Dimension Reduction, Regression and Discrimination for Chemometrics
Centers of classes
AIC and Cp for Univariate PLSR Models
Block autoscaling
CG Least Squares Models
Duplicated rows in datasets
Find and count NA values in a dataset
CovSel
Derivation by finite difference
Polynomial de-trend transformation
Degrees of freedom of Univariate PLSR Models
Direct KPLSR Models
Direct KRR Models
Multivariate normal probability density
Summary statistics of data subsets
Table of dummy variables
External parameter orthogonalization (EPO)
Matrix of distances
Factorial discriminant analysis
KNN selection
Kernel functions
Cross-validation
Tuning of predictive models on a validation dataset
Display of the first part of a data set
Resampling of spectra by interpolation methods
KNN-DA
KNN-R
KPCA
KPLSR Models
KPLSR-DA models
KRR (LS-SVMR)
KRR-DA models
LDA and QDA
Linear regression models
LMR-DA models
Locally weighted models
Aggregation of KNN-LWPLSDA models with different numbers of LVs
Aggregation of KNN-LWPLSR models with different numbers of LVs
KNN-LWPLSR
KNN-LWPLS-DA Models
Between and within covariance matrices
Smoothing by moving average
multi-block PLSDA models
MBPLSR or MBPLSDA analysis steps
multi-block PLSR algorithms
Orthogonal distances from a PCA or PLS score space
Orthogonalization of a matrix to another matrix
PCA algorithms
Moore-Penrose pseudo-inverse of a matrix
Jittered plot
Plotting errors rates
Plotting spectra
Plotting Missing Data in a Matrix
2-d scatter plot
PLSDA with aggregation of latent variables
PLSDA models
PLSR with aggregation of latent variables
PLSR or PLSDA analysis steps
PLSR algorithms
Removing vertical gaps in spectra
Linear Ridge Regression
RR-DA models
Within-class sampling
Duplex sampling
Kennard-Stone sampling
Savitzky-Golay smoothing
Score distances (SD) in a PCA or PLS score space
Residuals and prediction error rates
Segments for cross-validation
Heuristic selection of the dimension of a latent variable model with t...
Standard normal variate transformation (SNV)
Block dimension reduction by SO-PLS-DA
SOPLSR or SOPLSDA analysis steps
Block dimension reduction by SO-PLS
Source R functions in a directory
Description of the quantitative variables of a data set
SVM Regression and Discrimination
Generic transform function
Variable Importance in Projection (VIP)
Distance-based weights
Matrix fitting from a PCA or PLS model
Data exploration and prediction with focus on high dimensional data and chemometrics. The package was initially designed about partial least squares regression and discrimination models and variants, in particular locally weighted PLS models (LWPLS). Then, it has been expanded to many other methods for analyzing high dimensional data. The name 'rchemo' comes from the fact that the package is orientated to chemometrics, but most of the provided methods are fully generic to other domains. Functions such as transform(), predict(), coef() and summary() are available. Tuning the predictive models is facilitated by generic functions gridscore() (validation dataset) and gridcv() (cross-validation). Faster versions are also available for models based on latent variables (LVs) (gridscorelv() and gridcvlv()) and ridge regularization (gridscorelb() and gridcvlb()).