From: Benjamin Auder Date: Tue, 28 Mar 2017 23:52:01 +0000 (+0200) Subject: fix methods, update report generation X-Git-Url: https://git.auder.net/game/%7B%7B%20path%28%27mixstore_store_usecase_upsert%27%2C%20%7B%20pkgid:%20pkg.id%20%7D%29%20%7D%7D?a=commitdiff_plain;h=ee8b1b4e3c13f8dcf13a2c8da6a3bef1520c8252;p=talweg.git fix methods, update report generation --- diff --git a/pkg/DESCRIPTION b/pkg/DESCRIPTION index 8d3c4c3..c90ce4f 100644 --- a/pkg/DESCRIPTION +++ b/pkg/DESCRIPTION @@ -15,6 +15,7 @@ Imports: R6, methods Suggests: + parallel, devtools, roxygen2, testthat, @@ -22,7 +23,7 @@ Suggests: LazyData: yes URL: http://git.auder.net/?p=talweg.git License: MIT + file LICENSE -RoxygenNote: 5.0.1 +RoxygenNote: 6.0.1 Collate: 'A_NAMESPACE.R' 'Data.R' diff --git a/pkg/R/F_Neighbors.R b/pkg/R/F_Neighbors.R index 5b2c899..d889a34 100644 --- a/pkg/R/F_Neighbors.R +++ b/pkg/R/F_Neighbors.R @@ -31,7 +31,7 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster", } # Indices of similar days for cross-validation; TODO: 45 = magic number - sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE) + sdays = getSimilarDaysIndices(today, data, limit=45, same_season=FALSE) cv_days = intersect(fdays,sdays) # Limit to 20 most recent matching days (TODO: 20 == magic number) @@ -134,7 +134,12 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster", M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) ) sigma = cov(M) #NOTE: robust covariance is way too slow - sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed? + # TODO: 10 == magic number; more robust way == det, or always ginv() + sigma_inv = + if (length(fdays) > 10) + solve(sigma) + else + MASS::ginv(sigma) # Distances from last observed day to days in the past distances2 = sapply(seq_along(fdays), function(i) { @@ -143,7 +148,7 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster", }) sd_dist = sd(distances2) - if (sd_dist < .Machine$double.eps) + if (sd_dist < .25 * sqrt(.Machine$double.eps)) { # warning("All computed distances are very close: stdev too small") sd_dist = 1 #mostly for tests... FIXME: diff --git a/pkg/R/F_Neighbors2.R b/pkg/R/F_Neighbors2.R index 83ef453..787dd2b 100644 --- a/pkg/R/F_Neighbors2.R +++ b/pkg/R/F_Neighbors2.R @@ -9,15 +9,11 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster", inherit = Forecaster, public = list( -# predictSerie = function(data, today, memory, horizon, ...) -# { -# # Parameters (potentially) computed during shape prediction stage -# predicted_shape = self$predictShape(data, today, memory, horizon, ...) -## predicted_delta = private$.pjump(data,today,memory,horizon,private$.params,...) -# # Predicted shape is aligned it on the end of current day + jump -## predicted_shape+tail(data$getSerie(today),1)-predicted_shape[1]+predicted_delta -# predicted_shape -# }, + predictSerie = function(data, today, memory, horizon, ...) + { + # This method predict shape + level at the same time, all in next call + self$predictShape(data, today, memory, horizon, ...) + }, predictShape = function(data, today, memory, horizon, ...) { # (re)initialize computed parameters @@ -40,7 +36,7 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster", } # Indices of similar days for cross-validation; TODO: 45 = magic number - sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE) + sdays = getSimilarDaysIndices(today, data, limit=45, same_season=FALSE) cv_days = intersect(fdays,sdays) # Limit to 20 most recent matching days (TODO: 20 == magic number) @@ -101,24 +97,25 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster", { fdays = fdays[ fdays < today ] # TODO: 3 = magic number - if (length(fdays) < 1) + if (length(fdays) < 3) return (NA) # Neighbors: days in "same season" - sdays = getSimilarDaysIndices(today, limit=45, same_season=TRUE, data) + sdays = getSimilarDaysIndices(today, data, limit=45, same_season=TRUE) indices = intersect(fdays,sdays) + if (length(indices) <= 1) + return (NA) levelToday = data$getLevel(today) distances = sapply(indices, function(i) abs(data$getLevel(i)-levelToday)) + # 2 and 5 below == magic numbers (determined by Bruno & Michel) same_pollution = (distances <= 2) - if (sum(same_pollution) < 1) #TODO: 3 == magic number + if (sum(same_pollution) == 0) { same_pollution = (distances <= 5) - if (sum(same_pollution) < 1) + if (sum(same_pollution) == 0) return (NA) } indices = indices[same_pollution] - - #TODO: we shouldn't need that block if (length(indices) == 1) { if (final_call) @@ -169,8 +166,12 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster", M[i+1,] = c( data$getLevel(indices[i]), as.double(data$getExo(indices[i])) ) sigma = cov(M) #NOTE: robust covariance is way too slow -# sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed? - sigma_inv = MASS::ginv(sigma) + # TODO: 10 == magic number; more robust way == det, or always ginv() + sigma_inv = + if (length(indices) > 10) + solve(sigma) + else + MASS::ginv(sigma) # Distances from last observed day to days in the past distances2 = sapply(seq_along(indices), function(i) { diff --git a/pkg/R/J_Neighbors.R b/pkg/R/J_Neighbors.R index 3c9bc30..7ca0003 100644 --- a/pkg/R/J_Neighbors.R +++ b/pkg/R/J_Neighbors.R @@ -6,7 +6,7 @@ getNeighborsJumpPredict = function(data, today, memory, horizon, params, ...) { first_day = max(1, today-memory) - filter = params$indices >= first_day + filter = (params$indices >= first_day) indices = params$indices[filter] weights = params$weights[filter] diff --git a/pkg/R/computeForecast.R b/pkg/R/computeForecast.R index bd19b8d..d635560 100644 --- a/pkg/R/computeForecast.R +++ b/pkg/R/computeForecast.R @@ -19,6 +19,7 @@ #' } #' @param memory Data depth (in days) to be used for prediction #' @param horizon Number of time steps to predict +#' @param ncores Number of cores for parallel execution (1 to disable) #' @param ... Additional parameters for the forecasting models #' #' @return An object of class Forecast @@ -39,7 +40,7 @@ #' }} #' @export computeForecast = function(data, indices, forecaster, pjump, - memory=Inf, horizon=data$getStdHorizon(), ...) + memory=Inf, horizon=data$getStdHorizon(), ncores=3, ...) { # (basic) Arguments sanity checks horizon = as.integer(horizon)[1] @@ -56,39 +57,33 @@ computeForecast = function(data, indices, forecaster, pjump, forecaster = forecaster_class_name$new( #.pjump = getFromNamespace(paste("get",pjump,"JumpPredict",sep=""), "talweg")) -#oo = forecaster$predictSerie(data, integer_indices[1], memory, horizon, ...) -#browser() - - parll=TRUE #FALSE - if (parll) + if (ncores > 1 && requireNamespace("parallel",quietly=TRUE)) { - library(parallel) - ppp <- parallel::mclapply(seq_along(integer_indices), function(i) { + p <- parallel::mclapply(seq_along(integer_indices), function(i) { list( "forecast" = forecaster$predictSerie(data, integer_indices[i], memory, horizon, ...), "params"= forecaster$getParameters(), "index" = integer_indices[i] ) - }, mc.cores=3) + }, mc.cores=ncores) } else { - ppp <- lapply(seq_along(integer_indices), function(i) { + p <- lapply(seq_along(integer_indices), function(i) { list( "forecast" = forecaster$predictSerie(data, integer_indices[i], memory, horizon, ...), "params"= forecaster$getParameters(), "index" = integer_indices[i] ) }) } -#browser() - -for (i in seq_along(integer_indices)) -{ - pred$append( - new_serie = ppp[[i]]$forecast, - new_params = ppp[[i]]$params, - new_index_in_data = ppp[[i]]$index - ) -} + # TODO: find a way to fill pred in //... + for (i in seq_along(integer_indices)) + { + pred$append( + new_serie = p[[i]]$forecast, + new_params = p[[i]]$params, + new_index_in_data = p[[i]]$index + ) + } pred } diff --git a/pkg/R/utils.R b/pkg/R/utils.R index 20f396b..b3e66e1 100644 --- a/pkg/R/utils.R +++ b/pkg/R/utils.R @@ -56,52 +56,65 @@ integerIndexToDate = function(index, data) #' Find similar days indices in the past. #' #' @param index Day index (numeric or date) +#' @param data Reference dataset, object output of \code{getData} #' @param limit Maximum number of indices to return #' @param same_season Should the indices correspond to day in same season? -#' @param data Dataset is required for a search in same season #' #' @export -getSimilarDaysIndices = function(index, limit, same_season, data=NULL) +getSimilarDaysIndices = function(index, data, limit, same_season) { - index = dateIndexToInteger(index) + index = dateIndexToInteger(index, data) - #TODO: mardi similaire à lundi mercredi jeudi aussi ...etc ==> "isSimilarDay()..." - if (!same_season) - { - #take all similar days in recent past - nb_days = min( (index-1) %/% 7, limit) - return ( rep(index,nb_days) - 7*seq_len(nb_days) ) - } - - #Look for similar days in similar season - nb_days = min( (index-1) %/% 7, limit) - i = index - 7 + # Look for similar days (optionally in same season) + i = index - 1 days = c() - month_ref = as.POSIXlt(data$getTime(index)[1])$mon + 1 + dt_ref = as.POSIXlt(data$getTime(index)[1]) #first date-time of current day + day_ref = dt_ref$wday #1=monday, ..., 6=saturday, 0=sunday + month_ref = as.POSIXlt(data$getTime(index)[1])$mon+1 #month in 1...12 while (i >= 1 && length(days) < limit) { - if (isSameSeason(as.POSIXlt(data$getTime(i)[1])$mon + 1, month_ref)) - days = c(days, i) - i = i-7 + dt = as.POSIXlt(data$getTime(i)[1]) + if (.isSameDay(dt$wday, day_ref)) + { + if (!same_season || .isSameSeason(dt$mon+1, month_ref)) + days = c(days, i) + } + i = i - 1 } return ( days ) } -#TODO: use data... 12-12-1-2 CH, 3-4-9-10 EP et le reste NP -isSameSeason = function(month, month_ref) +# isSameSeason +# +# Check if two months fall in the same "season" (defined by estimated pollution rate) +# +# @param month month index to test +# @param month_ref month to compare to +# +.isSameSeason = function(month, month_ref) { - if (month_ref %in% c(11,12,1,2)) + if (month_ref %in% c(11,12,1,2)) #~= mid-polluted return (month %in% c(11,12,1,2)) - if (month_ref %in% c(3,4,9,10)) + if (month_ref %in% c(3,4,9,10)) #~= high-polluted return (month %in% c(3,4,9,10)) - return (month %in% c(5,6,7,8)) + return (month %in% c(5,6,7,8)) #~= non polluted } -#TODO: -#distinction lun-jeudi, puis ven, sam, dim -#isSameDay = function(day, day_ref) -#{ -# if (day_ref == +# isSameDay +# +# Monday=Tuesday=Wednesday=Thursday ; Friday, Saturday, Sunday: specials +# +# @param day day index to test +# @param day_ref day index to compare to +# +.isSameDay = function(day, day_ref) +{ + if (day_ref == 0) + return (day==0) + if (day_ref <= 4) + return (day <= 4) + return (day == day_ref) +} #' getNoNA2 #' diff --git a/reports/ipynb_generator.py b/reports/ipynb_generator.py index ce546ad..456fc22 100755 --- a/reports/ipynb_generator.py +++ b/reports/ipynb_generator.py @@ -123,15 +123,15 @@ def driver(): inputfile = sys.argv[1] with open(inputfile, 'r') as f: text = f.read() - outputfile = '-' if len(sys.argv) <= 2 else sys.argv[2] + # Assuming file extension .gj (generate Jupyter); TODO: less strict + outputfile = inputfile[:-3]+'.ipynb' if (len(sys.argv)<=2 or sys.argv[2]=='-') \ + else sys.argv[2] except (IndexError, IOError) as e: print('Usage: %s inputfile [outputfile|- [Mako args]]' % (sys.argv[0])) print(e) sys.exit(1) cells = read(text, argv=sys.argv[3:]) filestr = write(cells) - # Assuming file extension .gj (generate Jupyter); TODO: less strict - outputfile = inputfile[:-3]+'.ipynb' if outputfile == '-' else outputfile with open(outputfile, 'w') as f: f.write(filestr) diff --git a/reports/report.gj b/reports/report.gj index aee6ad4..657b1d7 100644 --- a/reports/report.gj +++ b/reports/report.gj @@ -2,15 +2,14 @@

Introduction

J'ai fait quelques essais dans différentes configurations pour la méthode "Neighbors" -(la seule dont on a parlé) et sa variante récente appelée pour l'instant "Neighbors2".
+(la seule dont on a parlé) et sa variante récente appelée pour l'instant "Neighbors2", +avec simtype="mix" : deux types de similarités prises en compte, puis multiplication des poids. +Pour Neighbors on prédit le saut (par la moyenne pondérée des sauts passés), et pour Neighbors2 +on n'effectue aucun raccordement (prévision directe). - * simtype="exo", "endo" ou "mix" : type de similarités (fenêtre optimisée par VC) - * same_season=FALSE : les indices pour la validation croisée ne tiennent pas compte des saisons - * mix_strategy="mult" : on multiplie les poids (au lieu d'en éteindre) - -J'ai systématiquement comparé à une approche naïve : la moyennes des lendemains des jours -"similaires" dans tout le passé ; à chaque fois sans prédiction du saut (sauf pour Neighbors : -prédiction basée sur les poids calculés). +J'ai systématiquement comparé à une approche naïve : la moyenne des lendemains des jours +"similaires" dans tout le passé, ainsi qu'à la persistence -- reproduisant le jour courant ou +allant chercher le futur similaire une semaine avant. Ensuite j'affiche les erreurs, quelques courbes prévues/mesurées, quelques filaments puis les histogrammes de quelques poids. Concernant les graphes de filaments, la moitié gauche du graphe @@ -29,8 +28,9 @@ H = ${H} #horizon (en heures) ts_data = read.csv(system.file("extdata","pm10_mesures_H_loc_report.csv",package="talweg")) exo_data = read.csv(system.file("extdata","meteo_extra_noNAs.csv",package="talweg")) -data = getData(ts_data, exo_data, input_tz = "Europe/Paris", working_tz="Europe/Paris", - predict_at=P) #predict from P+1 to P+H included +# NOTE: 'GMT' because DST gaps are filled and multiple values merged in above dataset. +# Prediction from P+1 to P+H included. +data = getData(ts_data, exo_data, input_tz = "GMT", working_tz="GMT", predict_at=P) indices_ch = seq(as.Date("2015-01-18"),as.Date("2015-01-24"),"days") indices_ep = seq(as.Date("2015-03-15"),as.Date("2015-03-21"),"days") @@ -40,35 +40,31 @@ indices_np = seq(as.Date("2015-04-26"),as.Date("2015-05-02"),"days") -----

${list_titles[i]}

-----r -p_nn_exo = computeForecast(data, ${list_indices[i]}, "Neighbors", "Neighbors", - horizon=H, simtype="exo") -p_nn_mix = computeForecast(data, ${list_indices[i]}, "Neighbors", "Neighbors", - horizon=H, simtype="mix") -p_az = computeForecast(data, ${list_indices[i]}, "Average", "Zero", - horizon=H) -p_pz = computeForecast(data, ${list_indices[i]}, "Persistence", "Zero", - horizon=${H}, same_day=${'TRUE' if loop.index < 2 else 'FALSE'}) +p_nn = computeForecast(data, ${list_indices[i]}, "Neighbors", "Neighbors", horizon=H) +p_nn2 = computeForecast(data, ${list_indices[i]}, "Neighbors2", "Zero", horizon=H) +p_az = computeForecast(data, ${list_indices[i]}, "Average", "Zero", horizon=H) +p_pz = computeForecast(data, ${list_indices[i]}, "Persistence", "Zero", horizon=H, same_day=${'TRUE' if loop.index < 2 else 'FALSE'}) -----r -e_nn_exo = computeError(data, p_nn_exo, H) -e_nn_mix = computeError(data, p_nn_mix, H) +e_nn = computeError(data, p_nn, H) +e_nn2 = computeError(data, p_nn2, H) e_az = computeError(data, p_az, H) e_pz = computeError(data, p_pz, H) options(repr.plot.width=9, repr.plot.height=7) -plotError(list(e_nn_mix, e_pz, e_az, e_nn_exo), cols=c(1,2,colors()[258], 4)) +plotError(list(e_nn, e_pz, e_az, e_nn2), cols=c(1,2,colors()[258], 4)) -# Noir: neighbors_mix, bleu: neighbors_exo, vert: moyenne, rouge: persistence +# Noir: Neighbors, bleu: Neighbors2, vert: moyenne, rouge: persistence -i_np = which.min(e_nn_exo$abs$indices) -i_p = which.max(e_nn_exo$abs$indices) +i_np = which.min(e_nn$abs$indices) +i_p = which.max(e_nn$abs$indices) -----r options(repr.plot.width=9, repr.plot.height=4) par(mfrow=c(1,2)) -plotPredReal(data, p_nn_exo, i_np); title(paste("PredReal nn exo day",i_np)) -plotPredReal(data, p_nn_exo, i_p); title(paste("PredReal nn exo day",i_p)) +plotPredReal(data, p_nn, i_np); title(paste("PredReal nn day",i_np)) +plotPredReal(data, p_nn2, i_p); title(paste("PredReal nn day",i_p)) -plotPredReal(data, p_nn_mix, i_np); title(paste("PredReal nn mix day",i_np)) -plotPredReal(data, p_nn_mix, i_p); title(paste("PredReal nn mix day",i_p)) +plotPredReal(data, p_nn2, i_np); title(paste("PredReal nn2 day",i_np)) +plotPredReal(data, p_nn2, i_p); title(paste("PredReal nn2 day",i_p)) plotPredReal(data, p_az, i_np); title(paste("PredReal az day",i_np)) plotPredReal(data, p_az, i_p); title(paste("PredReal az day",i_p)) @@ -76,50 +72,41 @@ plotPredReal(data, p_az, i_p); title(paste("PredReal az day",i_p)) # Bleu: prévue, noir: réalisée -----r par(mfrow=c(1,2)) -f_np_exo = computeFilaments(data, p_nn_exo, i_np, plot=TRUE); title(paste("Filaments nn exo day",i_np)) -f_p_exo = computeFilaments(data, p_nn_exo, i_p, plot=TRUE); title(paste("Filaments nn exo day",i_p)) +f_np = computeFilaments(data, p_nn, i_np, plot=TRUE); title(paste("Filaments nn day",i_np)) +f_p = computeFilaments(data, p_nn, i_p, plot=TRUE); title(paste("Filaments nn day",i_p)) -f_np_mix = computeFilaments(data, p_nn_mix, i_np, plot=TRUE); title(paste("Filaments nn mix day",i_np)) -f_p_mix = computeFilaments(data, p_nn_mix, i_p, plot=TRUE); title(paste("Filaments nn mix day",i_p)) +f_np2 = computeFilaments(data, p_nn2, i_np, plot=TRUE); title(paste("Filaments nn2 day",i_np)) +f_p2 = computeFilaments(data, p_nn2, i_p, plot=TRUE); title(paste("Filaments nn2 day",i_p)) -----r par(mfrow=c(1,2)) -plotFilamentsBox(data, f_np_exo); title(paste("FilBox nn exo day",i_np)) -plotFilamentsBox(data, f_p_exo); title(paste("FilBox nn exo day",i_p)) +plotFilamentsBox(data, f_np); title(paste("FilBox nn day",i_np)) +plotFilamentsBox(data, f_p); title(paste("FilBox nn day",i_p)) -plotFilamentsBox(data, f_np_mix); title(paste("FilBox nn mix day",i_np)) -plotFilamentsBox(data, f_p_mix); title(paste("FilBox nn mix day",i_p)) +plotFilamentsBox(data, f_np2); title(paste("FilBox nn2 day",i_np)) +plotFilamentsBox(data, f_p2); title(paste("FilBox nn2 day",i_p)) -----r par(mfrow=c(1,2)) -plotRelVar(data, f_np_exo); title(paste("StdDev nn exo day",i_np)) -plotRelVar(data, f_p_exo); title(paste("StdDev nn exo day",i_p)) +plotRelVar(data, f_np); title(paste("StdDev nn day",i_np)) +plotRelVar(data, f_p); title(paste("StdDev nn day",i_p)) -plotRelVar(data, f_np_mix); title(paste("StdDev nn mix day",i_np)) -plotRelVar(data, f_p_mix); title(paste("StdDev nn mix day",i_p)) +plotRelVar(data, f_np2); title(paste("StdDev nn2 day",i_np)) +plotRelVar(data, f_p2); title(paste("StdDev nn2 day",i_p)) # Variabilité globale en rouge ; sur les 60 voisins (+ lendemains) en noir -----r par(mfrow=c(1,2)) -plotSimils(p_nn_exo, i_np); title(paste("Weights nn exo day",i_np)) -plotSimils(p_nn_exo, i_p); title(paste("Weights nn exo day",i_p)) +plotSimils(p_nn, i_np); title(paste("Weights nn day",i_np)) +plotSimils(p_nn, i_p); title(paste("Weights nn day",i_p)) -plotSimils(p_nn_mix, i_np); title(paste("Weights nn mix day",i_np)) -plotSimils(p_nn_mix, i_p); title(paste("Weights nn mix day",i_p)) +plotSimils(p_nn2, i_np); title(paste("Weights nn2 day",i_np)) +plotSimils(p_nn2, i_p); title(paste("Weights nn2 day",i_p)) # - pollué à gauche, + pollué à droite -----r -# Fenêtres sélectionnées dans ]0,10] / endo à gauche, exo à droite -p_nn_exo$getParams(i_np)$window -p_nn_exo$getParams(i_p)$window +# Fenêtres sélectionnées dans ]0,7] / nn à gauche, nn2 à droite +p_nn$getParams(i_np)$window +p_nn$getParams(i_p)$window -p_nn_mix$getParams(i_np)$window -p_nn_mix$getParams(i_p)$window +p_nn2$getParams(i_np)$window +p_nn2$getParams(i_p)$window % endfor ------ -

Bilan

- -Problème difficile : on ne fait guère mieux qu'une naïve moyenne des lendemains des jours -similaires dans le passé, ce qui n'est pas loin de prédire une série constante égale à la -dernière valeur observée (méthode "zéro"). La persistence donne parfois de bons résultats -mais est trop instable (sensibilité à l'argument same_day). - -Comment améliorer la méthode ? diff --git a/reports/report.ipynb b/reports/report.ipynb index 3dac8ec..f0a06d0 100644 --- a/reports/report.ipynb +++ b/reports/report.ipynb @@ -75,17 +75,20 @@ "reload(\"../pkg\")\n", "#p1 = computeForecast(data, indices_ch, \"Neighbors\", \"Zero\", horizon=H, simtype=\"exo\")\n", "#p2 = computeForecast(data, indices_ch, \"Neighbors\", \"Zero\", horizon=H, simtype=\"endo\")\n", - "#p3 = computeForecast(data, indices_ch, \"Neighbors\", \"Zero\", horizon=H, simtype=\"mix\")\n", - "p4 = computeForecast(data, indices_ch, \"Neighbors2\", \"Zero\", horizon=H, simtype=\"exo\")\n", - "p5 = computeForecast(data, indices_ch, \"Neighbors2\", \"Zero\", horizon=H, simtype=\"endo\")\n", - "p6 = computeForecast(data, indices_ch, \"Neighbors2\", \"Zero\", horizon=H, simtype=\"mix\")" + "p3 = computeForecast(data, indices_ch, \"Neighbors\", \"Zero\", horizon=H, simtype=\"mix\")\n", + "p4 = computeForecast(data, indices_ch, \"Neighbors\", \"Neighbors\", horizon=H, simtype=\"mix\")\n", + "#p4 = computeForecast(data, indices_ch, \"Neighbors2\", \"Zero\", horizon=H, simtype=\"exo\")\n", + "#p5 = computeForecast(data, indices_ch, \"Neighbors2\", \"Zero\", horizon=H, simtype=\"endo\")\n", + "#p6 = computeForecast(data, indices_ch, \"Neighbors2\", \"Zero\", horizon=H, simtype=\"mix\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { - "collapsed": false + "collapsed": false, + "deletable": true, + "editable": true }, "outputs": [], "source": [ @@ -96,7 +99,9 @@ "cell_type": "code", "execution_count": null, "metadata": { - "collapsed": false + "collapsed": false, + "deletable": true, + "editable": true }, "outputs": [], "source": [ @@ -107,17 +112,19 @@ "cell_type": "code", "execution_count": null, "metadata": { - "collapsed": false + "collapsed": false, + "deletable": true, + "editable": true }, "outputs": [], "source": [ - "e1 = computeError(data, p1, H)\n", - "e2 = computeError(data, p2, H)\n", + "#e1 = computeError(data, p1, H)\n", + "#e2 = computeError(data, p2, H)\n", "e3 = computeError(data, p3, H)\n", "e4 = computeError(data, p4, H)\n", - "e5 = computeError(data, p5, H)\n", - "e6 = computeError(data, p6, H)\n", - "plotError(list(e1,e2,e3,e4,e5,e6), cols=c(1,2,colors()[258], 4,5,6))" + "#e5 = computeError(data, p5, H)\n", + "#e6 = computeError(data, p6, H)\n", + "plotError(list(e3,e4), cols=c(1,2))" ] }, { @@ -130,7 +137,30 @@ }, "outputs": [], "source": [ - "plotError(list(e4,e1,e2,e3, e5,e6), cols=c(1,2,3,4,5,6))" + "\tfirst_day = 1\n", + "params=p3$getParams(3)\n", + "\tfilter = (params$indices >= first_day)\n", + "\tindices = params$indices[filter]\n", + "\tweights = params$weights[filter]\n", + "\n", + "\n", + "\tgaps = sapply(indices, function(i) {\n", + "\t\tdata$getSerie(i+1)[1] - tail(data$getSerie(i), 1)\n", + "\t})\n", + "\tscal_product = weights * gaps\n", + "\tnorm_fact = sum( weights[!is.na(scal_product)] )\n", + "\tsum(scal_product, na.rm=TRUE) / norm_fact\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "hist(weights)" ] }, { @@ -146,14 +176,11 @@ "options(repr.plot.width=9, repr.plot.height=4)\n", "par(mfrow=c(1,2))\n", "\n", - "plotPredReal(data, p_nn_exo, i_np); title(paste(\"PredReal nn exo day\",i_np))\n", - "plotPredReal(data, p_nn_exo, i_p); title(paste(\"PredReal nn exo day\",i_p))\n", + "plotPredReal(data, p3, 3); title(paste(\"PredReal nn exo day\",3))\n", + "plotPredReal(data, p3, 5); title(paste(\"PredReal nn exo day\",5))\n", "\n", - "plotPredReal(data, p_nn_mix, i_np); title(paste(\"PredReal nn mix day\",i_np))\n", - "plotPredReal(data, p_nn_mix, i_p); title(paste(\"PredReal nn mix day\",i_p))\n", - "\n", - "plotPredReal(data, p_az, i_np); title(paste(\"PredReal az day\",i_np))\n", - "plotPredReal(data, p_az, i_p); title(paste(\"PredReal az day\",i_p))\n", + "plotPredReal(data, p4, 3); title(paste(\"PredReal nn mix day\",3))\n", + "plotPredReal(data, p4, 5); title(paste(\"PredReal nn mix day\",5))\n", "\n", "# Bleu: prévue, noir: réalisée" ]