[epclust.git] / code / README

To compile source code :

   (mkdir -p (src|test)/build
   cd (src|test)/build
   cmake ..
   make

Usage :

   mpirun -np nbProcess ppam.exe cluster ifilename nbSeriesInChunk nbClusters randomize p_for_dissims

Where :
   nbProcess = number of simultaneous processes
   ifilename = path to serialized dataset (read below)
   nbSeriesInChunk = number of time-series to process sequentially
   nbClusters = number of clusters
   randomize = 1 to dispatch time-series at random. 0 to process them in order
   p_for_dissims = the 'p' of L_p distance used to compute dissimilarities

Note : custom [de]serialization. Consider writing your own 
in src/TimeSeries/ folder if you plan to test the package.

See also src/main.c for the details.
Commit	Line	Data
	1	To compile source code :
	2
	3	(mkdir -p (src\|test)/build
	4	cd (src\|test)/build
	5	cmake ..
	6	make
	7
	8	Usage :
	9
	10	mpirun -np nbProcess ppam.exe cluster ifilename nbSeriesInChunk nbClusters randomize p_for_dissims
	11
	12	Where :
	13	nbProcess = number of simultaneous processes
	14	ifilename = path to serialized dataset (read below)
	15	nbSeriesInChunk = number of time-series to process sequentially
	16	nbClusters = number of clusters
	17	randomize = 1 to dispatch time-series at random. 0 to process them in order
	18	p_for_dissims = the 'p' of L_p distance used to compute dissimilarities
	19
	20	Note : custom [de]serialization. Consider writing your own
	21	in src/TimeSeries/ folder if you plan to test the package.
	22
	23	See also src/main.c for the details.