fix methods, update report generation

[talweg.git] / pkg / R / F_Neighbors2.R

diff --git a/pkg/R/F_Neighbors2.R b/pkg/R/F_Neighbors2.R
index 83ef453..787dd2b 100644 (file)
--- 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) {