removed plots, workspaces and moved to release. updated READMEs to reflect this.

Former-commit-id: 12da617

Author: Johan Dahlin

README.md

@@ -4,11 +4,11 @@ This code was downloaded from https://github.com/compops/pmh-tutorial and contai
 
 J. Dahlin and T. B. Schön, **Getting started with particle Metropolis-Hastings for inference in nonlinear models**. Pre-print, arXiv:1511:01707, 2017. 
 
-The papers are available as a preprint from http://arxiv.org/pdf/1511.01707
+The papers are available as a preprint from http://arxiv.org/pdf/1511.01707. The R package connected to this tutorial is available directly via CRAN and the source code is available at https://github.com/compops/pmh-tutorial-rpkg/.
 
 Included material
 --------------
-**r/** This is the main implementation. The complete R code developed and implemented in the tutorial. This code was used to make all the numerical illustrations in the tutorial including the figures and tables. The workspaces for these runs are also provided together with the code to reproduce all the figures. 
+**r/** This is the main implementation. The complete R code developed and implemented in the tutorial. This code was used to make all the numerical illustrations in the tutorial including the figures and tables. The workspaces for these runs are also provided as a [zip-file in the latest release of the code](https://github.com/compops/pmh-tutorial/releases/latest) to reproduce all the figures in the tutorial. 
 
 **python/** Code for Python to implement the basic algorithms covered in the tutorial. Implementations for the advanced topics are not provided. Only simple plotting is implemented and no figures or saved data from runs are provided.
 

r/README.md

@@ -24,7 +24,7 @@ These are the main script files that implement the various algorithms discussed
 **example5-sv.R** Modified version of the code in *example3-sv.R* to make use of another parameterisation of the model and a better tailored parameter proposal. The details are discussed in Section 6.3.3 and the results are presented in the same section. Note that the differences in the code is the use of another implemenation of PMH ant that the variable stepSize is changed.
 
 
-Additional script files for creating plots for tutorial (codeForPaper/)
+Additional script files for creating plots for tutorial (extra-code-for-tutorial/)
 --------------
 These are some additional files to recreate some extra results discussed in the tutorial.
 
@@ -47,8 +47,11 @@ Supporting files (helpers/)
 
 Saved results (savedWorkspaces/ and figures/)
 --------------
+These directories are placeholders for the output from running the code. The workspaces and plots used in the tutorial are found as a zip-file in the [latest release of the code](https://github.com/compops/pmh-tutorial/releases/latest) as binaries are not usually version controlled by Git and the workspaces are quite large (ca 80 mb).
+
 **savedWorkspaces/** Saved copies of the workspace after running the corresponding code. These outputs are used to generate all the results in the aper. Can be used to directly recreate the plots in the tutorial by setting the flags loadSavedWorkspace and savePlotToFile to TRUE.
 
+**figures/** Saved plots from running the files.
 
 Adapting the code for another model
 --------------

r/codeForPaper/example1-lgss-plotData.R renamed to r/extra-code-for-tutorial/example1-lgss-plotData.R

@@ -23,7 +23,7 @@ loadSavedWorkspace <- FALSE
 tuneProposals <- FALSE
 
 # Should we use the tuned proposals (requires "../savedWorkspaces/example4-sv-varyingN-proposals.RData")
-useTunedProposals <- TRUE
+useTunedProposals <- FALSE
 
 ##############################################################################
 # Load data