We confirm below various attributes of the agents that are logged.
We will do this in data.table for speed.
rm(list=ls())
library(data.table)Read the agent data into data-table:
agent_dt <- fread("/gpfs/data/akhann16/akhann16/cadre_simulated_data/2022-12-09/agent_log.csv")
last_tick <- max(agent_dt$tick)agent_dt[tick == last_tick, .N, by=race][,"%":=round(N/sum(N)*100)][order(race)]agent_dt[tick==last_tick, .N, by=female][order(female)]#[,"%":=N/sum(N)]
#[order(race)]agebreaks <- c(18, 25, 35, 45, 55, 65)
agelabels <- c("18-24", "25-34", "35-44", "45-54", "55-64")agent_dt[tick == last_tick, .N, ]## [1] 10000setDT(agent_dt)[ , age_groups := cut(age,
breaks = agebreaks,
include.lowest = TRUE,
right = FALSE,
labels = agelabels)]
nrow(agent_dt[tick == last_tick])## [1] 10000agent_dt[tick == last_tick, .N, by=c("age_groups", "race", "female")][order(age_groups, race, female)]agent_dt[tick == last_tick, .N, by=c("race", "age_groups", "female")][order(race, age_groups)]agent_dt[tick==last_tick, .N, by=c("race", "female")][,"%":=N/sum(N)*100][order(race)]agent_dt[tick==last_tick, .N, by=c("age_groups")][,"%":=round(N/sum(N)*100)][order(age_groups)]Median age at the start:
agent_dt[tick==1, median(age)]## [1] 41Median age at the end:
nrow(agent_dt[tick==last_tick])## [1] 10000agent_dt[tick==last_tick, median(age)]## [1] 41ans <- agent_dt[tick==last_tick & race == "Black" & female == 0, .N, by=c("smoking_status")][,"prop":=round(N/sum(N)*100, 0)][]
ansagent_dt[tick == last_tick, .N, by = c("alc_use_status")][,
"%" := round(N /sum(N) * 100, 0)][
order(alc_use_status)][
]We check below the ages of new agents, and if their initial age assignments and age increments are working correctly.
How many agents are present at the last tick:
agent_dt[tick == last_tick, .N] ## [1] 10000How many agents present at tick 991 entered after model initialization?
agent_dt[tick == 991 & id > 9999, .N] ## [1] 616The mean age of agents at time by time of entry at tick 1:
agent_dt[tick == 1,
.("mean_age_today"=mean(age), .N),
by=.(entry_at_tick),
]At tick 491:
agent_dt[tick == 491,
.("mean_age_today"=mean(age), .N),
by=.(entry_at_tick),
]And at tick 991:
agent_dt[tick == 991,
.("mean_age_today"=mean(age), .N),
by=.(entry_at_tick),
]These data seem to match expectations of aging of newly entering agents. See that at tick 1, only one agent had entered after model initialization. and this agent was 18 years old.
At tick 491, this agent was 19 years old (491-365 years older than 18, rounded), and at tick 991, this agent was 21 years old (991-365 years older than 18, rounded).
So, the aging process seems to work as expected.
Number and proportion of incarcerated persons at last tick:
agent_dt[tick==last_tick, .N, by=c("current_incarceration_status")][,"prop":=round(N/sum(N)*100, 0)][]Break down number and proportions of incarcerated persons at last tick by race, sex and age:
agent_dt[tick==last_tick & current_incarceration_status == 1,
.N,
by=c("race")][,"prop":=round(N/sum(N)*100, 0)][]agent_dt[tick==last_tick & current_incarceration_status == 1,
.N,
by=c("female")][,"prop":=round(N/sum(N)*100, 0)][]agent_dt[tick==last_tick & current_incarceration_status == 1,
.N,
by=c("age_groups")][,"prop":=round(N/sum(N)*100, 0)][]agent_dt[tick==last_tick & current_incarceration_status == 1,
.N,
by=c("race", "female", "age_groups")][order(race, female, age_groups)][,"prop":=round(N/sum(N)*100, 0)][]Break down number and proportions of persons every incarcerated at last tick by race, sex and age:
ever_inc_dt <-
agent_dt[tick==last_incarceration_tick & n_incarcerations > 0,
.N,
by=c("race", "female", "age_groups")][order(race, female, age_groups)][
,"prop":=round(N/sum(N)*100, 0)][]
ever_inc_dtever_inc_dt[, colSums(.SD), .SDcols = 4:5]## N prop
## 129 104Mean number of incarcerations at last tick:
agent_dt[tick == last_tick,
.(
"mean_n_incarcerations" = mean(n_incarcerations),
"min_n_incarcerations" = min(n_incarcerations),
"max_n_incarcerations" = max(n_incarcerations),
"median_n_incarcerations" = median(n_incarcerations),
"n_ever_incarcerated_agents"=sum(n_incarcerations > 0),
.N)] Compute statistics on agents whose last release date is after their last incarceration date.
agent_dt[tick == last_tick & last_release_tick >= last_incarceration_tick,
.(
"mean_duration" = mean(last_release_tick - last_incarceration_tick),
"max_duration" = max(last_release_tick - last_incarceration_tick),
"min_duration" = min(last_release_tick - last_incarceration_tick),
"median_duration" = median(last_release_tick - last_incarceration_tick),
.N)] agent_dt[tick == last_tick,
.(
"mean_n_releases" = mean(n_releases),
"min_n_releases" = min(n_releases),
"max_n_releases" = max(n_releases),
"median_n_releases" = median(n_releases),
"n_ever_released_agents"=sum(n_releases > 0),
.N)] Compute statistics on agents whose last release date is *before* their last incarceration date.
agent_dt[tick == last_tick & last_release_tick < last_incarceration_tick,
.(
"mean_rel_dur" = mean(abs(last_release_tick - last_incarceration_tick)),
"max_rel_dur" = max(abs(last_release_tick - last_incarceration_tick)),
"min_rel_dur" = min(abs(last_release_tick - last_incarceration_tick)),
"median_rel_dur" = median(abs(last_release_tick - last_incarceration_tick)),
.N)] agent_dt[tick == last_tick,
.(
"mean_n_smkg_trans" = mean(n_smkg_stat_trans),
"max_n_smkg_trans" = max(n_smkg_stat_trans),
"min_n_smkg_trans" = min(n_smkg_stat_trans),
"median_n_smkg_trans" = median(n_smkg_stat_trans),
.N)] Smoking State Distributions:
ans <- agent_dt[tick == last_tick, .N, by=c("race", "smoking_status")][order(race)]
ans ans[, prop := N / sum(N), by = race][]ans_num_smokers <- ans[smoking_status %in% c("Former", "Current", "Never"),
.(num_smokers = sum(N)),
by = race]
ans_num_smokerssum(ans_num_smokers$num_smokers)## [1] 10000agent_dt[tick == last_tick,
.(
"mean_n_alc_trans" = mean(n_alc_use_stat_trans),
"max_n_alc_trans" = max(n_alc_use_stat_trans),
"min_n_alc_trans" = min(n_alc_use_stat_trans),
"median_n_alc_trans" = median(n_alc_use_stat_trans),
.N)] Alcohol Use State Distributions:
ans <- agent_dt[tick == last_tick, .N, by=alc_use_status]
prop <- ans$N/sum(ans$N)
cbind(ans[,1], prop)