Code Monkey home page Code Monkey logo

ppbstats's People

Stargazers

avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar

Forkers

gaellevf farmlab famuvie rougerbaptiste mateothom marinantoine malacandon mturbetdelof

ppbstats's Issues

add ammi1 plot

$\alpha_{i}$ vs $\gamma_{i1}$ \citep{josse_inferring_2012}.\

add ad hoc GxE analysis

cf old R code + vignette:
2.1. barplot_variation_repartition ----------
dtmp = data.frame()
for(i in 1:length(out_ammi)){
d = out_ammi[[i]]$ANOVA$variability_repartition$data
d = cbind.data.frame(names(out_ammi)[i], d)
dtmp = rbind.data.frame(dtmp, d)
}
colnames(dtmp)[1] = "var"
p = ggplot(dtmp, aes(x = var, y = percentage_Sum_sq)) + geom_bar(stat = "identity", aes(fill = factor))
p = p + ylab("pourcentage de variation") + theme(axis.text.x = element_text(angle = 90))
cbbPalette <- c("#000000", "#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7")
barplot_variation_repartition = p + scale_fill_manual(values = cbbPalette)

\subsubsection{Post AMMI analysis}

\paragraph{Repartition of the variation for each variable}
<<message=TRUE,cache=FALSE>>=
ammi$Post_AMMI$barplot_variation_repartition
@

\paragraph{Germplasm effects}
<<message=TRUE,cache=FALSE>>=
ammi$Post_AMMI$PCA_G_effect$variation_dim
@

<<message=TRUE,cache=FALSE>>=
ammi$Post_AMMI$PCA_G_effect$ind
@

<<message=TRUE,cache=FALSE>>=
ammi$Post_AMMI$PCA_G_effect$var
@

\paragraph{Variance intra germplasm effects}
<<message=TRUE,cache=FALSE>>=
p1 = ammi$Post_AMMI$PCA_intraG_effect$variation_dim
p2 = ammi$Post_AMMI$PCA_intraG_effect$ind
p3 = ammi$Post_AMMI$PCA_intraG_effect$var
grid.arrange(p1, p2, p3, ncol=3, nrow=1)
@

\paragraph{Location effects}
<<message=TRUE,cache=FALSE>>=
ammi$Post_AMMI$PCA_E_effect$variation_dim
@

<<message=TRUE,cache=FALSE>>=
ammi$Post_AMMI$PCA_E_effect$ind
@

<<message=TRUE,cache=FALSE>>=
ammi$Post_AMMI$PCA_E_effect$var
@

Error downloading vignette data

When I get.PPBsttats.data() it downloads a bunch of 818-byte RData files, which are really plain text, all with the same HTML content:

<!DOCTYPE html>
<html>
<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>Dropbox - 403</title>
<link href="https://cfl.dropboxstatic.com/static/css/error.css" rel="stylesheet" type="text/css"/>
<link rel="shortcut icon" href="https://cfl.dropboxstatic.com/static/images/favicon.ico"/>

</head>
<body>
<div class="figure">
<img src="https://cfl.dropboxstatic.com/static/images/lockbox.png" alt="Error: 403"/>
</div>
<div id="errorbox">
<h1>Error (403)</h1>It seems you don't belong here! You should probably <b><a href="https://www.dropbox.com/login">sign in</a></b>. Check out our <a href="https://www.dropbox.com/help">Help Center</a> and <a href="https://forums.dropbox.com">forums</a> for help, or head back to <a href="https://www.dropbox.com/home">home</a>.
</div>

</body>
</html>

Which is, on the other hand, the same thing I get when I manually try to download a file directly from the dropbox:
https://dl.dropboxusercontent.com/s/6qvl515k5484zg4/comp.mu.RData

Either the files are no longer there, or they are not anymore publicly available.

Finalise variance_intra workflow

  • create a data set data_model_variance_intra

  • model_variance_intra.R :

    • check doc
    • why only mu and sigma in output ? Add residuals to check the model
    • why not add in the outut :
      "vec_env_with_no_data" = NULL,
      "vec_env_with_no_controls" = NULL,
      "data_env_with_no_controls" = NULL,
      "vec_env_with_controls" = NULL,

  • check_model.model_variance_intra.R :

    • debug function
    • add doc in check_model.R

  • plot.check_model_model_variance_intra.R

    • to test once check_model.model_variance_intra.R is ok
    • add doc in plot.PPBstats

  • mean_comparisons.check_model_variance_intra.R

    • to test once check_model.model_variance_intra.R is ok
    • replace argument data per x
    • is library(qdapRegex) useful ?
    • add doc in mean_comparisons

  • create a function plot.mean_comparisons_model_variance_intra.R

    • add doc in plot.PPBstats

  • check and update vignette

    • update vignettes/sections/variance_intra.Rnw

plot.data_network

interaction plot with model 1

it is correct ? because it is not possible to compare entry that are not on the same plot => put one color per group ?

add migrant residant model

  • update vignette
    • update decision tree ? design experiment = fully-replicated. Or maybe new decision tree regarding specific research questions ?
    • update agro workflow ?
    • home after how many year ? look at ref to discuss this

improve format_data_PPBstats()

  • take functions from shinemas2R :
    • translate.data()
    • encrypt.data()
  • type data_agro_version to do
  • when date, add a column with julian day
  • use class format

improve plots

Done in v0.23

  • change arg ggplot.type to plot_type

Still to do

  • cf p_out_check_model_1_bis = plot(out_check_model_1_bis), bug in the title
  • model 1, interaction plot: do the same legend as score + update vignette
  • add variable on each plots if it is not the case

interface to use the package

Some elements to start :

update vignette

  • ecovalence add that is on gxe + résiduals

  • in appendices : example with apply and a vector of variables for GxE for example

  • add decision tree from Isabelle

  • differenciate memory needed for the different analyses

add functions for balanced data

add function for AMMI and GGE analysis
This is useful for balanced data
Therefore change the vignette with two part: balanced and not balanced (make a function that say is it is balanced or not and advice an analysis? cf experimental_design in analysis.output

plot.data_agro

  • reformat code from shinemas2R::get.ggplot_plot.it and PPBstats::describe_data in order to take into account data format of PPBstats (cf head(data_GxE) for example)
    Note that for SR and S must be linked to data_version in PPBstats
  • doc in describe_data
  • create plot with dynamic in time
  • for radar plot : cf https://github.com/ricardo-bion/ggradar
  • update the vignette
  • update workflow of function in the vignette contribution
  • add grid argument

Update describe_data

  • create sub-function that are called into PPBstats::describe_data, maybe go throught get_ggplot directly as it is only plot ? With the data in argument

    • describe_data_network :

      • create a standard input format : look at shinemas2R::is.get.data.output.R and appendix D of the vignette of shinemas2R

      • reformat code from shinemas2R functions

        • shinemas2R::get.ggplot.R & shinemas2R::get.ggplot_hide.labels.part.R that may be useful if we keep the format of the seed lots GERMPLASM_LOCATION_YEAR_DIGIT

        • shinemas2R::get.ggplot_plot.network.R and shinemas2R::get.ggplot_ggnet.custom.R
          But see https://briatte.github.io/ggnetwork/ => maybe better to go from here and
          forget shinemas2R::get.ggplot_plot.network.R and shinemas2R::get.ggplot_ggnet.custom.R functions ?

        • shinemas2R::get.ggplot_network.relation.barplot.R

        • shinemas2R::get.ggplot_network.relation.map.R

    • pie on network or map : reformat code from shinemas2R function shinemas2R::get.ggplot_pie.on.ggplot
      But maybe forgot it and look at other solutions :
      http://stackoverflow.com/questions/10368180/plotting-pie-graphs-on-map-in-ggplot
      http://rgraphgallery.blogspot.fr/2013/04/rg-plot-pie-over-google-map.html
      https://qdrsite.wordpress.com/2016/06/26/pies-on-a-map/

    • describe_data_agro :

      • reformat code from shinemas2R::get.ggplot_plot.it and PPBstats::describe_data
        in order to take into account data format of PPBstats (cf head(data_GxE) for example)
        Note that for SR and S must be linked to data_version in PPBstats
      • create plot with dynamic in time

update vignette regarding model_variance_intra workflow

  • update 3.1.1 Workflow and function relations in PPBstats regarding agronomic analysis

  • update 3.2.1 Analysis carry out in PPBstats

  • fill 3.7.1 Family of analysis 3 : effects from family 1 and 2 in a network of farms model 3

    • create a data set is needed to perform and example

plot score model 1

  • add value in the box
  • think to a better legend or better value for the score which is closer to the real value of the data

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.