Demonstration datasets

Seeded synthetic datasets, made up but shaped like the data each family of the package reads, so that every tab of rmblapp() (and any example) has something realistic to run on without a download. Each call with the same name returns the same data, and the caller's random number stream is left as it was.

Usage

rmbldemo(name = NULL)

Arguments

name

The dataset, one of the names rmbldemo() lists; NULL (the default) lists them.

Value

A data frame; for "ledger" the ledger as ldgrread() returns it. With name = NULL, a data frame of name, rows and description.

Details

Every dataset is generated in R from a fixed seed, with mksyncol() for the categorical and count columns and base R's random number generators for the rest. None of it describes real people, courts or places.

court

576 rows: 16 courts by 36 months (2022 to 2024). Columns court, region, month (1 to 36), date, received, disposed, pending (the backlog carried forward), clearance (disposed per 100 received), caseload (cases received per judge), delay (median days to disposition), reformed (1 from the month a court adopted the reform) and refmonth (the month it did, NA for the eight that never did). Eight courts adopt a case-management reform in months 13, 19, 25 or 31; it lowers delay by 12 days, and the courts share a seasonal cycle and a common trend, so the parallel-trends assumption holds.

offences

1,440 rows: monthly offence counts for 10 areas, 2013 to 2024. Columns area, year, month, date, n (Poisson counts with a summer peak of about 15 percent) and pop (growing 1 percent a year). From April 2020 every area's level steps down by 28 percent and stays there.

offences_annual

120 rows: offences summed by area and year (n), with the mean population (pop).

survey

1,200 respondents of a stratified two-stage sample: 4 strata (stratum), 10 primary sampling units in each (psu), design weights (w), and 20 bootstrap replicate weights rw01 to rw20 (Rao-Wu: primary units drawn with replacement within each stratum). Variables age, sex, smoker (0/1), drinks per week, victim (0/1, victimized in the past year), trust (1 to 5) and income (with 8 percent missing and a few very large values).

fnmi

128 rows in the layout of indiex(): period (2015/2018, 2019/2022), group (First Nations, Metis, Inuit, Non-Indigenous), age, indicator (four health indicators), estimate, lower, upper (95 percent) and quality (A to E by coefficient of variation; F, with the estimate and its interval suppressed, above 33.3 percent).

otis

144 rows: admissions to 12 institutions in 2013 to 2024, as a stock and flow table. Columns inst, cd (census division), region, year, people (admissions), days (days in custody of those admitted) and releases. Lengths of stay are log-normal and drift up after 2019.

air

2,016 rows: hourly NO2 at 6 monitors for 14 days around one stack (10 g/s, effective height 50 m). Columns monitor, x, y, z (metres from the stack), hour, wind_from (degrees), wind_speed (m/s), stability (Pasquill-Gifford class) and no2 (micrograms per cubic metre): a diurnal background plus the stack's gplume() concentration at the monitor for that hour's wind.

hawkes

About 700 event times (t, in days, over 365 days) from a self-exciting process with a baseline of 0.9 events a day, branching ratio 0.55 and an exponential kernel of rate 0.8 a day, simulated by thinning; date and district are added.

drift

3,000 rows: a reference and a current snapshot (snapshot) of 1,500 rows each, with age, income, region, visits and satisfied. In the current snapshot age is 4 years older on average, income 16 percent higher, the North region larger and satisfaction lower; visits do not change.

waits

1,000 court cases: case_id, court_type, days to disposition (a gamma body with a heavy log-normal tail) and appearances (zero-inflated Poisson).

ledger

A proof ledger of 120 theorems (proved, sorry or axiom) covering the package's functions, written to a temporary JSON file and read back with ldgrread(); four theorems carry checks that ldgrchk() runs.

See also

rmblapp(), whose tabs open on these datasets; mksyncol().

Examples

rmbldemo()
#>               name rows
#> 1            court  576
#> 2         offences 1440
#> 3  offences_annual  120
#> 4           survey 1200
#> 5             fnmi  128
#> 6             otis  144
#> 7              air 2016
#> 8           hawkes   NA
#> 9            drift 3000
#> 10           waits 1000
#> 11          ledger  120
#>                                                                  description
#> 1           Court caseload panel, 16 courts by 36 months, a staggered reform
#> 2   Monthly offence counts by area, seasonal, with a step down in April 2020
#> 3                       The offence counts by area and year, with population
#> 4    Stratified two-stage survey with design and bootstrap replicate weights
#> 5  Published health table by distinction, suppressed cells and quality flags
#> 6       Custody admissions and days by institution and year (stock and flow)
#> 7                   Hourly NO2 at six monitors around a stack, with the wind
#> 8                                   Self-exciting event stream over one year
#> 9              Two snapshots of one table, reference and current, with drift
#> 10                  Days to disposition and appearances of 1,000 court cases
#> 11                 Proof ledger of 120 theorems and the functions they cover
head(rmbldemo("court"))
#>   court  region month       date received disposed pending clearance caseload
#> 1   C01 Central     1 2022-01-01      167      171     396     102.4     55.7
#> 2   C01 Central     2 2022-02-01      158      144     410      91.1     52.7
#> 3   C01 Central     3 2022-03-01      141      125     426      88.7     47.0
#> 4   C01 Central     4 2022-04-01      143      123     446      86.0     47.7
#> 5   C01 Central     5 2022-05-01      162      156     452      96.3     54.0
#> 6   C01 Central     6 2022-06-01      142      121     473      85.2     47.3
#>   delay reformed refmonth
#> 1 105.4        0       13
#> 2 109.9        0       13
#> 3 109.8        0       13
#> 4 107.9        0       13
#> 5 109.4        0       13
#> 6 100.7        0       13
identical(rmbldemo("survey"), rmbldemo("survey"))
#> [1] TRUE