Website created and minor tweaks

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: backfillz
 Type: Package
 Title: MCMC visualisation package
-Version: 0.9.9900
+Version: 1.0
 Authors@R: c(
             person('James', 'Tripp', email = 'james.tripp@warwick.ac.uk', role = c('aut', 'cre')),
             person('Gregory', 'McInerny', email = 'G.McInerny@warwick.ac.uk', role = 'aut')
@@ -11,4 +11,4 @@ Description: Visualisation package for creating diagnostic plots for MCMC chains
 License: GPL-3
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 6.1.1
+RoxygenNote: 7.1.0

NEWS.md

@@ -0,0 +1,10 @@
+NEWS
+================
+
+# lecat v1.00 (Release date: 2020-04-04)
+
+Changes:
+
+  - Used pkgdown to create site
+  - Created tutorials
+  - Plot save and recall added

NEWS.rmd

@@ -0,0 +1,13 @@
+---
+title: "NEWS"
+output: github_document
+---
+
+Backfillz v1.00 (Release date: 2020-04-04)
+==============
+
+Changes:
+
+* Used pkgdown to create site
+* Created tutorials
+* Plot save and recall added

R/df_to_stanarray.R

@@ -1,4 +1,4 @@
-#' Converts a data frame to the output structure of extract(stan_object, permuted = TRUE)
+#' Converts a data frame to the output structure of extract
 #'
 #' @param df                data frame with the column names 'parameters', 'iterations' and 'chains'
 #' @return                  An array from df with the dimensions [iteration, chain, parameters]

R/plot_slice_histogram.R

@@ -523,7 +523,7 @@ plot_slice_histogram <- function(object = NULL, slices = NULL, save_plot = FALSE
     data.frame(
       ID = ID,
       Date = date(),
-      Event = 'Slice Historgram',
+      Event = 'Slice Histogram',
       R_version = R.Version()$version.string,
       Saved = save_plot,
       stringsAsFactors = FALSE

README.md

@@ -1,7 +1,9 @@
-![](fig1.png)
-
+[![Build
+Status](https://travis-ci.org/warwickCIM/lecat.svg?branch=master)](https://travis-ci.org/WarwickCIM/backfillz)
 [![DOI](https://zenodo.org/badge/176701637.svg)](https://zenodo.org/badge/latestdoi/176701637)
 
+<img src="https://github.com/WarwickCIM/backfillz/raw/master/fig1.png" width=100% alt=""/>
+
 # New View of MCMC
 
 Backfillz.R provides new visual diagnostics for understanding MCMC (Markov Chain Monte Carlo) analyses and outputs. MCMC chains can defy a simple line graph. Unless the chain is very short (which isn’t often the case), plotting tens or hundreds of thousands of data points reveals very little other than a ‘trace plot’ where we only see the outermost points. Common plotting methods may only reveal when an MCMC really hasn’t worked, but not when it has.
@@ -12,48 +14,42 @@ BackFillz.R slices and dices MCMC chains so increasingly parameter rich, complex
 ```r
 install.packages(devtools)
 devtools::install_github('warwickCIM/backfillz')
-require(backfillz)
+library(backfillz)
 
 # convert sample data to backfillz object
 x <- as_backfillz(sample_stanfit)
 
-slices <- data.frame(
-  parameters = c('mu', 'mu', 'eta[1]', 'eta[1]'),
-  lower = c(0,   0.6, 0.2, 0.7),
-  upper= c(0.4, 0.9, 0.25, 1),
-  stringsAsFactors = FALSE
-)
-
 # change theme
 x <- set_theme(x, 'demo 1')
 
+# plot via generic plot method
+x <- plot(x, plotType = 'slice_histogram')
+
 # create prototype plots
 x <- plot_slice_histogram(x, slices)
 x <- plot_trace_dial(x)
 x <- plot_spiral_stream(x)
 ```
 
-# Current prototype
-
-In this first prototype we have implemented three new MCMC visual diagnostics. More functionality and tutorials to come! The documentation is available through R and the full package will be coming soon.
+# Current prototype plots
 
 ## Pretzel Plot – plot_trace_dial()
 
 This plot shows the chain and summary histograms in a format that can be easily arranged as a grid. The trace plot is stretched, clearly indicating ‘burn-in’, with density plots showing the burn-in and remainder of the chain in context. 
 
-![](fig2.png)
+<img src="https://github.com/WarwickCIM/backfillz/raw/master/fig2.png" width=100% alt=""/>
 
 ## Slice plot - plot_slice_histogram()
 
 By partitioning chain slices, in a faceted view, users can assess chain convergence. The slices are currently specified by the user and display density plots for each slice. Have my chains converged? The slice plot offers a clear view of when and how convergence is achieved. Further statistical diagnostics can be embedded in these plots as colour encodings or additional layers and annotations.
 
-![](fig3.png)
+<img src="https://github.com/WarwickCIM/backfillz/raw/master/fig3.png" width=100% alt=""/>
 
 ## Splash plot - plot_spiral_stream()
 
 Based on a Theodorus spiral, we turn MCMC chains into glyphs and extract properties to answer – What does ‘good mixing’ look like? In these plots variance windows are calculated across chains and parameters. The glyphs have clear diagnostic features and will allow gridded plots to investigate large numbers of parameters.
 
-![](fig4.png)
+<img src="https://github.com/WarwickCIM/backfillz/raw/master/fig4.png" width=100% alt=""/>
 
 # Acknowledgements