Metadata description

Metadata dataset contains 30 features describing 1636 buildings and 3053 meters. Code for this exploratory data analysis is available in this notebook.

• Distribution plot
• Buildings and meters per site
• Levels of categorical features
• Missing values

Distribution plot

Figure 1: Distribution plot of selected features.

Buildings an meters per site

Table 1: Number of buildings and meters per site ID.

Site	Buildings	Meters
Panther	136	299
Robin	52	67
Fox	137	306
Rat	305	305
Bear	92	92
Lamb	147	265
Eagle	106	298
Moose	15	43
Gator	74	74
Bull	124	308
Bobcat	36	116
Crow	5	15
Wolve	36	66
Hog	163	336
Peacock	47	106
Cockatoo	124	282
Shrew	9	13
Swan	21	55
Mouse	7	7

Categorical features

Table 2: Number (first row) and names of levels in each categorical feature.

site_id	primaryspaceusage	sub_primaryspaceusage	industry	subindustry	timezone
19	17	105	5	13	6
Panther	Lodging/residential	Residence Hall	Education	College/University	US/Eastern
Robin	Education	Research	Government	Animal Control	Europe/London
Fox	Office	Office	Hospitality	Public Assembly	US/Mountain
Rat	Entertainment/public assembly	Classroom	Healthcare	City, County, State	US/Pacific
Bear	Other	Stadium		Social Services	US/Central
Lamb	Retail	"Residence Hall		Hotel	Europe/Dublin
Eagle	Parking	Other		Water & Wastewater Treatment Facility
Moose	Public services	Retail		Library
Gator	Warehouse/storage	Parking Garage		Primary/Secondary School
Bull	Food sales and service	College Classroom		Other Government Buildings
Bobcat	Religious worship	College Laboratory		Hospital
Crow	Healthcare	Dormitory		Laboratory
Shrew	Utility	Gymnasium
Swan	Technology/science	Library
Wolve	Manufacturing/industrial	Police Station
Hog	Services	Museum
Peacock		Auditorium
Cockatoo		Warehouse
Mouse		Fitness Center
		Restaurant
		Student Union
		Athletic Field
		Chapel
		Sports Stadium
		Health Services
		Theater
		Primary/Secondary Classroom
		Swimming Pool
		Planetarium
		Central Plant
		Social/Meeting Hall
		K-12 School
		Other - Recreation
		Fire Station
		Other - Public Services
		Other - Education
		Other - Lodging/Residential
		Multifamily Housing
		Hospital (General Medical & Surgical)
		Retail Store
		Non-Refrigerated Warehouse
		Other - Entertainment/Public Assembly
		Parking
		Urgent Care Center/Clinic/Other Outpatient Office
		Prison/Incarceration
		Senior Care Community
		Worship Facility
		Other/Specialty Hospital
		Education
		Entertainment/public assembly
		Technology/science
		Lodging/residential
		Public services
		Utility
		Animal Kennels
		Campsites
		Community Center
		Creamatorium
		Greenhouse
		Hotel
		Industrial
		Market
		Park
		Gynasium
		Recreation Center
		Sports Facility
		Recreation Center, Community Centers
		Community Center, Community Centers
		Fire Station, Fire Stations
		Park, Community Centers
		Office, Fire Stations
		Performing Arts, Community Centers
		Conference Center
		garage
		office
		Academic
		Science Facility
		Student Center
		Residence Hall/Dormitory
		Data Centre
		School
		Hospital
		Parking: Enclosed Garage
		Animal Shelter
		Bar/Tavern
		Maintenance Repair Shop
		Parking: Open Air Ramp
		Ice Arena
		Lab Building
		Warehouse (Conditioned)
		Manufacturing Facility
		Warehouse (Unconditioned)
		Sports Arena
		Support
		Patient Care
		Dining
		Public Service
		Athletic
		Housing
		Data Center
		Religious building
		Services Plant
		Ice arena
		Laboratory

Missing values

Table 3: percentage of missing values in each feature.

Feature	% of missing values
building_id	0.00
site_id	0.00
building_id_kaggle	11.43
site_id_kaggle	2.26
primaryspaceusage	1.28
sub_primaryspaceusage	1.28
sqm	0.00
lat	14.49
lng	14.49
timezone	0.00
electricity	3.55
hotwater	88.69
chilledwater	66.08
steam	77.38
water	91.08
irrigation	97.74
solar	99.69
gas	89.18
industry	64.61
subindustry	64.61
heatingtype	86.86
yearbuilt	50.06
date_opened	98.72
numberoffloors	73.04
occupants	85.94
energystarscore	90.04
eui	81.72
site_eui	90.04
source_eui	90.04
leed_level	91.69
rating	88.75