Package 'IBCF.MTME'

barplot.IBCFY

Description

Barplot of the results from IBCFY object

Usage

## S3 method for class 'IBCFY'
barplot(height, select = "Pearson", ...)

Arguments

height	IBCFY object IBCFY object, result of use the IBCF.Years() function
select	character By default ('Pearson'), plot the Pearson Correlations of the IBCF Object, else ('MAAPE'), plot the MAAPE of the IBCF Object.
...	Further arguments passed to or from other methods.

---

Cross-Validation with Random Partitions

Description

This method consists of randomly dividing the training data set and the test data set. For each division, the approximation function is adjusted from the training data and calculates the output values for the test data set. The result corresponds to the arithmetic mean of the values obtained for the different divisions.

Usage

CV.RandomPart(DataSet, NPartitions = 10, PTesting = 0.35,
  Traits.testing = NULL, Set_seed = NULL)

Arguments

DataSet	data.frame The data set object is a data.frame object that contains 4 columns in the Tidy data format: $Line is the Line or genotype identifier, and the name of this column could change. $Env is the name of the evaluated environment (s). $Trait is the name of the evaluated trait (s). $Response Variable response obtained for the row corresponding to line and environment.
NPartitions	integer Number of Partitions for the Cross-Validation. Is 10 by default.
PTesting	Double Percentage of Testing for the Cross-Validation. Is 0.35 by default.
Traits.testing	character By default is null and use all the traits to fit the model, else only part of the traits specified be used to fit the model.
Set_seed	integer Number of seed for reproducible research. Is NULL by default.

Value

List A list object with length of NPartitions, every index has a matrix $n \times x$, where $n$ is the number of NLines and $x$ is the number of NEnv $\times$ NTraits. The values inside is 1 for training and 2 for testing.

Examples

## Not run: 
  library(IBCF.MTME)
  data('Wheat_IBCF')

  CV.RandomPart(Wheat_IBCF)
  CV.RandomPart(Wheat_IBCF, NPartitions = 10)
  CV.RandomPart(Wheat_IBCF, Traits.testing = 'DH')
  CV.RandomPart(Wheat_IBCF, NPartitions = 10, PTesting = .35)
  CV.RandomPart(Wheat_IBCF, NPartitions = 10, Traits.testing = 'DH')
  CV.RandomPart(Wheat_IBCF, NPartitions = 10, PTesting = .35, Set_seed = 5)
  CV.RandomPart(Wheat_IBCF, NPartitions = 10, PTesting = .35, Traits.testing = 'DH')
  CV.RandomPart(Wheat_IBCF, NPartitions = 10, PTesting = .35, Traits.testing = 'DH', Set_seed = 5 )

## End(Not run)

---

Tidy data format to Matrix format

Description

Tidy data format to Matrix format

Usage

getMatrixForm(Tidy_DataSet, onlyTrait = FALSE)

Arguments

Tidy_DataSet	data.frame object that contains 4 columns: $Line: Line or genotype identifier, and the name of this column could change. $Env: Name of the evaluated environment (s). $Trait: Name of the evaluated trait (s). $Response: Variable response obtained for the row corresponding to line and environment.
onlyTrait	logical by default is FALSE, if is TRUE only the column $Trait is transformed.

Value

A data.frame object with the $Response divided by $Traits columns.

Examples

## Not run: 
  data('Wheat_IBCF')
  M <- getMatrixForm(Wheat_IBCF)

## End(Not run)

## Not run: 
  data('Year_IBCF')
  M.Y <- getMatrixForm(Year_IBCF, onlyTrait = T)

## End(Not run)

---

Matrix format to Tidy data format

Description

Matrix format to Tidy data format

Usage

getTidyForm(Matrix_DataSet, onlyTrait = FALSE)

Arguments

Matrix_DataSet	A data.frame object with the response values divided in $n$ environments or traits columns
onlyTrait	logical by default is FALSE, if is TRUE only is considered the $Trait column.

Value

A data.frame object with the $Response divided by $Traits columns.

Examples

## Not run: 
  data('Wheat_IBCF')
  M <- getMatrixForm(Wheat_IBCF)
  Tidy <- getTidyForm(M)

## End(Not run)

## Not run: 
  data('Year_IBCF')
  M.Y <- getMatrixForm(Year_IBCF, onlyTrait = T)
  Tidy.Y <- getTidyForm(M.Y, onlyTrait = T)

## End(Not run)

---

IBCF

Description

Item Based Collaborative Filtering for multi-trait and multi-environment data.

Usage

IBCF(object, dec = 4)

Arguments

object	list CrossValidation object, is obtained from CV.RandomPartition function.
dec	integer Number of decimals to print in the results.

Value

A list with the next components

NPartitions	integer Number of partitions used for testing data
predictions_Summary	data.frame A data.frame with the results of the test
Predictions	list A list with the predicted results for each partition

Examples

## Not run: 
  library(IBCF.MTME)
  data('Wheat_IBCF')

  CV <- CV.RandomPart(Wheat_IBCF)
  IBCF(CV)

## End(Not run)

---

IBCF.MTME: Item Based Collaborative Filtering for Multi-Trait and Multi-Environment Data.

Description

The Item Based Collaborative Filtering for Multi-Trait and Multi-Environment Data (IBCF.MTME) package was developed to implement the item based collaborative filtering (IBCF) method for continues phenotypes in the context of plant breeding where data are collected for various traits that were studied in various environments. It is important to point out that the main difference of this package with the available packages that can implement IBCF is that this package was developed for continuous phenotypes which cannot be implemented in the current packages that can implement IBCF that only work for binary and ordinary phenotypes.

---

IBCF.Years

Description

Item Based Collaborative Filtering for Years data

Usage

IBCF.Years(DataSet, colYears = 1, colID = 2, Years.testing = "",
  Traits.testing = "", dec = 4)

Arguments

DataSet	data.frame A data set in Matrix Form.
colYears	string or integer A name or the position of the 'Years' column just in case that is not the first column.
colID	string or integer A name or the position of the 'ID' column, just in case that is not the second column.
Years.testing	vector A vector with the names of the years to use in test.
Traits.testing	vector A vector with the names of the traits to use in test.
dec	integer Number of decimals to print in the results.

Value

A list with the next components

Year.testing	vector a vector with the Years used for the testing data
Traits.testing	vector a vector with the Traits used for the testing data
Data_Obs_Pred	data.frame Contains the values observed and predicted (the predicted values has '.1' after the name)
predictions_Summary	data.frame Contains the summary of the correlation of the predictions and the MAAPE

Examples

## Not run: 
  library(IBCF.MTME)
  data('Year_IBCF')
  DataSet <- getMatrixForm(Year_IBCF, onlyTrait = TRUE)
  IBCF.Years(DataSet , Years.testing = c('2015', '2016'), Traits.testing = c('T5', 'T6'))


## End(Not run)

---

Plot IBCF graph

Description

Plot from IBCF object

Usage

## S3 method for class 'IBCF'
plot(x, select = "Pearson", ...)

Arguments

x	IBCF object IBCF object, result of use the IBCF() function
select	character By default ('Pearson'), plot the Pearson Correlations of the IBCF Object, else ('MAAPE'), plot the MAAPE of the IBCF Object.
...	Further arguments passed to or from other methods.

---

Print IBCF information object

Description

Print IBCF information object

Usage

## S3 method for class 'IBCF'
print(x, ...)

Arguments

x	IBCF object
...	Further arguments passed to or from other methods.

Value

printeable object

---

Print IBCFY information object

Description

Print IBCFY information object

Usage

## S3 method for class 'IBCFY'
print(x, ...)

Arguments

x	IBCFY object
...	Further arguments passed to or from other methods.

Value

printeable object

---

Summary

Description

Summary of IBCF object

Usage

## S3 method for class 'IBCF'
summary(object, information = "compact", digits = 4,
  ...)

Arguments

object	IBCF object IBCF object, result of use the IBCF() function
information	string ...
digits	numeric ...
...	Further arguments passed to or from other methods.

---

Summary

Description

Summary of IBCFY object

Usage

## S3 method for class 'IBCFY'
summary(object, digits = 4, ...)

Arguments

object	IBCFY object IBCFY object, result of use the IBCF.Years() function
digits	numeric Number of digits of the output.
...	Further arguments passed to or from other methods.

---

Wheat Data

Description

The package includes a data set based on a portion of the data used in the study of Montesinos-Lopez, O. A.; Montesinos-Lopez, A.; Crossa, J.; Toledo, F. H.; Montesinos-Lopez, J. C.; Singh, P. & Salinas-Ruiz, J. (2017). A Bayesian Poisson-lognormal Model for Count Data for Multiple-Trait Multiple-Environment Genomic-Enabled Prediction. G3: Genes|Genomes|Genetics 7(5):1595–1606. http://doi.org/10.1534/g3.117.039974. The data set consists of 250 wheat lines evaluated in 3 environments and 4 distinct traits, i.e. 3000 observations.

Usage

data(Wheat_IBCF)

Format

a TidyData format, 3000 row per 4 columns.

Author(s)

Montesinos-Lopez, O. A.

---

Year_IBCF Data

Description

Dataset based on simulated data with the next code:

set.seed(2)
A <- matrix(0.65,ncol=12,nrow=12)
diag(A) <- 1
Sdv <- diag(c(0.9^0.5,0.8^0.5,0.9^0.5,0.8^0.5,0.86^0.5,0.7^0.5,0.9^0.5,0.8^0.5,0.9^0.5,0.7^0.5,0.7^0.5,0.85^0.5))

Sigma <- Sdv
No.Lines <- 60
Z <- rmvnorm(No.Lines,mean=c(5,5.5,6,5.5,7,6.5,6.0,7,6.6,8,6.3,8),sigma=Sigma)
Years <- c(rep(2014,20),rep(2015,20),rep(2016,20))
Gids <- c(1:No.Lines)

Data.Final <- data.frame(cbind(Years,Gids,Z))

colnames(Data.Final) <- c("Years","Gids","T1","T2","T3","T4","T5","T6","T7","T8","T9","T10","T11","T12")
head(Data.Final)
Year_IBCF <- getTidyForm(Data.Final, onlyTrait = T)

Usage

data(Year_IBCF)

Format

a TidyData format, 750 row per 4 columns.

Author(s)

Montesinos-Lopez, O. A.

---