Location-Bound Entity
  • Poltergeist/Object Movement
  • Residual/Repeating Event
  • Sleep & Bedroom Encounters
  • Tragic Death Residual Haunting
  • Other/Mixed Phenomena
  • Unspecified

This product uses the TMDB API but is not endorsed or certified by TMDB.