| 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 K Number of clusters |
| 16 | #' @param nb_series_per_chunk (Maximum) number of series in each group |
| 17 | #' @param min_series_per_chunk Minimum number of series in each group |
| 18 | #' @param writeTmp Function to write temporary wavelets coefficients (+ identifiers); |
| 19 | #' see defaults in defaults.R |
| 20 | #' @param readTmp Function to read temporary wavelets coefficients (see defaults.R) |
| 21 | #' @param wf Wavelet transform filter; see ?wt.filter. Default: haar |
| 22 | #' @param WER "end" to apply stage 2 after stage 1 has iterated and finished, or "mix" |
| 23 | #' to apply it after every stage 1 |
| 24 | #' @param ncores number of parallel processes; if NULL, use parallel::detectCores() |
| 25 | #' |
| 26 | #' @return A data.frame of the final medoids curves (identifiers + values) |
| 27 | epclust = function(data, K, nb_series_per_chunk, min_series_per_chunk=10*K, |
| 28 | writeTmp=defaultWriteTmp, readTmp=defaultReadTmp, wf="haar", WER="end", ncores=NULL) |
| 29 | { |
| 30 | #TODO: setRefClass(...) to avoid copy data: |
| 31 | #http://stackoverflow.com/questions/2603184/r-pass-by-reference |
| 32 | |
| 33 | #0) check arguments |
| 34 | if (!is.data.frame(data) && !is.function(data)) |
| 35 | tryCatch( |
| 36 | { |
| 37 | if (is.character(data)) |
| 38 | { |
| 39 | data_con = file(data, open="r") |
| 40 | } else if (!isOpen(data)) |
| 41 | { |
| 42 | open(data) |
| 43 | data_con = data |
| 44 | } |
| 45 | }, |
| 46 | error="data should be a data.frame, a function or a valid connection") |
| 47 | if (!is.integer(K) || K < 2) |
| 48 | stop("K should be an integer greater or equal to 2") |
| 49 | if (!is.integer(nb_series_per_chunk) || nb_series_per_chunk < K) |
| 50 | stop("nb_series_per_chunk should be an integer greater or equal to K") |
| 51 | if (!is.function(writeTmp) || !is.function(readTmp)) |
| 52 | stop("read/writeTmp should be functional (see defaults.R)") |
| 53 | if (WER!="end" && WER!="mix") |
| 54 | stop("WER takes values in {'end','mix'}") |
| 55 | #concerning ncores, any non-integer type will be treated as "use parallel:detectCores()" |
| 56 | |
| 57 | #1) acquire data (process curves, get as coeffs) |
| 58 | #TODO: for data.frame and custom function, run in parallel (connections are sequential[?!]) |
| 59 | index = 1 |
| 60 | nb_curves = 0 |
| 61 | repeat |
| 62 | { |
| 63 | coeffs_chunk = NULL |
| 64 | if (is.data.frame(data)) |
| 65 | { |
| 66 | #full data matrix |
| 67 | if (index < nrow(data)) |
| 68 | { |
| 69 | coeffs_chunk = curvesToCoeffs( |
| 70 | data[index:(min(index+nb_series_per_chunk-1,nrow(data))),], wf) |
| 71 | } |
| 72 | } else if (is.function(data)) |
| 73 | { |
| 74 | #custom user function to retrieve next n curves, probably to read from DB |
| 75 | coeffs_chunk = curvesToCoeffs( data(index, nb_series_per_chunk), wf ) |
| 76 | } else |
| 77 | { |
| 78 | #incremental connection |
| 79 | #TODO: find a better way to parse than using a temp file |
| 80 | ascii_lines = readLines(data_con, nb_series_per_chunk) |
| 81 | if (length(ascii_lines > 0)) |
| 82 | { |
| 83 | series_chunk_file = ".tmp/series_chunk" |
| 84 | writeLines(ascii_lines, series_chunk_file) |
| 85 | coeffs_chunk = curvesToCoeffs( read.csv(series_chunk_file), wf ) |
| 86 | } |
| 87 | } |
| 88 | if (is.null(coeffs_chunk)) |
| 89 | break |
| 90 | writeTmp(coeffs_chunk) |
| 91 | nb_curves = nb_curves + nrow(coeffs_chunk) |
| 92 | index = index + nb_series_per_chunk |
| 93 | } |
| 94 | if (exists(data_con)) |
| 95 | close(data_con) |
| 96 | if (nb_curves < min_series_per_chunk) |
| 97 | stop("Not enough data: less rows than min_series_per_chunk!") |
| 98 | |
| 99 | #2) process coeffs (by nb_series_per_chunk) and cluster them in parallel |
| 100 | library(parallel) |
| 101 | ncores = ifelse(is.integer(ncores), ncores, parallel::detectCores()) |
| 102 | cl = parallel::makeCluster(ncores) |
| 103 | parallel::clusterExport(cl=cl, varlist=c("TODO:", "what", "to", "export?"), envir=environment()) |
| 104 | #TODO: be careful of writing to a new temp file, then flush initial one, then re-use it... |
| 105 | repeat |
| 106 | { |
| 107 | #while there is jobs to do (i.e. size of tmp "file" is greater than nb_series_per_chunk) |
| 108 | nb_workers = nb_curves %/% nb_series_per_chunk |
| 109 | indices = list() |
| 110 | #indices[[i]] == (start_index,number_of_elements) |
| 111 | for (i in 1:nb_workers) |
| 112 | indices[[i]] = c(nb_series_per_chunk*(i-1)+1, nb_series_per_chunk) |
| 113 | remainder = nb_curves %% nb_series_per_chunk |
| 114 | if (remainder >= min_series_per_chunk) |
| 115 | { |
| 116 | nb_workers = nb_workers + 1 |
| 117 | indices[[nb_workers]] = c(nb_curves-remainder+1, nb_curves) |
| 118 | } else if (remainder > 0) |
| 119 | { |
| 120 | #spread the load among other workers |
| 121 | #... |
| 122 | } |
| 123 | li = parallel::parLapply(cl, indices, processChunk, K, WER=="mix") |
| 124 | #C) flush tmp file (current parallel processes will write in it) |
| 125 | } |
| 126 | parallel::stopCluster(cl) |
| 127 | |
| 128 | #3) readTmp last results, apply PAM on it, and return medoids + identifiers |
| 129 | final_coeffs = readTmp(1, nb_series_per_chunk) |
| 130 | if (nrow(final_coeffs) == K) |
| 131 | { |
| 132 | return ( list( medoids=coeffsToCurves(final_coeffs[,2:ncol(final_coeffs)]), |
| 133 | ids=final_coeffs[,1] ) ) |
| 134 | } |
| 135 | pam_output = getClusters(as.matrix(final_coeffs[,2:ncol(final_coeffs)]), K) |
| 136 | medoids = coeffsToCurves(pam_output$medoids, wf) |
| 137 | ids = final_coeffs[,1] [pam_output$ranks] |
| 138 | |
| 139 | #4) apply stage 2 (in parallel ? inside task 2) ?) |
| 140 | if (WER == "end") |
| 141 | { |
| 142 | #from center curves, apply stage 2... |
| 143 | #TODO: |
| 144 | } |
| 145 | |
| 146 | return (list(medoids=medoids, ids=ids)) |
| 147 | } |
| 148 | |
| 149 | processChunk = function(indice, K, WER) |
| 150 | { |
| 151 | #1) retrieve data |
| 152 | coeffs = readTmp(indice[1], indice[2]) |
| 153 | #2) cluster |
| 154 | cl = getClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K) |
| 155 | #3) WER (optional) |
| 156 | #TODO: |
| 157 | } |
| 158 | |
| 159 | #TODO: difficulté : retrouver courbe à partir de l'identifiant (DB ok mais le reste ?) |
| 160 | #aussi : que passe-t-on aux noeuds ? curvesToCoeffs en // ? |
| 161 | #enfin : WER ?! |