X-Git-Url: https://git.auder.net/?a=blobdiff_plain;ds=sidebyside;f=reports%2Freport.gj;h=aee6ad45598ac2c63489469651be28f3164ea752;hb=a866acb3c0ae138b22df9dae9ec576b866794417;hp=3524e10e12c8f3e304fa9fff4669dd90ba82d816;hpb=0c1bf707abbc1b60db7f67c67c0cb123b3df85ff;p=talweg.git
diff --git a/reports/report.gj b/reports/report.gj
index 3524e10..aee6ad4 100644
--- a/reports/report.gj
+++ b/reports/report.gj
@@ -2,9 +2,9 @@
Introduction
J'ai fait quelques essais dans différentes configurations pour la méthode "Neighbors"
-(la seule dont on a parlé).
Il semble que le mieux soit
+(la seule dont on a parlé) et sa variante récente appelée pour l'instant "Neighbors2".
- * simtype="exo" ou "mix" : similarités exogènes avec/sans endogènes (fenêtre optimisée par VC)
+ * 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)
@@ -24,10 +24,13 @@ list_indices = ['indices_ch', 'indices_ep', 'indices_np']
-----r
library(talweg)
+P = ${P} #instant de prévision
+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
+ predict_at=P) #predict from P+1 to P+H included
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")
@@ -38,18 +41,18 @@ 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")
+ horizon=H, simtype="exo")
p_nn_mix = computeForecast(data, ${list_indices[i]}, "Neighbors", "Neighbors",
- horizon=${H}, simtype="mix")
+ horizon=H, simtype="mix")
p_az = computeForecast(data, ${list_indices[i]}, "Average", "Zero",
- horizon=${H})
+ horizon=H)
p_pz = computeForecast(data, ${list_indices[i]}, "Persistence", "Zero",
- horizon=${H}, same_day=TRUE)
+ 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_az = computeError(data, p_az, ${H})
-e_pz = computeError(data, p_pz, ${H})
+e_nn_exo = computeError(data, p_nn_exo, H)
+e_nn_mix = computeError(data, p_nn_mix, 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))