RBi Package---技术文档学习_rbinorm package-CSDN博客

本文链接：https://blog.csdn.net/xu_ampl/article/details/115264752

RBi包是用于与LibBi进行交互的R语言工具，支持加载、运行和分析状态空间模型。它提供了bi_model和libbi两个类，用于模型管理和运行推断。包内提供了bi_read和bi_write方法来处理NetCDF文件，以及get_traces函数分析MCMC轨迹。通过libbi类，可以进行模型的采样、拟合和预测。例如，SIR模型可以通过bi_generate_dataset生成数据，使用PMCMC方法进行参数估计。此外，RBi还支持保存和加载libbi对象，便于后续分析。

摘要由CSDN通过智能技术生成

RBi 技术文档

最近发现了一个包libbi（Library For Bayesian inference ）[ http://libbi.org ] 特别喜欢( ~~lunwenzhizaojiqi~~ )，它支持R接口😃，遂找到R的相关文档，学习了一下(在R中为RBi package)，以下是简单的翻译记录，文中所有代码都已运行实现，进一步的使用需要学习更多案例。

LibBi is used for Bayesian inference over state-space models, including simulation, filtering and smoothing for state estimation, and optimisation and sampling for parameter estimation.

1、Getting started

The RBi package requires R (>= 3.2.0) as well as the packages:

reshape2
ncdf4
data.table

The easiest way to install the latest stable version of RBi is via CRAN. The package name is rbi (all lowercase):

install.packages('rbi')

library('rbi')

The RBi package mainly provides two classes: bi_model and libbi. The bi_model class is used to load, view and manipulate LibBi model files. The libbi class is used to run LibBi and perform inference.

RBi包主要提供两类：bi_model和libbi。bi_model类被用于加载，预览，操作LibBi模型文件。libbi类被用于运行LibBi和运行推断。

The package also provides two methods for interacting with the NetCDF files used by LibBi, bi_read and bi_write. Lastly, it provides a get_traces function to analyse Markov-chain Monte Carlo (MCMC) traces using the coda package.

这个包还提供了与LibBi使用的NetCDF文件交互的两种方法:bi_read和bi_write。最后，它提供了一个get_traces函数来使用coda包分析Markov-chain Monte Carlo (MCMC)跟踪。

2、The bi_model class

As an example, we consider a simplified version of the SIR model discussed in Del Moral et al. (2014). This is included with the RBi package and can be loaded with
作为一个例子，我们考虑Del Moral等人(2014)中讨论的SIR模型的简化版本。这包含在RBi包中，可以加载

model_file <- system.file(package="rbi", "SIR.bi")
SIRmodel <- bi_model(model_file) # load model

Other ways of implementing a (deterministic or stochastic) SIR model can be found in the collection of SIR models for LibBi, where you also find how to load them into a bi_model object, e.g. SIRmodel. Feel free to run the commands below with different versions of the model.
其他实现(确定性或随机)SIR模型的方法可以在LibBi的SIR模型集合中找到，在那里你还可以找到如何将它们加载到bi_model对象中，例如SIRmodel。请随意使用模型的不同版本运行下面的命令。

加载下面命令可以看到模型详细说明：

SIRmodel

get_block()获取函数块

get_block(SIRmodel, "parameter")

## [1] "p_rep ~ uniform(0,1)" "p_R0 ~ uniform(1,3)"

var_names() 获取变量名

var_names(SIRmodel, type="state")

## [1] "S" "I" "R" "Z"

The fix method fixes a variable to one value. This can be useful, for example, to run the deterministic equivalent of a stochastic model for testing purposes:

fix方法将一个变量固定为一个值。这是有用的，例如，为了测试目的运行随机模型的确定性等价:

det_SIR_model <- fix(SIRmodel, n_transmission=0, n_recovery=0)

3、Generating a dataset

首先从SIR模型中创建一个数据集

set.seed(1001912)
SIRdata <- bi_generate_dataset(SIRmodel, end_time=16*7, 
noutputs=16)

This simulates the model a single time from time 0 until time 16*7 (say, 16 weeks with a daily time step), producing 16 outputs (one a week)

模拟模型单个时间从0到时间16*7，（16周以天为时间步骤），产生16个输出（一周）

Also note that LibBi compiles the model code only the first time it is run. If you run the command above a second time, it should run much faster.

还要注意，LibBi只在模型代码第一次运行时才编译它。如果您第二次运行上述命令，它应该会运行得快得多。

The bi_generate_dataset function returns a libbi object:

The generated dataset can be viewed and/or stored in a variable using bi_read:

生成的数据集可以使用bi_read查看