X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FF_Neighbors.R;h=c8a33554f92fef75dc327fb526faea9027b4b535;hb=6774e53de7b8bdac191d6203a380ad46c3b4d9ba;hp=a3d44a3916cc8b27195ddd693fc35f6dbcceb2b1;hpb=546b0cb65870355a2a2c3705c91418570499d3a6;p=talweg.git diff --git a/pkg/R/F_Neighbors.R b/pkg/R/F_Neighbors.R index a3d44a3..c8a3355 100644 --- a/pkg/R/F_Neighbors.R +++ b/pkg/R/F_Neighbors.R @@ -30,24 +30,24 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster", fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) ) } - # Indices of similar days for cross-validation; TODO: 45 = magic number - sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE) + # Indices of similar days for cross-validation; TODO: 20 = magic number + cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE, days_in=fdays) # Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days errorOnLastNdays = function(h, kernel, simtype) { error = 0 nb_jours = 0 - for (i in intersect(fdays,sdays)) + for (i in seq_along(cv_days)) { # mix_strategy is never used here (simtype != "mix"), therefore left blank prediction = private$.predictShapeAux(data, - fdays, i, horizon, h, kernel, simtype, FALSE) + fdays, cv_days[i], horizon, h, kernel, simtype, FALSE) if (!is.na(prediction[1])) { nb_jours = nb_jours + 1 error = error + - mean((data$getCenteredSerie(i+1)[1:horizon] - prediction)^2) + mean((data$getCenteredSerie(cv_days[i]+1)[1:horizon] - prediction)^2) } } return (error / nb_jours) @@ -96,19 +96,16 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster", h_endo = ifelse(simtype=="mix", h[1], h) # Distances from last observed day to days in the past - distances2 = rep(NA, length(fdays)) - for (i in seq_along(fdays)) - { - delta = data$getCenteredSerie(today) - data$getCenteredSerie(fdays[i]) - # Require at least half of non-NA common values to compute the distance - if ( !any( is.na(delta) ) ) - distances2[i] = mean(delta^2) - } + serieToday = data$getSerie(today) + distances2 = sapply(fdays, function(i) { + delta = serieToday - data$getSerie(i) + mean(delta^2) + }) sd_dist = sd(distances2) if (sd_dist < .Machine$double.eps) { - warning("All computed distances are very close: stdev too small") +# warning("All computed distances are very close: stdev too small") sd_dist = 1 #mostly for tests... FIXME: } simils_endo = @@ -133,20 +130,23 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster", M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) ) sigma = cov(M) #NOTE: robust covariance is way too slow - sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed? + # TODO: 10 == magic number; more robust way == det, or always ginv() + sigma_inv = + if (length(fdays) > 10) + solve(sigma) + else + MASS::ginv(sigma) # Distances from last observed day to days in the past - distances2 = rep(NA, nrow(M)-1) - for (i in 2:nrow(M)) - { - delta = M[1,] - M[i,] - distances2[i-1] = delta %*% sigma_inv %*% delta - } + distances2 = sapply(seq_along(fdays), function(i) { + delta = M[1,] - M[i+1,] + delta %*% sigma_inv %*% delta + }) sd_dist = sd(distances2) - if (sd_dist < .Machine$double.eps) + if (sd_dist < .25 * sqrt(.Machine$double.eps)) { - warning("All computed distances are very close: stdev too small") +# warning("All computed distances are very close: stdev too small") sd_dist = 1 #mostly for tests... FIXME: } simils_exo = @@ -171,7 +171,7 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster", prediction = rep(0, horizon) for (i in seq_along(fdays)) - prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon] + prediction = prediction + similarities[i] * data$getCenteredSerie(fdays[i]+1)[1:horizon] prediction = prediction / sum(similarities, na.rm=TRUE) if (final_call)