Bundled datasets

Bundled datasets

amorem ships the event logs and covariates below, each loadable with data(...). The tables and figures on this page are computed from them when the page is built. The data catalogue documents a wider collection, including datasets whose licences do not allow amorem to redistribute them.

Event logs

object	data	kind	events	actors	span
classroom_events	Classroom (McFarland 2001)	face-to-face, minutes	691	20	43.9 minutes
social_evolution_calls	Social Evolution calls (Madan et al. 2012)	phone calls	439	54	42.1 days
social_evolution_friendship	Social Evolution friendship survey	tie changes	766	76	40.0 days
radoslaw_email	Manufacturing company email (Nurek & Michalski 2020)	email	82,927	167	271 days
college_msg	CollegeMsg (Panzarasa et al. 2009)	instant messages	59,835	1,899	194 days
email_eu_core	Email-EU-core, one department (Paranjape et al. 2017)	email	12,216	89	802 days
copenhagen_calls	Copenhagen Networks Study calls	phone calls	3,600	536	28.0 days
copenhagen_sms	Copenhagen Networks Study text messages	text messages	24,333	568	28.0 days
us_leader_visits	US leader-to-leader visits 1945-2019	state visits	3,945	197	27,183 days
football_results	Men’s international football since 1872	matches	49,945	337	56,192 days
ucdp_dyads	UCDP armed conflict dyads 1946-2025	conflict dyad-years	3,518	704	79.0 years
alien_invasions	Alien species first records 1880-2005	species -> region	11,730	3,188	125 years

congress_bills_118 holds hyperevents: each of its 16,213 bills has one sponsor and a set of cosponsors (mean 10.0, largest 331), from 2023-01-03 to 2025-01-03. Actor attributes come in classroom_actors, social_evolution_actors, copenhagen_actors, congress_members_118 and radoslaw_hierarchy.

What each log looks like

For each event log: the network of the actors in its busiest pairs, then when the 30 most active of them are active. The data catalogue adds a close-up of single events and the counting processes of the busiest pairs.

classroom_events

The 20 actors of the busiest pairs, out of 20; events between two of them are 100.0% of all events. Each actor’s three strongest ties are drawn (39 of 73 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 20 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 691 events.

social_evolution_calls

The 54 actors of the busiest pairs, out of 54; events between two of them are 100.0% of all events. Each actor’s three strongest ties are drawn (61 of 64 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 439 events.

radoslaw_email

The 60 actors of the busiest pairs, out of 167; events between two of them are 64.9% of all events. Each actor’s three strongest ties are drawn (127 of 1,020 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 82,876 events.

college_msg

The 60 actors of the busiest pairs, out of 1,899; events between two of them are 8.9% of all events. Each actor’s three strongest ties are drawn (116 of 226 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 59,835 events.

email_eu_core

The 60 actors of the busiest pairs, out of 89; events between two of them are 89.4% of all events. Each actor’s three strongest ties are drawn (130 of 686 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 12,216 events.

copenhagen_calls

The 60 actors of the busiest pairs, out of 536; events between two of them are 36.0% of all events. Each actor’s three strongest ties are drawn (38 of 38 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 3,600 events.

copenhagen_sms

The 60 actors of the busiest pairs, out of 568; events between two of them are 56.7% of all events. Each actor’s three strongest ties are drawn (45 of 45 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 24,333 events.

us_leader_visits

The 60 actors of the busiest pairs, out of 197; events between two of them are 74.0% of all events. Each actor’s three strongest ties are drawn (59 of 59 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 3,945 events.

football_results

The 60 actors of the busiest pairs, out of 337; events between two of them are 23.7% of all events. Each actor’s three strongest ties are drawn (108 of 820 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 49,945 events.

ucdp_dyads

The 60 actors of the busiest pairs, out of 704; events between two of them are 31.2% of all events. Each actor’s three strongest ties are drawn (49 of 51 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 3,518 events.

alien_invasions

The 60 actors of the busiest pairs, out of 3,188; events between two of them are 1.2% of all events. Each actor’s three strongest ties are drawn (105 of 145 pairs that ever interacted): wider, darker lines carry more events, larger dots are more active actors, and colours are groups found by modularity (Louvain).

Each row is one of the 30 most active actors of the network, coloured by its group there; a cell is darker the more events (with anyone) the actor took part in during that stretch of time. The grey bars on top count all 11,730 events.

congress_bills_118

Each row is one of the 40 actors who take part in most of the 16,213 hyperevents, coloured by group (modularity on co-membership); a cell is darker the more hyperevents the actor joined in that stretch of time. The grey bars on top count all hyperevents.

Who is active

Share of all events in which the most active 10% of actors take part, and the Gini coefficient of actor activity (0 when all actors are equally active):

object	events with the top 10% of actors	Gini
classroom_events	23.4%	0.29
social_evolution_calls	57.1%	0.68
social_evolution_friendship	27.1%	0.40
radoslaw_email	40.9%	0.62
college_msg	60.2%	0.75
email_eu_core	34.3%	0.53
copenhagen_calls	42.8%	0.59
copenhagen_sms	61.3%	0.73
us_leader_visits	72.0%	0.79
football_results	30.2%	0.54
ucdp_dyads	58.9%	0.70
alien_invasions	62.7%	0.70

Logs with highly concentrated activity are where count statistics carry sender and receiver activity rather than dyadic history; see Analyses of bundled event logs for a comparison with and without a sender frailty.

Global covariates

• enso_nino34: tree-ring reconstruction of the winter Niño3.4 anomaly, 1301-2005 (see vignette("species-invasion")); oni: the instrumental Oceanic Niño Index since 1950.
• daily_weather: daily temperature and precipitation at Boston (Social Evolution, 2008), Santa Ana (CollegeMsg, 2004), and Warsaw and Wroclaw (manufacturing email, 2010).
• public_holidays: public holidays for the same countries and years.

They take one value at a time for every pair, so their effects are estimated with time-shifted sampling (sample_non_events(shift = "exponential")); the email case study does this with the clock.

dist_matrix holds distances between 56 US states and territories, used by the validation experiments.

Time conventions

Event times are days since the first event, except classroom_events (minutes since the start of the class), ucdp_dyads (year) and alien_invasions (years start and stop). Where the source gives clock time, attr(x, "unix_origin") holds the Unix time of time = 0:

format(as.POSIXct(attr(radoslaw_email, "unix_origin"), origin = "1970-01-01",
                  tz = "Europe/Warsaw"), usetz = TRUE)

## [1] "2010-01-02 17:40:10 CET"

format(as.POSIXct(attr(college_msg, "unix_origin"), origin = "1970-01-01",
                  tz = "America/Los_Angeles"), usetz = TRUE)

## [1] "2004-04-15 07:56:01 PDT"

Sources and licences

object	source	licence
radoslaw_email, radoslaw_hierarchy	Harvard Dataverse doi:10.7910/DVN/6Z3CGX	CC0 1.0
copenhagen_*	Figshare doi:10.6084/m9.figshare.7267433	MIT
congress_bills_118, congress_members_118	US GPO govinfo BILLSTATUS bulk data	public domain (US Government work)
us_leader_visits	Harvard Dataverse doi:10.7910/DVN/2ZNR5R	CC0 1.0
ucdp_dyads	Uppsala Conflict Data Program	CC BY 4.0
football_results	github.com/martj42/international_results	CC0 1.0
alien_invasions, alien_mammals	Dryad doi:10.5061/dryad.x69p8czpv	CC0 1.0
daily_weather, oni, enso_nino34	NOAA NCEI and CPC	public domain (US Government work)
public_holidays	Nager.Date API	dates and names (facts)
dist_matrix	US Census TIGER/Line	public domain (US Government work)
college_msg, email_eu_core	SNAP (Stanford)	no licence stated (citation requested)
classroom_events, classroom_actors	networkDynamic R package	package licence GPL-3
social_evolution_*	goldfish R package	package licence GPL-3

Each object’s help page (?radoslaw_email, ?ucdp_dyads, …) gives the reference to cite. Please cite the original source of any dataset you use, in addition to amorem.