Commit e45647a0 authored by kosnil's avatar kosnil
Browse files
parents db182bf0 0396502c
forecast_date,target,horizon,q0.025,q0.25,q0.5,q0.75,q0.975
2021-11-10,DAX,1 day,-1.814,-0.319,0.107,0.585,1.644
2021-11-10,DAX,2 day, -1.895,-0.392,0.135,0.703,2.350
2021-11-10,DAX,5 day,-2.130,-0.480,0.228,0.979,3.269
2021-11-10,DAX,6 day,-2.012,-0.477,0.240,1.097,3.330
2021-11-10,DAX,7 day,-2.563,-0.315,0.404,1.243,3.206
2021-11-10,temperature,36 hour,-0.02505758,3.889791 ,5.574968 ,7.260145 , 11.17499
2021-11-10,temperature,48 hour,-0.34429335,3.652610 ,5.373108 ,7.093605 ,11.09051
2021-11-10,temperature,60 hour,-0.49696121,3.613992 ,5.383584 ,7.153175 ,11.26413
2021-11-10,temperature,72 hour,-0.61484476,3.579935 ,5.385610 ,7.191285 ,11.38606
2021-11-10,temperature,84 hour,-0.72564287,3.546917 ,5.386073 ,7.225229 ,11.49779
2021-11-10,wind,36 hour,14.27400 ,15.74250 ,17.48000 ,18.75000 ,20.25925
2021-11-10,wind,48 hour,16.11750 ,18.38750 ,19.15000 ,20.25750 ,21.05025
2021-11-10,wind,60 hour,18.83750 ,19.58500 ,21.08500 ,21.86250 ,22.80025
2021-11-10,wind,72 hour,15.47475 ,16.54750 ,17.60500 ,18.75500 ,19.95700
2021-11-10,wind,84 hour,12.82375 ,16.45500 ,17.52500 ,19.11750 ,21.80400
2021-11-17,DAX,1 day,-1.814,-0.319,0.107,0.585,1.644
2021-11-17,DAX,2 day, -1.895,-0.392,0.135,0.703,2.350
2021-11-17,DAX,5 day,-2.130,-0.480,0.228,0.979,3.269
2021-11-17,DAX,6 day,-2.012,-0.477,0.240,1.097,3.330
2021-11-17,DAX,7 day,-2.563,-0.315,0.404,1.243,3.206
2021-11-17,temperature,36 hour,-0.02505758,3.889791 ,5.574968 ,7.260145 , 11.17499
2021-11-17,temperature,48 hour,-0.34429335,3.652610 ,5.373108 ,7.093605 ,11.09051
2021-11-17,temperature,60 hour,-0.49696121,3.613992 ,5.383584 ,7.153175 ,11.26413
2021-11-17,temperature,72 hour,-0.61484476,3.579935 ,5.385610 ,7.191285 ,11.38606
2021-11-17,temperature,84 hour,-0.72564287,3.546917 ,5.386073 ,7.225229 ,11.49779
2021-11-17,wind,36 hour,14.27400 ,15.74250 ,17.48000 ,18.75000 ,20.25925
2021-11-17,wind,48 hour,16.11750 ,18.38750 ,19.15000 ,20.25750 ,21.05025
2021-11-17,wind,60 hour,18.83750 ,19.58500 ,21.08500 ,21.86250 ,22.80025
2021-11-17,wind,72 hour,15.47475 ,16.54750 ,17.60500 ,18.75500 ,19.95700
2021-11-17,wind,84 hour,12.82375 ,16.45500 ,17.52500 ,19.11750 ,21.80400
"","forecast_date","target","horizon","q0.025","q0.25","q0.5","q0.75","q0.975"
"1",2021-11-17,"DAX","1 day",-1.57152914236947,-0.295182292861882,0.104228498090919,0.499484115054545,1.58283659066339
"2",2021-11-17,"DAX","2 day",-2.32371665370188,-0.449384869210265,0.200808713624701,0.792686492633507,2.33324122455029
"3",2021-11-17,"temperature","36 hour",6.61567043446514,8.21840283882026,8.97243927314119,9.73068059344852,11.4685930980837
"4",2021-11-17,"wind","36 hour",13.4591072334399,17.6054525506645,19.9968089521247,22.196977855739,26.5938099504582
"5",2021-11-17,"temperature","48 hour",7.02707267269022,8.59856533162044,9.33133774948013,10.0964527553537,11.5939305226164
"6",2021-11-17,"wind","48 hour",15.0824531337348,19.5177417663306,21.90008518923,24.295823468101,28.88318556459
"7",2021-11-17,"DAX","5 day",-2.98031532000631,-0.448601799569716,0.317830991925405,1.08403333598929,3.08340779645031
"8",2021-11-17,"DAX","6 day",-3.28187566397024,-0.453092771923311,0.431842291529563,1.28010319945916,3.51652672910777
"9",2021-11-17,"temperature","60 hour",8.75429041801458,10.6343397288614,11.5380999571924,12.4382422153515,14.2272628227255
"10",2021-11-17,"wind","60 hour",16.8645553290555,21.1754969297571,23.5424948782682,25.7296901083719,29.9683445907247
"11",2021-11-17,"DAX","7 day",-3.35679575206473,-0.362225012005841,0.601610467445612,1.50029247048715,3.83715652111091
"12",2021-11-17,"temperature","72 hour",7.95069205792286,9.69952815181624,10.5412275495903,11.4131663311393,12.9863958271016
"13",2021-11-17,"wind","72 hour",13.4126716609587,17.5748529956256,19.8728946327418,22.162478566952,26.5492329556628
"14",2021-11-17,"temperature","84 hour",8.48855652980981,10.3295866925623,11.2501222549611,12.2526437652045,14.0110086866859
"15",2021-11-17,"wind","84 hour",12.3218961236354,17.5962722753366,20.1481065630052,22.6759697142911,27.7222601977991
"","forecast_date","target","horizon","q0.025","q0.25","q0.5","q0.75","q0.975"
"1",2021-11-17,"DAX","1 day",-1.54343797650373,-0.32416844322487,0.0944938780424375,0.52465379715795,1.39242060217205
"2",2021-11-17,"DAX","2 day",-1.9565053511336,-0.462724242148174,0.165072327412297,0.808803224789637,2.02047159820379
"3",2021-11-17,"temperature","36 hour",7.19445777758113,8.5757864761853,9.28080475447274,9.8933468354176,11.3617059881068
"4",2021-11-17,"wind","36 hour",13.7882216526812,18.1525188718824,20.4424704607395,22.7079012300849,27.0967193117186
"5",2021-11-17,"temperature","48 hour",7.731872697483,9.02638425728935,9.73274747776319,10.439110698237,11.785330888749
"6",2021-11-17,"wind","48 hour",16.2449781700328,20.4607040035523,22.8652025683021,25.268284625,29.8119697102133
"7",2021-11-17,"DAX","5 day",-2.7693541525176,-0.658825020617326,0.235986225953511,1.08612131019882,2.7773211552435
"8",2021-11-17,"DAX","6 day",-3.12135092017086,-0.712971954106715,0.295841734753477,1.10617974892811,3.33
"9",2021-11-17,"temperature","60 hour",9.71872436061509,11.3016405773884,11.9831877165721,12.7765004868147,14.5408418224545
"10",2021-11-17,"wind","60 hour",18.1077129922569,21.980235351982,24.234608612468,26.3430801603896,30.3615042326793
"11",2021-11-17,"DAX","7 day",-3.37847577683741,-0.725192042805581,0.404,1.28463,3.206
"12",2021-11-17,"temperature","72 hour",8.69726188790589,10.2106671737387,11.0112501618941,11.8133657548541,13.3406717837718
"13",2021-11-17,"wind","72 hour",14.6185314577549,18.192221198101,20.6728094775886,23.1550558847443,27.594388707069
"14",2021-11-17,"temperature","84 hour",9.13145269302764,10.875,11.7477556203114,12.601120361518,14.2722179866091
"15",2021-11-17,"wind","84 hour",12.8260294690029,17.9133205472468,20.6699352731085,23.3182947121471,28.5218392126887
"forecast_date","target","horizon","q0.025","q0.25","q0.5","q0.75","q0.975"
"2021-11-24","DAX","1 day",-2.65844263691718,-0.478408853013734,0.0733950537846084,0.656902293272221,2.22946787319034
"2021-11-24","DAX","2 day",-3.76658704113496,-0.732473649417953,0.162164603826653,0.905783297834439,3.10108794007109
"2021-11-24","DAX","5 day",-4.73040567059547,-0.830364194262723,0.165364453806394,1.1996376118808,3.89032640718187
"2021-11-24","DAX","6 day",-5.23203014061953,-0.933589441129046,0.258010752090598,1.39631925115538,4.57407374600166
"2021-11-24","DAX","7 day",-5.68685922947709,-1.06446218815517,0.383246813585902,1.49206818774594,5.19223708311003
"forecast_date","target","horizon","q0.025","q0.25","q0.5","q0.75","q0.975"
2021-11-24,"temperature","36 hour",0.314900203796237,1.91670095840109,2.75716758306953,3.59763420773797,5.19943496234282
2021-11-24,"temperature","48 hour",1.57518730635196,2.87210948462161,3.55260598363646,4.2331024826513,5.53002466092096
2021-11-24,"temperature","60 hour",3.02947376843326,4.56010713795586,5.36323215708778,6.1663571762197,7.6969905457423
2021-11-24,"temperature","72 hour",-0.619112316822949,0.96412599545742,1.79485288614133,2.62557977682525,4.20881808910561
2021-11-24,"temperature","84 hour",1.38735892675847,3.2302024887888,4.1971445406757,5.1640865925626,7.00693015459293
"forecast_date","target","horizon","q0.025","q0.25","q0.5","q0.75","q0.975"
2021-11-24,"temperature","36 hour",0.79775,1.655,2.14,2.65,4.00625
2021-11-24,"temperature","48 hour",1.9895,2.525,2.82,3.1975,3.751
2021-11-24,"temperature","60 hour",3.86775,4.3475,4.81,5.2525,6.1015
2021-11-24,"temperature","72 hour",-0.82775,0.65,1.155,1.485,2.87975
2021-11-24,"temperature","84 hour",2.4105,3.1175,3.79,4.1775,4.8195
"forecast_date","target","horizon","q0.025","q0.25","q0.5","q0.75","q0.975"
2021-11-24,"wind","36 hour",6.18301684924082,10.1985282433147,12.3062944299935,14.4141429015515,18.4314476462152
2021-11-24,"wind","48 hour",8.54704234407223,12.7638783683188,14.976509294123,17.1891454563085,21.4060956784116
2021-11-24,"wind","60 hour",5.5296670253095,10.318128085505,12.8376988149323,15.3579789396711,20.1618350300108
2021-11-24,"wind","72 hour",2.94784369394155,9.16084478428958,12.6555010815204,16.1771448451584,22.9115418900785
2021-11-24,"wind","84 hour",5.79177412369743,11.3532454437786,14.285536993294,17.2192594332228,22.8116716892064
"forecast_date","target","horizon","q0.025","q0.25","q0.5","q0.75","q0.975"
2021-11-24,"wind","36 hour",6.8185,9.1275,9.855,10.7025,11.78725
2021-11-24,"wind","48 hour",9.383,11.3925,12.59,13.37,14.57075
2021-11-24,"wind","60 hour",5.2915,8.935,10.385,11.655,14.86325
2021-11-24,"wind","72 hour",5.2785,8.1775,9.77,13.2025,17.56225
2021-11-24,"wind","84 hour",5.88925,9.605,11.05,13.57,17.49425
......@@ -6,7 +6,7 @@
# source functions:
source("code/functions.R")
forecast_date <- as.Date("2021-11-03")
forecast_date <- as.Date("2021-11-10")
wt <- gsub("-", "", as.character(forecast_date))
# get all forecasts:
......@@ -39,7 +39,7 @@ for(i in seq_along(files)){
library(quantmod)
getSymbols('^GDAXI',src='yahoo', from = as.Date("2021-09-01"))
dat_dax <- data.frame("date" = date(GDAXI), value = GDAXI$GDAXI.Close)
dat_dax <- data.frame("date" = index(GDAXI), value = GDAXI$GDAXI.Close)
colnames(dat_dax) <- c("date", "value")
dat_dax$date <- as.Date(dat_dax$date)
reference_value <- dat_dax$value[dat_dax$date == forecast_date]
......
......@@ -3,6 +3,8 @@
# needs to be run from repository root folder
# setwd("/home/johannes/Documents/Teaching/Ensemble_Seminar/ptsfc_results/")
library(dplyr)
eval_files <- list.files("evaluation")
eval_files <- eval_files[grep("evaluation_2", eval_files)]
......@@ -18,20 +20,55 @@ for(fl in eval_files){
}
}
# need to trnasform booleans to numeric to avoid weird behaviour:
# need to transform booleans to numeric to avoid weird behaviour:
all_evals$interval_coverage_0.5 <- as.numeric(all_evals$interval_coverage_0.5)
all_evals$interval_coverage_0.95 <- as.numeric(all_evals$interval_coverage_0.95)
all_evals$scores_imputed <- as.numeric(all_evals$scores_imputed)
summary_all_evals <- aggregate(cbind(ae, mean_qscore, interval_coverage_0.5, interval_coverage_0.95) ~ model + target + horizon,
data = all_evals, FUN = mean, na.rm = TRUE)
# compute summary evaluation
# step 1: prepare data
summary_all_evals1 <- all_evals %>%
# remove weather forecasts from Oct 27 (location changed from KA to B)
filter(! (forecast_date == "2021-10-27" & target != "DAX") ) %>%
# remove cases with missing ae (due to missing truth data)
filter(!is.na(ae)) %>%
# remove imputed benchmark forecasts for other variables
filter(! ( (model == "DAX_benchmark") & (target != "DAX") ),
! ( (model == "t2m_benchmark") & (target != "temperature") ),
! ( (model == "wind_benchmark") & (target != "wind") )) %>%
# assign same name to all benchmark models
mutate(model = if_else(grepl("benchmark", model), "Benchmark", model))
# add number of forecasts counted:
all_evals$n <- 1
n_forecasts <- aggregate(cbind(n, scores_imputed) ~ model + target + horizon,
data = all_evals, FUN = sum, na.rm = TRUE)
# step 2: stats by model, target and horizon
summary_all_evals2 <- summary_all_evals1 %>%
group_by(model, target, horizon) %>%
summarise(ae = mean(ae),
mean_qscore = mean(mean_qscore),
interval_coverage_0.5 = mean(interval_coverage_0.5),
interval_coverage_0.95 = mean(interval_coverage_0.95),
n = n(), scores_imputed = sum(scores_imputed),
.groups = "keep") %>% ungroup
# step 3: stats by model and target (aggregated over horizons)
summary_all_evals3 <- summary_all_evals1 %>%
group_by(model, target) %>%
summarise(ae = mean(ae),
mean_qscore = mean(mean_qscore),
interval_coverage_0.5 = mean(interval_coverage_0.5),
interval_coverage_0.95 = mean(interval_coverage_0.5),
n = n(), scores_imputed = sum(scores_imputed),
.groups = "keep") %>% ungroup %>%
mutate(horizon = "[All]")
summary_all_evals <- merge(summary_all_evals, n_forecasts, by = c("model", "target", "horizon"))
# Finally: Merge results from steps 2 and 3, compute skill scores
summary_all_evals <- rbind(summary_all_evals2, summary_all_evals3) %>%
group_by(target, horizon) %>%
# convert scores to skill scores (1 = perfect, <0 = worse than benchmark)
mutate(ae = (ae[model == "Benchmark"]-ae)/ae[model == "Benchmark"],
mean_qscore = (mean_qscore[model == "Benchmark"] - mean_qscore)/
mean_qscore[model == "Benchmark"]) %>%
# drop benchmark
filter(model != "Benchmark") %>% ungroup
write.csv(summary_all_evals, file = "ptsfc_viz/plot_data/summary_eval.csv", row.names = FALSE)
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
......@@ -59,6 +59,11 @@
2021-10-20 23:59:00,"wind","60 hour",8,10,12,14,16,"Yoda",2021-10-22 12:00:00,NA,NA
2021-10-20 23:59:00,"wind","72 hour",8,10,12,14,18,"Yoda",2021-10-23 00:00:00,NA,NA
2021-10-20 23:59:00,"wind","84 hour",7,9,12,15,17,"Yoda",2021-10-23 12:00:00,NA,NA
2021-10-20 23:59:00,"DAX","1 day",-2.65844263691718,-0.485396555504147,0.0657882169970314,0.652898469731245,2.22946787319034,"DAX_benchmark",2021-10-21 17:30:00,NA,NA
2021-10-20 23:59:00,"DAX","2 day",-3.76658704113496,-0.754702332963619,0.13670459761812,0.9054642766952,3.10108794007109,"DAX_benchmark",2021-10-22 17:30:00,NA,NA
2021-10-20 23:59:00,"DAX","5 day",-4.73040567059547,-0.849379110212389,0.143043446923219,1.18607119760754,3.89032640718187,"DAX_benchmark",2021-10-25 17:30:00,NA,NA
2021-10-20 23:59:00,"DAX","6 day",-5.23203014061953,-0.968345906220103,0.193504753259699,1.39125836779996,4.57407374600166,"DAX_benchmark",2021-10-26 17:30:00,NA,NA
2021-10-20 23:59:00,"DAX","7 day",-5.68685922947709,-1.09164649900868,0.346636456527527,1.48817956141838,5.19223708311003,"DAX_benchmark",2021-10-27 17:30:00,NA,NA
2021-10-20 23:59:00,"DAX","1 day",-4,-2,0,2,4,"Joey",2021-10-21 17:30:00,NA,NA
2021-10-20 23:59:00,"DAX","2 day",-4,-2,0,2,4,"Joey",2021-10-22 17:30:00,NA,NA
2021-10-20 23:59:00,"DAX","5 day",-4,-2,0,2,4,"Joey",2021-10-25 17:30:00,NA,NA
......
......@@ -59,6 +59,11 @@
"ChandlerBing","wind","60 hour",2021-11-03 23:59:00,9.24068657518788,13.7321478318721,16.0888225127788,18.4454971936854,22.9369584503697,2021-11-05 12:00:00,0.846533152377396,1.19117748722122
"ChandlerBing","wind","72 hour",2021-11-03 23:59:00,5.79067569596977,11.4160943980665,14.3677578027102,17.319421207354,22.9448399094507,2021-11-06 00:00:00,1.04342588360561,1.40775780271023
"ChandlerBing","wind","84 hour",2021-11-03 23:59:00,9.6363498234925,14.8243879666068,17.5465573089917,20.2687266513767,25.4567647944909,2021-11-06 12:00:00,1.08132655638863,1.89344269100828
"DAX_benchmark","DAX","1 day",2021-11-03 23:59:00,-2.65844263691718,-0.481709571803846,0.0733950537846084,0.662320554605333,2.22946787319034,2021-11-04 17:30:00,0.235718875789296,0.362183790236514
"DAX_benchmark","DAX","2 day",2021-11-03 23:59:00,-3.76658704113496,-0.732473649417953,0.142980430012329,0.907244580165889,3.10108794007109,2021-11-05 17:30:00,0.32197483531504,0.446631312722979
"DAX_benchmark","DAX","5 day",2021-11-03 23:59:00,-4.73040567059547,-0.81103402646141,0.16179836626895,1.18916624608452,3.89032640718187,2021-11-08 17:30:00,0.36201979748195,0.378962247247916
"DAX_benchmark","DAX","6 day",2021-11-03 23:59:00,-5.23203014061953,-0.933589441129046,0.219661627911449,1.39266918407004,4.57407374600166,2021-11-09 17:30:00,0.387364945028201,0.2833902182104
"DAX_benchmark","DAX","7 day",2021-11-03 23:59:00,-5.68685922947709,-1.06110544198859,0.357564327371396,1.47103419000207,5.19223708311003,2021-11-10 17:30:00,0.425187520582424,0.315912971287435
"DexterJettster","DAX","1 day",2021-11-03 23:59:00,-1.81771946224871,-0.324364624775741,0.132224049112306,0.587625273755954,1.65836811742549,2021-11-04 17:30:00,0.186630824631675,0.303354794908817
"DexterJettster","DAX","2 day",2021-11-03 23:59:00,-1.9565053511336,-0.403422667832487,0.123443620893227,0.702845994161949,2.23012289348735,2021-11-05 17:30:00,0.245726773014069,0.466168121842081
"DexterJettster","DAX","5 day",2021-11-03 23:59:00,-2.10031350630918,-0.497557194515696,0.191502017973022,0.899735463518514,2.7773211552435,2021-11-08 17:30:00,0.258357331527717,0.349258595543844
......@@ -209,26 +214,26 @@
"KyloRen","wind","60 hour",2021-11-03 23:59:00,3.7600581875,12.586653375,15.888412,18.89478,29.220265825,2021-11-05 12:00:00,1.163732338875,1.391588
"KyloRen","wind","72 hour",2021-11-03 23:59:00,2.712087445,10.930212,14.044305,17.53092875,24.443586325,2021-11-06 00:00:00,1.0942476638,1.084305
"KyloRen","wind","84 hour",2021-11-03 23:59:00,7.2699999075,14.60614075,17.5528725,20.28316625,26.796521925,2021-11-06 12:00:00,1.140393270175,1.8871275
"mean_ensemble","DAX","1 day",2021-11-03 23:59:00,-2.02825898441139,-0.382001114867622,0.10646219401679,0.633568222797302,1.86430620015501,2021-11-04 17:30:00,0.206305444701855,0.329114176445635
"mean_ensemble","DAX","2 day",2021-11-03 23:59:00,-2.74695666220728,-0.609587052303678,0.160394206437615,0.904187452769997,2.60680672504881,2021-11-05 17:30:00,0.290758005947395,0.429215782698045
"mean_ensemble","DAX","5 day",2021-11-03 23:59:00,-3.31093102313141,-0.681457329407887,0.201764033474751,1.09415412610773,3.19590694803525,2021-11-08 17:30:00,0.310428364826715,0.338995843046203
"mean_ensemble","DAX","6 day",2021-11-03 23:59:00,-3.55656715945281,-0.732380411676226,0.251937471326226,1.19760493702535,3.44623593877625,2021-11-09 17:30:00,0.3132932836704,0.251239975120149
"mean_ensemble","DAX","7 day",2021-11-03 23:59:00,-3.98233713943126,-0.688140361611747,0.377582682970036,1.36055346804885,3.85014046324557,2021-11-10 17:30:00,0.342366428869296,0.295946946921395
"mean_ensemble","temperature","36 hour",2021-11-03 23:59:00,6.58620605884461,7.7506624957451,8.68378920482086,9.50701099823736,11.3500111396742,2021-11-04 12:00:00,1.20617030240816,2.19887807534744
"mean_ensemble","temperature","48 hour",2021-11-03 23:59:00,5.9984966070696,7.35573287499317,8.24920588295004,9.14893596011242,10.890294935311,2021-11-05 00:00:00,0.495937493984541,1.04353647840509
"mean_ensemble","temperature","60 hour",2021-11-03 23:59:00,7.95356347772432,9.33802823170524,10.2373395363912,11.1364453601363,13.0548273975841,2021-11-05 12:00:00,0.55221054855125,1.1363931643125
"mean_ensemble","temperature","72 hour",2021-11-03 23:59:00,4.81460433233148,6.40831686470388,7.28975322128959,8.30333526087144,10.2953196880303,2021-11-06 00:00:00,0.288969269542204,0.21697712576916
"mean_ensemble","temperature","84 hour",2021-11-03 23:59:00,8.10517745576832,9.86660792726265,10.8222082295159,11.906013247873,14.0972340463277,2021-11-06 12:00:00,0.306994187215521,0.213940398842301
"mean_ensemble","wind","36 hour",2021-11-03 23:59:00,9.04714733905533,13.9751781342818,16.529877924591,19.2028606263171,24.1361491198693,2021-11-04 12:00:00,0.822624146821284,0.757120916314101
"mean_ensemble","wind","48 hour",2021-11-03 23:59:00,7.35974664186218,13.3216369884164,16.7115266126322,20.1742319234263,27.0266024502523,2021-11-05 00:00:00,3.52403395140322,6.7087822552448
"mean_ensemble","wind","60 hour",2021-11-03 23:59:00,9.8362678914806,13.8965251671767,16.1051717120068,18.3069123196153,22.7969139267778,2021-11-05 12:00:00,0.803774682230195,1.173491799993
"mean_ensemble","wind","72 hour",2021-11-03 23:59:00,7.01753841107474,11.8130856280002,14.0781243592871,16.7708662808547,22.0051857623602,2021-11-06 00:00:00,0.864081449792889,1.1128386063238
"mean_ensemble","wind","84 hour",2021-11-03 23:59:00,10.0523076471881,14.9813668508167,17.5948664518429,20.1178464249406,25.0170925090548,2021-11-06 12:00:00,1.0300781838756,1.842933912358
"mean_ensemble","DAX","1 day",2021-11-03 23:59:00,-2.02825898441139,-0.382001114867622,0.10646219401679,0.633568222797302,1.86430620015501,2021-11-04 17:30:00,0.206305915613023,0.329116650004333
"mean_ensemble","DAX","2 day",2021-11-03 23:59:00,-2.74695666220728,-0.609587052303678,0.160394206437615,0.904187452769997,2.60680672504881,2021-11-05 17:30:00,0.290758591639467,0.429217536297693
"mean_ensemble","DAX","5 day",2021-11-03 23:59:00,-3.31093102313141,-0.681457329407887,0.201764033474751,1.09415412610773,3.19590694803525,2021-11-08 17:30:00,0.310428841271651,0.338996580042115
"mean_ensemble","DAX","6 day",2021-11-03 23:59:00,-3.55656715945281,-0.732380411676226,0.251937471326226,1.19760493702535,3.44623593877625,2021-11-09 17:30:00,0.313249440811573,0.251114374795623
"mean_ensemble","DAX","7 day",2021-11-03 23:59:00,-3.98233713943126,-0.688140361611747,0.377582682970036,1.36055346804885,3.85014046324557,2021-11-10 17:30:00,0.342373082130587,0.295894615688795
"mean_ensemble","temperature","36 hour",2021-11-03 23:59:00,6.58620605884461,7.7506624957451,8.68378920482086,9.50701099823736,11.3500111396742,2021-11-04 12:00:00,1.19477816385758,2.18378920482086
"mean_ensemble","temperature","48 hour",2021-11-03 23:59:00,5.9984966070696,7.35573287499317,8.24920588295004,9.14893596011242,10.890294935311,2021-11-05 00:00:00,0.500372618381615,1.04920588295004
"mean_ensemble","temperature","60 hour",2021-11-03 23:59:00,7.95356347772432,9.33802823170524,10.2373395363912,11.1364453601363,13.0548273975841,2021-11-05 12:00:00,0.55353355200204,1.1373395363912
"mean_ensemble","temperature","72 hour",2021-11-03 23:59:00,4.81460433233148,6.40831686470388,7.28975322128959,8.30333526087144,10.2953196880303,2021-11-06 00:00:00,0.286358348915826,0.21024677871041
"mean_ensemble","temperature","84 hour",2021-11-03 23:59:00,8.10517745576832,9.86660792726265,10.8222082295159,11.906013247873,14.0972340463277,2021-11-06 12:00:00,0.308302743869809,0.2222082295159
"mean_ensemble","wind","36 hour",2021-11-03 23:59:00,9.04714733905533,13.9751781342818,16.529877924591,19.2028606263171,24.1361491198693,2021-11-04 12:00:00,0.823682682093471,0.750122075409003
"mean_ensemble","wind","48 hour",2021-11-03 23:59:00,7.35974664186218,13.3216369884164,16.7115266126322,20.1742319234263,27.0266024502523,2021-11-05 00:00:00,3.50992995968793,6.6884733873678
"mean_ensemble","wind","60 hour",2021-11-03 23:59:00,9.8362678914806,13.8965251671767,16.1051717120068,18.3069123196153,22.7969139267778,2021-11-05 12:00:00,0.805610833195472,1.1748282879932
"mean_ensemble","wind","72 hour",2021-11-03 23:59:00,7.01753841107474,11.8130856280002,14.0781243592871,16.7708662808547,22.0051857623602,2021-11-06 00:00:00,0.869279410655725,1.1181243592871
"mean_ensemble","wind","84 hour",2021-11-03 23:59:00,10.0523076471881,14.9813668508167,17.5948664518429,20.1178464249406,25.0170925090548,2021-11-06 12:00:00,1.03232251566248,1.8451335481571
"median_ensemble","DAX","1 day",2021-11-03 23:59:00,-2.04976467492226,-0.38839125675774,0.0777342832969625,0.6356064,1.73087533532045,2021-11-04 17:30:00,0.211775077923033,0.35784456072416
"median_ensemble","DAX","2 day",2021-11-03 23:59:00,-2.57505889304754,-0.661153491194609,0.140027900120636,0.905783297834439,2.5199783,2021-11-05 17:30:00,0.297560819356315,0.449583842614672
"median_ensemble","DAX","5 day",2021-11-03 23:59:00,-3.04769045711534,-0.716860000349991,0.193204562953042,1.1539173162404,2.88964264274188,2021-11-08 17:30:00,0.315962272770376,0.347556050563824
"median_ensemble","DAX","6 day",2021-11-03 23:59:00,-3.63802382151669,-0.780501133717677,0.23829450651625,1.19767268981571,3.01097030020352,2021-11-09 17:30:00,0.31770833282615,0.266045984105931
"median_ensemble","DAX","7 day",2021-11-03 23:59:00,-3.94690480781968,-0.752178574485322,0.36609577980414,1.35719286699481,3.61684968248609,2021-11-10 17:30:00,0.347965702532313,0.3079242395083
"median_ensemble","DAX","6 day",2021-11-03 23:59:00,-3.63802382151669,-0.780501133717677,0.23829450651625,1.19767268981571,3.01097030020352,2021-11-09 17:30:00,0.317258791491661,0.264757339605599
"median_ensemble","DAX","7 day",2021-11-03 23:59:00,-3.94690480781968,-0.752178574485322,0.36609577980414,1.35719286699481,3.61684968248609,2021-11-10 17:30:00,0.348050992822009,0.307381518854691
"median_ensemble","temperature","36 hour",2021-11-03 23:59:00,6.31578327832365,7.63136770881847,8.32165631218293,9.01194491554739,10.3275293460422,2021-11-04 12:00:00,0.995053527314051,1.82165631218293
"median_ensemble","temperature","48 hour",2021-11-03 23:59:00,6.24817763140052,7.64982543943644,8.38527159202891,9.12071774462139,10.5223655526573,2021-11-05 00:00:00,0.606815603911421,1.18527159202891
"median_ensemble","temperature","60 hour",2021-11-03 23:59:00,7.99191374474882,9.47950937595391,10.26005246628,11.0405955434807,12.5281911878111,2021-11-05 12:00:00,0.585285634820866,1.16005246628
......
This diff is collapsed.
"model","n_eval_cases","mean_rk_wind","mean_rk_temp","mean_rk_dax","mean_rk_overall"
"AryaStark",34,7.5,9,8,8.16666666666667
"Bronn",34,16.8,15.8,20.2,17.6
"CaptainRaymondHolt",34,7,8.4,11,8.8
"ChandlerBing",34,9.8,5.8,7,7.53333333333333
"DexterJettster",34,16.4,10,3.2,9.86666666666667
"DougJudy",34,9.2,9.4,6.8,8.46666666666667
"GeneralGrievous",34,19.4,20.6,11.6,17.2
"GinaLinetti",34,21,1.8,15.4,12.7333333333333
"HanSolo",34,2.4,19.2,13.4,11.6666666666667
"HotPie",34,11.6,5.8,6,7.8
"JabbaTheHutt",34,11.6,11,6.6,9.73333333333333
"Joey",34,8.2,11,11.8,10.3333333333333
"Joffrey_Baratheon",34,19,8.6,16.4,14.6666666666667
"KyloRen",34,8,6.8,12.4,9.06666666666667
"ObiWanKenobi",34,8.2,9,10,9.06666666666667
"PhoebeBuffay",34,3.4,13.2,6.6,7.73333333333333
"RossGeller",34,15.6,18.6,15.2,16.4666666666667
"SamwellTarly",34,16.6,15.4,20.6,17.5333333333333
"Shaggydog",34,6,13.2,17.2,12.1333333333333
"UglyNakedGuy",34,5.8,9.4,6.2,7.13333333333333
"Yoda",34,7.5,9,5.4,7.3
"AryaStark",48,5,9.8,6,6.93333333333333
"Bronn",48,15.6,14.8,19.2,16.5333333333333
"CaptainRaymondHolt",48,5.8,6.6,10.4,7.6
"ChandlerBing",48,7.2,4.6,5.8,5.86666666666667
"DexterJettster",48,15.6,9.8,2.8,9.4
"DougJudy",48,10.8,8.2,6.6,8.53333333333333
"GeneralGrievous",48,19.8,20.6,17.8,19.4
"GinaLinetti",48,21,15.4,14.6,17
"HanSolo",48,5,18.2,12.8,12
"HotPie",48,12,5.6,4.4,7.33333333333333
"JabbaTheHutt",48,12.6,10,11.8,11.4666666666667
"Joey",48,8.6,11.8,10.8,10.4
"Joffrey_Baratheon",48,17.8,7.6,15,13.4666666666667
"KyloRen",48,9.4,6.2,11.6,9.06666666666667
"ObiWanKenobi",48,8.6,7.8,7.4,7.93333333333333
"PhoebeBuffay",48,4,11.2,6,7.06666666666667
"RossGeller",48,19.2,19.8,18.6,19.2
"SamwellTarly",48,15.2,14.8,19.6,16.5333333333333
"Shaggydog",48,4,11,15.6,10.2
"UglyNakedGuy",48,7,9.4,6.4,7.6
"Yoda",48,6.8,7.8,7.8,7.46666666666667
This diff is collapsed.
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment