DistributionFit: General distribution fitting algorithms
In terminological/uk-covid-datatools: Functions for sourcing, cleaning and calculating Rt for uk covid timeseries data
Description
Super class
Methods
Description
General distribution fitting algorithms
General distribution fitting algorithms
Super class
ukcovidtools::PassthroughFilesystemCache -> DistributionFit
Methods
Public methods
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Inherited methods
Method new()
New distribution fitter
Usage
DistributionFit$new(
distributions = c("weibull", "gamma", "lnorm", "exp", "norm", "tnorm"),
shifted = 0,
...
)
Arguments
distributions- the distributions to fit
shifted- a shift to apply to all data
...for compatibility
Returns
Method setModels()
Usage
DistributionFit$setModels(
distributions = c("weibull", "gamma", "lnorm", "exp", "norm", "tnorm"),
shifted = 0
)
Method fromUncensoredData()
Usage
DistributionFit$fromUncensoredData(
groupedDf,
valueExpr = value,
truncate = TRUE,
bootstraps = 100,
seed = 101,
...
)
Method fromCensoredData()
Usage
DistributionFit$fromCensoredData(
groupedDf,
lowerValueExpr,
upperValueExpr,
truncate = TRUE,
bootstraps = 100,
seed = 101,
...
)
Method withSingleDistribution()
Usage
DistributionFit$withSingleDistribution(
dist,
paramDf,
bootstraps = 1000,
epiestimMode = FALSE,
...
)
Method fromBootstrappedDistributions()
Usage
DistributionFit$fromBootstrappedDistributions(
fittedDistributions,
confint = c(0.025, 0.975),
...
)
Method fromBootstrappedData()
Usage
DistributionFit$fromBootstrappedData(
bootstrappedDf,
valueExpr = value,
truncate = TRUE,
...
)
Method plot()
Usage
DistributionFit$plot(
xlim,
binwidth = 1,
summary = FALSE,
pts = 8,
facet2d = TRUE
)
Method extractFitted()
Usage
DistributionFit$extractFitted(
distFit,
isCensored,
bootstraps = 100,
seed = 101
)
Method filterModels()
Usage
DistributionFit$filterModels(...)
Method generateSamples()
Usage
DistributionFit$generateSamples(sampleExpr = 1000, seed = 101)
Method calculateDensities()
calculates a set of pdfs from bootstrapped distributions
Usage
DistributionFit$calculateDensities(x, summarise = TRUE)
Arguments
support- the range of values of X for which to calculate the density.
Returns
a list of randomly selected bootstraps from the fitted models.
Method calculateCumulativeDistributions()
calculates a set of pdfs from bootstrapped distributions
Usage
DistributionFit$calculateCumulativeDistributions(q, summarise = TRUE)
Arguments
support- the range of values of X for which to calculate the density.
Returns
a list of randomly selected bootstraps from the fitted models.
Method calculateQuantiles()
calculates a set of quantiles from bootstrapped distributions
Usage
DistributionFit$calculateQuantiles(p, summarise = TRUE)
Arguments
support- the range of values of X for which to calculate the density.
Returns
a list of randomly selected bootstraps from the fitted models.
Method discreteProbabilities()
Usage
DistributionFit$discreteProbabilities(q, summarise = TRUE)
Method discreteSurvival()
Usage
DistributionFit$discreteSurvival(q, summarise = TRUE)
Method sampledProbabilities()
Usage
DistributionFit$sampledProbabilities(q, summarise = TRUE)
Method sevenNumbers()
Usage
DistributionFit$sevenNumbers(groupedDf, colVar)
Method printDistributionSummary()
Usage
DistributionFit$printDistributionSummary(confint = c(0.025, 0.975))
Method printDistributionDetail()
Usage
DistributionFit$printDistributionDetail(confint = c(0.025, 0.975))
Method tsParameterizedConvolution()
applies a set of parameterised convolution functions groupwise to input data
Usage
DistributionFit$tsParameterizedConvolution(
groupedDf,
distributionsDf,
outputVar = "output",
valueVar = "value",
dateVar = "date",
distributionVar = "dist",
paramNameVar = "param",
paramValueVar = "paramValue",
days = 30,
timepoints = 0:days,
padLeft = NA_real_,
padRight = NA_real_
)
Arguments
groupedDf- an optionally grouped dataframe, containing at dateVar, and a valueVar to be colvolved
distributionsDf- a dataframe containing the same grouping columns as groupedDf plus "distribution", and relevant distribution parameter columns
dateVar-
days-
timepoints- the times to
padLeft- what can we assume about the run in to the current values? default NA.
Returns
a list of matrices
Method tsDiscreteConvolution()
applies a set of parameterised convolution functions groupwise to input data
Usage
DistributionFit$tsDiscreteConvolution(
groupedDf,
discreteDistDf,
outputVar = "output",
valueVar = "value",
dateVar = "date",
pExpr = "prob",
padLeft = NA_real_,
padRight = NA_real_
)
Arguments
groupedDf- an optionally grouped dataframe, containing at dateVar, and a valueVar to be colvolved
discreteDistDf- a dataframe containing the same grouping columns as groupedDf plus "start", "end" and "prob" columns
dateVar-
padLeft- what can we assume about the run in to the current values? default NA.
padRight- what can we assume about the run in to the current values? default NA.
Returns
a list of matrices
Method tsBootstrapConvolution()
executes a convolution using bootstrapped parameterized distributions
Usage
DistributionFit$tsBootstrapConvolution(
groupedDf,
distributionDistDf,
bootstraps = 100,
outputVar = "output",
valueVar = "value",
dateVar = "date",
days = 30,
timepoints = 0:days,
padLeft = NA_real_,
padRight = NA_real_
)
Arguments
distributionDistDf- a grouped data frame containing the same columns as those grouped in groupedDf, plus "distribution" and columns for "<parameter>_mean","<parameter>_sd","<parameter>_min","<parameter>_max" e.g. shape_mean, shape_sd, shape_min, shape_max, rate_mean, rate_sd, rate_min, rate_max
bootstraps- number of bootstrap iterations
Returns
the full bootstrap result (i.e. not summarized) which can be futher convoluted (asd long as the number of bootstrap iterations are kept the same).
Method summariseBootstrap()
summarise the result of a bootstrapped convolution using parameterized distributions
Usage
DistributionFit$summariseBootstrap(
groupedDf,
outputVars = vars(output),
dateVar = "date"
)
Arguments
distributionDistDf- a grouped data frame containing the same columns as those grouped in groupedDf, plus "distribution" and columns for "<parameter>_mean","<parameter>_sd","<parameter>_min","<parameter>_max" e.g. shape_mean, shape_sd, shape_min, shape_max, rate_mean, rate_sd, rate_min, rate_max
bootstraps- number of bootstrap iterations
Returns
the full bootstrap result (i.e. not summarized) which can be futher convoluted (asd long as the number of bootstrap iterations are kept the same).
Method clone()
The objects of this class are cloneable with this method.
Usage
DistributionFit$clone(deep = FALSE)
Arguments
deepWhether to make a deep clone.
terminological/uk-covid-datatools documentation built on June 24, 2021, 8:16 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Description Super class Methods
Description
General distribution fitting algorithms
General distribution fitting algorithms
Super class
ukcovidtools::PassthroughFilesystemCache -> DistributionFit
Methods
Public methods
Inherited methods
Method new()
New distribution fitter
Usage
DistributionFit$new(
distributions = c("weibull", "gamma", "lnorm", "exp", "norm", "tnorm"),
shifted = 0,
...
)Arguments
distributions- the distributions to fit
shifted- a shift to apply to all data
...for compatibility
Returns
Method setModels()
Usage
DistributionFit$setModels(
distributions = c("weibull", "gamma", "lnorm", "exp", "norm", "tnorm"),
shifted = 0
)Method fromUncensoredData()
Usage
DistributionFit$fromUncensoredData( groupedDf, valueExpr = value, truncate = TRUE, bootstraps = 100, seed = 101, ... )
Method fromCensoredData()
Usage
DistributionFit$fromCensoredData( groupedDf, lowerValueExpr, upperValueExpr, truncate = TRUE, bootstraps = 100, seed = 101, ... )
Method withSingleDistribution()
Usage
DistributionFit$withSingleDistribution( dist, paramDf, bootstraps = 1000, epiestimMode = FALSE, ... )
Method fromBootstrappedDistributions()
Usage
DistributionFit$fromBootstrappedDistributions( fittedDistributions, confint = c(0.025, 0.975), ... )
Method fromBootstrappedData()
Usage
DistributionFit$fromBootstrappedData( bootstrappedDf, valueExpr = value, truncate = TRUE, ... )
Method plot()
Usage
DistributionFit$plot( xlim, binwidth = 1, summary = FALSE, pts = 8, facet2d = TRUE )
Method extractFitted()
Usage
DistributionFit$extractFitted( distFit, isCensored, bootstraps = 100, seed = 101 )
Method filterModels()
Usage
DistributionFit$filterModels(...)
Method generateSamples()
Usage
DistributionFit$generateSamples(sampleExpr = 1000, seed = 101)
Method calculateDensities()
calculates a set of pdfs from bootstrapped distributions
Usage
DistributionFit$calculateDensities(x, summarise = TRUE)
Arguments
support- the range of values of X for which to calculate the density.
Returns
a list of randomly selected bootstraps from the fitted models.
Method calculateCumulativeDistributions()
calculates a set of pdfs from bootstrapped distributions
Usage
DistributionFit$calculateCumulativeDistributions(q, summarise = TRUE)
Arguments
support- the range of values of X for which to calculate the density.
Returns
a list of randomly selected bootstraps from the fitted models.
Method calculateQuantiles()
calculates a set of quantiles from bootstrapped distributions
Usage
DistributionFit$calculateQuantiles(p, summarise = TRUE)
Arguments
support- the range of values of X for which to calculate the density.
Returns
a list of randomly selected bootstraps from the fitted models.
Method discreteProbabilities()
Usage
DistributionFit$discreteProbabilities(q, summarise = TRUE)
Method discreteSurvival()
Usage
DistributionFit$discreteSurvival(q, summarise = TRUE)
Method sampledProbabilities()
Usage
DistributionFit$sampledProbabilities(q, summarise = TRUE)
Method sevenNumbers()
Usage
DistributionFit$sevenNumbers(groupedDf, colVar)
Method printDistributionSummary()
Usage
DistributionFit$printDistributionSummary(confint = c(0.025, 0.975))
Method printDistributionDetail()
Usage
DistributionFit$printDistributionDetail(confint = c(0.025, 0.975))
Method tsParameterizedConvolution()
applies a set of parameterised convolution functions groupwise to input data
Usage
DistributionFit$tsParameterizedConvolution( groupedDf, distributionsDf, outputVar = "output", valueVar = "value", dateVar = "date", distributionVar = "dist", paramNameVar = "param", paramValueVar = "paramValue", days = 30, timepoints = 0:days, padLeft = NA_real_, padRight = NA_real_ )
Arguments
groupedDf- an optionally grouped dataframe, containing at dateVar, and a valueVar to be colvolved
distributionsDf- a dataframe containing the same grouping columns as groupedDf plus "distribution", and relevant distribution parameter columns
dateVar-
days-
timepoints- the times to
padLeft- what can we assume about the run in to the current values? default NA.
Returns
a list of matrices
Method tsDiscreteConvolution()
applies a set of parameterised convolution functions groupwise to input data
Usage
DistributionFit$tsDiscreteConvolution( groupedDf, discreteDistDf, outputVar = "output", valueVar = "value", dateVar = "date", pExpr = "prob", padLeft = NA_real_, padRight = NA_real_ )
Arguments
groupedDf- an optionally grouped dataframe, containing at dateVar, and a valueVar to be colvolved
discreteDistDf- a dataframe containing the same grouping columns as groupedDf plus "start", "end" and "prob" columns
dateVar-
padLeft- what can we assume about the run in to the current values? default NA.
padRight- what can we assume about the run in to the current values? default NA.
Returns
a list of matrices
Method tsBootstrapConvolution()
executes a convolution using bootstrapped parameterized distributions
Usage
DistributionFit$tsBootstrapConvolution( groupedDf, distributionDistDf, bootstraps = 100, outputVar = "output", valueVar = "value", dateVar = "date", days = 30, timepoints = 0:days, padLeft = NA_real_, padRight = NA_real_ )
Arguments
distributionDistDf- a grouped data frame containing the same columns as those grouped in groupedDf, plus "distribution" and columns for "<parameter>_mean","<parameter>_sd","<parameter>_min","<parameter>_max" e.g. shape_mean, shape_sd, shape_min, shape_max, rate_mean, rate_sd, rate_min, rate_max
bootstraps- number of bootstrap iterations
Returns
the full bootstrap result (i.e. not summarized) which can be futher convoluted (asd long as the number of bootstrap iterations are kept the same).
Method summariseBootstrap()
summarise the result of a bootstrapped convolution using parameterized distributions
Usage
DistributionFit$summariseBootstrap( groupedDf, outputVars = vars(output), dateVar = "date" )
Arguments
distributionDistDf- a grouped data frame containing the same columns as those grouped in groupedDf, plus "distribution" and columns for "<parameter>_mean","<parameter>_sd","<parameter>_min","<parameter>_max" e.g. shape_mean, shape_sd, shape_min, shape_max, rate_mean, rate_sd, rate_min, rate_max
bootstraps- number of bootstrap iterations
Returns
the full bootstrap result (i.e. not summarized) which can be futher convoluted (asd long as the number of bootstrap iterations are kept the same).
Method clone()
The objects of this class are cloneable with this method.
Usage
DistributionFit$clone(deep = FALSE)
Arguments
deepWhether to make a deep clone.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.