[epclust.git] / epclust / R / main.R

#' @include defaults.R

#' @title Cluster power curves with PAM in parallel
#'
#' @description Groups electricity power curves (or any series of similar nature) by applying PAM
#' algorithm in parallel to chunks of size \code{nb_series_per_chunk}
#'
#' @param data Access to the data, which can be of one of the three following types:
#' \itemize{
#'   \item data.frame: each line contains its ID in the first cell, and all values after
#'   \item connection: any R connection object (e.g. a file) providing lines as described above
#'   \item function: a custom way to retrieve the curves; it has two arguments: the start index
#'     (start) and number of curves (n); see example in package vignette.
#' }
#' @param K1 Number of super-consumers to be found after stage 1 (K1 << N)
#' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
#' @param ntasks Number of tasks (parallel iterations to obtain K1 medoids); default: 1.
#'   Note: ntasks << N, so that N is "roughly divisible" by N (number of series)
#' @param nb_series_per_chunk (Maximum) number of series in each group, inside a task
#' @param min_series_per_chunk Minimum number of series in each group
#' @param writeTmp Function to write temporary wavelets coefficients (+ identifiers);
#'   see defaults in defaults.R
#' @param readTmp Function to read temporary wavelets coefficients (see defaults.R)
#' @param wf Wavelet transform filter; see ?wt.filter. Default: haar
#' @param WER "end" to apply stage 2 after stage 1 has iterated and finished, or "mix"
#'   to apply it after every stage 1
#' @param ncores_tasks number of parallel tasks (1 to disable: sequential tasks)
#' @param ncores_clust number of parallel clusterings in one task
#'
#' @return A data.frame of the final medoids curves (identifiers + values)
#'
#' @examples
#' getData = function(start, n) {
#'   con = dbConnect(drv = RSQLite::SQLite(), dbname = "mydata.sqlite")
#'   df = dbGetQuery(con, paste(
#'     "SELECT * FROM times_values GROUP BY id OFFSET ",start,
#'     "LIMIT ", n, " ORDER BY date", sep=""))
#'   return (df)
#' }
#' cl = epclust(getData, K1=200, K2=15, ntasks=1000, nb_series_per_chunk=5000, WER="mix")
#' @export
epclust = function(data, K1, K2,
	ntasks=1, nb_series_per_chunk=50*K1, min_series_per_chunk=5*K1,
	writeTmp=defaultWriteTmp, readTmp=defaultReadTmp, wf="haar", WER="end",
	ncores_tasks=1, ncores_clust=4)
{
	#TODO: setRefClass(...) to avoid copy data:
	#http://stackoverflow.com/questions/2603184/r-pass-by-reference

	#0) check arguments
	if (!is.data.frame(data) && !is.function(data))
		tryCatch(
			{
				if (is.character(data))
				{
					data_con = file(data, open="r")
				} else if (!isOpen(data))
				{
					open(data)
					data_con = data
				}
			},
			error="data should be a data.frame, a function or a valid connection")
	if (!is.integer(K) || K < 2)
		stop("K should be an integer greater or equal to 2")
	if (!is.integer(nb_series_per_chunk) || nb_series_per_chunk < K)
		stop("nb_series_per_chunk should be an integer greater or equal to K")
	if (!is.function(writeTmp) || !is.function(readTmp))
		stop("read/writeTmp should be functional (see defaults.R)")
	if (WER!="end" && WER!="mix")
		stop("WER takes values in {'end','mix'}")
	#concerning ncores, any non-integer type will be treated as "use parallel:detectCores()/4"

	#1) acquire data (process curves, get as coeffs)
	#TODO: for data.frame and custom function, run in parallel (connections are sequential[?!])
	index = 1
	nb_curves = 0
	repeat
	{
		coeffs_chunk = NULL
		if (is.data.frame(data))
		{
			#full data matrix
			if (index < nrow(data))
			{
				coeffs_chunk = curvesToCoeffs(
					data[index:(min(index+nb_series_per_chunk-1,nrow(data))),], wf)
			}
		} else if (is.function(data))
		{
			#custom user function to retrieve next n curves, probably to read from DB
			coeffs_chunk = curvesToCoeffs( data(index, nb_series_per_chunk), wf )
		} else
		{
			#incremental connection
			#TODO: find a better way to parse than using a temp file
			ascii_lines = readLines(data_con, nb_series_per_chunk)
			if (length(ascii_lines > 0))
			{
				series_chunk_file = ".tmp/series_chunk"
				writeLines(ascii_lines, series_chunk_file)
				coeffs_chunk = curvesToCoeffs( read.csv(series_chunk_file), wf )
			}
		}
		if (is.null(coeffs_chunk))
			break
		writeTmp(coeffs_chunk)
		nb_curves = nb_curves + nrow(coeffs_chunk)
		index = index + nb_series_per_chunk
	}
	if (exists(data_con))
		close(data_con)
	if (nb_curves < min_series_per_chunk)
		stop("Not enough data: less rows than min_series_per_chunk!")

	#2) process coeffs (by nb_series_per_chunk) and cluster them in parallel
	library(parallel)
	cl_tasks = parallel::makeCluster(ncores_tasks)
	#Nothing to export because each worker retrieve and put data from/on files (or DB)
	#parallel::clusterExport(cl=cl, varlist=c("nothing","to","export"), envir=environment())
	#TODO: be careful of writing to a new temp file, then flush initial one, then re-use it...
	res_tasks = parallel::parSapply(cl_tasks, 1:ntasks, function() {
		cl_clust = parallel::makeCluster(ncores_clust)
		repeat
		{
			#while there are jobs to do
			#(i.e. size of tmp "file" is greater than ntasks * nb_series_per_chunk)
			nb_workers = nb_curves %/% nb_series_per_chunk
			indices = list()
			#indices[[i]] == (start_index,number_of_elements)
			for (i in 1:nb_workers)
				indices[[i]] = c(nb_series_per_chunk*(i-1)+1, nb_series_per_chunk)
			remainder = nb_curves %% nb_series_per_chunk
			if (remainder >= min_series_per_chunk)
			{
				nb_workers = nb_workers + 1
				indices[[nb_workers]] = c(nb_curves-remainder+1, nb_curves)
			} else if (remainder > 0)
			{
				#spread the load among other workers
				#...
			}
			res_clust = parallel::parSapply(cl, indices, processChunk, K, WER=="mix")
			#C) flush tmp file (current parallel processes will write in it)
		}
		parallel:stopCluster(cl_clust)
	})
	parallel::stopCluster(cl_tasks)

	#3) readTmp last results, apply PAM on it, and return medoids + identifiers
	final_coeffs = readTmp(1, nb_series_per_chunk)
	if (nrow(final_coeffs) == K)
	{
		return ( list( medoids=coeffsToCurves(final_coeffs[,2:ncol(final_coeffs)]),
			ids=final_coeffs[,1] ) )
	}
	pam_output = getClusters(as.matrix(final_coeffs[,2:ncol(final_coeffs)]), K)
	medoids = coeffsToCurves(pam_output$medoids, wf)
	ids = final_coeffs[,1] [pam_output$ranks]

	#4) apply stage 2 (in parallel ? inside task 2) ?)
	if (WER == "end")
	{
		#from center curves, apply stage 2...
		#TODO:
	}

	return (list(medoids=medoids, ids=ids))
}

processChunk = function(indice, K, WER)
{
	#1) retrieve data
	coeffs = readTmp(indice[1], indice[2])
	#2) cluster
	cl = getClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K)
	#3) WER (optional)
	#TODO:
}

#TODO: difficulté : retrouver courbe à partir de l'identifiant (DB ok mais le reste ?)
#aussi : que passe-t-on aux noeuds ? curvesToCoeffs en // ?
#enfin : WER ?!
#TODO: bout de code qui calcule les courbes synchrones après étapes 1+2 à partir des ID médoïdes
Commit	Line	Data
	1	#' @include defaults.R
	2
	3	#' @title Cluster power curves with PAM in parallel
	4	#'
	5	#' @description Groups electricity power curves (or any series of similar nature) by applying PAM
	6	#' algorithm in parallel to chunks of size \code{nb_series_per_chunk}
	7	#'
	8	#' @param data Access to the data, which can be of one of the three following types:
	9	#' \itemize{
	10	#' \item data.frame: each line contains its ID in the first cell, and all values after
	11	#' \item connection: any R connection object (e.g. a file) providing lines as described above
	12	#' \item function: a custom way to retrieve the curves; it has two arguments: the start index
	13	#' (start) and number of curves (n); see example in package vignette.
	14	#' }
	15	#' @param K1 Number of super-consumers to be found after stage 1 (K1 << N)
	16	#' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
	17	#' @param ntasks Number of tasks (parallel iterations to obtain K1 medoids); default: 1.
	18	#' Note: ntasks << N, so that N is "roughly divisible" by N (number of series)
	19	#' @param nb_series_per_chunk (Maximum) number of series in each group, inside a task
	20	#' @param min_series_per_chunk Minimum number of series in each group
	21	#' @param writeTmp Function to write temporary wavelets coefficients (+ identifiers);
	22	#' see defaults in defaults.R
	23	#' @param readTmp Function to read temporary wavelets coefficients (see defaults.R)
	24	#' @param wf Wavelet transform filter; see ?wt.filter. Default: haar
	25	#' @param WER "end" to apply stage 2 after stage 1 has iterated and finished, or "mix"
	26	#' to apply it after every stage 1
	27	#' @param ncores_tasks number of parallel tasks (1 to disable: sequential tasks)
	28	#' @param ncores_clust number of parallel clusterings in one task
	29	#'
	30	#' @return A data.frame of the final medoids curves (identifiers + values)
	31	#'
	32	#' @examples
	33	#' getData = function(start, n) {
	34	#' con = dbConnect(drv = RSQLite::SQLite(), dbname = "mydata.sqlite")
	35	#' df = dbGetQuery(con, paste(
	36	#' "SELECT * FROM times_values GROUP BY id OFFSET ",start,
	37	#' "LIMIT ", n, " ORDER BY date", sep=""))
	38	#' return (df)
	39	#' }
	40	#' cl = epclust(getData, K1=200, K2=15, ntasks=1000, nb_series_per_chunk=5000, WER="mix")
	41	#' @export
	42	epclust = function(data, K1, K2,
	43	ntasks=1, nb_series_per_chunk=50K1, min_series_per_chunk=5K1,
	44	writeTmp=defaultWriteTmp, readTmp=defaultReadTmp, wf="haar", WER="end",
	45	ncores_tasks=1, ncores_clust=4)
	46	{
	47	#TODO: setRefClass(...) to avoid copy data:
	48	#http://stackoverflow.com/questions/2603184/r-pass-by-reference
	49
	50	#0) check arguments
	51	if (!is.data.frame(data) && !is.function(data))
	52	tryCatch(
	53	{
	54	if (is.character(data))
	55	{
	56	data_con = file(data, open="r")
	57	} else if (!isOpen(data))
	58	{
	59	open(data)
	60	data_con = data
	61	}
	62	},
	63	error="data should be a data.frame, a function or a valid connection")
	64	if (!is.integer(K) \|\| K < 2)
	65	stop("K should be an integer greater or equal to 2")
	66	if (!is.integer(nb_series_per_chunk) \|\| nb_series_per_chunk < K)
	67	stop("nb_series_per_chunk should be an integer greater or equal to K")
	68	if (!is.function(writeTmp) \|\| !is.function(readTmp))
	69	stop("read/writeTmp should be functional (see defaults.R)")
	70	if (WER!="end" && WER!="mix")
	71	stop("WER takes values in {'end','mix'}")
	72	#concerning ncores, any non-integer type will be treated as "use parallel:detectCores()/4"
	73
	74	#1) acquire data (process curves, get as coeffs)
	75	#TODO: for data.frame and custom function, run in parallel (connections are sequential[?!])
	76	index = 1
	77	nb_curves = 0
	78	repeat
	79	{
	80	coeffs_chunk = NULL
	81	if (is.data.frame(data))
	82	{
	83	#full data matrix
	84	if (index < nrow(data))
	85	{
	86	coeffs_chunk = curvesToCoeffs(
	87	data[index:(min(index+nb_series_per_chunk-1,nrow(data))),], wf)
	88	}
	89	} else if (is.function(data))
	90	{
	91	#custom user function to retrieve next n curves, probably to read from DB
	92	coeffs_chunk = curvesToCoeffs( data(index, nb_series_per_chunk), wf )
	93	} else
	94	{
	95	#incremental connection
	96	#TODO: find a better way to parse than using a temp file
	97	ascii_lines = readLines(data_con, nb_series_per_chunk)
	98	if (length(ascii_lines > 0))
	99	{
	100	series_chunk_file = ".tmp/series_chunk"
	101	writeLines(ascii_lines, series_chunk_file)
	102	coeffs_chunk = curvesToCoeffs( read.csv(series_chunk_file), wf )
	103	}
	104	}
	105	if (is.null(coeffs_chunk))
	106	break
	107	writeTmp(coeffs_chunk)
	108	nb_curves = nb_curves + nrow(coeffs_chunk)
	109	index = index + nb_series_per_chunk
	110	}
	111	if (exists(data_con))
	112	close(data_con)
	113	if (nb_curves < min_series_per_chunk)
	114	stop("Not enough data: less rows than min_series_per_chunk!")
	115
	116	#2) process coeffs (by nb_series_per_chunk) and cluster them in parallel
	117	library(parallel)
	118	cl_tasks = parallel::makeCluster(ncores_tasks)
	119	#Nothing to export because each worker retrieve and put data from/on files (or DB)
	120	#parallel::clusterExport(cl=cl, varlist=c("nothing","to","export"), envir=environment())
	121	#TODO: be careful of writing to a new temp file, then flush initial one, then re-use it...
	122	res_tasks = parallel::parSapply(cl_tasks, 1:ntasks, function() {
	123	cl_clust = parallel::makeCluster(ncores_clust)
	124	repeat
	125	{
	126	#while there are jobs to do
	127	#(i.e. size of tmp "file" is greater than ntasks * nb_series_per_chunk)
	128	nb_workers = nb_curves %/% nb_series_per_chunk
	129	indices = list()
	130	#indices[[i]] == (start_index,number_of_elements)
	131	for (i in 1:nb_workers)
	132	indices[[i]] = c(nb_series_per_chunk*(i-1)+1, nb_series_per_chunk)
	133	remainder = nb_curves %% nb_series_per_chunk
	134	if (remainder >= min_series_per_chunk)
	135	{
	136	nb_workers = nb_workers + 1
	137	indices[[nb_workers]] = c(nb_curves-remainder+1, nb_curves)
	138	} else if (remainder > 0)
	139	{
	140	#spread the load among other workers
	141	#...
	142	}
	143	res_clust = parallel::parSapply(cl, indices, processChunk, K, WER=="mix")
	144	#C) flush tmp file (current parallel processes will write in it)
	145	}
	146	parallel:stopCluster(cl_clust)
	147	})
	148	parallel::stopCluster(cl_tasks)
	149
	150	#3) readTmp last results, apply PAM on it, and return medoids + identifiers
	151	final_coeffs = readTmp(1, nb_series_per_chunk)
	152	if (nrow(final_coeffs) == K)
	153	{
	154	return ( list( medoids=coeffsToCurves(final_coeffs[,2:ncol(final_coeffs)]),
	155	ids=final_coeffs[,1] ) )
	156	}
	157	pam_output = getClusters(as.matrix(final_coeffs[,2:ncol(final_coeffs)]), K)
	158	medoids = coeffsToCurves(pam_output$medoids, wf)
	159	ids = final_coeffs[,1] [pam_output$ranks]
	160
	161	#4) apply stage 2 (in parallel ? inside task 2) ?)
	162	if (WER == "end")
	163	{
	164	#from center curves, apply stage 2...
	165	#TODO:
	166	}
	167
	168	return (list(medoids=medoids, ids=ids))
	169	}
	170
	171	processChunk = function(indice, K, WER)
	172	{
	173	#1) retrieve data
	174	coeffs = readTmp(indice[1], indice[2])
	175	#2) cluster
	176	cl = getClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K)
	177	#3) WER (optional)
	178	#TODO:
	179	}
	180
	181	#TODO: difficulté : retrouver courbe à partir de l'identifiant (DB ok mais le reste ?)
	182	#aussi : que passe-t-on aux noeuds ? curvesToCoeffs en // ?
	183	#enfin : WER ?!
	184	#TODO: bout de code qui calcule les courbes synchrones après étapes 1+2 à partir des ID médoïdes