Help for package FactoInvestigate

Type:

Package

Title:

Automatic Description of Factorial Analysis

Version:

1.9

Author:

Simon Thuleau, Francois Husson

Maintainer:

Francois Husson <francois.husson@institut-agro.fr>

Description:

Brings a set of tools to help and automatically realise the description of principal component analyses (from 'FactoMineR' functions). Detection of existing outliers, identification of the informative components, graphical views and dimensions description are performed threw dedicated functions. The Investigate() function performs all these functions in one, and returns the result as a report document (Word, PDF or HTML).

Depends:

R (≥ 4.0)

URL:

http://factominer.free.fr/reporting/

Imports:

FactoMineR, stats, methods, graphics, rmarkdown, parallel, ggplot2

License:

GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]

Encoding:

UTF-8

LazyLoad:

yes

NeedsCompilation:

Packaged:

2023-11-27 14:36:00 UTC; husson

Repository:

CRAN

Date/Publication:

2023-11-27 19:20:25 UTC

Automatic Description of Factorial Analysis

Description

Details

The DESCRIPTION file:

Package:	FactoInvestigate
Type:	Package
Title:	Automatic Description of Factorial Analysis
Version:	1.9
Author:	Simon Thuleau, Francois Husson
Maintainer:	Francois Husson <francois.husson@institut-agro.fr>
Description:	Brings a set of tools to help and automatically realise the description of principal component analyses (from 'FactoMineR' functions). Detection of existing outliers, identification of the informative components, graphical views and dimensions description are performed threw dedicated functions. The Investigate() function performs all these functions in one, and returns the result as a report document (Word, PDF or HTML).
Depends:	R (>= 4.0)
URL:	http://factominer.free.fr/reporting/
Imports:	FactoMineR, stats, methods, graphics, rmarkdown, parallel, ggplot2
License:	GPL (>= 2)
Encoding:	UTF-8
LazyLoad:	yes

Index of help topics:

FactoInvestigate-package
                        Automatic Description of Factorial Analysis
Investigate             Resume factorial Analysis
classif                 Classification description
createRmd               Create Rmarkdown file
description             Factorial dimensions description
dimActive               Number of active dimensions
dimRestrict             Significant dimensions identification
eigenRef                Reference eigen value
factoGraph              Factorial graphs
getParam                Factorial parameters
graphCA                 Correspondance Analysis factor map
graphHab                Colored factor graph
graphInd                Individuals factor map
graphSup                Supplementary variables factor map
graphVar                Variables factor map
inertiaDistrib          Inertia distribution analysis
outliers                Outliers detection
readRmd                 Read Rmarkdown file
scriptRmd               File script
selection               Graphical elements selection
whichFacto              Analysis class
writeRmd                Write Rmarkdown file

An overview of how to use the package, including the most important functions

Author(s)

Simon Thuleau, Francois Husson

Maintainer: Francois Husson <francois.husson@institut-agro.fr>

Resume factorial Analysis

Description

Compute all the package functions : detection of outliers, evaluation of inertia distribution, dimensions description, classification and realisation of graphical views. All the results are written as Word, html or PDF documents.

Usage

Investigate(res, file = "Investigate.Rmd", document = c("html_document"), 
            Iselec = "contrib", Vselec = "cos2", Rselec = "contrib", 
            Cselec = "cos2", Mselec = "cos2", Icoef = 1, Vcoef = 1, Rcoef = 1, 
            Ccoef = 1, Mcoef = 1, ncp = NULL, time = "10s", nclust = -1, 
            mmax = 10, nmax = 10, hab = NULL, ellipse = TRUE, display.HCPC = TRUE, 
            out.selec = TRUE, remove.temp = TRUE, parallel = TRUE, cex = 0.7,
			openFile = TRUE, keepRmd = FALSE, codeGraphInd = NULL, 
			codeGraphVar=NULL, codeGraphCA = NULL, options = NULL, 
			language = "auto")

Arguments

res

a PCA, CA or MCA object.

file

the file path where to write the description in Rmarkdown language. If the file already exists, its content is overwritten. If not specified, the description is written in the console.

document

a character vector giving the document format desired between "word_document", "pdf_document" and "html_document".

Iselec

the individuals to select ; see the details section.

Vselec

the variables to select ; see the details section.

Rselec

the rows to select (for a CA res object) ; see the details section.

Cselec

the columns to select (for a CA res object) ; see the details section.

Mselec

the supplementary variables to select ; see the details section.

Icoef

a numerical coefficient to adjust the individuals selection rule ; see the details section.

Vcoef

a numerical coefficient to adjust the variables selection rule ; see the details section.

Rcoef

a numerical coefficient to adjust the rows selection rule (for a CA res object) ; see the details section.

Ccoef

a numerical coefficient to adjust the columns selection rule (for a CA res object) ; see the details section.

Mcoef

a numerical coefficient to adjust the supplementary variables selection rule ; see the details section.

ncp

an integer to force the number of dimension to analyse.

time

a character indicating the loop condition. This string is made of a number and a letter coupled. The number X with letter L means to compute X datasets exactly. The number X with letter s means to compute as many datasets as possible during approximativley X seconds.

nclust

an integer to force the number of cluster for the classification.

mmax

an integer giving the maximum number of individuals (or rows) to illustrate each group (by defaut 10).

nmax

an integer giving the maximum number of variables (or columns) to illustrate each group of individuals (by defaut 10).

hab

a variable name or index to use to color the individuals (or rows) among the variable categories.

ellipse

a boolean : if TRUE, ellipses are plotted with the coloration of individuals (or rows).

display.HCPC

a boolean : if TRUE, the function performs the classification.

out.selec

a boolean : if TRUE, the function performs the detection of outliers.

remove.temp

a boolean : if TRUE, the temporary files created are deleted after the function execution.

parallel

a boolean : if TRUE, the computation uses map reduce on the processor cores to increase the performance. Useful for huge datasets.

cex

an optional argument for the generic plot functions, used to adjust the size of the elements plotted.

openFile

Open the file with the appropriate application; TRUE by default

keepRmd

Keep the Rmd file; FALSE by default

codeGraphInd

a character string corresponding to the code to use for the individuals graph.

codeGraphVar

a character string corresponding to the code to use for the variables graph.

codeGraphCA

a character string corresponding to the code to use for the CA graph.

options

a character string that gives the output options fir the figures. If NULL, options="r, echo = FALSE, fig.align = 'center', fig.height = 3.5, fig.width = 5.5" for linux and Mac and options="r, echo = FALSE, fig.height = 3.5, fig.width = 5.5" for Windows

language

possible values "auto", "en", or "fr": by default, "auto" detects the language (English or French), "en" for English and "fr" for "French"

Details

The Iselec argument (respectively Vselec, Rselec or Cselec) is used in order to select a part of the elements that are drawn and described. For example, you can use either :
- Iselec = 1:5 then the individuals (respectively the variables, the rows or the columns) numbered 1 to 5 are drawn.
- Iselec = c("name1","name5") then the individuals (respectively the variables, the rows or the columns) named name1 and name5 are drawn.
- Iselec = "contrib 10" then the 10 active or illustrative individuals (respectively the variables, the rows or the columns) that have the highest contribution on the 2 dimensions of the plane are drawn.
- Iselec = "contrib" then the optimal number of active or illustrative individuals (respectively the variables, the rows or the columns) that have the highest contribution on the 2 dimensions of the plane are drawn.
- Iselec = "cos2 5" then the 5 active or illustrative individuals (respectively the variables, the rows or the columns) that have the highest cos2 on the 2 dimensions of the plane are drawn.
- Iselec = "cos2 0.8" then the active or illustrative individuals (respectively the variables, the rows or the columns) that have a cos2 higher to 0.8 on the plane are drawn.
- Iselec = "cos2" then the optimal number of active or illustrative individuals (respectively the variables, the rows or the columns) that have the highest cos2 on the 2 dimensions of the plane are drawn.

The Icoef argument (respectively Vcoef, Rcoef or Ccoef) is used in order to adjust the selection of the elements when based on Iselec = "contrib" or Iselec = "cos2". For example :
- if Icoef = 2, the threshold is 2 times higher, and thus 2 times more restrictive.
- if Icoef = 0.5, the threshold is 2 times lower, and thus 2 times less restrictive.

Value

the function creates and opens a Word, html or PDF document that contains all the descriptions of analysis.

Author(s)

Simon Thuleau and Francois Husson

Examples

require(FactoMineR)
data(decathlon)
## Not run: 
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
Investigate(res.pca, file = "PCA.Rmd", document = "html_document", time = "1000L", 
            parallel = FALSE)

data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
Investigate(res.ca, file = "CA.Rmd", document = "pdf_document")

data(tea)
res.mca = MCA(tea, quanti.sup = 19,quali.sup = 20:36, graph = FALSE)
Investigate(res.mca, file = "MCA.Rmd", document = c("word_document", "pdf_document"))

## End(Not run)

Classification description

Description

Realise the hierachical ascending classification (HCPC function) of the individuals (or rows) and describe the specifications of each cluster.

Usage

classif(res, file = "", dim = 1:2, nclust = -1, selec = "contrib", coef = 1, 
        mmax = 10, nmax = 10, figure.title = "Figure", graph = TRUE, options = NULL)

Arguments

res

an object of class PCA, CA or MCA.

file

the file path where to write the description in Rmarkdown langage. If not specified, the description is written in the console.

dim

a 2 dimensional numerical vector giving the factorial dimensions to describe (by default the first plane).

nclust

an integer forcing the number of clusters desired. The value -1 return the clustering evaluated as the most appropriate (default).

selec

the selection criterion of individuals to plot on the graph.

coef

a numerical coefficient to adjust the selection rule (exemple : if equals 2, the threshold is 2 times higher, and thus more restrictive)

mmax

an integer giving the maximum number of individuals to illustrate each cluster (by defaut 10).

nmax

an integer giving the maximum number of variables to illustrate each cluster (by defaut 10).

figure.title

the text label to add before graph title.

graph

a boolean : if TRUE, the graph is ploted into the console.

options

a character string that gives the output options for the figures. If NULL, options="r, echo = FALSE, fig.align = 'center', fig.height = 3.5, fig.width = 5.5" for linuw and Mac and options="r, echo = FALSE, fig.height = 3.5, fig.width = 5.5" for Windows

Details

The selec argument is used in order to select a part of the individuals that are drawn and described. For example, you can use either :
- selec = 1:5 then the individuals numbered 1 to 5 are drawn.
- selec = c("name1","name5") then the individuals named name1 and name5 are drawn.
- selec = "contrib 10" then the 10 active or illustrative individuals that have the highest contribution on the 2 dimensions of the plane are drawn.
- selec = "contrib" then the optimal number of active or illustrative individuals that have the highest contribution on the 2 dimensions of the plane are drawn.
- selec = "cos2 5" then the 5 active or illustrative individuals that have the highest cos2 on the 2 dimensions of the plane are drawn.
- selec = "cos2 0.8" then the active or illustrative individuals that have a cos2 higher to 0.8 on the plane are drawn.
- selec = "cos2" then the optimal number of active or illustrative individuals that have the highest cos2 on the 2 dimensions of the plane are drawn.

The coef argument is used in order to adjust the selection of the individuals when based on selec = "contrib" or selec = "cos2". For example :
- if coef = 2, the threshold is 2 times higher, and thus 2 times more restrictive.
- if coef = 0.5, the threshold is 2 times lower, and thus 2 times less restrictive.

Value

res.hcpc

the result of the HCPC function on the dimensions specified.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
classif(res.pca, file = "PCA.Rmd")

data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
classif(res.ca, file = "CA.Rmd")

data(tea)
res.mca = MCA(tea, quanti.sup = 19,quali.sup = 20:36, graph = FALSE)
classif(res.mca, file = "MCA.Rmd")

## End(Not run)

Create Rmarkdown file

Description

Intialise a Rmarkdown file in which to write the results of the package functions.

Usage

createRmd(res, analyse = "PCA", file = "", 
          document = c("word_document", "pdf_document", "html_document"))

Arguments

res

an object of class PCA, CA or MCA.

analyse

A character string corresponding to the method for which the Rmd is created

file

the file path where to write the description in Rmarkdown langage. If the file already exists, its content is overwritten. If not specified, the description is written in the console.

document

a character vector giving the document format desired between "word_document", "pdf_document" and "html_document".

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
createRmd(res.pca, file = "PCA.Rmd", document = "pdf_document")

data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
createRmd(res.ca, file = "CA.Rmd", document = "html_document")

data(tea)
res.mca = MCA(tea, quanti.sup = 19,quali.sup = 20:36, graph = FALSE)
createRmd(res.mca, file = "MCA.Rmd", document = c("word_document", "pdf_document"))

## End(Not run)

Factorial dimensions description

Description

Describe a couple of dimensions, giving the individuals specific to each dimension, and the variables that characterize each group of individuals.

Usage

description(res, file = "", dim = 1:2, desc = dim, Iselec = "contrib", 
            Vselec = "cos2", Rselec = "cos2", Cselec = "cos2", Icoef = 1, 
            Vcoef = 1, Rcoef = 1, Ccoef = 1, mmax = 10, nmax = 10)

Arguments

res

an object of class PCA, CA or MCA.

file

the file path where to write the description in Rmarkdown language. If not specified, the description is written in the console.

dim

a 2 dimensional numerical vector giving the factorial dimensions to use for the representation (by default the first plane).

desc

a 2 dimensional numerical vector giving the factorial dimensions to describe (by default the dim value).

Iselec

the individuals to select; see the details section.

Vselec

the variables to select; see the details section.

Rselec

the rows to select (for a CA res object); see the details section.

Cselec

the columns to select (for a CA res object); see the details section.

Icoef

a numerical coefficient to adjust the individuals selection rule; see the details section.

Vcoef

a numerical coefficient to adjust the variables selection rule; see the details section.

Rcoef

a numerical coefficient to adjust the rows selection rule (for a CA res object); see the details section.

Ccoef

a numerical coefficient to adjust the columns selection rule (for a CA res object); see the details section.

mmax

an integer giving the maximum number of individuals to illustrate each cluster (by default 10).

nmax

an integer giving the maximum number of variables to illustrate each cluster (by default 10).

Details

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
description(res.pca, file = "PCA.Rmd", dim = 1:2)

## End(Not run)

Number of active dimensions

Description

Give the number of active elements used to build the factorial analysis : individuals (or rows) and variables (or columns)

Usage

dimActive(res)

Arguments

res

an object of class PCA, CA or MCA.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
dimActive(res.pca)

## End(Not run)

Significant dimensions identification

Description

Evaluate the number of significant dimensions in the data.

Usage

dimRestrict(res, file = "", rand = NULL)

Arguments

res

an object of class PCA, CA or MCA.

file

the file path where to write the function execution in Rmarkdown language. If not specified, the description is written in the console.

rand

an optional vector of eigenvalues to compare the observation with. If NULL, use the result of the eigenRef function for comparison.

Value

ncp

the number of significant dimensions.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
dimRestrict(res.pca, file = "PCA.Rmd")

## End(Not run)

Reference eigen value

Description

Compute the eigen values of random datasets, with the hypothesis of independence.

Usage

eigenRef(res, dim = NULL, q = 0.95, time = "10000L", parallel = TRUE)

Arguments

res

an object of class PCA, CA or MCA

dim

a numerical vector giving the factorial dimensions for with to compute the eigenvalues calculation.

q

the quantile of computed values to use as reference value (ie. the confidence about the signification of dimensions)

time

parallel

a boolean : if TRUE, the computation uses map reduce on the processor cores to increase the performance. Useful for huge datasets

Value

datasets

the number of random datasets simulated.

quantile

the quantile used for the reference definition.

inertia

the reference inertia for the dimensions declared.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
eigenRef(res.pca, q = 0.95, time = "10s")

data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
eigenRef(res.ca, q = 0.99, time = "10000L")

data(tea)
res.mca = MCA(tea, quanti.sup = 19,quali.sup = 20:36, graph = FALSE)
eigenRef(res.mca, dim = 1:8, q = 0.90, time = "10s")

## End(Not run)

Factorial graphs

Description

Realise all optimised factorial graphs

Usage

factoGraph(res, file = "", dim = 1:2, hab = NULL, ellipse = TRUE, Iselec = "contrib", 
           Vselec = "cos2", Rselec = "cos2", Cselec = "cos2", Mselec = "cos2", 
           Icoef = 1, Vcoef = 1, Rcoef = 1, Ccoef = 1, Mcoef = 1, 
           figure.title = "Figure", graph = TRUE, cex = 0.7, 
		   codeGraphInd = NULL, codeGraphVar = NULL ,codeGraphCA = NULL, 
		   options = NULL)

Arguments

res

an object of class PCA, CA or MCA

file

the file path where to write the description in Rmarkdown language. If not specified, the description is written in the console.

dim

a 2 dimensional numerical vector giving the factorial dimensions to use for the representation (by default the first plane)

hab

a variable name or index to use to color the individuals (or rows) among the variable categories.

ellipse

a boolean : if TRUE, ellipses are plotted with the coloration of individuals (or rows).

Iselec

the individuals to select ; see the details section

Vselec

the variables to select ; see the details section

Rselec

the rows to select (for a CA res object) ; see the details section

Cselec

the columns to select (for a CA res object) ; see the details section

Mselec

the supplementary variables to select ; see the details section

Icoef

a numerical coefficient to adjust the individuals selection rule ; see the details section

Vcoef

a numerical coefficient to adjust the variables selection rule ; see the details section

Rcoef

a numerical coefficient to adjust the rows selection rule (for a CA res object) ; see the details section

Ccoef

a numerical coefficient to adjust the columns selection rule (for a CA res object) ; see the details section

Mcoef

a numerical coefficient to adjust the supplementary variables selection rule ; see the details section

figure.title

the text label to add before graph title

graph

a boolean : if TRUE, graphs are plotted.

cex

an optional argument for the generic plot functions, used to adjust the size of the elements plotted.

codeGraphInd

a character string corresponding to the code to use for the individuals graph.

codeGraphVar

a character string corresponding to the code to use for the variables graph.

codeGraphCA

a character string corresponding to the code to use for the CA graph.

options

Details

Author(s)

Simon Thuleau and Francois Husson

Examples

require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
## Not run: 
factoGraph(res.pca)

require(FactoMineR)
data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
factoGraph(res.ca)

data(tea)
res.mca = MCA(tea, quanti.sup = 19,quali.sup = 20:36, graph = FALSE)
factoGraph(res.mca)

## End(Not run)

Factorial parameters

Description

Get all the factorial object parameters

Usage

getParam(res)

Arguments

res

an object of class PCA, CA or MCA.

Value

data

the dataset.

ind

the number of individuals.

var

the number of variables.

row

the number of rows (CA).

col

the number of columns (CA).

ind.sup

the number of supplementary individuals.

quanti.sup

the number of quantitative supplementary variables.

quali.sup

the number of qualitative supplementary variables.

row.sup

the number of supplementary rows (CA).

col.sup

the number of supplementary columns (CA).

row.w

the weights of each row.

col.w

the weights of each columns.

scale

a boolean indicating if the variables are scaled or not.

ncp.mod

the number of component kept in the analysis object.

modalites

the list of factors for each qualitative variables.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
getParam(res.pca)

## End(Not run)

Correspondance Analysis factor map

Description

Realise the Correspondence Analysis simultaneous graph

Usage

graphCA(res, file = "", dim = 1:2, Rselec = "cos2", Cselec = "cos2", Rcoef = 1, 
        Ccoef = 1, figure.title = "Figure", graph = TRUE, cex = 0.7, 
		codeGraphCA = NULL,options = NULL)

Arguments

res

an object of class CA.

file

the file path where to write the description in Rmarkdown language. If not specified, the description is written in the console.

dim

a 2 dimensional numerical vector giving the factorial dimensions to use for the representation (by default the first plane)

Rselec

the rows to select ; see the details section.

Cselec

the columns to select ; see the details section.

Rcoef

a numerical coefficient to adjust the rows selection rule ; see the details section.

Ccoef

a numerical coefficient to adjust the columns selection rule ; see the details section.

figure.title

the text label to add before graph title.

graph

a boolean : if TRUE, graphs are plotted.

cex

an optional argument for the generic plot functions, used to adjust the size of the elements plotted.

codeGraphCA

a character string corresponding to the code to use for the CA graph.

options

Details

The Rselec argument (respectively Cselec) is used in order to select a part of the elements that are drawn and described. For example, you can use either :
- Rselec = 1:5 then the rows (the columns) numbered 1 to 5 are drawn.
- Rselec = c("name1","name5") and then the rows (the columns) named name1 and name5 are drawn.
- Rselec = "contrib 10" then the 10 active or illustrative rows (the columns) that have the highest contribution on the 2 dimensions of the plane are drawn.
- Rselec = "contrib" then the optimal number of active or illustrative rows (the columns) that have the highest contribution on the 2 dimensions of the plane are drawn.
- Rselec = "cos2 5" then the 5 active or illustrative rows (the columns) that have the highest cos2 on the 2 dimensions of the plane are drawn.
- Rselec = "cos2 0.8" then the active or illustrative rows (the columns) that have a cos2 higher to 0.8 on the plane are drawn.
- Rselec = "cos2" then the optimal number of active or illustrative rows (the columns) that have the highest cos2 on the 2 dimensions of the plane are drawn.

The Rcoef argument (respectively Ccoef) is used in order to adjust the selection of the elements when based on Rselec = "contrib" or Rselec = "cos2". For example :
- if Rcoef = 2, the threshold is 2 times higher, and thus 2 times more restrictive.
- if Rcoef = 0.5, the threshold is 2 times lower, and thus 2 times less restrictive.

Author(s)

Simon Thuleau and Francois Husson

Examples

require(FactoMineR)
data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
## Not run: 
graphCA(res.ca)

## End(Not run)

Colored factor graph

Description

Realised the graph of individuals colored after a variable categories

Usage

graphHab(res, file = "", dim = 1:2, hab = NULL, ellipse = TRUE, Iselec = "contrib", 
         Rselec = "cos2", Cselec = "contrib", Icoef = 1, Rcoef = 1, Ccoef = 1, 
         figure.title = "Figure", graph = TRUE, cex = 0.7, options = NULL)

Arguments

res

an object of class PCA, CA or MCA.

file

the file path where to write the description in Rmarkdown language. If not specified, the description is written in the console.

dim

a 2 dimensional numerical vector giving the factorial dimensions to use for the representation (by default the first plane).

hab

a variable name or index to use to color the individuals (or rows) among the variable categories.

ellipse

a boolean : if TRUE, ellipses are plotted with the coloration of individuals (or rows).

Iselec

the individuals to select ; see the details section.

Rselec

the rows to select (for a CA res object) ; see the details section.

Cselec

the columns to select (for a CA res object) ; see the details section.

Icoef

a numerical coefficient to adjust the individuals selection rule ; see the details section.

Rcoef

a numerical coefficient to adjust the rows selection rule (for a CA res object) ; see the details section.

Ccoef

a numerical coefficient to adjust the columns selection rule (for a CA res object) ; see the details section.

figure.title

the text label to add before graph title.

graph

a boolean : if TRUE, graphs are ploted.

cex

an optional argument for the generic plot functions, used to adjust the size of the elements plotted.

options

Details

The Iselec argument (respectively Rselec or Cselec) is used in order to select a part of the elements that are drawn and described. For example, you can use either :
- Iselec = 1:5 then the individuals (respectively the rows or the columns) numbered 1 to 5 are drawn.
- Iselec = c("name1","name5") then the individuals (respectively the rows or the columns) named name1 and name5 are drawn.
- Iselec = "contrib 10" then the 10 active or illustrative individuals (respectively the rows or the columns) that have the highest contribution on the 2 dimensions of the plane are drawn.
- Iselec = "contrib" then the optimal number of active or illustrative individuals (respectively the rows or the columns) that have the highest contribution on the 2 dimensions of the plane are drawn.
- Iselec = "cos2 5" then the 5 active or illustrative individuals (respectively the rows or the columns) that have the highest cos2 on the 2 dimensions of the plane are drawn.
- Iselec = "cos2 0.8" then the active or illustrative individuals (respectively the rows or the columns) that have a cos2 higher to 0.8 on the plane are drawn.
- Iselec = "cos2" then the optimal number of active or illustrative individuals (respectively the rows or the columns) that have the highest cos2 on the 2 dimensions of the plane are drawn.

The Icoef argument (respectively Rcoef or Ccoef) is used in order to adjust the selection of the elements when based on Iselec = "contrib" or Iselec = "cos2". For example :
- if Icoef = 2, the threshold is 2 times higher, and thus 2 times more restrictive.
- if Icoef = 0.5, the threshold is 2 times lower, and thus 2 times less restrictive.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
graphHab(res.pca)

## End(Not run)

Individuals factor map

Description

Realise the optimised individuals graph

Usage

graphInd(res, file = "", dim = 1:2, Iselec = "contrib", Icoef = 1, 
         figure.title = "Figure", graph = TRUE, cex = 0.7, 
		 codeGraphInd = NULL, options=NULL)

Arguments

res

an object of class PCA or MCA.

file

the file path where to write the description in Rmarkdown language. If not specified, the description is written in the console.

dim

a 2 dimensional numerical vector giving the factorial dimensions to use for the representation (by default the first plane).

Iselec

the individuals to select ; see the details section.

Icoef

a numerical coefficient to adjust the individuals selection rule ; see the details section.

figure.title

the text label to add before graph title.

graph

a boolean : if TRUE, graphs are plotted.

cex

an optional argument for the generic plot functions, used to adjust the size of the elements plotted.

codeGraphInd

a character string corresponding to the code to use for the individuals graph.

options

Details

The Iselec argument is used in order to select a part of the individuals that are drawn and described. For example, you can use either :
- Iselec = 1:5 and then the individuals numbered 1 to 5 are drawn.
- Iselec = c("name1","name5") then the individuals named name1 and name5 are drawn.
- Iselec = "contrib 10" then the 10 active or illustrative individuals that have the highest contribution on the 2 dimensions of the plane are drawn.
- Iselec = "contrib" then the optimal number of active or illustrative individuals (respectively the variables, the rows or the columns) that have the highest contribution on the 2 dimensions of the plane are drawn.
- Iselec = "cos2 5" then the 5 active or illustrative individuals that have the highest cos2 on the 2 dimensions of the plane are drawn.
- Iselec = "cos2 0.8" then the active or illustrative individuals that have a cos2 higher to 0.8 on the plane are drawn.
- Iselec = "cos2" then the optimal number of active or illustrative individuals that have the highest cos2 on the 2 dimensions of the plane are drawn.

The Icoef argument is used in order to adjust the selection of the individuals when based on Iselec = "contrib" or Iselec = "cos2". For example :
- if Icoef = 2, the threshold is 2 times higher, and thus 2 times more restrictive.
- if Icoef = 0.5, the threshold is 2 times lower, and thus 2 times less restrictive.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
graphInd(res.pca)

## End(Not run)

Supplementary variables factor map

Description

Realise the optimised graph of supplementary variables

Usage

graphSup(res, file = "", dim = 1:2, Mselec = "cos2", Mcoef = 1, 
         figure.title = "Figure", graph = TRUE, cex = 0.7, options=NULL)

Arguments

res

an object of class PCA, CA or MCA.

file

the file path where to write the description in Rmarkdown language. If not specified, the description is written in the console.

dim

a 2 dimensional numerical vector giving the factorial dimensions to use for the representation (by default the first plane).

Mselec

the supplementary variables to select ; see the details section.

Mcoef

a numerical coefficient to adjust the supplementary variables selection rule ; see the details section.

figure.title

the text label to add before graph title.

graph

a boolean : if TRUE, graphs are plotted.

cex

an optional argument for the generic plot functions, used to adjust the size of the elements plotted.

options

Details

The Mselec argument is used in order to select a part of the illustrative variables that are drawn and described. For example, you can use either :
- Mselec = 1:5 then the illustrative variables numbered 1 to 5 are drawn.
- Mselec = c("name1","name5") then the illustrative variables named name1 and name5 are drawn.
- Mselec = "cos2 5" then the 5 illustrative variables that have the highest cos2 on the 2 dimensions of the plane are drawn.
- Mselec = "cos2 0.8" then the illustrative variables that have a cos2 higher to 0.8 on the plane are drawn.
- Mselec = "cos2" then the optimal number of illustrative variables that have the highest cos2 on the 2 dimensions of the plane are drawn.

The Mcoef argument is used in order to adjust the selection of the illustrative variables when based on Mselec = "cos2". For example :
- if Mcoef = 2, the threshold is 2 times higher, and thus 2 times more restrictive.
- if Mcoef = 0.5, the threshold is 2 times lower, and thus 2 times less restrictive.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
graphSup(res.pca)

## End(Not run)

Variables factor map

Description

Realise the optimised variables graph

Usage

graphVar(res, file = "", dim = 1:2, Vselec = "cos2", Vcoef = 1, 
         figure.title = "Figure", graph = TRUE, cex = 0.7, 
		 codeGraphVar=NULL, options=NULL)

Arguments

res

an object of class PCA or MCA.

file

the file path where to write the description in Rmarkdown language. If not specified, the description is written in the console.

dim

a 2 dimensional numerical vector giving the factorial dimensions to use for the representation (by default the first plane).

Vselec

the variables to select ; see the details section.

Vcoef

a numerical coefficient to adjust the variables selection rule ; see the details section.

figure.title

the text label to add before graph title.

graph

a boolean : if TRUE, graphs are plotted.

cex

an optional argument for the generic plot functions, used to adjust the size of the elements plotted.

codeGraphVar

a character string corresponding to the code to use for the variables graph.

options

Details

The Vselec argument is used in order to select a part of the variables that are drawn and described. For example, you can use either :
- Vselec = 1:5 then the variables numbered 1 to 5 are drawn.
- Vselec = c("name1","name5") then the variables named name1 and name5 are drawn.
- Vselec = "contrib 10" then the 10 active or illustrative variables that have the highest contribution on the 2 dimensions of the plane are drawn.
- Vselec = "contrib" then the optimal number of active or illustrative variables that have the highest contribution on the 2 dimensions of the plane are drawn.
- Vselec = "cos2 5" then the 5 active or illustrative variables that have the highest cos2 on the 2 dimensions of the plane are drawn.
- Vselec = "cos2 0.8" then the active or illustrative variables that have a cos2 higher to 0.8 on the plane are drawn.
- Vselec = "cos2" then the optimal number of active or illustrative variables that have the highest cos2 on the 2 dimensions of the plane are drawn.

The Vcoef argument is used in order to adjust the selection of the variables when based on Vselec = "contrib" or Vselec = "cos2". For example :
- if Vcoef = 2, the threshold is 2 times higher, and thus 2 times more restrictive.
- if Vcoef = 0.5, the threshold is 2 times lower, and thus 2 times less restrictive.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
graphVar(res.pca)

## End(Not run)

Inertia distribution analysis

Description

Analysis of the inertia distribution among each axis, the amount and the significativity

Usage

inertiaDistrib(res, file = "", ncp = NULL, q = 0.95, time = "10000L", 
        parallel = TRUE, figure.title = "Figure", graph = TRUE, options = NULL)

Arguments

res

an object of class PCA, CA or MCA.

file

the file path where to write the description in Rmarkdown language. If not specified, the description is written in the console.

ncp

an integer to force the number of dimension to analyse.

q

the quantile of computed values to use as reference value (ie. the confidence about the signification of dimensions).

time

parallel

a boolean : if TRUE, the computation uses map reduce on the processor cores to increase the performance. Useful for huge datasets.

figure.title

the text label to add before graph title.

graph

a boolean : if TRUE, graphs are plotted.

options

Value

ncp

the number of significant dimensions (or the dimensions kept).

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
inertiaDistrib(res.pca, q = 0.95, time = "10s")

data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
inertiaDistrib(res.ca, q = 0.99, time = "10000L")

data(tea)
res.mca = MCA(tea, quanti.sup = 19,quali.sup = 20:36, graph = FALSE)
inertiaDistrib(res.mca, dim = 1:8, q = 0.90, time = "10s")

## End(Not run)

Outliers detection

Description

Detection of singular individuals that concentrates too much inertia.

Usage

outliers(res, file = "", Vselec = "cos2", Vcoef = 1, nmax = 10, 
         figure.title = "Figure", graph = TRUE, cex = 0.7, options = NULL)

Arguments

res

an object of class PCA or MCA.

file

a numerical vector giving the factorial dimensions for with to compute the eigen values calculation.

Vselec

the variables to select ; see the details section.

Vcoef

a numerical coefficient to adjust the variables selection rule ; see the details section.

nmax

an integer giving the maximum number of variables to illustrate each outlier (by default 10).

figure.title

the text label to add before graph title.

graph

a boolean : if TRUE, graphs are plotted.

cex

an optional argument for the generic plot functions, used to adjust the size of the elements plotted.

options

a character string that gives the output options for the figures. If NULL, options="r, echo = FALSE, fig.align = 'center', fig.height = 3.5, fig.width = 5.5" for linux and Mac and options="r, echo = FALSE, fig.height = 3.5, fig.width = 5.5" for Windows

Details

The algorithm detects an individual as an outlier if its contribution to the plane if higher to 3 standard deviation.

The Vselec argument is used in order to select a part of the variables that are drawn and described. For example, you can use either :
- Vselec = 1:5 then the variables numbered 1 to 5 are drawn.
- Vselec = c("name1","name5") then the variables named name1 and name5 are drawn.
- Vselec = "contrib 10" then the 10 active or illustrative variables that have the highest contribution on the 2 dimensions of the plane are drawn.
- Vselec = "contrib" then the optimal number of active or illustrative variables that have the highest contribution on the 2 dimensions of the plane are drawn.
- Vselec = "cos2 5" then the 5 active or illustrative variables that have the highest cos2 on the 2 dimensions of the plane are drawn.
- Vselec = "cos2 0.8" then the active or illustrative variables that have a cos2 higher to 0.8 on the plane are drawn.
- Vselec = "cos2" then the optimal number of active or illustrative variables that have the highest cos2 on the 2 dimensions of the plane are drawn.

The Vcoef argument is used in order to adjust the selection of the variables when based on Vselec = "contrib" or Vselec = "cos2". For example :
- if Vcoef = 2, the threshold is 2 times higher, and thus 2 times more restrictive.
- if Vcoef = 0.5, the threshold is 2 times lower, and thus 2 times less restrictive.

Value

new.res

the res object without the outliers (they are completely eliminated).

res.out

the res object with the outliers as supplementary individuals.

memory

the original res object.

N

the number of outliers.

ID

the label of outliers.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
outliers(res.pca, file = "PCA.Rmd")

## End(Not run)

Read Rmarkdown file

Description

Compile and open a Rmarkdown file.

Usage

readRmd(file, document = "html_document")

Arguments

file

the file path where to write the description in Rmarkdown langage. If not specified, the description is written in the console.

document

a character vector giving the document format desired between "word_document", "pdf_document" and "html_document". This have to be any of those indicated in the file config (by createRmd).

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
create.rmd(res.pca, file = "PCA.Rmd", document = "pdf_document")
readRmd(file = "PCA.Rmd", document = "pdf_document")

data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
create.rmd(res.ca, file = "CA.Rmd", document = "html_document")
readRmd(file = "CA.Rmd", document = "html_document")

data(tea)
res.mca = MCA(tea, quanti.sup = 19,quali.sup = 20:36, graph = FALSE)
create.rmd(res.mca, file = "MCA.Rmd", document = c("word_document", "pdf_document"))
readRmd(file = "MCA.Rmd", document = "word_document")

## End(Not run)

File script

Description

Read the script of a file and return each line as a character chain

Usage

scriptRmd(file, output = "code.R")

Arguments

file

the file path to read.

output

the file path to write the R code.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
create.rmd(res.pca, file = "PCA.Rmd", document = "pdf_document")
scriptRmd(file = "PCA.Rmd")

data(children)
res.ca = CA(children, row.sup = 15:18, col.sup = 6:8, graph = FALSE)
create.rmd(res.ca, file = "CA.Rmd", document = "html_document")
scriptRmd(file = "CA.Rmd")

data(tea)
res.mca = MCA(tea, quanti.sup = 19,quali.sup = 20:36, graph = FALSE)
create.rmd(res.mca, file = "MCA.Rmd", document = c("word_document", "pdf_document"))
scriptRmd(file = "MCA.Rmd")

## End(Not run)

Graphical elements selection

Description

Select the best elements to plot in a graph

Usage

selection(res, dim = 1:2, margin = 1, selec = "cos2", coef = 1)

Arguments

res

an object of class PCA, CA or MCA.

dim

a 2 dimensional numerical vector giving the factorial dimensions to use for the representation (by default the first plane).

margin

an integer (by default 1). If equals 1, the function computes on the individuals (or rows). If equals 2, the function computes on the active variables (or columns). If equals 3, the function computes on the supplementary variables.

selec

the elements to select ; see the details section.

coef

a numerical coefficient to adjust the elements selection rule ; see the details section.

Details

The selec argument is used in order to select a part of the elements that are drawn and described. For example, you can use either :
- selec = 1:5 then the elements numbered 1 to 5 are drawn.
- selec = c("name1","name5") then the elements named name1 and name5 are drawn.
- selec = "contrib 10" then the 10 active or illustrative elements that have the highest contribution on the 2 dimensions of the plane are drawn.
- selec = "contrib" then the optimal number of active or illustrative elements that have the highest contribution on the 2 dimensions of the plane are drawn.
- selec = "cos2 5" then the 5 active or illustrative elements that have the highest cos2 on the 2 dimensions of the plane are drawn.
- selec = "cos2 0.8" then the active or illustrative elements that have a cos2 higher to 0.8 on the plane are drawn.
- selec = "cos2" then the optimal number of active or illustrative elements that have the highest cos2 on the 2 dimensions of the plane are drawn.

The coef argument is used in order to adjust the selection of the elements when based on selec = "contrib" or selec = "cos2". For example :
- if coef = 2, the threshold is 2 times higher, and thus 2 times more restrictive.
- if coef = 0.5, the threshold is 2 times lower, and thus 2 times less restrictive.

Value

drawn

the elements selected.

what.drawn

the criterion of selection (as a sentence).

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
selection(res.pca, margin = 1, selec = "contrib 10")

## End(Not run)

Analysis class

Description

Return the class of the factorial object (ie. the kind of analysis performed)

Usage

whichFacto(res)

Arguments

res

an object of class PCA, CA or MCA.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
whichFacto(res.pca)

## End(Not run)

Write Rmarkdown file

Description

Writes text or dumps a variable in a Rmarkdown file, and declares the utilisation and the configuration of a chunk.

Usage

writeRmd(..., file = "", append = TRUE, sep = " ", end = "\n", dump = FALSE, 
         start = FALSE, stop = FALSE, options = NULL)

Arguments

...

some R objects or other arguments to pass to the cat function.

file

the file path where to write the description in Rmarkdown langage. If not specified, the description is written in the console.

append

a boolean, if TRUE the text is written at the end of the file. Else it is overwritten.

sep

a character chain to insert between each element written in the file (by default a blank space).

end

a character chain to add at the end of the text written in the file (by default a line break).

dump

a boolean : if TRUE, the text send to the function is interpreted as a variable name. A dump as to be written in a chunck declaration.

start

a boolean : if TRUE, the text written is preceded by a beginning chunk declaration.

stop

a boolean : if TRUE, the text written is preceded by a ending chunk declaration.

options

a character chain listing the options to declare for a chunk declaration.

Details

To learn about all the possible chunck options, see https://yihui.org/knitr/options.
Anyway, to declare a R langage chunk, write at least "r" as option.

Author(s)

Simon Thuleau and Francois Husson

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
res.pca = PCA(decathlon, quanti.sup = c(11:12), quali.sup = c(13), graph = FALSE)
create.rmd(res.pca, file = "PCA.Rmd", document = "pdf_document")

drawn = selection(res.pca)$drawn

writeRmd(start = TRUE, options = "r, echo = FALSE, fig.align = 'center', fig.height = 3.5, 
         fig.width = 5.5", file = "PCA.Rmd", end = "")
writeRmd("drawn", file = file, dump = TRUE)
writeRmd("plot.PCA(res, select = drawn, choix = 'ind', invisible = 'quali', title = '')", 
         stop = TRUE, file = "PCA.Rmd")
           
writeRmd("**", figure.title, " - ", "Individuals factor map (PCA)", "**", file = "PCA.Rmd", 
         sep = "")

## End(Not run)

Automatic Description of Factorial Analysis

Description

Details

Author(s)

See Also

Resume factorial Analysis

Description

Usage

Arguments

Details

Value

Author(s)

Examples

Classification description

Description

Usage

Arguments

Details

Value

Author(s)

See Also

Examples

Create Rmarkdown file

Description

Usage

Arguments

Author(s)

See Also

Examples

Factorial dimensions description

Description

Usage

Arguments

Details

Author(s)

See Also

Examples

Number of active dimensions

Description

Usage

Arguments

Author(s)

Examples

Significant dimensions identification

Description

Usage

Arguments

Value

Author(s)

See Also

Examples

Reference eigen value

Description

Usage

Arguments

Value

Author(s)

See Also

Examples

Factorial graphs

Description

Usage

Arguments

Details

Author(s)

See Also

Examples

Factorial parameters

Description

Usage

Arguments

Value

Author(s)

See Also

Examples

Correspondance Analysis factor map

Description

Usage

Arguments

Details