Package 'ggoutbreak'

Description

Insert a layer at the bottom of a ggplot

Usage

plot %above% layer

Arguments

Value

a ggplot

Description

Convert time period to dates

Usage

## S3 method for class 'time_period'
as.Date(x, ...)

## S3 method for class 'time_period'
as.POSIXct(x, ...)

Arguments

Value

a vector of dates representing the start of each of the input time_period entries

Functions

• as.POSIXct(time_period): Convert to a vector of POSIXct

Description

Time periods are just a zero based numeric representation of dates with a time unit baked in. This allows variable length periods (e.g. days or weeks), and fractional days to be represented in a consistent(ish) way

Usage

as.time_period(x, unit = NULL, start_date = NULL, anchor = NULL, ...)

## S3 method for class 'time_period'
c(..., recursive = F)

## S3 method for class 'time_period'
x[...]

## S3 replacement method for class 'time_period'
x[...] <- value

## S3 method for class 'time_period'
x[[...]]

## S3 replacement method for class 'time_period'
x[[...]] <- value

## S3 method for class 'time_period'
seq(from, to = from, ...)

is.time_period(x)

## S3 method for class 'time_period'
print(x, ...)

Arguments

Value

a time_period class, consisting of a vector of numbers, with attributes for time period and start_date

Functions

• c(time_period): Combine time_period

• [: Subset a time_period

• `[`(time_period) <- value: Assign values to a subset of a time_period

• [[: Get a value in a time_period

• `[[`(time_period) <- value: Assign a value in a time_period

• seq(time_period): Create a sequence using time_periods

• is.time_period(): Check is a time_period

• print(time_period): Print a time_period

Examples

# 100 weeks from 2020-01-01

tmp = as.time_period(0:100, 7, "2020-01-01")
as.Date(tmp)

range(tmp)
min(tmp)
tmp2 = as.integer(as.Date(tmp))
# testthat::expect_true(all(na.omit(tmp2-lag(tmp2)) == 7))

tmp2 = as.time_period(0:23, 1/24, "2020-01-01")
as.POSIXct(tmp2)

# convert timeseries to new "unit"
tmp = as.time_period(0:100, 7, "2020-01-01")
tmp2 = as.time_period(tmp,1)
testthat::expect_equal(as.numeric(tmp2), 0:100*7)

Description

A scales breaks generator for log1p scales

Usage

breaks_log1p(n = 5, base = 10)

Arguments

Value

a function for ggplot scale breaks

Examples

ggplot2::ggplot(ggplot2::diamonds, ggplot2::aes(x=price))+
  ggplot2::geom_density()+
  ggplot2::scale_x_continuous(trans="log1p", breaks=breaks_log1p())

Description

Generate a random probability based on features of the simulation

Usage

cfg_beta_prob_rng(probability_fn = ~0.8, kappa_fn = ~0.1)

Arguments

Value

a time dependent function that inputs a time (as a time_period) and returns an probability for each day defined by the probability_fn and kappa_fn

See Also

rbeta2()

Examples

fn = cfg_beta_prob_rng(~ ifelse(.x<=5,0.1,0.9))
fn(1:10)

Description

Get a IP generating function from time varying mean and SD of a gamma function

Usage

cfg_gamma_ip_fn(mean_fn = ~2, sd_fn = function(mean) sqrt(mean))

Arguments

Value

a time dependent function that inputs a time (as a time_period) and returns an ip delay distribution for each day defined by the mean_fn and sd_fn

Examples

fn = cfg_gamma_ip_fn(mean_fn = \(t) ifelse(t < 5, 4, 2))
# a gamma function that changes mean at time 5
fn(4)
fn(7)

Description

This is used for random sampling from the infectivity profile for times to infection, for example. There is nothing to stop you putting in a delay distribution with negative times but strange things may happen in your simulation.

Usage

cfg_ip_sampler_rng(ip = i_empirical_ip)

Arguments

Value

a function which accepts n parameter which produces random samples from the ip distribution

Examples

tmp = cfg_ip_sampler_rng(ganyani_ip_2)(10000)

# This discretised ganyani distribution is based on these figures:
# mean: 5.2 (3.78-6.78) and sd: 1.72 (0.91-3.93)
format_ip(ganyani_ip_2)

mean(tmp) # Should be about 5.2
stats::sd(tmp) # Should be about 1.72

Description

Linear function from dataframe

Usage

cfg_linear_fn(changes, ..., col_name = setdiff(colnames(changes), "t"))

Arguments

Value

a function that inputs a vector t and returns a linearly interpolated value from ⁠<col_name>⁠

Description

Step function from dataframe

Usage

cfg_step_fn(changes, ..., col_name = setdiff(colnames(changes), "t"))

Arguments

Value

a function that inputs a vector t and returns the next smallest corresponding value in ⁠<col_name>⁠ (or the first one)

Description

This is particularly designed for use within the fn_list_next_gen parameter of sim_branching_process() to allow age group contract matrices to be applied for example (assuming a categorical age).

Usage

cfg_transition_fn(transition)

Arguments

Value

a function that given an input will return samples of the output class according to the probability distributions.

Examples

age = rep(c("child","adult","elderly"),100)

fn = cfg_transition_fn(tibble::tribble(
  ~input, ~output, ~probability,
  "child", "child", 0.5,
  "child", "adult", 0.5,
  "adult", "child", 0.5,
  "adult", "adult", 0.3,
  "adult", "elderly", 0.2,
  "elderly","elderly", 0.5,
  "elderly","adult", 0.5,
))

table(fn(age),age)

Description

This function returns a random number generator from a gamma distribution that has a weekly period and configurable degree of additional variability around weekly pattern. It is suited to delays of things like testing which may depend on the day of week.

Usage

cfg_weekly_gamma_rng(
  mean = c(1, 1, 1, 1, 4, 3, 2),
  sd = sqrt(mean),
  week_starts = weekdays(as.Date("2024-10-14"))
)

Arguments

Value

a random number generator taking t time parameter and returning a duration the that time t depending on the day of the week.

Examples

fn = cfg_weekly_gamma_rng(c(1,1,1,1,4,3,2))
matrix(fn(1:42),ncol=7,byrow=TRUE)

Description

Weekly convolution distribution function

Usage

cfg_weekly_ip_fn(
  mean = c(1, 1, 1, 1, 4, 3, 2),
  sd = sqrt(mean),
  week_starts = weekdays(as.Date("2024-10-14"))
)

Arguments

Value

a time dependent function that inputs a time (as a time_period) and generates an IP delay distribution for each day varying by day of week

Examples

cat(sapply(cfg_weekly_ip_fn()(1:7),format_ip),sep = "\n")

Description

This function returns a random probability generator that has a weekly period and configurable degree of additional variability around weekly pattern. It is suited to probabilities of things like testing which may depend on the day of week.

Usage

cfg_weekly_proportion_rng(
  prob = c(0.8, 0.8, 0.8, 0.8, 0.8, 0.5, 0.5),
  kappa = 0.1,
  week_starts = weekdays(as.Date("2024-10-14"))
)

Arguments

Value

a random number generator function taking t time parameter and returning a probability of ascertainment for that time, depending on day of week etc.

Examples

fn = cfg_weekly_proportion_rng(c(0.9,0.9,0.9,0.9,0.9,0.1,0.1))
matrix(fn(1:42),ncol=7,byrow=TRUE)

Description

An infectivity profile derived from a meta-analysis of serial intervals.

Usage

data(covid_ip)

Format

A dataframe containing the following columns:

• boot (anything + default(1)) - a bootstrap identifier

• probability (proportion) - the probability of infection between previous time period until time

• time (double) - the end of the time period (in days)

Must be grouped by: boot (exactly).

A dataframe containing the following columns:

• boot (anything + default(1)) - a bootstrap identifier

• probability (proportion) - the probability of infection between previous time period until time

• tau (numeric) - the time index this probability relates to (in days)

• a0 (numeric) - the beginning of the time period

• a1 (numeric) - the end of the time period

Grouped by: boot.

1400 rows and 5 columns

Description

The probability of detecting COVID using PCR given time since infection, based on Binny et al 2023.

Usage

data(covid_test_sensitivity)

Format

A dataframe containing the following columns:

• tau (numeric) - the time column

• probability (numeric) - the probability column

• boot (integer) - the boot column

Must be grouped by: boot (and other groupings allowed).

5100 rows and 3 columns

References

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9384503/

Description

The COVID-19 viral shedding duration

Usage

data(covid_viral_shedding)

Format

A dataframe containing the following columns:

• boot (anything + default(1)) - a bootstrap identifier

• probability (proportion) - the probability of infection between previous time period until time

• tau (numeric) - the time index this probability relates to (in days)

• a0 (numeric) - the beginning of the time period

• a1 (numeric) - the end of the time period

Grouped by: boot.

2600 rows and 3 columns

References

https://www.nature.com/articles/s41467-020-20568-4 From Von Kampen et al.

Description

The counterpart to date_seq_dates(). Take an original set of data and place it within a regular time series where the periodicity of the time series may be expressed as numbers of days, weeks, months quarters, or years, and the periods are defined by an anchoring date, day of the week or by reference to the start or end of the input dates. This can either return the periods as dates or factors (e.g. for plotting) or as a time_period for analysis that relies on a numeric representation of the date or duration from the anchor.

Usage

cut_date(
  dates,
  unit,
  anchor = "start",
  output = c("date", "factor", "time_period"),
  dfmt = "%d/%b/%y",
  ifmt = "{start} — {end}",
  ...
)

Arguments

Value

a set of dates, times or a factor level, representing the start of the period the date falls into, where the period is defined by the duration and the anchor

Examples

dates = as.Date(c("2020-01-01","2020-02-01","2020-01-15","2020-02-03",NA))
fs = ggoutbreak::date_seq(dates, "2 days")
dates - cut_date(dates, "2 days")
cut_date(dates,unit="2 days", output="time_period")

# A weekly set of dates:
dates2 = Sys.Date() + floor(stats::runif(50,max=10))*7

# in this specific situation the final date is not truncated because the
# input data is seen as an exact match for the whole output period.
cut_date(dates2, "1 week", "sun", output="factor")
cut_date(dates2, dfmt = "%d/%b", output="factor", unit = "2 weeks", anchor="sun")

Description

This is useful if you want to fill in missing values that should have been observed but weren't. For example, date_seq(c(1, 2, 4, 6), 1) will return 1:6.

Usage

date_seq(x, period, ...)

Arguments

Value

a vector of the same type as the input

Examples

date_seq(c(1, 2, 4, 5, 10), 1)

Description

Derive from a vector of observation dates, a complete ordered sequence of periods in a regular time series, where the length of the periods is specified, as a number of days, weeks, years etcetera. E.g. this can convert a random set of dates to a ordered complete list of 1 week intervals (or 2 month intervals) spanning the same range as the dates. This has some interesting problems regarding where to put breaks within a month or week. Often this is either based on a specific date (e.g. yearly periods starting at 2020-01-01) or a day of week (e.g. 2 weekly periods staring on a Sunday) or maybe relative to the input time series (weekly ending on the last date of the data). There is also a problem when we consider data that may have incomplete starting and end periods, which may not be comparable to other periods, and we may need to exclude these from the result.

Usage

## S3 method for class 'Date'
date_seq(x, period = .day_interval(x), anchor = "start", complete = FALSE, ...)

Arguments

Value

a vector of dates for regular periods between the minimum and maximum of dates, with the boundaries defined by the anchor.

Examples

date_seq(as.Date(c("2020-01-01","2020-02-01","2020-01-15","2020-02-01",NA)), "2 days")

Description

This is useful if you want to fill in missing values that should have been observed but weren't. For example, date_seq(c(1, 2, 4, 6), 1) will return 1:6.

Usage

## S3 method for class 'numeric'
date_seq(x, period = 1, tol = 1e-06, ...)

Arguments

Value

a vector of the same type as the input

Examples

date_seq(c(1, 2, 4, 5, 10), 1)

Description

Derive from a vector of observation time_periods, a complete ordered sequence of periods in a regular time series, where the length of the periods is specified, as a number of days, weeks, years etc. E.g. this can convert a random set of times to a ordered complete list of 1 week intervals (or 2 month intervals) spanning the same range as the dates. This has some interesting problems regarding where to put breaks within a month or week. Often this is either based on a specific date (e.g. yearly periods starting at 2020-01-01) or a day of week (e.g. 2 weekly periods staring on a sunday) or maybe relative to the input time series (weekly ending on the last date of the data). There is also a problem when we consider data that may have incomplete starting and end periods, which may not be comparable to other periods, and we may need to exclude these from the result.

Usage

## S3 method for class 'time_period'
date_seq(x, period = attributes(x)$unit, complete = FALSE, ...)

Arguments

Value

a vector of time_periods for regular periods between the minimum and maximum of dates, with the boundaries defined by the anchor.

Examples

tmp = as.time_period(c(0,10,100), 7, "2020-01-01")
date_seq(tmp, "7 days")
date_seq(tmp, "1 day")

Description

Using a start_date and a unit specification

Usage

date_to_time(
  dates,
  unit = .day_interval(dates),
  start_date = getOption("day_zero", "2019-12-29")
)

Arguments

Value

a vector of class time_period

Examples

times = date_to_time(as.Date("2019-12-29")+0:100, "1 week")
dates = time_to_date(times)

Description

Density, distribution function, quantile function and random generation for the Beta distribution with parameters shape1 and shape2 (and optional non-centrality parameter ncp).

Usage

dbeta2(x, prob, kappa, log = FALSE)

Arguments

Value

dbeta gives the density, pbeta the distribution function, qbeta the quantile function, and rbeta generates random deviates.

Invalid arguments will result in return value NaN, with a warning.

The length of the result is determined by n for rbeta, and is the maximum of the lengths of the numerical arguments for the other functions.

The numerical arguments other than n are recycled to the length of the result. Only the first elements of the logical arguments are used.

See Also

stats::dbeta()

Examples

dbeta2(c(0.25,0.5,0.75), 0.5, 0.25)

Description

Density, distribution function, quantile function and random generation for the Gamma distribution with parameters shape and scale.

Usage

dgamma2(x, mean, sd = sqrt(mean), log = FALSE, convex = TRUE)

Arguments

Value

dgamma gives the density, pgamma gives the distribution function, qgamma gives the quantile function, and rgamma generates random deviates.

Invalid arguments will result in return value NaN, with a warning.

The length of the result is determined by n for rgamma, and is the maximum of the lengths of the numerical arguments for the other functions.

The numerical arguments other than n are recycled to the length of the result. Only the first elements of the logical arguments are used.

See Also

stats::dgamma()

Examples

dgamma2(seq(0,4,0.25), 2, 1)

Description

Density, distribution function, quantile function and random generation for the log normal distribution whose logarithm has mean equal to meanlog and standard deviation equal to sdlog.

Usage

dlnorm2(x, mean = 1, sd = sqrt(exp(1) - 1), log = FALSE)

Arguments

Details

The log normal distribution has density

$f(x) = \frac{1}{\sqrt{2\pi}\sigma x} e^{-(\log(x) - \mu)^2/2 \sigma^2}$

where $\mu$ and $\sigma$ are the mean and standard deviation of the logarithm. The mean is $E(X) = exp(\mu + 1/2 \sigma^2)$, the median is $med(X) = exp(\mu)$, and the variance $Var(X) = exp(2\mu + \sigma^2)(exp(\sigma^2) - 1)$ and hence the coefficient of variation is $\sqrt{exp(\sigma^2) - 1}$ which is approximately $\sigma$ when that is small (e.g., $\sigma < 1/2$).

Value

dlnorm gives the density, plnorm gives the distribution function, qlnorm gives the quantile function, and rlnorm generates random deviates.

The length of the result is determined by n for rlnorm, and is the maximum of the lengths of the numerical arguments for the other functions.

The numerical arguments other than n are recycled to the length of the result. Only the first elements of the logical arguments are used.

Note

The cumulative hazard $H(t) = - \log(1 - F(t))$ is -plnorm(t, r, lower = FALSE, log = TRUE).

Source

dlnorm is calculated from the definition (in ‘Details’). [pqr]lnorm are based on the relationship to the normal.

Consequently, they model a single point mass at exp(meanlog) for the boundary case sdlog = 0.

References

Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988) The New S Language. Wadsworth & Brooks/Cole.

Johnson, N. L., Kotz, S. and Balakrishnan, N. (1995) Continuous Univariate Distributions, volume 1, chapter 14. Wiley, New York.

See Also

Distributions for other standard distributions, including dnorm for the normal distribution.

Examples

dlnorm2(seq(0,4,0.25), 2, 1)

Description

Density, distribution function, quantile function and random generation for the negative binomial distribution with parameters size and prob.

Usage

dnbinom2(x, mean, sd = sqrt(mean), log = FALSE)

Arguments

Details

The negative binomial distribution with size $= n$ and prob $= p$ has density

$p(x) = \frac{\Gamma(x+n)}{\Gamma(n) x!} p^n (1-p)^x$

for $x = 0, 1, 2, \ldots$, $n > 0$ and $0 < p \le 1$.

This represents the number of failures which occur in a sequence of Bernoulli trials before a target number of successes is reached. The mean is $\mu = n(1-p)/p$ and variance $n(1-p)/p^2$.

A negative binomial distribution can also arise as a mixture of Poisson distributions with mean distributed as a gamma distribution (see pgamma) with scale parameter (1 - prob)/prob and shape parameter size. (This definition allows non-integer values of size.)

An alternative parametrization (often used in ecology) is by the mean mu (see above), and size, the dispersion parameter, where prob = size/(size+mu). The variance is mu + mu^2/size in this parametrization.

If an element of x is not integer, the result of dnbinom is zero, with a warning.

The case size == 0 is the distribution concentrated at zero. This is the limiting distribution for size approaching zero, even if mu rather than prob is held constant. Notice though, that the mean of the limit distribution is 0, whatever the value of mu.

The quantile is defined as the smallest value $x$ such that $F(x) \ge p$, where $F$ is the distribution function.

Value

dnbinom gives the density, pnbinom gives the distribution function, qnbinom gives the quantile function, and rnbinom generates random deviates.

Invalid size or prob will result in return value NaN, with a warning.

The length of the result is determined by n for rnbinom, and is the maximum of the lengths of the numerical arguments for the other functions.

The numerical arguments other than n are recycled to the length of the result. Only the first elements of the logical arguments are used.

rnbinom returns a vector of type integer unless generated values exceed the maximum representable integer when double values are returned.

Source

dnbinom computes via binomial probabilities, using code contributed by Catherine Loader (see dbinom).

pnbinom uses pbeta.

qnbinom uses the Cornish–Fisher Expansion to include a skewness correction to a normal approximation, followed by a search.

rnbinom uses the derivation as a gamma mixture of Poisson distributions, see

Devroye, L. (1986) Non-Uniform Random Variate Generation. Springer-Verlag, New York. Page 480.

See Also

Distributions for standard distributions, including dbinom for the binomial, dpois for the Poisson and dgeom for the geometric distribution, which is a special case of the negative binomial.

Examples

dnbinom2(0:5, 2, sqrt(2))

Description

The unit of doubling times is always days.

Usage

doubling_time(x, ...)

Arguments

Value

the same dataframe with additional columns for doubling time or relative doubling time plus confidence intervals.

Examples

ggoutbreak::england_covid %>%
  ggoutbreak::poisson_locfit_model(window=21) %>%
  ggoutbreak::doubling_time() %>%
  dplyr::glimpse()

Description

From Z. Du, X. Xu, Y. Wu, L. Wang, B. J. Cowling, and L. A. Meyers, ‘Serial Interval of COVID-19 among Publicly Reported Confirmed Cases’, Emerg Infect Dis, vol. 26, no. 6, pp. 1341–1343, Jun. 2020, doi: 10.3201/eid2606.200357.

Usage

data(du_serial_interval_ip)

Format

A dataframe containing the following columns:

• boot (anything + default(1)) - a bootstrap identifier

• probability (proportion) - the probability of infection between previous time period until time

• tau (numeric) - the time index this probability relates to (in days)

• a0 (numeric) - the beginning of the time period

• a1 (numeric) - the end of the time period

Grouped by: boot.

2603 rows and 5 columns

Description

The wedge distribution has a domain of 0 to 1 and has a linear probability density function over that domain.

Usage

dwedge(x, a, lower.tail = TRUE, log = FALSE)

Arguments

Details

The rwedge can be combined with quantile functions to skew standard distributions, or introduce correlation or down weight certain parts of the distribution.

Value

a vector of probabilities, quantiles, densities or samples.

Examples

pwedge(seq(0,1,0.1), a=1)
dwedge(seq(0,1,0.1), a=1)
qwedge(c(0.25,0.5,0.75), a=-1)

stats::cor(
  stats::qnorm(rwedge(1000, a=2)),
  stats::qnorm(rwedge(1000, a=-2))
)

Description

SPI-M-O used a range of different statistical and mechanistic models to produce estimates of the growth rate of the epidemic from various data sources (including with an early version of ggoutbreak).

Usage

data(england_consensus_growth_rate)

Format

A dataframe containing the following columns:

• date (date) - the date of the estimate

• low (numeric) - the lower published estimate of the growth rate

• high (numeric) - the higher published estimate of the growth rate

No mandatory groupings.

No default value.

111 rows and 3 columns

Description

SPI-M-O used a range of different statistical and mechanistic models to produce estimates of the reproduction number of the epidemic from various data sources.

Usage

data(england_consensus_rt)

Format

A dataframe containing the following columns:

• date (date) - the date of the estimate

• low (numeric) - the lower published estimate of the reproduction number

• high (numeric) - the higher published estimate of the reproduction number

No mandatory groupings.

No default value.

113 rows and 3 columns

Description

A dataset of the daily count of COVID-19 cases by age group in England downloaded from the UKHSA coronavirus API, and formatted for use in ggoutbreak. A denominator is calculated which is the overall positive count for all age groups. This data set can be used to calculate group-wise incidence and absolute growth rates and group wise proportions and relative growth rates by age group.

Usage

data(england_covid)

Format

A dataframe containing the following columns:

• date (as.Date) - the date column

• class (enum(⁠00_04⁠,⁠05_09⁠,⁠10_14⁠,⁠15_19⁠,⁠20_24⁠,⁠25_29⁠,⁠30_34⁠,⁠35_39⁠,⁠40_44⁠,⁠45_49⁠,⁠50_54⁠,⁠55_59⁠,⁠60_64⁠,⁠65_69⁠,⁠70_74⁠,⁠75_79⁠,⁠80_84⁠,⁠85_89⁠,⁠90+⁠)) - the class column

• count (numeric) - the test positives for each age group

• denom (numeric) - the test positives for all age groups

• time (time_period) - the time column

Must be grouped by: class (and other groupings allowed).

No default value.

26790 rows and 5 columns

Details

You may want england_covid_proportion instead which includes the population denominator. The denominator here is the total number of positive tests in all age groups and not the tests taken or denominators.

Description

The coronavirus.gov.uk dashboard published tests conducted and positive results as separate data sets for a range of geographies. In this case the data is combined with testing rate as denominator, and positives as count for England.

Usage

data(england_covid_pcr_positivity)

Format

A dataframe containing the following columns:

• date (date) - a daily time series

• time (time_period) - the time column

• count (numeric) - test positives in England on that day

• denom (numeric) - total tests conducted on that day

No mandatory groupings.

No default value.

1413 rows and 4 columns

Description

An age group stratified dataset from

Usage

data(england_covid_proportion)

Format

A dataframe containing the following columns:

• class (character) - the age group

• date (date) - the start date of a week

• count (numeric) - the count of COVID positives

• denom (numeric) - the number of COVID tests performed

• population (numeric) - the size of the population at this age group

• time (time_period) - the time column (weekly)

Must be grouped by: class (and other groupings allowed).

No default value.

1050 rows and 6 columns

Details

• the coronavirus.gov.uk site for positive cases aggregated to 10 year age groups and by weekly time.

• NHS test and trace date which reported regional by age group testing effort aggregated to country level.

• ONS 2021 census population aggregated to 10 year age groups.

Description

Population counts by 5 year age group for England only from the 2021 census.

Usage

data(england_demographics)

Format

A dataframe containing the following columns:

• class (enum(⁠00_04⁠,⁠05_09⁠,⁠10_14⁠,⁠15_19⁠,⁠20_24⁠,⁠25_29⁠,⁠30_34⁠,⁠35_39⁠,⁠40_44⁠,⁠45_49⁠,⁠50_54⁠,⁠55_59⁠,⁠60_64⁠,⁠65_69⁠,⁠70_74⁠,⁠75_79⁠,⁠80_84⁠,⁠85_89⁠,⁠90+⁠)) - the class column

• population (numeric) - the population count column

• baseline_proportion (numeric) - the baseline proportion is the proportion this age group makes up of the total.

Must be grouped by: class (and other groupings allowed).

No default value.

19 rows and 3 columns

Source

https://www.ons.gov.uk/file?uri=/peoplepopulationandcommunity/populationandmigration/populationestimates/datasets/populationandhouseholdestimatesenglandandwalescensus2021/census2021/census2021firstresultsenglandwales1.xlsx

Description

This includes mainly the dates of lockdowns, releases from social distancing measures and the dates that new variants were first detected.

Usage

data(england_events)

Format

A dataframe containing the following columns:

• label (character) - the event label

• start (date) - the event start date

• end (date) - the (optional) event end date

No mandatory groupings.

No default value.

13 rows and 3 columns

Description

check-in (social activity) and alerts (self isolation instruction) data from the NHS COVID-19 app, aggregated to country level on a week by week basis.

Usage

data(england_nhs_app)

Format

A dataframe containing the following columns:

• date (date) - the start date of the week

• alerts (integer) - the count of self-isolation alerts

• visits (integer) - the number of venue check-ins representing visits to social venues.

• time (time_period) - the time column

No mandatory groupings.

No default value.

137 rows and 4 columns

Description

The COVID-19 ONS infection survey took a random sample of the population and provides an estimate of the prevalence of COVID-19 that is supposedly free from ascertainment bias.

Usage

data(england_ons_infection_survey)

Format

A dataframe containing the following columns:

• date (date) - the date column

• geography (character) - the geography column

• prevalence.0.5 (numeric) - the median proportion of people in the region testing positive for COVID-19

• prevalence.0.025 (numeric) - the lower CI of the proportion of people in the region testing positive for COVID-19

• prevalence.0.975 (numeric) - the upper CI of the proportion of people in the region testing positive for COVID-19

• denom (integer) - the sample size on which this estimate was made (daily rate inferred from weekly sample sizes.)

• time (time_period) - the time column

No mandatory groupings.

No default value.

9820 rows and 7 columns

Details

The data is available here: https://www.ons.gov.uk/file?uri=/peoplepopulationandcommunity/healthandsocialcare/conditionsanddiseases/datasets/coronaviruscovid19infectionsurveydata/2023/20230310covid19infectionsurveydatasetsengland.xlsx

Description

Data from the COG-UK and Sanger centre sequencing programme. The data were made available through the Welcome foundation at Lower tier local authority level, and is weekly time series of counts per variant. Variants were assigned using the tree structure of the Pango lineage. Different sub-lineages are aggregated to the major WHO variants of concern.

Usage

data(england_variants)

Format

A dataframe containing the following columns:

• date (date) - the end date of the week

• time (time_period) - the time column

• class (enum(Other,Alpha (B.1.1.7),Delta (B.1.617.2),Delta (AY.4),Omicron (Other),Omicron (BA.2),Omicron (BA.4),Omicron (BA.5),XBB (Other),Kraken (XBB.1.5),Arcturus (XBB.1.16),Eris (EG.5.1))) - the class column

• who_class (enum(Other,Alpha,Delta,Omicron,Kraken,Arcturus,Eris)) - the who_class column

• count (numeric) - the weekly count column

• denom (numeric) - the number of sequences performed in that week

Must be grouped by: class (and other groupings allowed).

No default value.

479 rows and 6 columns

Description

Format date as dmy

Usage

fdmy(date)

Arguments

Value

the formatted date

Examples

fdmy(Sys.Date())

Description

Print a summary of an infectivity profile

Usage

format_ip(ip = i_empirical_ip)

Arguments

Value

an infectivity profile description

Examples

format_ip(ganyani_ip)

Description

A COVID-19 infectivity profile based on an Ganyani et al 2020

The Ganyani serial interval dataset, compatible with EpiEstim

Usage

data(ganyani_ip)

Format

A dataframe containing the following columns:

• boot (anything + default(1)) - a bootstrap identifier

• probability (proportion) - the probability of infection between previous time period until time

• tau (double) - the time index this probability relates to (in days)

• a0 - the beginning of the time period

• a1 - the end of the time period

Grouped by boot (exactly).

A dataframe containing the following columns:

• boot (anything + default(1)) - a bootstrap identifier

• probability (proportion) - the probability of infection between previous time period until time

• tau (numeric) - the time index this probability relates to (in days)

• a0 (numeric) - the beginning of the time period

• a1 (numeric) - the end of the time period

Grouped by: boot.

2400 rows and 5 columns

References

https://www.eurosurveillance.org/content/10.2807/1560-7917.ES.2020.25.17.2000257

Description

This version is discretised in a manner that makes it incompatible with EpiEstim.

Usage

data(ganyani_ip_2)

Format

A dataframe containing the following columns:

• boot (anything + default(1)) - a bootstrap identifier

• probability (proportion) - the probability of infection between previous time period until time

• tau (double) - the time index this probability relates to (in days)

• a0 - the beginning of the time period

• a1 - the end of the time period

Grouped by boot (exactly).

A dataframe containing the following columns:

• boot (anything + default(1)) - a bootstrap identifier

• probability (proportion) - the probability of infection between previous time period until time

• tau (numeric) - the time index this probability relates to (in days)

• a0 (numeric) - the beginning of the time period

• a1 (numeric) - the end of the time period

Grouped by: boot.

2800 rows and 5 columns

References

https://www.eurosurveillance.org/content/10.2807/1560-7917.ES.2020.25.17.2000257

Description

The x axis must be a date.

Usage

geom_events(
  events = i_events,
  event_label_size = 7,
  event_label_colour = "black",
  event_label_angle = -30,
  event_line_colour = "grey50",
  event_fill_colour = "grey50",
  hide_labels = FALSE,
  guide_axis = ggplot2::derive(),
  ...
)

Arguments

Value

a set of geoms for a time series.

Description

A dataset of the weekly count of COVID-19 cases by age group in Germany downloaded from the Robert Koch Institute Survstat service, and formatted for use in growth rates. A denominator is calculated which is the overall positive count for all age groups. This data set can be used to calculate group-wise incidence and absolute growth rates and group wise proportions and relative growth rates.

Usage

data(germany_covid)

Format

A dataframe containing the following columns:

• class (enum(⁠0–14⁠,⁠15–19⁠,⁠20–24⁠,⁠25–29⁠,⁠30–39⁠,⁠40–49⁠,⁠50–59⁠,⁠60–69⁠,⁠70–79⁠,⁠80+⁠,Unknown, .ordered=TRUE)) - the age group

• date (as.Date) - the date column

• count (integer) - the test positives for each age group

• time (time_period) - the time column

• denom (integer) - the test positives for all age groups

Must be grouped by: class (and other groupings allowed).

No default value.

2070 rows and 6 columns

Description

Derived from the Robert Koch Survstat service by comparing counts and incidence rates.

Usage

data(germany_demographics)

Format

A dataframe containing the following columns:

• class (enum(⁠0–14⁠,⁠15–19⁠,⁠20–24⁠,⁠25–29⁠,⁠30–39⁠,⁠40–49⁠,⁠50–59⁠,⁠60–69⁠,⁠70–79⁠,⁠80+⁠, .ordered=TRUE)) - the class column

• population (integer) - the population column

Must be grouped by: class (and other groupings allowed).

No default value.

10 rows and 2 columns

Description

This function augments any timeseries with a population denominator. The population data may be static estimates, or a set of estimates at time points. The population data may be grouped in which case the grouping might be geographical area or age group or gender for example. The two inputs must have compatible grouping (i.e. all the groups in the population data must be present in the timeseries).

Usage

infer_population(df = i_timeseries, pop = i_population_data)

Arguments

Value

the df timeseries with additional population column

Examples

ggoutbreak::england_covid %>%
  ggoutbreak::infer_population(ggoutbreak::england_demographics) %>%
  dplyr::glimpse()

Description

Log-scaled incidence estimates are used to generate samples of incidence. These are convolved with the infectivity profile (as a set of discrete distributions) and the result is evaluated as a fraction of population. The result is fitted to a logit-normal (using moments) and quantiles produced from samples.

Usage

infer_prevalence(
  modelled = i_incidence_model,
  pop = i_population_data,
  ip = i_discrete_ip,
  bootstraps = 1000,
  seed = Sys.time(),
  ...
)

Arguments

Value

the modelled input with additional proportion columns

Examples

tmp = ggoutbreak::england_covid %>%
  dplyr::filter(date < "2021-01-01") %>%
  time_aggregate(count=sum(count)) %>%
  ggoutbreak::poisson_locfit_model(window=21) %>%
  ggoutbreak::infer_prevalence(
     pop = 56489700,
     # N.B. timing is difficult in this example, as we are using cases.
     ip = ggoutbreak::covid_test_sensitivity
  )

if(interactive()) {
  plot_prevalence(tmp)
}

Description

This enables incidence rates are able to be compared to a baseline figure for incidence. The baseline could come for example from a population average or average incidence over time. The output is an incidence rate ratio. The incidence_baseline column is a rate of events per unit time. The time unit is expected to be the same as that of the date in modelled and this is not checked.

Usage

infer_rate_ratio(
  modelled = i_incidence_model,
  base = i_baseline_incidence_data,
  ...
)

Arguments

Value

a dataframe with incidence rate ratios for each of the classes in modelled. A dataframe containing the following columns:

• time (ggoutbreak::time_period + group_unique) - A (usually complete) set of singular observations per unit time as a time_period

• rate_ratio.0.025 (positive_double) - lower confidence limit of the rate ratio for a population group

• rate_ratio.0.5 (positive_double) - median estimate of the rate ratio for a population group

• rate_ratio.0.975 (positive_double) - upper confidence limit of the rate ratio for a population group

Any grouping allowed.

Examples

baseline = ggoutbreak::england_covid %>%
  ggoutbreak::time_aggregate() %>%
  ggoutbreak::poisson_locfit_model(window=21) %>%
  dplyr::mutate(baseline_incidence = incidence.0.5)


tmp = ggoutbreak::england_covid %>%
  ggoutbreak::poisson_locfit_model(window=21) %>%
  ggoutbreak::infer_rate_ratio(baseline) %>%
  dplyr::glimpse()

Description

This assumes that for example, case distribution proportions are stratified by a population grouping, e.g. geography or age, and we have estimates of the size of that population during that time period. Normalising by population proportion allows us to compare the relative risk of the outcome in groups, compared to the expected population risk if the outcome is evenly distributed across the population. There may be other proportions other than population fractions that may be useful to compare. At the moment this does not handle any uncertainty.

Usage

infer_risk_ratio(
  modelled = i_proportion_model,
  base = i_baseline_proportion_data,
  ...
)

Arguments

Value

a dataframe with relative risk / risk ratio columns. A dataframe containing the following columns:

• time (ggoutbreak::time_period + group_unique) - A (usually complete) set of singular observations per unit time as a time_period

• risk_ratio.0.025 (positive_double) - lower confidence limit of the excess risk ratio for a population group

• risk_ratio.0.5 (positive_double) - median estimate of the excess risk ratio for a population group

• risk_ratio.0.975 (positive_double) - upper confidence limit of the excess risk ratio for a population group

Any grouping allowed.

Examples

tmp = ggoutbreak::england_covid %>%
  ggoutbreak::proportion_locfit_model(window=21) %>%
  ggoutbreak::infer_risk_ratio(ggoutbreak::england_demographics) %>%
  dplyr::glimpse()

if(interactive()) {
  plot_growth_phase(tmp)
}

Description

Strictly integer breaks for continuous scale

Usage

integer_breaks(n = 5, ...)

Arguments

Value

a ggplot breaks function

Description

Calculate a growth rate from a reproduction number and an infectivity profile

Usage

inv_wallinga_lipsitch(
  Rt,
  y = i_empirical_ip,
  a1 = seq(0.5, length.out = length(y)),
  a0 = dplyr::lag(a1, default = 0)
)

Arguments

Value

an vector of growth rates

Examples

y=stats::pgamma(seq(0.5,length.out=50), 5,2)-stats::pgamma(c(0,seq(0.5,length.out=49)), 5,2)
inv_wallinga_lipsitch(Rt=seq(0.5,2.5,length.out=9), y=y)

Description

Check whether vector is a date

Usage

is.Date(x)

Arguments

Value

TRUE if dates, FALSE otherwise

Examples

is.Date(Sys.Date())

Description

Extract the weekday, month or quarter, or the Julian time (days since some origin). These are generic functions: the methods for the internal date-time classes are documented here.

Usage

## S3 method for class 'time_period'
julian(x, ...)

Arguments

Value

weekdays and months return a character vector of names in the locale in use, i.e., Sys.getlocale("LC_TIME").

quarters returns a character vector of "Q1" to "Q4".

julian returns the number of days (possibly fractional) since the origin, with the origin as a "origin" attribute. All time calculations in R are done ignoring leap-seconds.

Note

Other components such as the day of the month or the year are very easy to compute: just use as.POSIXlt and extract the relevant component. Alternatively (especially if the components are desired as character strings), use strftime.

See Also

DateTimeClasses, Date; Sys.getlocale("LC_TIME") crucially for months() and weekdays().

Examples

## first two are locale dependent:
weekdays(.leap.seconds)
months  (.leap.seconds)
quarters(.leap.seconds)

## Show how easily you get month, day, year, day (of {month, week, yr}), ... :
## (remember to count from 0 (!): mon = 0..11, wday = 0..6,  etc !!)

##' Transform (Time-)Date vector  to  convenient data frame :
dt2df <- function(dt, dName = deparse(substitute(dt))) {
    DF <- as.data.frame(unclass(as.POSIXlt( dt )))
    `names<-`(cbind(dt, DF, deparse.level=0L), c(dName, names(DF)))
}
## e.g.,
dt2df(.leap.seconds)    # date+time
dt2df(Sys.Date() + 0:9) # date

##' Even simpler:  Date -> Matrix - dropping time info {sec,min,hour, isdst}
d2mat <- function(x) simplify2array(unclass(as.POSIXlt(x))[4:7])
## e.g.,
d2mat(seq(as.Date("2000-02-02"), by=1, length.out=30)) # has R 1.0.0's release date


## Julian Day Number (JDN, https://en.wikipedia.org/wiki/Julian_day)
## is the number of days since noon UTC on the first day of 4317 BCE.
## in the proleptic Julian calendar.  To more recently, in
## 'Terrestrial Time' which differs from UTC by a few seconds
## See https://en.wikipedia.org/wiki/Terrestrial_Time
julian(Sys.Date(), -2440588) # from a day
floor(as.numeric(julian(Sys.time())) + 2440587.5) # from a date-time

Description

Create a set of labels for a time period based on the start and duration of the period. The format is configurable using the start and end dates and the dfmt and ifmt parameters, however if the time period has names then these are used in preference.

Usage

## S3 method for class 'time_period'
labels(
  object,
  ...,
  dfmt = "%d/%b",
  ifmt = "{start} — {end}",
  na.value = "Unknown"
)

Arguments

Value

a set of character labels for the time

Examples

eg = as.time_period(Sys.Date()+0:10*7, anchor="start")
labels(eg)
labels(eg, ifmt="{start}", dfmt="%d/%b/%y")
labels(eg, ifmt="until {end}", dfmt="%d %b %Y")

# labels retained in constructor:
eg2 = Sys.Date()+0:10*7
names(eg2) = paste0("week ",0:10)
labels(eg2)
labels(as.time_period(eg2, anchor="start"))

Description

Perform logit scaling with correct axis formatting. To not be used directly but with ggplot (e.g. ggplot2::scale_y_continuous(trans = "logit") )

Usage

logit_trans(n = 5, ...)

Arguments

Value

A scales object

Examples

library(ggplot2)
library(tibble)

tibble::tibble(pvalue = c(0.001, 0.05, 0.1), fold_change = 1:3) %>%
 ggplot2::ggplot(aes(fold_change , pvalue)) +
 ggplot2::geom_point() +
 ggplot2::scale_y_continuous(trans = "logit")

Description

Recover a long format infectivity profile from an EpiEstim style matrix

Usage

make_empirical_ip(omega, normalise = TRUE)

Arguments

Value

a long format ip delay distribution

Examples

format_ip(make_empirical_ip(c(0,0,1,1,1,2,2,2,1,1)))

Description

The infectivity profile is typically fitted to data by MCMC and reported as median and 95% credible intervals, of the mean, and the SD of (usually_ a gamma distribution. This function generates a discrete infectivity probability distribution representing the chance that an infectee was infected on any specific day after the infector was infected (given that the infectee was infected).

Usage

make_gamma_ip(
  median_of_mean,
  lower_ci_of_mean = median_of_mean,
  upper_ci_of_mean = median_of_mean,
  median_of_sd = sqrt(median_of_mean),
  lower_ci_of_sd = median_of_sd,
  upper_ci_of_sd = median_of_sd,
  correlation = NA,
  n_boots = 100,
  epiestim_compat = FALSE,
  epiestim_sampler = epiestim_compat,
  z_crit = 0.95
)

Arguments

Details

EpiEstim generates these distributions by sampling from a truncated normal distribution for both mean and sd. The means and sds thus produced are discretised using a gamma distribution offset by 1 day, to enforce that the probability of infection on day zero is zero.

This constraint changes the shape of the distribution somewhat and may cause a small bias (although there is no ground truth to evaluate). A different sampling and discretisation strategy is provided. The sampler uses log-normal distributions for both mean and SD with a degree of correlation. The discretizer assigns probabilities direct from the CDF of the gamma distribution without offset. This results in non zero values for the probability at time zero and can only be used with Rt estimation methods that can handle zero/negative serial intervals (e.g. rt_from_incidence or rt_from_renewal, or rt_from_growth_rate).

Value

a long format infectivity profile data frame, or a list of dataframes if input is a vector.

Examples

# COVID-19 estimates from Ganyani et al 2020.
tmp = make_gamma_ip(5.2, 3.78, 6.78, 1.72, 0.91, 3.93,
  epiestim_sampler=FALSE, epiestim_compat=FALSE)

tmp %>%
  dplyr::group_by(boot) %>%
  dplyr::summarise(
    mean = sum(tau*probability),
    sd = sqrt(sum((tau-sum(tau*probability))^2*probability))
  ) %>%
  dplyr::summarise(
    mean = sprintf("%1.2f [%1.2f-%1.2f]",
      stats::quantile(mean,0.5),
      stats::quantile(mean,0.025),
      stats::quantile(mean,0.975)),
    sd = sprintf("%1.2f [%1.2f-%1.2f]",
      stats::quantile(sd,0.5),
      stats::quantile(sd,0.025),
      stats::quantile(sd,0.975))
  )

if(interactive()) {
  plot_ip(tmp, alpha=0.1) +
    ggplot2::coord_cartesian(xlim=c(0,15))
}

means = c(3,4,5)
ips = make_gamma_ip(means)

if (interactive()) {
  purrr::map2(ips,means, ~ .x %>% dplyr::mutate(label = sprintf("Mean: %1.2f",.y))) %>%
    purrr::map( ~ plot_ip(.x,alpha=0.1)+ggplot2::facet_wrap(~label))
}

Description

The infectivity profile is typically fitted to data by MCMC as a gamma distribution. This function generates a discrete infectivity probability distribution representing the chance that an infectee was infected on any specific day after the infector was infected (given that the infectee was infected), from posterior samples.

Usage

make_posterior_ip(
  ...,
  mean,
  sd,
  shape,
  rate,
  scale,
  epiestim_compat = FALSE,
  n_boots = 100
)

Arguments

Details

If using EpiEstim and coarseDataTools::dic.fit.mcmc the output of the MCMC will be a S4 object with a samples slot, containing a dataframe of shape=var1 and scale=var2 columns. to use this output with make_posterior_ip invoke it like this:

do.call(make_posterior_ip, SI_fit_clever@samples %>% dplyr::rename(shape=var1, scale=var2))

N.b. only one combination of mean and sd, shape and rate, or shape and scale, are required.

Value

a long format ip delay distribution

Examples

tmp = make_posterior_ip(
  mean = stats::rnorm(100,5,0.1),
  sd = stats::rnorm(100,1.5,0.1)
)
tmp %>% dplyr::glimpse()
if (interactive()) plot_ip(tmp)

Description

Suits larger contact tracing data sets where there is a delay between 2 events which may or may not be precisely known.

Usage

make_resampled_ip(
  tau,
  min_tau = pmax(tau - 0.5, truncate),
  max_tau = tau + 0.5,
  add_noise = TRUE,
  truncate = 0,
  n_boots = 100,
  seed = Sys.time()
)

Arguments

Value

a long format ip delay distribution

Examples

tau = rgamma2(100, 5,2)
ip = make_resampled_ip(min_tau = tau-1, max_tau = tau+1, seed = 100)
if(interactive()) {
  plot_ip(ip,alpha=0.1)
}

Description

max.Date returns an integer and -Inf for a set of NA dates. This is usually inconvenient.

Usage

max_date(x, ...)

Arguments

Value

a date. '0001-01-01“ if there is no well defined minimum.

Examples

max_date(NA)

Description

min.Date returns an integer and Inf for a set of NA dates. This is usually inconvenient.

Usage

min_date(x, ...)

Arguments

Value

a date. 9999-12-31 if there is no well defined minimum.

Examples

min_date(NA)

Description

Extract the weekday, month or quarter, or the Julian time (days since some origin). These are generic functions: the methods for the internal date-time classes are documented here.

Usage

## S3 method for class 'time_period'
months(x, abbreviate = FALSE)

Arguments

Value

weekdays and months return a character vector of names in the locale in use, i.e., Sys.getlocale("LC_TIME").

quarters returns a character vector of "Q1" to "Q4".

julian returns the number of days (possibly fractional) since the origin, with the origin as a "origin" attribute. All time calculations in R are done ignoring leap-seconds.

Note

Other components such as the day of the month or the year are very easy to compute: just use as.POSIXlt and extract the relevant component. Alternatively (especially if the components are desired as character strings), use strftime.

See Also

DateTimeClasses, Date; Sys.getlocale("LC_TIME") crucially for months() and weekdays().

Examples

## first two are locale dependent:
weekdays(.leap.seconds)
months  (.leap.seconds)
quarters(.leap.seconds)

## Show how easily you get month, day, year, day (of {month, week, yr}), ... :
## (remember to count from 0 (!): mon = 0..11, wday = 0..6,  etc !!)

##' Transform (Time-)Date vector  to  convenient data frame :
dt2df <- function(dt, dName = deparse(substitute(dt))) {
    DF <- as.data.frame(unclass(as.POSIXlt( dt )))
    `names<-`(cbind(dt, DF, deparse.level=0L), c(dName, names(DF)))
}
## e.g.,
dt2df(.leap.seconds)    # date+time
dt2df(Sys.Date() + 0:9) # date

##' Even simpler:  Date -> Matrix - dropping time info {sec,min,hour, isdst}
d2mat <- function(x) simplify2array(unclass(as.POSIXlt(x))[4:7])
## e.g.,
d2mat(seq(as.Date("2000-02-02"), by=1, length.out=30)) # has R 1.0.0's release date


## Julian Day Number (JDN, https://en.wikipedia.org/wiki/Julian_day)
## is the number of days since noon UTC on the first day of 4317 BCE.
## in the proleptic Julian calendar.  To more recently, in
## 'Terrestrial Time' which differs from UTC by a few seconds
## See https://en.wikipedia.org/wiki/Terrestrial_Time
julian(Sys.Date(), -2440588) # from a day
floor(as.numeric(julian(Sys.time())) + 2440587.5) # from a date-time

Description

Takes a list of times, classes and counts, e.g. a COGUK variant like data set with time, (multinomial) class (e.g. variant) and count being the count in that time period. Fits a quadratic B-spline on time to the proportion of the data using nnet::multinom, with approx one degree of freedom per class and per window units of the time series

Usage

multinomial_nnet_model(
  d = i_multinomial_input,
  ...,
  window = 14,
  frequency = "1 day",
  predict = TRUE
)

Arguments

Value

a new dataframe with time (as a time period), class, and proportion.0.5, or a model object

Examples

if (interactive()) {
  # not run due to long running
  tmp = ggoutbreak::england_covid %>%
    dplyr::filter(date > "2022-01-01") %>%
    ggoutbreak::multinomial_nnet_model(window=21) %>%
    dplyr::glimpse()
}

Description

This assumes positive disease counts are stratified by a population grouping, e.g. geography or age, and we have estimates of the size of that population during that time period. Normalising by population size allows us to compare groups.

Usage

normalise_count(
  raw = i_incidence_data,
  pop = i_population_data,
  ...,
  population_unit = 1e+05,
  normalise_time = FALSE
)

Arguments

Value

a dataframe with incidence rates per unit capita. A dataframe containing the following columns:

• population (positive_integer) - Size of population

• count (positive_integer) - Positive case counts associated with the specified time frame

• time (ggoutbreak::time_period + group_unique) - A (usually complete) set of singular observations per unit time as a time_period

• population_unit (double) - The population unit on which the per capita incidence rate is calculated

• time_unit (lubridate::as.period) - The time period over which the per capita incidence rate is calculated

Any grouping allowed.

Examples

tmp = ggoutbreak::england_covid %>%
  ggoutbreak::normalise_count(ggoutbreak::england_demographics) %>%
  dplyr::glimpse()

Description

This assumes positive disease counts are stratified by a population grouping, e.g. geography or age, and we have estimates of the size of that population during that time period. Normalising by population size allows us to compare groups.

Usage

normalise_incidence(
  modelled = i_incidence_model,
  pop = i_population_data,
  ...,
  population_unit = 1e+05,
  normalise_time = FALSE
)

Arguments

Value

a dataframe with incidence rates per unit capita. A dataframe containing the following columns:

• time (ggoutbreak::time_period + group_unique) - A (usually complete) set of singular observations per unit time as a time_period

• incidence.per_capita.fit (double) - an estimate of the incidence per capita rate on a log scale

• incidence.per_capita.se.fit (positive_double) - the standard error of the incidence per capita rate estimate on a log scale

• incidence.per_capita.0.025 (positive_double) - lower confidence limit of the incidence per capita rate (true scale)

• incidence.per_capita.0.5 (positive_double) - median estimate of the incidence per capita rate (true scale)

• incidence.per_capita.0.975 (positive_double) - upper confidence limit of the incidence per capita rate (true scale)

• population_unit (double) - The population unit on which the per capita incidence rate is calculated

• time_unit (lubridate::as.period) - The time period over which the per capita incidence rate is calculated

Any grouping allowed.

Examples

tmp = ggoutbreak::england_covid %>%
  ggoutbreak::poisson_locfit_model(window=21) %>%
  ggoutbreak::normalise_incidence(ggoutbreak::england_demographics) %>%
  dplyr::glimpse()

Description

Density, distribution function, quantile function and random generation for the Beta distribution with parameters shape1 and shape2 (and optional non-centrality parameter ncp).

Usage

pbeta2(q, prob, kappa, lower.tail = TRUE, log.p = FALSE)

Arguments

Value

dbeta gives the density, pbeta the distribution function, qbeta the quantile function, and rbeta generates random deviates.

Invalid arguments will result in return value NaN, with a warning.

The length of the result is determined by n for rbeta, and is the maximum of the lengths of the numerical arguments for the other functions.

The numerical arguments other than n are recycled to the length of the result. Only the first elements of the logical arguments are used.

See Also

stats::pbeta()

Examples

pbeta2(c(0.25,0.5,0.75), 0.5, 0.25)

Description

Density, distribution function, quantile function and random generation for the Gamma distribution with parameters shape and scale.

Usage

pgamma2(
  q,
  mean,
  sd = sqrt(mean),
  lower.tail = TRUE,
  log.p = FALSE,
  convex = TRUE
)

Arguments

Value

dgamma gives the density, pgamma gives the distribution function, qgamma gives the quantile function, and rgamma generates random deviates.

Invalid arguments will result in return value NaN, with a warning.

The length of the result is determined by n for rgamma, and is the maximum of the lengths of the numerical arguments for the other functions.

The numerical arguments other than n are recycled to the length of the result. Only the first elements of the logical arguments are used.

See Also

stats::pgamma()

Examples

pgamma2(seq(0,4,0.25), 2, 1)

Description

Density, distribution function, quantile function and random generation for the log normal distribution whose logarithm has mean equal to meanlog and standard deviation equal to sdlog.

Usage

plnorm2(q, mean = 1, sd = sqrt(exp(1) - 1), lower.tail = TRUE, log.p = FALSE)

Arguments

Details

The log normal distribution has density

$f(x) = \frac{1}{\sqrt{2\pi}\sigma x} e^{-(\log(x) - \mu)^2/2 \sigma^2}$

where $\mu$ and $\sigma$ are the mean and standard deviation of the logarithm. The mean is $E(X) = exp(\mu + 1/2 \sigma^2)$, the median is $med(X) = exp(\mu)$, and the variance $Var(X) = exp(2\mu + \sigma^2)(exp(\sigma^2) - 1)$ and hence the coefficient of variation is $\sqrt{exp(\sigma^2) - 1}$ which is approximately $\sigma$ when that is small (e.g., $\sigma < 1/2$).

Value

dlnorm gives the density, plnorm gives the distribution function, qlnorm gives the quantile function, and rlnorm generates random deviates.

The length of the result is determined by n for rlnorm, and is the maximum of the lengths of the numerical arguments for the other functions.

The numerical arguments other than n are recycled to the length of the result. Only the first elements of the logical arguments are used.

Note

The cumulative hazard $H(t) = - \log(1 - F(t))$ is -plnorm(t, r, lower = FALSE, log = TRUE).

Source

dlnorm is calculated from the definition (in ‘Details’). [pqr]lnorm are based on the relationship to the normal.

Consequently, they model a single point mass at exp(meanlog) for the boundary case sdlog = 0.

References

Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988) The New S Language. Wadsworth & Brooks/Cole.

Johnson, N. L., Kotz, S. and Balakrishnan, N. (1995) Continuous Univariate Distributions, volume 1, chapter 14. Wiley, New York.

See Also

Distributions for other standard distributions, including dnorm for the normal distribution.

Examples

plnorm2(seq(0,4,0.25), 2, 1)

Description

Plot a raw case counts as a histogram

Usage

plot_cases(
  raw = i_timestamped,
  ...,
  mapping = .check_for_aes(raw, ..., class_aes = "fill"),
  events = i_events
)

Arguments

Value

a ggplot object

Examples

# 50 random times:
tmp = tibble::tibble(
  time = as.time_period( sample.int(10,50,replace=TRUE) ,"1 day"),
  class = rep(c("one","two","three"), length.out=50)
)

if(interactive()) {
  plot_cases(tmp)
}

Description

Plot a raw case count timeseries

Usage

plot_counts(
  raw = i_incidence_data,
  ...,
  mapping = .check_for_aes(raw, ...),
  events = i_events
)

Arguments

Value

a ggplot object

Examples

# example code

tmp = ggoutbreak::england_covid %>%
  time_aggregate(count=sum(count)) %>%
  normalise_count(pop=56489700, population_unit=1000, normalise_time=TRUE)

# normalised by England population (56489700 people)

if(interactive()) {
  plot_counts(tmp, colour="blue",size=0.25)
}

Description

Plot an incidence or proportion versus growth phase diagram

Usage

plot_growth_phase(
  modelled = i_timestamped,
  timepoints = NULL,
  duration = max(dplyr::count(modelled)$n),
  interval = 7,
  mapping = if (interfacer::is_col_present(modelled, class)) ggplot2::aes(colour = class)
    else ggplot2::aes(),
  cis = TRUE,
  ...
)

Arguments

Value

a ggplot

Examples

tmp = ggoutbreak::england_covid %>%
  time_aggregate(count=sum(count))

tmp_pop = ggoutbreak::england_demographics %>%
  dplyr::ungroup() %>%
  dplyr::summarise(population = sum(population))

# If the incidence is normalised by population
tmp2 = tmp %>%
  poisson_locfit_model() %>%
  normalise_incidence(tmp_pop)

timepoints = as.Date(c("Lockdown 1" = "2020-03-30", "Lockdown 2" = "2020-12-31"))

if(interactive()) {
  plot_growth_phase(tmp2, timepoints, duration=108)
}

Description

Growth rate timeseries diagram

Usage

plot_growth_rate(
  modelled = i_timeseries,
  ...,
  mapping = .check_for_aes(modelled, ...),
  events = i_events
)

Arguments

Value

a ggplot

Examples

# example code
tmp = ggoutbreak::england_covid %>%
  time_aggregate(count=sum(count))

tmp_pop = ggoutbreak::england_demographics %>%
  dplyr::ungroup() %>%
  dplyr::summarise(population = sum(population))

# If the incidence is normalised by population
tmp2 = tmp %>%
  poisson_locfit_model() %>%
  normalise_incidence(tmp_pop)

if(interactive()) {
  plot_growth_rate(tmp2,colour="blue")
}

tmp3 = ggoutbreak::england_covid %>%
  proportion_locfit_model()

if(interactive()) {
  plot_growth_rate(tmp3)
}

Description

Plot an incidence timeseries

Usage

plot_incidence(
  modelled = i_incidence_model,
  raw = i_incidence_data,
  ...,
  mapping = .check_for_aes(modelled, ...),
  events = i_events
)

Arguments