Welcome to pydiodon’s documentation!¶
A python library for linear dimension reduction.
Identity card
 authors:
Alain Franc
JeanMarc Frigerio
 mail:
 contributors:
Olivier Coulaud
Romain Peressoni
Florent Pruvost
 maintainer:
Alain Franc
 started:
21/02/17
 version:
23.06.12
 release:
0.0.4
 licence:
GPL3.0 or later
This file is part of diodon project. You can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or any later version.
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
Information: the development of this library still is ongoing. When a function has not been tested or its development still in infancy, this is indicated in its documentation, and it is advised not to use it.
Functions¶
Correspondance Analysis of an array 

Multidimensional Scaling of a distance or dissimilarity array 

Principal Component Analysis 

Computes the eigenvalues and eigenvectors of a matrix 

SVD of a (large) matrix by Gaussian Random Projection 

Bicentering a matrix 

Centering operator for a matrix 

centers a matrix columnwise 

centers a matrix rowwise 

Scales a matrix columnwise 

Gets the correlation matrix 

Computes a Gram matrix knowing a distance matrix 

core method for PCA (Principal Component Analysis) of an array 

PCA of an array with metrics on rows and/or columns  without guaranty 

PCA of an array with instrumental variables 

Builds the projection operator on space spanned by the columns of an array 

A generic function for loading datasets as numpy arrays 

Loads an ascii file as a numpy array 

loads a hdf5 file as a numpy array 

Loads datasets provided as examples after having cloned companion git of (py)diodon. 

A generic function for saving a numpy array as a file 

Write an ascii file 

Write a hdf5 file 

Plots the singular or eigenvalues 

Scatter plot of the result of a Principal Component Analysis 

Plots principal components as lines smoothed with cublic splines, one per item 

plots the quality per item 

Scatter plot of the principal components with each dot colored according to the cumulated quality of the item for a given axis 

Plots the correlations between the variables 

Plots a heatmap of the coordinates of the principal axis 

Plots a heatmap of the correlation matrix 

Scatter plot of the result of a Correspondence Analysis 

Display a label of one dot selected with the mouse in a scatter plot 

Builds the density heatmap of the point cloud of the components of a PCA 