##### The contribution of Earth observation technologies to the reporting obligations####
###of the Habitats Directive and Natura 2000 network in a protected wetland #####
# Authors: Adrian Regos & Jesus Dominguez (University of Santiago de Compostela & CIOBIO/InBIO)##
################################################################################################
#### Pre-processing of Landsat images for year 2003, classification and validation procedures###
################################################################################################
library(RStoolbox)
library(raster)
## Loading required package: sp
library(rgdal)
## rgdal: version: 1.2-8, (SVN revision 663)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 2.0.1, released 2015/09/15
## Path to GDAL shared files: C:/Users/Usuario/Documents/R/win-library/3.4/rgdal/gdal
## Loaded PROJ.4 runtime: Rel. 4.9.2, 08 September 2015, [PJ_VERSION: 492]
## Path to PROJ.4 shared files: C:/Users/Usuario/Documents/R/win-library/3.4/rgdal/proj
## Linking to sp version: 1.2-5
metaL7Mar2003 <- readMeta("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/LandsatData/2003/LE72050302003079EDC00/LE72050302003079EDC00_MTL.txt")
metaL5Oct2003 <- readMeta("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/LandsatData/2003/LT52050302003279MTI01/LT52050302003279MTI01_MTL.txt")
summary(metaL7Mar2003)
## Scene: LE72050302003079EDC00
## Satellite: LANDSAT7
## Sensor: ETM
## Date: 2003-03-20
## Path/Row: 205/30
## Projection: +proj=utm +zone=29 +units=m +datum=WGS84 +ellps=WGS84 +towgs84=0,0,0
##
## Data:
## FILES QUANTITY CATEGORY
## B1_dn LE72050302003079EDC00_B1.TIF dn image
## B2_dn LE72050302003079EDC00_B2.TIF dn image
## B3_dn LE72050302003079EDC00_B3.TIF dn image
## B4_dn LE72050302003079EDC00_B4.TIF dn image
## B5_dn LE72050302003079EDC00_B5.TIF dn image
## B6_VCID_1_dn LE72050302003079EDC00_B6_VCID_1.TIF dn image
## B6_VCID_2_dn LE72050302003079EDC00_B6_VCID_2.TIF dn image
## B7_dn LE72050302003079EDC00_B7.TIF dn image
## B8_dn LE72050302003079EDC00_B8.TIF dn pan
##
## Available calibration parameters (gain and offset):
## dn -> radiance (toa)
## dn -> brightness temperature (toa)
summary(metaL5Oct2003)
## Scene: LT52050302003279MTI01
## Satellite: LANDSAT5
## Sensor: TM
## Date: 2003-10-06
## Path/Row: 205/30
## Projection: +proj=utm +zone=29 +units=m +datum=WGS84 +ellps=WGS84 +towgs84=0,0,0
##
## Data:
## FILES QUANTITY CATEGORY
## B1_dn LT52050302003279MTI01_B1.TIF dn image
## B2_dn LT52050302003279MTI01_B2.TIF dn image
## B3_dn LT52050302003279MTI01_B3.TIF dn image
## B4_dn LT52050302003279MTI01_B4.TIF dn image
## B5_dn LT52050302003279MTI01_B5.TIF dn image
## B6_dn LT52050302003279MTI01_B6.TIF dn image
## B7_dn LT52050302003279MTI01_B7.TIF dn image
##
## Available calibration parameters (gain and offset):
## dn -> radiance (toa)
## dn -> brightness temperature (toa)
L7Mar2003 <- stackMeta(metaL7Mar2003)
L5Oct2003 <- stackMeta(metaL5Oct2003)
################### calibration and radiometric correction if necessary
#Data conversion: From DNs to Reflectances
#Radiometric calibration
metaL7Mar2003$CALRAD
## offset gain
## B1_dn -6.97874 0.779
## B2_dn -7.19882 0.799
## B3_dn -5.62165 0.622
## B4_dn -5.73976 0.640
## B5_dn -1.12622 0.126
## B6_VCID_1_dn -0.06709 0.067
## B6_VCID_2_dn 3.16280 0.037
## B7_dn -0.39390 0.044
## B8_dn -5.67559 0.976
metaL5Oct2003$CALRAD
## offset gain
## B1_dn -2.28583 0.766
## B2_dn -4.28819 1.448
## B3_dn -2.21398 1.044
## B4_dn -2.38602 0.876
## B5_dn -0.49035 0.120
## B6_dn 1.18243 0.055
## B7_dn -0.21555 0.066
L7Mar2003_rad <- radCor(L7Mar2003, metaData = metaL7Mar2003, method="rad")
L5Oct2003_rad <- radCor(L5Oct2003, metaData = metaL5Oct2003, method="rad")
dataType(L7Mar2003_rad[[1]]) #dataType from integer to float
## [1] "FLT8S"
dataType(L5Oct2003_rad[[1]])
## [1] "FLT8S"
plotRGB(L7Mar2003_rad, r = 3, g = 2, b = 1, stretch = "lin")
plot(L7Mar2003_rad)
plotRGB(L5Oct2003_rad, r = 3, g = 2, b = 1, stretch = "lin")
plot(L5Oct2003_rad)
##crop the images to our study area (Natural Park - Corrubedo)
study_area <- readOGR("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/AreaEstudio/LimiteParque", "PNCorrubedo_reproj")
## OGR data source with driver: ESRI Shapefile
## Source: "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/AreaEstudio/LimiteParque", layer: "PNCorrubedo_reproj"
## with 1 features
## It has 10 fields
#March
L7Mar2003_rad_PN <- crop(L7Mar2003_rad,study_area)
L7Mar2003_rad_PN_mask <- mask(L7Mar2003_rad_PN, study_area)
plotRGB(L7Mar2003_rad_PN_mask, r = 3, g = 2, b = 1, stretch = "hist")#rgb
plotRGB(L7Mar2003_rad_PN_mask, r = 5, g = 4, b = 2, stretch = "hist")#vegetation
plotRGB(L7Mar2003_rad_PN_mask, r = 4, g = 5, b = 1, stretch = "hist")# brown
plotRGB(L7Mar2003_rad_PN_mask, r = 4, g = 3, b = 2, stretch = "hist")# brown
#October
L5Oct2003_rad_PN <- crop(L5Oct2003_rad,study_area)
L5Oct2003_rad_PN_mask <- mask(L5Oct2003_rad_PN,study_area)
plotRGB(L5Oct2003_rad_PN_mask, r = 3, g = 2, b = 1, stretch = "hist")#rgb
plotRGB(L5Oct2003_rad_PN_mask, r = 5, g = 4, b = 2, stretch = "hist")#vegetation
plotRGB(L5Oct2003_rad_PN_mask, r = 4, g = 5, b = 1, stretch = "hist")# brown
plotRGB(L5Oct2003_rad_PN_mask, r = 4, g = 3, b = 2, stretch = "hist")#red
#Spectral index - Normalised Difference Water Index: NDWI = (green - nir)/(green + nir)
NDWI_Mar <- spectralIndices(L7Mar2003_rad_PN_mask, blue = "B1_tra", green = "B2_tra", red = "B3_tra",
nir = "B4_tra", swir2 = "B5_tra", indices = "NDWI")#
NDWI_Oct <- spectralIndices(L5Oct2003_rad_PN_mask, blue = "B1_tra", green = "B2_tra", red = "B3_tra",
nir = "B4_tra", swir2 = "B5_tra", indices = "NDWI")#
NDVI_Mar <- spectralIndices(L7Mar2003_rad_PN_mask, blue = "B1_tra", green = "B2_tra", red = "B3_tra",
nir = "B4_tra", swir2 = "B5_tra", indices = "NDVI")#
NDVI_Oct <- spectralIndices(L5Oct2003_rad_PN_mask, blue = "B1_tra", green = "B2_tra", red = "B3_tra",
nir = "B4_tra", swir2 = "B5_tra", indices = "NDVI")#
plot(NDWI_Mar)
plot(NDWI_Oct)
plot(NDVI_Mar)
plot(NDVI_Oct)
#join both datasets (Oct - Mar)
L72003 <- stack(L7Mar2003_rad_PN_mask, L5Oct2003_rad_PN_mask)
L72003 <- L72003[[c(1,2,3,4,5,8,9,10,11,12,13,15)]] #subset - only optical radiometric bands
#join with spectral indices
L72003 <- stack(L72003,NDWI_Mar,NDWI_Oct)
L72003 <- stack(L72003,NDVI_Mar,NDVI_Oct)
############### training data #############
#read vector files for training dataset
train_2003 <- readOGR("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/TrainAreas", "TrainAreas_2003_7cat_v2")
## OGR data source with driver: ESRI Shapefile
## Source: "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/TrainAreas", layer: "TrainAreas_2003_7cat_v2"
## with 45 features
## It has 2 fields
## Integer64 fields read as strings: id
val_2003 <- readOGR("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/TrainAreas", "TestAreas_2003_7cat")
## OGR data source with driver: ESRI Shapefile
## Source: "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/TrainAreas", layer: "TestAreas_2003_7cat"
## with 47 features
## It has 2 fields
## Integer64 fields read as strings: id
######### classification procedures
library(caret)
## Loading required package: lattice
## Loading required package: ggplot2
## Warning: package 'ggplot2' was built under R version 3.4.3
library(randomForest)
## randomForest 4.6-12
## Type rfNews() to see new features/changes/bug fixes.
##
## Attaching package: 'randomForest'
## The following object is masked from 'package:ggplot2':
##
## margin
library(party)
## Warning: package 'party' was built under R version 3.4.2
## Loading required package: grid
## Loading required package: mvtnorm
## Loading required package: modeltools
## Loading required package: stats4
## Loading required package: strucchange
## Warning: package 'strucchange' was built under R version 3.4.2
## Loading required package: zoo
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
## Loading required package: sandwich
## Warning: package 'sandwich' was built under R version 3.4.2
library(pls)
## Warning: package 'pls' was built under R version 3.4.2
##
## Attaching package: 'pls'
## The following object is masked from 'package:caret':
##
## R2
## The following object is masked from 'package:stats':
##
## loadings
library(e1071)
## Warning: package 'e1071' was built under R version 3.4.2
##
## Attaching package: 'e1071'
## The following object is masked from 'package:raster':
##
## interpolate
library(kernlab)
##
## Attaching package: 'kernlab'
## The following object is masked from 'package:modeltools':
##
## prior
## The following object is masked from 'package:ggplot2':
##
## alpha
## The following objects are masked from 'package:raster':
##
## buffer, rotated
library(adaptDA)
## Warning: package 'adaptDA' was built under R version 3.4.2
## Loading required package: MASS
##
## Attaching package: 'MASS'
## The following objects are masked from 'package:raster':
##
## area, select
#ensemble of predictions
models <- c("svmPoly", "svmRadial", "svmLinear", "rf", "knn", "gbm", "pls", "mda", "amdai", "avNNet")
ensemble <- lapply (models, function(mod){
set.seed(5)
sc <- superClass(L72003, model= mod, trainData = train_2003,
responseCol = "class")
return(sc$map)
})
## Loading required package: gbm
## Loading required package: survival
##
## Attaching package: 'survival'
## The following object is masked from 'package:caret':
##
## cluster
## Loading required package: splines
## Loading required package: parallel
## Loaded gbm 2.1.3
## Loading required package: plyr
##
## Attaching package: 'plyr'
## The following object is masked from 'package:modeltools':
##
## empty
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.8008
## 2 1.4967 nan 0.1000 0.4520
## 3 1.2351 nan 0.1000 0.3050
## 4 1.0500 nan 0.1000 0.2539
## 5 0.8983 nan 0.1000 0.1704
## 6 0.7886 nan 0.1000 0.1775
## 7 0.6864 nan 0.1000 0.1227
## 8 0.6074 nan 0.1000 0.1132
## 9 0.5347 nan 0.1000 0.0870
## 10 0.4789 nan 0.1000 0.0887
## 20 0.1654 nan 0.1000 0.0172
## 40 0.0268 nan 0.1000 0.0009
## 60 0.0065 nan 0.1000 0.0001
## 80 0.0021 nan 0.1000 0.0000
## 100 0.0010 nan 0.1000 -0.0004
## 120 0.0007 nan 0.1000 0.0003
## 140 0.0003 nan 0.1000 -0.0000
## 150 0.0003 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.8837
## 2 1.4555 nan 0.1000 0.4450
## 3 1.1804 nan 0.1000 0.3337
## 4 0.9800 nan 0.1000 0.2524
## 5 0.8052 nan 0.1000 0.2308
## 6 0.6710 nan 0.1000 0.1627
## 7 0.5703 nan 0.1000 0.1469
## 8 0.4784 nan 0.1000 0.1164
## 9 0.4041 nan 0.1000 0.0889
## 10 0.3458 nan 0.1000 0.0764
## 20 0.0774 nan 0.1000 0.0099
## 40 0.0103 nan 0.1000 -0.0004
## 60 0.0040 nan 0.1000 -0.0014
## 80 0.0021 nan 0.1000 -0.0001
## 100 0.0014 nan 0.1000 -0.0008
## 120 0.0012 nan 0.1000 -0.0000
## 140 0.0010 nan 0.1000 -0.0001
## 150 0.0013 nan 0.1000 -0.0010
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.8900
## 2 1.4025 nan 0.1000 0.4550
## 3 1.1299 nan 0.1000 0.3718
## 4 0.9067 nan 0.1000 0.2492
## 5 0.7532 nan 0.1000 0.1965
## 6 0.6273 nan 0.1000 0.1583
## 7 0.5352 nan 0.1000 0.1045
## 8 0.4615 nan 0.1000 0.1159
## 9 0.3864 nan 0.1000 0.0868
## 10 0.3307 nan 0.1000 0.0830
## 20 0.0711 nan 0.1000 0.0081
## 40 0.0068 nan 0.1000 0.0003
## 60 0.0019 nan 0.1000 -0.0001
## 80 0.0008 nan 0.1000 -0.0006
## 100 0.0006 nan 0.1000 0.0001
## 120 0.0003 nan 0.1000 -0.0001
## 140 0.0001 nan 0.1000 -0.0000
## 150 0.0001 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.6953
## 2 1.5242 nan 0.1000 0.4043
## 3 1.2696 nan 0.1000 0.3317
## 4 1.0774 nan 0.1000 0.2565
## 5 0.9269 nan 0.1000 0.2019
## 6 0.8111 nan 0.1000 0.1603
## 7 0.7165 nan 0.1000 0.1302
## 8 0.6352 nan 0.1000 0.1196
## 9 0.5609 nan 0.1000 0.0943
## 10 0.4977 nan 0.1000 0.0801
## 20 0.1735 nan 0.1000 0.0250
## 40 0.0308 nan 0.1000 -0.0020
## 60 0.0100 nan 0.1000 -0.0001
## 80 0.0046 nan 0.1000 -0.0016
## 100 0.0024 nan 0.1000 -0.0009
## 120 0.0013 nan 0.1000 -0.0001
## 140 0.0008 nan 0.1000 -0.0001
## 150 0.0007 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.9568
## 2 1.3903 nan 0.1000 0.4555
## 3 1.1048 nan 0.1000 0.2939
## 4 0.9204 nan 0.1000 0.2708
## 5 0.7607 nan 0.1000 0.1881
## 6 0.6423 nan 0.1000 0.1612
## 7 0.5354 nan 0.1000 0.1286
## 8 0.4506 nan 0.1000 0.1158
## 9 0.3779 nan 0.1000 0.0820
## 10 0.3214 nan 0.1000 0.0607
## 20 0.0795 nan 0.1000 0.0097
## 40 0.0115 nan 0.1000 0.0002
## 60 0.0026 nan 0.1000 -0.0006
## 80 0.0006 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 -0.0001
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0004 nan 0.1000 -0.0004
## 150 0.0003 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.7579
## 2 1.4519 nan 0.1000 0.4498
## 3 1.1735 nan 0.1000 0.3532
## 4 0.9538 nan 0.1000 0.2458
## 5 0.8038 nan 0.1000 0.1953
## 6 0.6707 nan 0.1000 0.1605
## 7 0.5649 nan 0.1000 0.1198
## 8 0.4846 nan 0.1000 0.1317
## 9 0.4078 nan 0.1000 0.0903
## 10 0.3497 nan 0.1000 0.0770
## 20 0.0768 nan 0.1000 0.0081
## 40 0.0062 nan 0.1000 0.0008
## 60 0.0017 nan 0.1000 -0.0009
## 80 0.0008 nan 0.1000 -0.0001
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0007 nan 0.1000 -0.0006
## 140 0.0006 nan 0.1000 -0.0002
## 150 0.0005 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.8238
## 2 1.4896 nan 0.1000 0.4286
## 3 1.2332 nan 0.1000 0.2879
## 4 1.0628 nan 0.1000 0.2633
## 5 0.9102 nan 0.1000 0.1912
## 6 0.7943 nan 0.1000 0.1672
## 7 0.6913 nan 0.1000 0.1312
## 8 0.6104 nan 0.1000 0.1139
## 9 0.5424 nan 0.1000 0.0885
## 10 0.4871 nan 0.1000 0.0829
## 20 0.1751 nan 0.1000 0.0142
## 40 0.0288 nan 0.1000 0.0000
## 60 0.0067 nan 0.1000 -0.0011
## 80 0.0024 nan 0.1000 -0.0000
## 100 0.0009 nan 0.1000 0.0000
## 120 0.0005 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 150 0.0001 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.9249
## 2 1.4329 nan 0.1000 0.4950
## 3 1.1456 nan 0.1000 0.3592
## 4 0.9256 nan 0.1000 0.2631
## 5 0.7785 nan 0.1000 0.1909
## 6 0.6571 nan 0.1000 0.1628
## 7 0.5530 nan 0.1000 0.1325
## 8 0.4669 nan 0.1000 0.1087
## 9 0.3943 nan 0.1000 0.0852
## 10 0.3343 nan 0.1000 0.0684
## 20 0.0685 nan 0.1000 0.0128
## 40 0.0062 nan 0.1000 -0.0006
## 60 0.0019 nan 0.1000 -0.0006
## 80 0.0010 nan 0.1000 -0.0007
## 100 0.0006 nan 0.1000 -0.0003
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.7989
## 2 1.4402 nan 0.1000 0.4446
## 3 1.1742 nan 0.1000 0.3808
## 4 0.9470 nan 0.1000 0.2795
## 5 0.7777 nan 0.1000 0.1931
## 6 0.6601 nan 0.1000 0.1744
## 7 0.5556 nan 0.1000 0.1430
## 8 0.4646 nan 0.1000 0.1129
## 9 0.3932 nan 0.1000 0.1048
## 10 0.3264 nan 0.1000 0.0721
## 20 0.0758 nan 0.1000 0.0104
## 40 0.0050 nan 0.1000 0.0005
## 60 0.0008 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0001
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0001 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.8133
## 2 1.5006 nan 0.1000 0.4677
## 3 1.2355 nan 0.1000 0.3154
## 4 1.0560 nan 0.1000 0.2590
## 5 0.9087 nan 0.1000 0.1915
## 6 0.7924 nan 0.1000 0.1567
## 7 0.6962 nan 0.1000 0.1407
## 8 0.6087 nan 0.1000 0.1116
## 9 0.5412 nan 0.1000 0.0976
## 10 0.4808 nan 0.1000 0.0714
## 20 0.1665 nan 0.1000 0.0150
## 40 0.0332 nan 0.1000 0.0007
## 60 0.0093 nan 0.1000 0.0002
## 80 0.0039 nan 0.1000 -0.0012
## 100 0.0017 nan 0.1000 -0.0001
## 120 0.0008 nan 0.1000 -0.0001
## 140 0.0006 nan 0.1000 -0.0003
## 150 0.0005 nan 0.1000 -0.0001
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.8665
## 2 1.4069 nan 0.1000 0.5121
## 3 1.0977 nan 0.1000 0.3410
## 4 0.8934 nan 0.1000 0.2729
## 5 0.7344 nan 0.1000 0.2023
## 6 0.6156 nan 0.1000 0.1547
## 7 0.5161 nan 0.1000 0.1428
## 8 0.4288 nan 0.1000 0.1044
## 9 0.3677 nan 0.1000 0.0892
## 10 0.3105 nan 0.1000 0.0701
## 20 0.0656 nan 0.1000 0.0105
## 40 0.0066 nan 0.1000 -0.0011
## 60 0.0028 nan 0.1000 -0.0004
## 80 0.0012 nan 0.1000 -0.0001
## 100 0.0007 nan 0.1000 -0.0001
## 120 0.0007 nan 0.1000 -0.0002
## 140 0.0004 nan 0.1000 -0.0000
## 150 0.0004 nan 0.1000 0.0001
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.8833
## 2 1.3938 nan 0.1000 0.5102
## 3 1.1065 nan 0.1000 0.3347
## 4 0.8971 nan 0.1000 0.2380
## 5 0.7535 nan 0.1000 0.1903
## 6 0.6358 nan 0.1000 0.1676
## 7 0.5279 nan 0.1000 0.1322
## 8 0.4472 nan 0.1000 0.1010
## 9 0.3823 nan 0.1000 0.1016
## 10 0.3206 nan 0.1000 0.0767
## 20 0.0707 nan 0.1000 0.0124
## 40 0.0062 nan 0.1000 0.0008
## 60 0.0014 nan 0.1000 -0.0005
## 80 0.0007 nan 0.1000 -0.0002
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0002
## 140 0.0002 nan 0.1000 -0.0001
## 150 0.0001 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.7992
## 2 1.4927 nan 0.1000 0.4331
## 3 1.2348 nan 0.1000 0.3138
## 4 1.0491 nan 0.1000 0.2485
## 5 0.9081 nan 0.1000 0.1920
## 6 0.7951 nan 0.1000 0.1584
## 7 0.6981 nan 0.1000 0.1320
## 8 0.6185 nan 0.1000 0.1127
## 9 0.5424 nan 0.1000 0.1041
## 10 0.4806 nan 0.1000 0.0878
## 20 0.1591 nan 0.1000 0.0213
## 40 0.0244 nan 0.1000 -0.0018
## 60 0.0055 nan 0.1000 -0.0002
## 80 0.0016 nan 0.1000 0.0001
## 100 0.0006 nan 0.1000 0.0001
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.7560
## 2 1.4860 nan 0.1000 0.5244
## 3 1.1653 nan 0.1000 0.3250
## 4 0.9590 nan 0.1000 0.2925
## 5 0.7939 nan 0.1000 0.2118
## 6 0.6598 nan 0.1000 0.1705
## 7 0.5510 nan 0.1000 0.1332
## 8 0.4664 nan 0.1000 0.1027
## 9 0.4007 nan 0.1000 0.0908
## 10 0.3442 nan 0.1000 0.0783
## 20 0.0749 nan 0.1000 0.0114
## 40 0.0067 nan 0.1000 0.0003
## 60 0.0008 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.9053
## 2 1.4048 nan 0.1000 0.4968
## 3 1.0962 nan 0.1000 0.3094
## 4 0.9001 nan 0.1000 0.2524
## 5 0.7412 nan 0.1000 0.1850
## 6 0.6257 nan 0.1000 0.1586
## 7 0.5318 nan 0.1000 0.1210
## 8 0.4521 nan 0.1000 0.1136
## 9 0.3812 nan 0.1000 0.0738
## 10 0.3297 nan 0.1000 0.0776
## 20 0.0801 nan 0.1000 0.0124
## 40 0.0053 nan 0.1000 0.0009
## 60 0.0011 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 1.9459 nan 0.1000 0.7764
## 2 1.4831 nan 0.1000 0.3972
## 3 1.2351 nan 0.1000 0.3165
## 4 1.0531 nan 0.1000 0.2502
## 5 0.9042 nan 0.1000 0.1969
## 6 0.7898 nan 0.1000 0.1691
## 7 0.6892 nan 0.1000 0.1206
## 8 0.6132 nan 0.1000 0.0955
## 9 0.5493 nan 0.1000 0.0839
## 10 0.4921 nan 0.1000 0.0913
## 20 0.1698 nan 0.1000 0.0226
## 40 0.0326 nan 0.1000 0.0037
## 50 0.0172 nan 0.1000 -0.0011
## Loading required package: mda
## Loading required package: class
## Loaded mda 0.4-9
## Loading required package: nnet
## Warning: executing %dopar% sequentially: no parallel backend registered
## Fitting Repeat 1
##
## # weights: 31
## initial value 315.429594
## final value 167.000000
## converged
## Fitting Repeat 2
##
## # weights: 31
## initial value 307.849874
## final value 167.000000
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 271.272372
## final value 166.999096
## converged
## Fitting Repeat 4
##
## # weights: 31
## initial value 268.704972
## iter 10 value 166.878519
## iter 20 value 159.569846
## final value 154.329308
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 351.973158
## final value 167.000000
## converged
## Fitting Repeat 1
##
## # weights: 79
## initial value 257.208222
## iter 10 value 154.329335
## iter 10 value 154.329335
## iter 10 value 154.329335
## final value 154.329335
## converged
## Fitting Repeat 2
##
## # weights: 79
## initial value 296.816724
## final value 167.000000
## converged
## Fitting Repeat 3
##
## # weights: 79
## initial value 314.848229
## iter 10 value 151.359246
## final value 151.161677
## converged
## Fitting Repeat 4
##
## # weights: 79
## initial value 292.084638
## final value 167.000000
## converged
## Fitting Repeat 5
##
## # weights: 79
## initial value 407.179091
## final value 167.000000
## converged
## Fitting Repeat 1
##
## # weights: 127
## initial value 292.893853
## iter 10 value 154.329341
## iter 10 value 154.329341
## iter 10 value 154.329341
## final value 154.329341
## converged
## Fitting Repeat 2
##
## # weights: 127
## initial value 407.314062
## final value 167.000000
## converged
## Fitting Repeat 3
##
## # weights: 127
## initial value 360.894975
## final value 167.000000
## converged
## Fitting Repeat 4
##
## # weights: 127
## initial value 334.206361
## final value 167.000000
## converged
## Fitting Repeat 5
##
## # weights: 127
## initial value 376.560152
## final value 154.329342
## converged
## Fitting Repeat 1
##
## # weights: 31
## initial value 321.894382
## iter 10 value 144.963833
## iter 20 value 140.834156
## iter 30 value 136.662344
## iter 40 value 119.283285
## iter 50 value 109.188227
## iter 60 value 106.857399
## iter 70 value 106.805098
## iter 80 value 106.798890
## final value 106.798878
## converged
## Fitting Repeat 2
##
## # weights: 31
## initial value 281.198932
## iter 10 value 149.515444
## iter 20 value 140.527039
## iter 30 value 135.960722
## iter 40 value 120.012088
## iter 50 value 115.806153
## iter 60 value 113.475309
## iter 70 value 113.168209
## iter 80 value 113.128262
## iter 80 value 113.128261
## iter 80 value 113.128261
## final value 113.128261
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 262.292878
## iter 10 value 140.972624
## iter 20 value 140.531770
## iter 30 value 136.838155
## iter 40 value 127.243019
## iter 50 value 123.270109
## iter 60 value 120.893964
## iter 70 value 116.881820
## iter 80 value 114.426201
## iter 90 value 111.807360
## iter 100 value 111.685315
## final value 111.685315
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 31
## initial value 271.663345
## iter 10 value 147.003514
## iter 20 value 139.743942
## iter 30 value 139.341690
## iter 40 value 139.321189
## final value 139.320468
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 318.633934
## iter 10 value 152.212453
## iter 20 value 138.219066
## iter 30 value 122.753846
## iter 40 value 122.020699
## iter 50 value 120.740199
## iter 60 value 118.900900
## iter 70 value 116.112549
## iter 80 value 111.779147
## iter 90 value 111.568409
## final value 111.568155
## converged
## Fitting Repeat 1
##
## # weights: 79
## initial value 299.879056
## iter 10 value 151.348363
## iter 20 value 139.928274
## iter 30 value 134.355468
## iter 40 value 112.976520
## iter 50 value 86.913142
## iter 60 value 78.688375
## iter 70 value 71.844112
## iter 80 value 71.278277
## iter 90 value 70.794976
## iter 100 value 70.761142
## final value 70.761142
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 79
## initial value 312.871271
## iter 10 value 149.466855
## iter 20 value 126.656396
## iter 30 value 117.351445
## iter 40 value 111.912886
## iter 50 value 111.383193
## iter 60 value 92.824952
## iter 70 value 82.114817
## iter 80 value 75.246281
## iter 90 value 73.986763
## iter 100 value 71.337349
## final value 71.337349
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 249.523901
## iter 10 value 142.169479
## iter 20 value 140.375306
## iter 30 value 138.686145
## iter 40 value 120.504522
## iter 50 value 91.282502
## iter 60 value 87.558072
## iter 70 value 86.377297
## iter 80 value 82.728647
## iter 90 value 78.460520
## iter 100 value 59.715674
## final value 59.715674
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 381.337820
## iter 10 value 155.126820
## iter 20 value 141.444508
## iter 30 value 127.840301
## iter 40 value 104.401538
## iter 50 value 100.118377
## iter 60 value 97.224790
## iter 70 value 86.993932
## iter 80 value 50.700135
## iter 90 value 44.901006
## iter 100 value 44.116500
## final value 44.116500
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 79
## initial value 298.482346
## iter 10 value 154.616604
## iter 20 value 139.211749
## iter 30 value 122.789545
## iter 40 value 98.487477
## iter 50 value 72.682075
## iter 60 value 64.389152
## iter 70 value 61.940499
## iter 80 value 58.311558
## iter 90 value 54.353750
## iter 100 value 43.432173
## final value 43.432173
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 338.068473
## iter 10 value 165.748491
## iter 20 value 142.362147
## iter 30 value 132.357087
## iter 40 value 105.903215
## iter 50 value 78.580836
## iter 60 value 71.640070
## iter 70 value 62.681100
## iter 80 value 51.082549
## iter 90 value 42.189832
## iter 100 value 39.657668
## final value 39.657668
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 318.239377
## iter 10 value 150.619134
## iter 20 value 139.308369
## iter 30 value 126.781615
## iter 40 value 122.888854
## iter 50 value 119.684130
## iter 60 value 102.787900
## iter 70 value 95.700293
## iter 80 value 86.192328
## iter 90 value 61.952380
## iter 100 value 42.577610
## final value 42.577610
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 299.734434
## iter 10 value 164.245473
## iter 20 value 141.803560
## iter 30 value 121.311474
## iter 40 value 113.104519
## iter 50 value 110.852521
## iter 60 value 102.093944
## iter 70 value 79.684353
## iter 80 value 69.906847
## iter 90 value 47.882626
## iter 100 value 33.690784
## final value 33.690784
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 409.920091
## iter 10 value 148.535082
## iter 20 value 138.918289
## iter 30 value 133.356413
## iter 40 value 121.881576
## iter 50 value 92.883667
## iter 60 value 75.681498
## iter 70 value 56.821903
## iter 80 value 45.906039
## iter 90 value 38.650535
## iter 100 value 32.254808
## final value 32.254808
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 369.805259
## iter 10 value 150.672992
## iter 20 value 121.405654
## iter 30 value 114.591903
## iter 40 value 89.655622
## iter 50 value 77.258212
## iter 60 value 64.065507
## iter 70 value 60.248136
## iter 80 value 55.217273
## iter 90 value 49.175846
## iter 100 value 35.763748
## final value 35.763748
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 31
## initial value 290.066226
## iter 10 value 167.345890
## iter 20 value 167.325020
## iter 30 value 167.287434
## iter 40 value 167.179510
## iter 50 value 154.605284
## iter 60 value 146.898088
## iter 70 value 146.143082
## iter 80 value 143.183826
## iter 90 value 138.323675
## iter 100 value 138.228429
## final value 138.228429
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 31
## initial value 352.741561
## iter 10 value 167.464259
## iter 20 value 160.065355
## iter 30 value 147.711321
## iter 40 value 144.514987
## iter 50 value 142.373276
## iter 60 value 139.056048
## iter 70 value 138.992189
## iter 80 value 138.246422
## iter 90 value 138.175901
## final value 137.990847
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 341.847092
## iter 10 value 142.903544
## iter 20 value 138.008454
## iter 30 value 137.995628
## iter 40 value 133.305885
## iter 50 value 121.483868
## iter 60 value 121.326225
## iter 70 value 121.314867
## iter 80 value 121.307854
## iter 90 value 121.295521
## iter 100 value 121.288453
## final value 121.288453
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 31
## initial value 351.985205
## iter 10 value 164.068791
## iter 20 value 155.035078
## iter 30 value 154.186621
## iter 40 value 148.982963
## iter 50 value 141.642739
## iter 60 value 138.312784
## iter 70 value 138.235982
## iter 80 value 138.052543
## final value 137.989905
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 327.611367
## iter 10 value 166.846618
## iter 20 value 161.693733
## iter 30 value 161.545644
## iter 40 value 158.714003
## iter 50 value 146.824693
## iter 60 value 144.180875
## iter 70 value 143.472454
## iter 80 value 141.478581
## iter 90 value 141.463077
## iter 100 value 141.385576
## final value 141.385576
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 79
## initial value 256.409767
## iter 10 value 167.070964
## iter 20 value 160.323033
## iter 30 value 145.183891
## iter 40 value 138.066369
## iter 50 value 137.153793
## iter 60 value 137.091671
## iter 70 value 137.086033
## iter 80 value 137.080521
## iter 90 value 137.078149
## iter 100 value 137.074422
## final value 137.074422
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 79
## initial value 323.663415
## iter 10 value 155.989366
## iter 20 value 139.528429
## iter 30 value 133.184350
## iter 40 value 113.511498
## iter 50 value 106.943288
## iter 60 value 104.391163
## iter 70 value 91.521808
## iter 80 value 88.553394
## iter 90 value 88.278991
## iter 100 value 88.266176
## final value 88.266176
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 290.759971
## iter 10 value 154.974534
## iter 20 value 151.810771
## iter 30 value 149.722223
## iter 40 value 148.557551
## iter 50 value 147.553545
## iter 60 value 145.914931
## iter 70 value 145.344884
## iter 80 value 140.542617
## iter 90 value 140.500724
## iter 100 value 140.360236
## final value 140.360236
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 309.739003
## iter 10 value 167.090566
## iter 20 value 167.044057
## iter 30 value 167.011605
## iter 40 value 166.886887
## iter 50 value 161.668907
## iter 60 value 160.272282
## iter 70 value 159.514819
## iter 80 value 158.879595
## iter 90 value 146.846387
## iter 100 value 146.768885
## final value 146.768885
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 79
## initial value 334.807201
## iter 10 value 167.118676
## iter 20 value 167.109319
## iter 30 value 167.083645
## iter 40 value 166.664489
## iter 50 value 154.458574
## iter 60 value 154.344142
## iter 70 value 154.331980
## iter 80 value 154.289586
## iter 90 value 151.169508
## iter 100 value 149.162045
## final value 149.162045
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 439.605592
## iter 10 value 155.365057
## iter 20 value 127.656696
## iter 30 value 126.632678
## iter 40 value 126.425351
## iter 50 value 125.948123
## iter 60 value 121.853791
## iter 70 value 105.745062
## iter 80 value 101.181974
## iter 90 value 98.722030
## iter 100 value 98.533482
## final value 98.533482
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 344.005485
## iter 10 value 170.743956
## iter 20 value 166.294371
## iter 30 value 165.144526
## iter 40 value 164.541045
## iter 50 value 156.488078
## iter 60 value 146.127959
## iter 70 value 145.629970
## iter 80 value 144.297373
## iter 90 value 144.193459
## iter 100 value 144.049526
## final value 144.049526
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 412.011740
## iter 10 value 167.089537
## iter 20 value 165.191305
## iter 30 value 151.209893
## iter 40 value 132.559990
## iter 50 value 125.735861
## iter 60 value 125.667515
## iter 70 value 125.592682
## iter 80 value 125.516433
## iter 90 value 125.358687
## iter 100 value 125.251607
## final value 125.251607
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 235.563993
## iter 10 value 166.849294
## iter 20 value 163.615875
## iter 30 value 163.552503
## iter 40 value 158.167200
## iter 50 value 145.540646
## iter 60 value 143.589226
## iter 70 value 113.157433
## iter 80 value 112.669936
## iter 90 value 112.580140
## iter 100 value 110.193562
## final value 110.193562
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 329.663584
## iter 10 value 167.079403
## iter 20 value 167.074313
## iter 30 value 167.063124
## iter 40 value 166.996000
## iter 50 value 162.990819
## iter 60 value 148.159787
## iter 70 value 134.252064
## iter 80 value 133.593836
## iter 90 value 110.580443
## iter 100 value 110.330582
## final value 110.330582
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 31
## initial value 331.560090
## iter 10 value 165.846420
## iter 20 value 154.091841
## final value 153.253024
## converged
## Fitting Repeat 2
##
## # weights: 31
## initial value 249.519751
## iter 10 value 152.811582
## iter 20 value 148.186752
## final value 148.186747
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 231.101766
## final value 165.999267
## converged
## Fitting Repeat 4
##
## # weights: 31
## initial value 306.797755
## iter 10 value 165.946180
## iter 20 value 165.889675
## iter 30 value 164.587520
## final value 162.530120
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 266.581335
## final value 166.000000
## converged
## Fitting Repeat 1
##
## # weights: 79
## initial value 241.759506
## final value 166.000000
## converged
## Fitting Repeat 2
##
## # weights: 79
## initial value 272.737840
## final value 166.000000
## converged
## Fitting Repeat 3
##
## # weights: 79
## initial value 403.909129
## final value 166.000000
## converged
## Fitting Repeat 4
##
## # weights: 79
## initial value 330.438104
## final value 166.000000
## converged
## Fitting Repeat 5
##
## # weights: 79
## initial value 263.617480
## final value 165.999506
## converged
## Fitting Repeat 1
##
## # weights: 127
## initial value 370.233980
## final value 166.000000
## converged
## Fitting Repeat 2
##
## # weights: 127
## initial value 369.160160
## final value 162.530120
## converged
## Fitting Repeat 3
##
## # weights: 127
## initial value 315.472898
## final value 166.000000
## converged
## Fitting Repeat 4
##
## # weights: 127
## initial value 323.499485
## final value 166.000000
## converged
## Fitting Repeat 5
##
## # weights: 127
## initial value 219.783337
## iter 10 value 153.253034
## final value 153.253014
## converged
## Fitting Repeat 1
##
## # weights: 31
## initial value 253.879203
## iter 10 value 150.195661
## iter 20 value 139.569381
## iter 30 value 139.218667
## iter 40 value 134.150592
## iter 50 value 130.119540
## iter 60 value 120.881852
## iter 70 value 119.987699
## iter 80 value 118.507391
## iter 90 value 113.347192
## iter 100 value 112.049664
## final value 112.049664
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 31
## initial value 273.003891
## iter 10 value 140.337904
## iter 20 value 136.710881
## iter 30 value 123.514604
## iter 40 value 112.989012
## iter 50 value 108.155414
## iter 60 value 105.886775
## iter 70 value 105.861022
## final value 105.860955
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 328.561435
## iter 10 value 141.748765
## iter 20 value 133.744902
## iter 30 value 114.804125
## iter 40 value 111.907821
## iter 50 value 111.019199
## iter 60 value 109.968557
## iter 70 value 109.895828
## final value 109.895821
## converged
## Fitting Repeat 4
##
## # weights: 31
## initial value 349.213703
## iter 10 value 149.406965
## iter 20 value 139.831041
## iter 30 value 138.839240
## iter 40 value 115.485078
## iter 50 value 108.361256
## iter 60 value 106.024593
## iter 70 value 105.866109
## final value 105.860955
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 283.453853
## iter 10 value 139.021814
## iter 20 value 138.318098
## final value 138.317974
## converged
## Fitting Repeat 1
##
## # weights: 79
## initial value 266.785585
## iter 10 value 141.379895
## iter 20 value 121.129203
## iter 30 value 118.262891
## iter 40 value 117.492588
## iter 50 value 113.318801
## iter 60 value 89.266944
## iter 70 value 87.031619
## iter 80 value 86.052463
## iter 90 value 85.283044
## iter 100 value 81.800817
## final value 81.800817
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 79
## initial value 250.410167
## iter 10 value 147.140502
## iter 20 value 130.274966
## iter 30 value 122.165215
## iter 40 value 119.499630
## iter 50 value 105.663466
## iter 60 value 96.346032
## iter 70 value 93.813754
## iter 80 value 91.813139
## iter 90 value 87.975862
## iter 100 value 72.449122
## final value 72.449122
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 303.136780
## iter 10 value 142.110145
## iter 20 value 138.125452
## iter 30 value 117.531563
## iter 40 value 111.925035
## iter 50 value 104.762688
## iter 60 value 83.507383
## iter 70 value 73.241056
## iter 80 value 72.745574
## iter 90 value 72.489371
## iter 100 value 72.013879
## final value 72.013879
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 308.845301
## iter 10 value 164.626717
## iter 20 value 125.663623
## iter 30 value 117.682521
## iter 40 value 113.547604
## iter 50 value 86.836989
## iter 60 value 64.697881
## iter 70 value 58.782128
## iter 80 value 49.759231
## iter 90 value 41.710309
## iter 100 value 41.431648
## final value 41.431648
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 79
## initial value 421.121831
## iter 10 value 157.695304
## iter 20 value 139.574478
## iter 30 value 131.430081
## iter 40 value 109.755866
## iter 50 value 93.595304
## iter 60 value 86.242377
## iter 70 value 75.390645
## iter 80 value 73.919226
## iter 90 value 71.984508
## iter 100 value 69.931308
## final value 69.931308
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 325.007625
## iter 10 value 154.331174
## iter 20 value 141.032468
## iter 30 value 135.491774
## iter 40 value 118.092123
## iter 50 value 87.390752
## iter 60 value 77.093532
## iter 70 value 73.070870
## iter 80 value 49.593657
## iter 90 value 41.577925
## iter 100 value 36.561998
## final value 36.561998
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 358.467101
## iter 10 value 162.975186
## iter 20 value 135.619092
## iter 30 value 127.809678
## iter 40 value 116.317317
## iter 50 value 88.893168
## iter 60 value 71.900116
## iter 70 value 57.579908
## iter 80 value 49.009762
## iter 90 value 37.165981
## iter 100 value 33.385220
## final value 33.385220
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 296.953263
## iter 10 value 141.333706
## iter 20 value 122.353798
## iter 30 value 117.785534
## iter 40 value 114.890483
## iter 50 value 91.051905
## iter 60 value 86.181018
## iter 70 value 74.436614
## iter 80 value 68.939500
## iter 90 value 53.880674
## iter 100 value 50.087841
## final value 50.087841
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 259.182639
## iter 10 value 141.859497
## iter 20 value 138.140489
## iter 30 value 118.809271
## iter 40 value 106.907637
## iter 50 value 84.339915
## iter 60 value 63.831345
## iter 70 value 60.642784
## iter 80 value 48.616191
## iter 90 value 37.363695
## iter 100 value 34.632097
## final value 34.632097
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 272.635432
## iter 10 value 165.192151
## iter 20 value 135.276882
## iter 30 value 101.997328
## iter 40 value 89.054997
## iter 50 value 71.737219
## iter 60 value 61.711971
## iter 70 value 53.789163
## iter 80 value 44.072885
## iter 90 value 32.488616
## iter 100 value 29.722425
## final value 29.722425
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 31
## initial value 222.181259
## iter 10 value 165.996179
## iter 20 value 161.376403
## iter 30 value 160.784162
## iter 40 value 158.842478
## iter 50 value 157.079047
## iter 60 value 155.689467
## iter 70 value 155.525658
## iter 80 value 146.082294
## iter 90 value 145.951618
## iter 100 value 143.842600
## final value 143.842600
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 31
## initial value 304.879970
## iter 10 value 165.792997
## iter 20 value 153.360911
## iter 30 value 150.040733
## iter 40 value 149.897318
## iter 50 value 142.434093
## iter 60 value 140.334750
## iter 70 value 137.691839
## iter 80 value 137.194283
## iter 90 value 137.084510
## iter 100 value 136.970744
## final value 136.970744
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 31
## initial value 272.958096
## iter 10 value 154.813824
## iter 20 value 151.162466
## iter 30 value 151.048735
## iter 40 value 150.905497
## iter 50 value 150.474102
## iter 60 value 144.714583
## iter 70 value 143.624201
## iter 80 value 143.593666
## iter 90 value 137.806051
## iter 100 value 136.965365
## final value 136.965365
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 31
## initial value 371.440524
## iter 10 value 166.070149
## iter 20 value 148.248539
## iter 30 value 145.703847
## iter 40 value 144.296839
## iter 50 value 139.524543
## iter 60 value 137.308613
## iter 70 value 137.244098
## iter 80 value 137.224316
## iter 90 value 137.148594
## iter 100 value 137.020615
## final value 137.020615
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 31
## initial value 299.305773
## iter 10 value 166.070592
## iter 20 value 166.068184
## iter 30 value 166.065099
## iter 40 value 166.060872
## iter 50 value 166.054427
## iter 60 value 166.042550
## iter 70 value 166.008665
## iter 80 value 164.430469
## iter 90 value 162.289794
## iter 100 value 150.134932
## final value 150.134932
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 79
## initial value 309.720924
## iter 10 value 164.772330
## iter 20 value 162.349716
## iter 30 value 137.080294
## iter 40 value 136.969265
## iter 50 value 136.966193
## final value 136.965766
## converged
## Fitting Repeat 2
##
## # weights: 79
## initial value 260.853733
## iter 10 value 166.402485
## iter 20 value 166.268692
## iter 30 value 153.715421
## iter 40 value 153.210014
## iter 50 value 148.666970
## iter 60 value 148.245479
## iter 70 value 146.183885
## iter 80 value 146.001286
## iter 90 value 135.348050
## iter 100 value 132.773308
## final value 132.773308
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 249.298763
## iter 10 value 165.550793
## iter 20 value 158.820876
## iter 30 value 156.628826
## iter 40 value 153.735202
## iter 50 value 153.144599
## iter 60 value 140.328479
## iter 70 value 124.862350
## iter 80 value 116.216485
## iter 90 value 115.789104
## iter 100 value 112.646706
## final value 112.646706
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 332.840922
## iter 10 value 168.828074
## iter 20 value 168.426959
## iter 30 value 165.232443
## iter 40 value 137.030389
## final value 136.967066
## converged
## Fitting Repeat 5
##
## # weights: 79
## initial value 331.119935
## iter 10 value 172.033381
## iter 20 value 160.393587
## iter 30 value 150.997230
## iter 40 value 142.193534
## iter 50 value 139.880627
## iter 60 value 129.682133
## iter 70 value 128.768935
## iter 80 value 127.629443
## iter 90 value 123.919297
## iter 100 value 121.718763
## final value 121.718763
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 316.013227
## iter 10 value 166.093980
## iter 20 value 150.601707
## iter 30 value 125.971922
## iter 40 value 107.520791
## iter 50 value 106.581986
## iter 60 value 106.523946
## iter 70 value 106.370277
## iter 80 value 106.184056
## iter 90 value 105.895790
## iter 100 value 105.378738
## final value 105.378738
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 395.525356
## iter 10 value 166.248350
## iter 20 value 166.205762
## iter 30 value 154.178467
## iter 40 value 153.425169
## iter 50 value 148.399850
## iter 60 value 132.777131
## iter 70 value 131.804626
## iter 80 value 124.993221
## iter 90 value 118.902543
## iter 100 value 118.181429
## final value 118.181429
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 333.542311
## iter 10 value 154.416653
## iter 20 value 152.216018
## iter 30 value 148.240110
## iter 40 value 136.342856
## iter 50 value 132.552404
## iter 60 value 130.101460
## iter 70 value 128.440516
## iter 80 value 128.387960
## iter 90 value 126.631999
## iter 100 value 126.598803
## final value 126.598803
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 347.792288
## iter 10 value 166.143753
## iter 20 value 166.129133
## iter 30 value 166.066893
## iter 40 value 153.513892
## iter 50 value 152.554630
## iter 60 value 134.588320
## iter 70 value 131.351537
## iter 80 value 130.925015
## iter 90 value 130.480784
## iter 100 value 130.443232
## final value 130.443232
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 375.389847
## iter 10 value 166.200158
## iter 20 value 136.979532
## iter 30 value 136.973636
## iter 40 value 136.962324
## iter 50 value 118.953969
## iter 60 value 115.360303
## iter 70 value 85.619363
## iter 80 value 61.233421
## iter 90 value 58.104631
## iter 100 value 54.474059
## final value 54.474059
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 31
## initial value 280.379762
## iter 10 value 152.727289
## final value 152.727160
## converged
## Fitting Repeat 2
##
## # weights: 31
## initial value 299.702975
## final value 164.999965
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 343.737248
## final value 165.000000
## converged
## Fitting Repeat 4
##
## # weights: 31
## initial value 338.254274
## final value 165.000000
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 340.151964
## final value 165.000000
## converged
## Fitting Repeat 1
##
## # weights: 79
## initial value 383.502187
## final value 165.000000
## converged
## Fitting Repeat 2
##
## # weights: 79
## initial value 308.749966
## final value 165.000000
## converged
## Fitting Repeat 3
##
## # weights: 79
## initial value 274.573386
## final value 164.999874
## converged
## Fitting Repeat 4
##
## # weights: 79
## initial value 334.880562
## iter 10 value 152.782764
## iter 20 value 152.706167
## iter 30 value 152.690095
## iter 40 value 152.606445
## iter 50 value 147.272733
## final value 147.272727
## converged
## Fitting Repeat 5
##
## # weights: 79
## initial value 319.204201
## final value 165.000000
## converged
## Fitting Repeat 1
##
## # weights: 127
## initial value 351.706710
## iter 10 value 156.337423
## iter 20 value 156.332940
## iter 30 value 156.221811
## final value 153.133333
## converged
## Fitting Repeat 2
##
## # weights: 127
## initial value 400.003533
## final value 165.000000
## converged
## Fitting Repeat 3
##
## # weights: 127
## initial value 332.602943
## iter 10 value 161.793996
## final value 161.793946
## converged
## Fitting Repeat 4
##
## # weights: 127
## initial value 307.437533
## final value 165.000000
## converged
## Fitting Repeat 5
##
## # weights: 127
## initial value 324.239530
## final value 165.000000
## converged
## Fitting Repeat 1
##
## # weights: 31
## initial value 278.287284
## iter 10 value 167.119109
## iter 20 value 139.388754
## iter 30 value 138.818633
## iter 40 value 137.669535
## iter 50 value 137.606245
## iter 60 value 137.605949
## iter 70 value 134.584355
## iter 80 value 121.667800
## iter 90 value 120.616703
## iter 100 value 118.927077
## final value 118.927077
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 31
## initial value 280.410152
## iter 10 value 149.739142
## iter 20 value 137.811139
## iter 30 value 137.606121
## final value 137.606102
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 316.860312
## iter 10 value 140.105170
## iter 20 value 138.958658
## iter 30 value 138.843394
## iter 40 value 128.856732
## iter 50 value 112.111391
## iter 60 value 109.880728
## iter 70 value 106.647035
## iter 80 value 106.390222
## iter 90 value 106.121105
## iter 100 value 105.707409
## final value 105.707409
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 31
## initial value 309.298900
## iter 10 value 152.240007
## iter 20 value 137.606740
## iter 30 value 137.606128
## final value 137.606113
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 238.057420
## iter 10 value 157.781808
## iter 20 value 114.939457
## iter 30 value 110.588850
## iter 40 value 106.873139
## iter 50 value 105.828012
## iter 60 value 105.705807
## final value 105.705722
## converged
## Fitting Repeat 1
##
## # weights: 79
## initial value 370.482145
## iter 10 value 142.108912
## iter 20 value 138.715882
## iter 30 value 135.868449
## iter 40 value 127.697104
## iter 50 value 93.230372
## iter 60 value 74.876362
## iter 70 value 69.334938
## iter 80 value 68.406010
## iter 90 value 67.427925
## iter 100 value 65.358414
## final value 65.358414
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 79
## initial value 309.187298
## iter 10 value 138.503638
## iter 20 value 120.353978
## iter 30 value 116.698538
## iter 40 value 90.046376
## iter 50 value 78.113965
## iter 60 value 70.185095
## iter 70 value 66.427265
## iter 80 value 65.392776
## iter 90 value 64.476195
## iter 100 value 64.408534
## final value 64.408534
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 311.373092
## iter 10 value 149.804462
## iter 20 value 138.765886
## iter 30 value 124.071281
## iter 40 value 119.145873
## iter 50 value 117.395122
## iter 60 value 110.517426
## iter 70 value 99.651808
## iter 80 value 85.628179
## iter 90 value 60.222881
## iter 100 value 56.615142
## final value 56.615142
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 291.342141
## iter 10 value 156.973433
## iter 20 value 137.959056
## iter 30 value 137.171648
## iter 40 value 135.616034
## iter 50 value 120.459112
## iter 60 value 100.181982
## iter 70 value 84.974893
## iter 80 value 73.192212
## iter 90 value 69.966813
## iter 100 value 68.409783
## final value 68.409783
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 79
## initial value 375.620734
## iter 10 value 145.382327
## iter 20 value 136.968755
## iter 30 value 120.820855
## iter 40 value 103.869761
## iter 50 value 97.412168
## iter 60 value 92.051115
## iter 70 value 85.385633
## iter 80 value 73.212094
## iter 90 value 68.025581
## iter 100 value 66.593244
## final value 66.593244
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 368.724648
## iter 10 value 147.676235
## iter 20 value 142.207652
## iter 30 value 121.306081
## iter 40 value 94.692988
## iter 50 value 87.577081
## iter 60 value 86.299254
## iter 70 value 80.188247
## iter 80 value 68.114148
## iter 90 value 59.504455
## iter 100 value 52.923571
## final value 52.923571
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 336.951331
## iter 10 value 146.113737
## iter 20 value 138.945804
## iter 30 value 125.415250
## iter 40 value 89.600477
## iter 50 value 63.068919
## iter 60 value 56.059186
## iter 70 value 39.205690
## iter 80 value 32.397413
## iter 90 value 30.308082
## iter 100 value 30.085368
## final value 30.085368
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 286.569435
## iter 10 value 148.490699
## iter 20 value 127.418854
## iter 30 value 122.427953
## iter 40 value 101.064907
## iter 50 value 90.900756
## iter 60 value 81.641970
## iter 70 value 60.613146
## iter 80 value 53.850254
## iter 90 value 51.634328
## iter 100 value 50.274929
## final value 50.274929
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 277.681964
## iter 10 value 170.682859
## iter 20 value 139.142924
## iter 30 value 126.983600
## iter 40 value 119.096675
## iter 50 value 114.549311
## iter 60 value 82.446705
## iter 70 value 73.268889
## iter 80 value 68.911263
## iter 90 value 67.879615
## iter 100 value 61.693839
## final value 61.693839
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 426.233509
## iter 10 value 140.997456
## iter 20 value 122.120153
## iter 30 value 104.307946
## iter 40 value 90.504150
## iter 50 value 69.983224
## iter 60 value 62.533611
## iter 70 value 60.784635
## iter 80 value 57.447286
## iter 90 value 56.137033
## iter 100 value 47.468159
## final value 47.468159
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 31
## initial value 282.764027
## iter 10 value 164.964817
## iter 20 value 150.794148
## iter 30 value 145.443003
## iter 40 value 145.247118
## iter 50 value 142.150067
## iter 60 value 141.519743
## iter 70 value 139.929865
## iter 80 value 136.694289
## iter 90 value 136.643318
## iter 100 value 136.613554
## final value 136.613554
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 31
## initial value 312.880868
## iter 10 value 165.634653
## iter 20 value 165.626099
## iter 30 value 165.613546
## iter 40 value 165.590647
## iter 50 value 165.523166
## iter 60 value 160.007233
## iter 70 value 153.340266
## iter 80 value 147.591087
## iter 90 value 146.683279
## iter 100 value 144.191422
## final value 144.191422
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 31
## initial value 300.143812
## iter 10 value 165.172570
## iter 20 value 165.133456
## iter 30 value 164.858446
## iter 40 value 159.680120
## iter 50 value 143.035142
## iter 60 value 124.978929
## iter 70 value 120.400957
## iter 80 value 113.301426
## iter 90 value 112.817702
## iter 100 value 108.053309
## final value 108.053309
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 31
## initial value 296.995734
## iter 10 value 165.202557
## iter 20 value 165.192971
## iter 30 value 165.175923
## iter 40 value 165.132973
## iter 50 value 164.759282
## iter 60 value 152.937193
## iter 70 value 147.243172
## iter 80 value 147.171114
## iter 90 value 142.146160
## iter 100 value 141.627422
## final value 141.627422
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 31
## initial value 287.761511
## iter 10 value 165.846379
## iter 20 value 165.842063
## iter 30 value 165.837598
## iter 40 value 165.832932
## iter 50 value 165.827987
## iter 60 value 165.822644
## iter 70 value 165.816707
## iter 80 value 165.809831
## iter 90 value 165.801339
## iter 100 value 165.789714
## final value 165.789714
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 79
## initial value 339.373550
## iter 10 value 159.797931
## iter 20 value 145.521308
## iter 30 value 139.600797
## iter 40 value 136.930624
## iter 50 value 119.193695
## iter 60 value 118.682652
## iter 70 value 118.615469
## iter 80 value 118.515637
## iter 90 value 113.707377
## iter 100 value 113.546409
## final value 113.546409
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 79
## initial value 310.536205
## iter 10 value 167.349972
## iter 20 value 167.156055
## iter 30 value 160.572726
## iter 40 value 159.349298
## iter 50 value 159.223845
## iter 60 value 156.680293
## iter 70 value 145.205487
## iter 80 value 144.642422
## iter 90 value 144.637791
## iter 100 value 144.301855
## final value 144.301855
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 326.368579
## iter 10 value 170.751980
## iter 20 value 151.947959
## iter 30 value 139.573007
## iter 40 value 136.553559
## iter 50 value 136.542285
## iter 60 value 136.534350
## iter 70 value 136.327780
## iter 80 value 136.271495
## iter 90 value 136.250180
## iter 100 value 113.384605
## final value 113.384605
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 314.920449
## iter 10 value 165.028179
## iter 20 value 160.916385
## iter 30 value 136.831518
## iter 40 value 135.318278
## iter 50 value 120.138761
## iter 60 value 120.112875
## iter 70 value 120.078663
## iter 80 value 120.077359
## iter 90 value 120.075842
## iter 100 value 120.073977
## final value 120.073977
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 79
## initial value 285.928478
## iter 10 value 163.346409
## iter 20 value 163.046751
## iter 30 value 160.759161
## iter 40 value 160.681448
## iter 50 value 150.622102
## iter 60 value 148.415015
## iter 70 value 145.036201
## iter 80 value 138.036090
## iter 90 value 136.529690
## iter 100 value 136.491953
## final value 136.491953
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 416.471328
## iter 10 value 165.195953
## iter 20 value 165.057402
## iter 30 value 165.040703
## iter 40 value 161.881443
## iter 50 value 155.445716
## iter 60 value 149.587464
## iter 70 value 148.710628
## iter 80 value 141.981700
## iter 90 value 138.817597
## iter 100 value 136.495885
## final value 136.495885
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 240.774947
## iter 10 value 165.185490
## iter 20 value 153.198360
## iter 30 value 152.657019
## iter 40 value 135.742313
## iter 50 value 122.878590
## iter 60 value 117.185835
## iter 70 value 112.954806
## iter 80 value 112.619310
## iter 90 value 110.812922
## iter 100 value 105.961901
## final value 105.961901
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 328.468517
## iter 10 value 153.974124
## iter 20 value 152.915262
## iter 30 value 147.695195
## iter 40 value 147.630754
## iter 50 value 147.428713
## iter 60 value 144.447927
## iter 70 value 143.513428
## iter 80 value 140.255452
## iter 90 value 136.562405
## iter 100 value 136.458565
## final value 136.458565
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 351.482318
## iter 10 value 164.761575
## iter 20 value 152.654166
## iter 30 value 152.336714
## iter 40 value 150.620935
## iter 50 value 149.129978
## iter 60 value 147.416228
## iter 70 value 141.979548
## iter 80 value 139.009060
## iter 90 value 138.785942
## iter 100 value 138.716394
## final value 138.716394
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 312.741420
## iter 10 value 165.136036
## iter 20 value 143.089405
## iter 30 value 136.480124
## iter 40 value 136.071825
## iter 50 value 119.459326
## iter 60 value 116.213569
## iter 70 value 114.574356
## iter 80 value 114.164132
## iter 90 value 114.119676
## iter 100 value 113.977756
## final value 113.977756
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 31
## initial value 349.961919
## final value 166.000000
## converged
## Fitting Repeat 2
##
## # weights: 31
## initial value 346.709643
## final value 166.000000
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 348.488582
## final value 166.000000
## converged
## Fitting Repeat 4
##
## # weights: 31
## initial value 298.838584
## final value 166.000000
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 311.423642
## final value 166.000000
## converged
## Fitting Repeat 1
##
## # weights: 79
## initial value 347.249343
## final value 166.000000
## converged
## Fitting Repeat 2
##
## # weights: 79
## initial value 352.803100
## final value 160.578313
## converged
## Fitting Repeat 3
##
## # weights: 79
## initial value 309.690843
## final value 166.000000
## converged
## Fitting Repeat 4
##
## # weights: 79
## initial value 317.220550
## final value 166.000000
## converged
## Fitting Repeat 5
##
## # weights: 79
## initial value 334.540739
## final value 166.000000
## converged
## Fitting Repeat 1
##
## # weights: 127
## initial value 253.335366
## final value 160.578313
## converged
## Fitting Repeat 2
##
## # weights: 127
## initial value 322.368192
## iter 10 value 162.530346
## final value 162.530120
## converged
## Fitting Repeat 3
##
## # weights: 127
## initial value 243.386574
## iter 10 value 162.530259
## final value 162.530123
## converged
## Fitting Repeat 4
##
## # weights: 127
## initial value 301.009858
## final value 166.000000
## converged
## Fitting Repeat 5
##
## # weights: 127
## initial value 303.686517
## final value 165.999962
## converged
## Fitting Repeat 1
##
## # weights: 31
## initial value 284.720419
## iter 10 value 145.346285
## iter 20 value 139.886517
## iter 30 value 134.986341
## iter 40 value 130.464706
## iter 50 value 127.286020
## iter 60 value 120.864034
## iter 70 value 117.693324
## iter 80 value 114.317198
## iter 90 value 113.692872
## final value 113.692369
## converged
## Fitting Repeat 2
##
## # weights: 31
## initial value 264.330489
## iter 10 value 141.985852
## iter 20 value 133.444481
## iter 30 value 122.273650
## iter 40 value 120.601501
## iter 50 value 119.650717
## iter 60 value 117.420959
## iter 70 value 114.810019
## iter 80 value 113.380029
## iter 90 value 113.312742
## final value 113.297373
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 294.938748
## iter 10 value 149.929411
## iter 20 value 138.653033
## final value 138.631207
## converged
## Fitting Repeat 4
##
## # weights: 31
## initial value 287.727823
## iter 10 value 168.467317
## iter 20 value 138.635989
## final value 138.631208
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 368.967547
## iter 10 value 159.181611
## iter 20 value 139.874704
## iter 30 value 133.736304
## iter 40 value 121.106453
## iter 50 value 117.018669
## iter 60 value 113.971690
## iter 70 value 113.298675
## final value 113.297373
## converged
## Fitting Repeat 1
##
## # weights: 79
## initial value 270.729892
## iter 10 value 146.901521
## iter 20 value 114.537360
## iter 30 value 108.773629
## iter 40 value 102.549688
## iter 50 value 93.411500
## iter 60 value 89.083148
## iter 70 value 85.696243
## iter 80 value 78.196625
## iter 90 value 68.922581
## iter 100 value 66.250215
## final value 66.250215
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 79
## initial value 349.151894
## iter 10 value 166.013694
## iter 20 value 141.464997
## iter 30 value 127.047955
## iter 40 value 119.836098
## iter 50 value 118.872453
## iter 60 value 117.811303
## iter 70 value 108.586959
## iter 80 value 75.502811
## iter 90 value 50.566202
## iter 100 value 46.490595
## final value 46.490595
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 339.138546
## iter 10 value 171.611849
## iter 20 value 144.181828
## iter 30 value 128.454864
## iter 40 value 122.426564
## iter 50 value 96.335477
## iter 60 value 89.176086
## iter 70 value 81.909877
## iter 80 value 76.541007
## iter 90 value 67.228919
## iter 100 value 56.387247
## final value 56.387247
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 319.852564
## iter 10 value 171.491490
## iter 20 value 138.645816
## iter 30 value 117.644214
## iter 40 value 107.184494
## iter 50 value 105.510016
## iter 60 value 105.250826
## iter 70 value 103.860632
## iter 80 value 92.099059
## iter 90 value 73.248515
## iter 100 value 60.955630
## final value 60.955630
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 79
## initial value 307.300897
## iter 10 value 156.199230
## iter 20 value 138.158942
## iter 30 value 128.744755
## iter 40 value 101.491385
## iter 50 value 91.058236
## iter 60 value 87.902180
## iter 70 value 83.323307
## iter 80 value 78.092284
## iter 90 value 65.636571
## iter 100 value 61.838710
## final value 61.838710
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 291.333985
## iter 10 value 142.771309
## iter 20 value 124.398615
## iter 30 value 113.351486
## iter 40 value 111.586018
## iter 50 value 102.618270
## iter 60 value 85.341622
## iter 70 value 76.029871
## iter 80 value 60.645436
## iter 90 value 43.661945
## iter 100 value 39.100692
## final value 39.100692
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 271.233293
## iter 10 value 157.565120
## iter 20 value 139.298671
## iter 30 value 137.817201
## iter 40 value 120.397895
## iter 50 value 119.146212
## iter 60 value 96.296914
## iter 70 value 82.671631
## iter 80 value 79.603889
## iter 90 value 67.710651
## iter 100 value 57.299504
## final value 57.299504
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 347.973238
## iter 10 value 140.851484
## iter 20 value 138.035761
## iter 30 value 136.700983
## iter 40 value 120.129885
## iter 50 value 77.632854
## iter 60 value 58.410513
## iter 70 value 53.579554
## iter 80 value 41.315878
## iter 90 value 33.344370
## iter 100 value 32.086743
## final value 32.086743
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 320.894822
## iter 10 value 142.305807
## iter 20 value 123.912450
## iter 30 value 119.648290
## iter 40 value 111.563736
## iter 50 value 94.038066
## iter 60 value 68.185060
## iter 70 value 48.012699
## iter 80 value 43.832555
## iter 90 value 43.174330
## iter 100 value 41.232876
## final value 41.232876
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 380.949566
## iter 10 value 181.735615
## iter 20 value 136.657136
## iter 30 value 124.450698
## iter 40 value 103.746029
## iter 50 value 88.939299
## iter 60 value 86.213565
## iter 70 value 85.525915
## iter 80 value 83.443307
## iter 90 value 79.489031
## iter 100 value 68.068566
## final value 68.068566
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 31
## initial value 264.593712
## iter 10 value 161.699237
## iter 20 value 157.497707
## iter 30 value 154.334314
## iter 40 value 154.008551
## iter 50 value 140.814084
## iter 60 value 139.371389
## iter 70 value 137.701133
## iter 80 value 137.609336
## iter 90 value 137.606400
## iter 100 value 137.598885
## final value 137.598885
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 31
## initial value 284.125671
## iter 10 value 166.101075
## iter 20 value 166.092489
## iter 30 value 166.078110
## iter 40 value 166.046647
## iter 50 value 165.903274
## iter 60 value 160.696044
## iter 70 value 159.122217
## iter 80 value 149.159549
## iter 90 value 148.474708
## iter 100 value 134.568524
## final value 134.568524
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 31
## initial value 325.088682
## iter 10 value 166.113850
## iter 20 value 166.021739
## iter 30 value 163.464904
## iter 40 value 162.614325
## iter 50 value 150.788411
## iter 60 value 150.571202
## iter 70 value 143.430187
## iter 80 value 139.264658
## iter 90 value 137.732673
## iter 100 value 137.334855
## final value 137.334855
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 31
## initial value 247.838552
## iter 10 value 154.211104
## iter 20 value 153.644363
## iter 30 value 148.242088
## iter 40 value 144.757582
## iter 50 value 141.755429
## iter 60 value 141.702066
## iter 70 value 141.435878
## iter 80 value 139.832919
## iter 90 value 139.491902
## iter 100 value 139.477505
## final value 139.477505
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 31
## initial value 310.942641
## iter 10 value 166.659236
## iter 20 value 166.656249
## iter 30 value 166.653241
## iter 40 value 166.650205
## iter 50 value 166.647136
## iter 60 value 166.644025
## iter 70 value 166.640862
## iter 80 value 166.637633
## iter 90 value 166.634321
## iter 100 value 166.630902
## final value 166.630902
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 79
## initial value 373.118359
## iter 10 value 166.058376
## iter 20 value 150.340850
## iter 30 value 145.156187
## iter 40 value 140.794435
## iter 50 value 137.755195
## iter 60 value 137.630184
## iter 70 value 129.322697
## iter 80 value 123.450166
## iter 90 value 122.343412
## iter 100 value 121.747874
## final value 121.747874
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 79
## initial value 361.086959
## iter 10 value 166.310764
## iter 20 value 166.292361
## iter 30 value 166.258913
## iter 40 value 166.165448
## iter 50 value 154.753904
## iter 60 value 152.609537
## iter 70 value 151.847167
## iter 80 value 148.558446
## iter 90 value 147.586456
## iter 100 value 127.014093
## final value 127.014093
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 300.397679
## iter 10 value 163.853983
## iter 20 value 159.667623
## iter 30 value 159.456808
## iter 40 value 154.206786
## iter 50 value 154.027392
## iter 60 value 142.111451
## iter 70 value 141.829262
## iter 80 value 141.610159
## iter 90 value 141.554833
## iter 100 value 137.370137
## final value 137.370137
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 252.445032
## iter 10 value 165.875959
## iter 20 value 155.484947
## iter 30 value 143.502515
## iter 40 value 143.128408
## iter 50 value 114.003515
## iter 60 value 108.863957
## iter 70 value 105.711778
## iter 80 value 103.449660
## iter 90 value 101.869025
## iter 100 value 101.810695
## final value 101.810695
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 79
## initial value 288.497498
## iter 10 value 168.062877
## iter 20 value 168.011445
## iter 30 value 155.902406
## iter 40 value 153.354359
## iter 50 value 148.498131
## iter 60 value 148.366638
## iter 70 value 146.466175
## iter 80 value 142.492794
## iter 90 value 137.641217
## iter 100 value 137.321951
## final value 137.321951
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 263.424704
## iter 10 value 153.570889
## iter 20 value 133.476519
## iter 30 value 132.470236
## iter 40 value 132.361815
## iter 50 value 122.901096
## iter 60 value 122.377844
## iter 70 value 122.343922
## iter 80 value 122.252219
## iter 90 value 119.257196
## iter 100 value 109.422379
## final value 109.422379
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 326.381968
## iter 10 value 157.975480
## iter 20 value 129.856396
## iter 30 value 115.686265
## iter 40 value 113.728981
## iter 50 value 90.489319
## iter 60 value 88.802147
## iter 70 value 87.947143
## iter 80 value 85.451918
## iter 90 value 82.412269
## iter 100 value 72.867692
## final value 72.867692
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 253.404689
## iter 10 value 167.310732
## iter 20 value 147.495795
## iter 30 value 145.929894
## iter 40 value 145.748506
## iter 50 value 143.734798
## iter 60 value 143.478196
## iter 70 value 138.536377
## iter 80 value 138.134575
## iter 90 value 137.761297
## iter 100 value 137.568894
## final value 137.568894
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 403.354097
## iter 10 value 159.701379
## iter 20 value 143.206912
## iter 30 value 143.150543
## iter 40 value 143.034787
## iter 50 value 129.020704
## iter 60 value 113.288832
## iter 70 value 108.202588
## iter 80 value 106.265790
## iter 90 value 106.193164
## iter 100 value 106.147858
## final value 106.147858
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 251.166646
## iter 10 value 166.147022
## iter 20 value 164.850319
## iter 30 value 162.693068
## iter 40 value 150.431348
## iter 50 value 135.882937
## iter 60 value 125.865716
## iter 70 value 125.559342
## iter 80 value 125.278679
## iter 90 value 125.158516
## iter 100 value 119.355855
## final value 119.355855
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 31
## initial value 325.924147
## final value 164.000000
## converged
## Fitting Repeat 2
##
## # weights: 31
## initial value 293.162653
## final value 164.000000
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 374.795727
## final value 164.000000
## converged
## Fitting Repeat 4
##
## # weights: 31
## initial value 284.224234
## final value 164.000000
## converged
## Fitting Repeat 5
##
## # weights: 31
## initial value 286.130241
## iter 10 value 151.097561
## iter 10 value 151.097561
## iter 10 value 151.097561
## final value 151.097561
## converged
## Fitting Repeat 1
##
## # weights: 79
## initial value 292.808693
## iter 10 value 163.402369
## final value 160.774390
## converged
## Fitting Repeat 2
##
## # weights: 79
## initial value 342.876619
## final value 164.000000
## converged
## Fitting Repeat 3
##
## # weights: 79
## initial value 284.674371
## final value 163.999978
## converged
## Fitting Repeat 4
##
## # weights: 79
## initial value 232.576227
## final value 164.000000
## converged
## Fitting Repeat 5
##
## # weights: 79
## initial value 280.555169
## final value 164.000000
## converged
## Fitting Repeat 1
##
## # weights: 127
## initial value 290.277369
## final value 164.000000
## converged
## Fitting Repeat 2
##
## # weights: 127
## initial value 319.134548
## final value 164.000000
## converged
## Fitting Repeat 3
##
## # weights: 127
## initial value 414.062039
## final value 164.000000
## converged
## Fitting Repeat 4
##
## # weights: 127
## initial value 353.148199
## iter 10 value 123.393859
## iter 20 value 122.510016
## final value 122.509804
## converged
## Fitting Repeat 5
##
## # weights: 127
## initial value 375.135101
## final value 164.000000
## converged
## Fitting Repeat 1
##
## # weights: 31
## initial value 295.053492
## iter 10 value 136.894886
## iter 20 value 121.142939
## iter 30 value 118.102311
## iter 40 value 117.747443
## iter 50 value 115.088047
## iter 60 value 111.176095
## iter 70 value 109.912927
## iter 80 value 109.239662
## final value 109.236551
## converged
## Fitting Repeat 2
##
## # weights: 31
## initial value 265.642836
## iter 10 value 153.356644
## iter 20 value 136.500393
## iter 30 value 136.479137
## iter 30 value 136.479137
## iter 30 value 136.479137
## final value 136.479137
## converged
## Fitting Repeat 3
##
## # weights: 31
## initial value 306.708657
## iter 10 value 151.635719
## iter 20 value 137.677862
## iter 30 value 136.557797
## iter 40 value 136.479144
## final value 136.479137
## converged
## Fitting Repeat 4
##
## # weights: 31
## initial value 269.258682
## iter 10 value 144.230273
## iter 20 value 136.720219
## iter 30 value 130.905348
## iter 40 value 119.519152
## iter 50 value 118.191849
## iter 60 value 117.901486
## iter 70 value 117.540431
## iter 80 value 116.825543
## iter 90 value 112.719743
## iter 100 value 111.389068
## final value 111.389068
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 31
## initial value 276.875754
## iter 10 value 152.023363
## iter 20 value 137.674260
## iter 30 value 123.728097
## iter 40 value 119.636461
## iter 50 value 117.471022
## iter 60 value 115.502735
## iter 70 value 110.077783
## iter 80 value 104.114010
## iter 90 value 103.775504
## iter 100 value 103.731568
## final value 103.731568
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 79
## initial value 266.220026
## iter 10 value 169.640408
## iter 20 value 136.150265
## iter 30 value 114.945242
## iter 40 value 112.400910
## iter 50 value 107.301421
## iter 60 value 92.177363
## iter 70 value 77.023809
## iter 80 value 70.868102
## iter 90 value 67.242838
## iter 100 value 66.079914
## final value 66.079914
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 79
## initial value 240.716857
## iter 10 value 138.832485
## iter 20 value 122.141691
## iter 30 value 118.511850
## iter 40 value 101.962572
## iter 50 value 89.159514
## iter 60 value 84.480333
## iter 70 value 83.059083
## iter 80 value 82.333780
## iter 90 value 80.030813
## iter 100 value 71.490954
## final value 71.490954
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 386.296370
## iter 10 value 137.176236
## iter 20 value 122.837121
## iter 30 value 106.951406
## iter 40 value 103.885829
## iter 50 value 103.724417
## iter 60 value 103.703859
## iter 70 value 103.700866
## iter 80 value 103.698405
## iter 90 value 103.681398
## iter 100 value 103.353643
## final value 103.353643
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 293.527885
## iter 10 value 156.921065
## iter 20 value 139.181374
## iter 30 value 122.557712
## iter 40 value 120.319513
## iter 50 value 118.275492
## iter 60 value 116.355373
## iter 70 value 114.927513
## iter 80 value 76.033990
## iter 90 value 57.037417
## iter 100 value 55.432289
## final value 55.432289
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 79
## initial value 282.718262
## iter 10 value 141.235217
## iter 20 value 137.479245
## iter 30 value 123.463911
## iter 40 value 117.315296
## iter 50 value 115.250136
## iter 60 value 92.522917
## iter 70 value 88.172954
## iter 80 value 80.977453
## iter 90 value 76.191639
## iter 100 value 73.210641
## final value 73.210641
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 335.416751
## iter 10 value 158.410421
## iter 20 value 133.427123
## iter 30 value 109.155646
## iter 40 value 107.617648
## iter 50 value 98.797537
## iter 60 value 79.996050
## iter 70 value 50.844874
## iter 80 value 40.271007
## iter 90 value 36.596569
## iter 100 value 35.870738
## final value 35.870738
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 255.380632
## iter 10 value 142.799669
## iter 20 value 122.289234
## iter 30 value 116.505249
## iter 40 value 112.786855
## iter 50 value 108.022173
## iter 60 value 93.305037
## iter 70 value 90.397478
## iter 80 value 77.837444
## iter 90 value 70.998564
## iter 100 value 69.092851
## final value 69.092851
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 317.862424
## iter 10 value 146.042207
## iter 20 value 126.652114
## iter 30 value 122.673265
## iter 40 value 109.754209
## iter 50 value 99.279204
## iter 60 value 75.733709
## iter 70 value 54.376561
## iter 80 value 40.029621
## iter 90 value 37.061773
## iter 100 value 33.382545
## final value 33.382545
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 312.554735
## iter 10 value 158.125612
## iter 20 value 139.651982
## iter 30 value 135.722348
## iter 40 value 122.978151
## iter 50 value 103.496124
## iter 60 value 80.503799
## iter 70 value 57.565724
## iter 80 value 52.654433
## iter 90 value 51.041576
## iter 100 value 50.521202
## final value 50.521202
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 316.125254
## iter 10 value 198.412316
## iter 20 value 170.226324
## iter 30 value 122.089391
## iter 40 value 98.158950
## iter 50 value 88.338702
## iter 60 value 85.468952
## iter 70 value 83.628279
## iter 80 value 81.240495
## iter 90 value 73.353371
## iter 100 value 53.852745
## final value 53.852745
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 31
## initial value 325.003699
## iter 10 value 164.149907
## iter 20 value 155.607772
## iter 30 value 141.301203
## iter 40 value 141.273255
## iter 50 value 140.667121
## iter 60 value 115.488774
## iter 70 value 112.961648
## iter 80 value 112.421382
## iter 90 value 111.463409
## iter 100 value 110.084395
## final value 110.084395
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 31
## initial value 287.966423
## iter 10 value 162.651745
## iter 20 value 137.639642
## iter 30 value 116.591011
## iter 40 value 115.621209
## iter 50 value 113.842120
## iter 60 value 110.849161
## iter 70 value 102.163294
## iter 80 value 96.891607
## iter 90 value 90.930903
## iter 100 value 87.565702
## final value 87.565702
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 31
## initial value 279.556093
## iter 10 value 151.103398
## iter 20 value 148.910446
## iter 30 value 144.673929
## iter 40 value 143.740894
## iter 50 value 141.470402
## iter 60 value 140.583186
## iter 70 value 140.490882
## iter 80 value 137.371545
## iter 90 value 137.305059
## iter 100 value 135.694160
## final value 135.694160
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 31
## initial value 312.779400
## iter 10 value 164.025750
## iter 20 value 163.972475
## iter 30 value 163.199613
## iter 40 value 160.711905
## iter 50 value 148.599221
## iter 60 value 142.801038
## iter 70 value 142.742157
## iter 80 value 140.451254
## iter 90 value 138.489709
## iter 100 value 135.352665
## final value 135.352665
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 31
## initial value 303.184933
## iter 10 value 164.045425
## iter 20 value 163.297717
## iter 30 value 147.935127
## iter 40 value 145.784792
## iter 50 value 142.042279
## iter 60 value 139.931265
## iter 70 value 138.565995
## iter 80 value 137.862222
## iter 90 value 135.346813
## iter 100 value 135.262284
## final value 135.262284
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 79
## initial value 237.426192
## iter 10 value 164.368639
## iter 20 value 164.324052
## iter 30 value 151.619292
## iter 40 value 150.824156
## iter 50 value 149.190102
## iter 60 value 143.722890
## iter 70 value 143.714651
## iter 80 value 141.304678
## iter 90 value 140.491205
## iter 100 value 122.518139
## final value 122.518139
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 79
## initial value 329.300717
## iter 10 value 163.700210
## iter 20 value 160.524387
## iter 30 value 157.709286
## iter 40 value 144.806668
## iter 50 value 143.104129
## iter 60 value 137.872481
## iter 70 value 135.426629
## iter 80 value 117.706507
## iter 90 value 111.704116
## iter 100 value 111.550471
## final value 111.550471
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 79
## initial value 257.912873
## iter 10 value 164.186938
## iter 20 value 164.180158
## iter 30 value 164.165651
## iter 40 value 161.108057
## iter 50 value 149.310790
## iter 60 value 149.145479
## iter 70 value 144.025667
## iter 80 value 144.019536
## iter 90 value 141.085979
## iter 100 value 140.792402
## final value 140.792402
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 79
## initial value 417.131887
## iter 10 value 153.087733
## iter 20 value 150.995944
## iter 30 value 145.994151
## iter 40 value 143.870484
## iter 50 value 138.952419
## iter 60 value 138.584776
## iter 70 value 135.981291
## iter 80 value 135.339974
## iter 90 value 135.136951
## iter 100 value 135.129587
## final value 135.129587
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 79
## initial value 361.540206
## iter 10 value 163.908848
## iter 20 value 154.483962
## iter 30 value 151.718215
## iter 40 value 151.709957
## iter 50 value 145.750399
## iter 60 value 145.666186
## iter 70 value 144.752985
## iter 80 value 144.729374
## iter 90 value 144.635834
## iter 100 value 135.424986
## final value 135.424986
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 315.154185
## iter 10 value 164.446620
## iter 20 value 158.464403
## iter 30 value 156.210931
## iter 40 value 153.772693
## iter 50 value 153.511441
## iter 60 value 153.485847
## iter 70 value 153.469824
## iter 80 value 142.114948
## iter 90 value 140.579803
## iter 100 value 140.560621
## final value 140.560621
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 357.441586
## iter 10 value 165.071674
## iter 20 value 147.735437
## iter 30 value 140.917045
## iter 40 value 134.806666
## iter 50 value 133.608818
## iter 60 value 120.182983
## iter 70 value 119.158153
## iter 80 value 118.469402
## iter 90 value 118.198662
## iter 100 value 103.387833
## final value 103.387833
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 289.012645
## iter 10 value 164.151870
## iter 20 value 164.145216
## iter 30 value 164.131205
## iter 40 value 164.074791
## iter 50 value 160.988625
## iter 60 value 160.672912
## iter 70 value 147.688150
## iter 80 value 145.715314
## iter 90 value 138.864448
## iter 100 value 133.799232
## final value 133.799232
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 315.572690
## iter 10 value 166.082692
## iter 20 value 158.839249
## iter 30 value 145.778434
## iter 40 value 129.845364
## iter 50 value 129.565623
## iter 60 value 112.109437
## iter 70 value 91.017853
## iter 80 value 89.630758
## iter 90 value 84.876302
## iter 100 value 83.686301
## final value 83.686301
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 292.128410
## iter 10 value 163.366612
## iter 20 value 143.733267
## iter 30 value 140.512592
## iter 40 value 140.023807
## iter 50 value 136.489931
## iter 60 value 135.350309
## iter 70 value 135.283484
## iter 80 value 135.137721
## iter 90 value 135.127928
## iter 100 value 128.409654
## final value 128.409654
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 127
## initial value 496.782379
## iter 10 value 194.706864
## iter 20 value 173.310084
## iter 30 value 172.523798
## iter 40 value 149.243683
## iter 50 value 136.878458
## iter 60 value 120.532026
## iter 70 value 114.537248
## iter 80 value 93.868967
## iter 90 value 83.998916
## iter 100 value 63.580810
## final value 63.580810
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 127
## initial value 413.704684
## iter 10 value 203.809428
## iter 20 value 147.737364
## iter 30 value 105.908245
## iter 40 value 95.272392
## iter 50 value 79.384334
## iter 60 value 61.838929
## iter 70 value 60.207525
## iter 80 value 56.459920
## iter 90 value 39.484891
## iter 100 value 31.818594
## final value 31.818594
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 127
## initial value 289.593449
## iter 10 value 172.893334
## iter 20 value 169.956522
## iter 30 value 132.692761
## iter 40 value 117.063088
## iter 50 value 104.649917
## iter 60 value 96.182552
## iter 70 value 90.625599
## iter 80 value 64.239252
## iter 90 value 38.767366
## iter 100 value 33.202739
## final value 33.202739
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 127
## initial value 537.037849
## iter 10 value 204.836220
## iter 20 value 178.180130
## iter 30 value 172.408877
## iter 40 value 156.601084
## iter 50 value 143.768218
## iter 60 value 88.820218
## iter 70 value 72.528848
## iter 80 value 66.001124
## iter 90 value 49.079135
## iter 100 value 41.835933
## final value 41.835933
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 127
## initial value 386.380833
## iter 10 value 261.957871
## iter 20 value 181.648209
## iter 30 value 172.112124
## iter 40 value 171.672350
## iter 50 value 157.546931
## iter 60 value 149.794735
## iter 70 value 142.385808
## iter 80 value 131.175192
## iter 90 value 104.110232
## iter 100 value 87.435405
## final value 87.435405
## stopped after 100 iterations
prediction_stack <- stack(ensemble)
names(prediction_stack) <- models
plot(prediction_stack)
############### Accuracy assessment - confusion matrices - ####
models <- c("svmPoly", "svmRadial", "svmLinear", "rf", "knn", "gbm", "pls", "mda", "amdai", "avNNet", "Ens_SV", "Ens_WV")
mymodels <- data.frame(matrix (nrow=length(models), ncol= 7))
colnames (mymodels) <- c("Accuracy", "Kappa", "AccuracyLower", "AccuracyUpper",
"AccuracyNull", "AccuracyPValue", "McnemarPValue")
rownames(mymodels) <- models
#empty table for Producer's and user's accuracies
my.acc <- data.frame(matrix (nrow=length(levels(train_2003$class)), ncol= 3))
colnames (my.acc) <- c("PrA", "UrA", "alg")
rownames(my.acc) <- levels(train_2003$class)
myacc <- do.call("rbind", replicate(10, my.acc, simplify = F))
myacc$class <- levels(train_2003$class)
myacc$alg <- rep(models[1:10], each=length(levels(train_2003$class)))
#
uniqueClasses <- unique(train_2003$class)
set.seed(7)
xy_val <- lapply (uniqueClasses, function(class_i){
class_data <- subset(val_2003, class == class_i)
classpts <- spsample(class_data, type = "stratified", n = 100)
classpts$class <-rep(class_i, length(classpts))
return(classpts)
})
#rbind the spatialpointdataframe into asingle object
xy_val <- do.call("rbind", xy_val)
models <- c("svmPoly", "svmRadial", "svmLinear", "rf", "knn", "gbm", "pls", "mda", "amdai", "avNNet")
for (mod in models){
#extract predictions
pred <- extract(prediction_stack[[mod]], xy_val, cellnumbers=T)
#discard duplicates cells and 'cell' column
dup <- duplicated(pred)
pred <- pred[!dup,mod]
obs <- xy_val$class[!dup]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
valFactor <- uniqueClasses[pred]
head(valFactor)
mymodels[rownames(mymodels) %in% mod,] <- confusionMatrix(obs, reference = valFactor)[[3]]
table <- confusionMatrix(obs, reference = valFactor)[[2]]
PrA <- diag(table)/rowSums(table)
UrA <- diag(table)/colSums(table)
myacc[myacc$alg %in% mod,"PrA"] <- as.vector(PrA)
myacc[myacc$alg %in% mod,"UrA"] <- as.vector(UrA)
}
## validate the ensemble map
#simply voting ensemble procedure
Ensemble <- modal(prediction_stack[[c(1,2,3,4,5,6,8,9)]])
names(Ensemble) <- "Ens_SV"
pred <- extract(Ensemble, xy_val, cellnumbers=T)
#discard duplicates cells and 'cell' column
dup <- duplicated(pred)
pred <- pred[!dup,"Ens_SV"]
obs <- xy_val$class[!dup]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
valFactor <- uniqueClasses[pred]
head(valFactor)
## [1] Area Area Duna gris Area Area Area
## 7 Levels: Area Auga Bosque Carrizal Duna gris ... Vexetacion halofila
mymodels[rownames(mymodels) %in% "Ens_SV",] <-confusionMatrix(obs, reference = valFactor)[[3]]
table <- confusionMatrix(obs, reference = valFactor)[[2]]
PrA <- diag(table)/rowSums(table)
UrA <- diag(table)/colSums(table)
myacc_Ens_SV <- as.data.frame(cbind(PrA, UrA))
myacc_Ens_SV$alg <- "Ens_SV"
myacc_Ens_SV$class <- rownames(myacc_Ens_SV)
##weithed voting ensemnble procedure
Ensemble2 <- modal(stack(replicate(mymodels[rownames(mymodels)[2], "Accuracy"]*100, prediction_stack[[1]])),
stack(replicate(mymodels[rownames(mymodels)[8], "Accuracy"]*100, prediction_stack[[2]])),
stack(replicate(mymodels[rownames(mymodels)[8], "Accuracy"]*100, prediction_stack[[3]])),
stack(replicate(mymodels[rownames(mymodels)[8], "Accuracy"]*100, prediction_stack[[4]])),
stack(replicate(mymodels[rownames(mymodels)[8], "Accuracy"]*100, prediction_stack[[5]])),
stack(replicate(mymodels[rownames(mymodels)[8], "Accuracy"]*100, prediction_stack[[6]])),
stack(replicate(mymodels[rownames(mymodels)[8], "Accuracy"]*100, prediction_stack[[8]])),
stack(replicate(mymodels[rownames(mymodels)[9], "Accuracy"]*100, prediction_stack[[9]])))
names(Ensemble2) <- "Ens_Wv"
pred <- extract(Ensemble2, xy_val, cellnumbers=T)
#discard duplicates cells and 'cell' column
dup <- duplicated(pred)
pred <- pred[!dup,"Ens_Wv"]
obs <- xy_val$class[!dup]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
valFactor <- uniqueClasses[pred]
head(valFactor)
## [1] Area Area Duna gris Area Area Area
## 7 Levels: Area Auga Bosque Carrizal Duna gris ... Vexetacion halofila
mymodels[rownames(mymodels) %in% "Ens_WV",] <-confusionMatrix(obs, reference = valFactor)[[3]]
table <- confusionMatrix(obs, reference = valFactor)[[2]]
PrA <- diag(table)/rowSums(table)
UrA <- diag(table)/colSums(table)
myacc_Ens_WV <- as.data.frame(cbind(PrA, UrA))
myacc_Ens_WV$alg <- "Ens_WV"
myacc_Ens_WV$class <- rownames(myacc_Ens_WV)
####
myacc <- rbind(myacc, myacc_Ens_SV, myacc_Ens_WV)
library(rasterVis)
## Loading required package: latticeExtra
## Loading required package: RColorBrewer
##
## Attaching package: 'latticeExtra'
## The following object is masked from 'package:ggplot2':
##
## layer
library(ggplot2)
### 9 x 9; 7 x 6
gplot(Ensemble) + geom_raster(aes(fill = value)) +
facet_wrap(~ variable) +
scale_fill_gradientn(name="Environmental units 2013",colours=c("grey90", "blue3", "darkgreen" ,"yellow", "seagreen4","orange1","yellowgreen"),
breaks=c(1,2,3,4,5,6,7), na.value = "white", labels=c("Sand", "Water", "Forest", "Reeds", "Grey Dunes","Meadows and grasslands", "Halophyte vegetation")) +
theme(plot.margin = unit(c(0.001,0.001,0.001,0.001), "cm"), panel.grid.major = element_line(colour = "grey70", size = 0.2),
panel.grid.minor = element_blank(), panel.background = element_rect(fill = "white", colour = "white"))
gplot(Ensemble2) + geom_raster(aes(fill = value)) +
facet_wrap(~ variable) +
scale_fill_gradientn(name="Environmental units 2013",colours=c("grey90", "blue3", "darkgreen" ,"yellow", "seagreen4","orange1","yellowgreen"),
breaks=c(1,2,3,4,5,6,7), na.value = "white", labels=c("Sand", "Water", "Forest", "Reeds", "Grey Dunes","Meadows and grasslands", "Halophyte vegetation")) +
theme(plot.margin = unit(c(0.001,0.001,0.001,0.001), "cm"), panel.grid.major = element_line(colour = "grey70", size = 0.2),
panel.grid.minor = element_blank(), panel.background = element_rect(fill = "white", colour = "white"))
#write.csv2(mymodels, "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/models.metrics2003_rev.csv")
#write.csv2(myacc, "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/acc.metrics2003_rev.csv")
#writeRaster(Ensemble, bylayer = T, suffix = 'names', filename = "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/Ens_SV_2003.tif", datatype = 'INT2S', overwrite=T, options=c("TFW=YES"))
#writeRaster(Ensemble2, filename = "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/Ens_WV_2003.tif", datatype = 'INT2S', overwrite=T, options=c("TFW=YES"))
#writeRaster(prediction_stack, bylayer = T, suffix = 'names', filename = "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/Raster/LULCmap_2003.tif", datatype = 'INT2S', overwrite=T, options=c("TFW=YES"))
save.image("E://USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/ImageProcess2003_revision.RData")
################################################################################################
#### Pre-processing of Landsat images for year 2016, classification and validation procedures###
################################################################################################
library(RStoolbox)
library(raster)
library(rgdal)
metaL8May2016 <- readMeta("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/LandsatData/2016/LC82050302016123LGN00/LC82050302016123LGN00/LC82050302016123LGN00_MTL.txt")
metaL8Sep2016 <- readMeta("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/LandsatData/2016/LC82050302016267LGN00/LC82050302016267LGN00/LC82050302016267LGN00_MTL.txt")
summary(metaL8May2016)
## Scene: LC82050302016123LGN00
## Satellite: LANDSAT8
## Sensor: OLI_TIRS
## Date: 2016-05-02
## Path/Row: 205/30
## Projection: +proj=utm +zone=29 +units=m +datum=WGS84 +ellps=WGS84 +towgs84=0,0,0
##
## Data:
## FILES QUANTITY CATEGORY
## B1_dn LC82050302016123LGN00_B1.TIF dn image
## B2_dn LC82050302016123LGN00_B2.TIF dn image
## B3_dn LC82050302016123LGN00_B3.TIF dn image
## B4_dn LC82050302016123LGN00_B4.TIF dn image
## B5_dn LC82050302016123LGN00_B5.TIF dn image
## B6_dn LC82050302016123LGN00_B6.TIF dn image
## B7_dn LC82050302016123LGN00_B7.TIF dn image
## B9_dn LC82050302016123LGN00_B9.TIF dn image
## B10_dn LC82050302016123LGN00_B10.TIF dn image
## B11_dn LC82050302016123LGN00_B11.TIF dn image
## B8_dn LC82050302016123LGN00_B8.TIF dn pan
## QA_dn LC82050302016123LGN00_BQA.TIF dn qa
##
## Available calibration parameters (gain and offset):
## dn -> radiance (toa)
## dn -> reflectance (toa)
## dn -> brightness temperature (toa)
summary(metaL8Sep2016)
## Scene: LC82050302016267LGN00
## Satellite: LANDSAT8
## Sensor: OLI_TIRS
## Date: 2016-09-23
## Path/Row: 205/30
## Projection: +proj=utm +zone=29 +units=m +datum=WGS84 +ellps=WGS84 +towgs84=0,0,0
##
## Data:
## FILES QUANTITY CATEGORY
## B1_dn LC82050302016267LGN00_B1.TIF dn image
## B2_dn LC82050302016267LGN00_B2.TIF dn image
## B3_dn LC82050302016267LGN00_B3.TIF dn image
## B4_dn LC82050302016267LGN00_B4.TIF dn image
## B5_dn LC82050302016267LGN00_B5.TIF dn image
## B6_dn LC82050302016267LGN00_B6.TIF dn image
## B7_dn LC82050302016267LGN00_B7.TIF dn image
## B9_dn LC82050302016267LGN00_B9.TIF dn image
## B10_dn LC82050302016267LGN00_B10.TIF dn image
## B11_dn LC82050302016267LGN00_B11.TIF dn image
## B8_dn LC82050302016267LGN00_B8.TIF dn pan
## QA_dn LC82050302016267LGN00_BQA.TIF dn qa
##
## Available calibration parameters (gain and offset):
## dn -> radiance (toa)
## dn -> reflectance (toa)
## dn -> brightness temperature (toa)
L8May2016 <- stackMeta(metaL8May2016)
L8Sep2016 <- stackMeta(metaL8Sep2016)
################### calibration and radiometric correction if necessary
#Data conversion: From DNs to Reflectances
#Radiometric calibration
metaL8May2016$CALRAD
## offset gain
## B1_dn -61.78698 0.01235700
## B2_dn -63.27062 0.01265400
## B3_dn -58.30334 0.01166100
## B4_dn -49.16466 0.00983290
## B5_dn -30.08632 0.00601730
## B6_dn -7.48219 0.00149640
## B7_dn -2.52190 0.00050438
## B8_dn -55.64086 0.01112800
## B9_dn -11.75842 0.00235170
## B10_dn 0.10000 0.00033420
## B11_dn 0.10000 0.00033420
metaL8Sep2016$CALRAD
## offset gain
## B1_dn -62.36891 0.01247400
## B2_dn -63.86652 0.01277300
## B3_dn -58.85245 0.01177000
## B4_dn -49.62770 0.00992550
## B5_dn -30.36968 0.00607390
## B6_dn -7.55266 0.00151050
## B7_dn -2.54565 0.00050913
## B8_dn -56.16490 0.01123300
## B9_dn -11.86916 0.00237380
## B10_dn 0.10000 0.00033420
## B11_dn 0.10000 0.00033420
L8May2016_rad <- radCor(L8May2016, metaData = metaL8May2016, method="rad")
L8Sep2016_rad <- radCor(L8Sep2016, metaData = metaL8Sep2016, method="rad")
dataType(L8May2016_rad[[1]]) #dataType from integer to float
## [1] "FLT8S"
dataType(L8Sep2016_rad[[1]])
## [1] "FLT8S"
plotRGB(L8May2016_rad, r = 4, g = 3, b = 2, stretch = "lin")
plot(L8May2016_rad)
plotRGB(L8Sep2016_rad, r = 4, g = 3, b = 2, stretch = "lin")
plot(L8Sep2016_rad)
##crop the images to our study area (Natural Park - Corrubedo)
study_area <- readOGR("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/AreaEstudio/LimiteParque", "PNCorrubedo_reproj")
## OGR data source with driver: ESRI Shapefile
## Source: "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/AreaEstudio/LimiteParque", layer: "PNCorrubedo_reproj"
## with 1 features
## It has 10 fields
#May
L8May2016_rad_PN <- crop(L8May2016_rad,study_area)
L8May2016_rad_PN_mask <- mask(L8May2016_rad_PN, study_area)
plotRGB(L8May2016_rad_PN_mask, r = 4, g = 3, b = 2, stretch = "hist")#rgb
plotRGB(L8May2016_rad_PN_mask, r = 6, g = 5, b = 3, stretch = "hist")#vegetation
plotRGB(L8May2016_rad_PN_mask, r = 5, g = 6, b = 2, stretch = "hist")# brown
#September
L8Sep2016_rad_PN <- crop(L8Sep2016_rad,study_area)
L8Sep2016_rad_PN_mask <- mask(L8Sep2016_rad_PN,study_area)
plotRGB(L8Sep2016_rad_PN_mask, r = 4, g = 3, b = 2, stretch = "hist")#rgb
plotRGB(L8Sep2016_rad_PN_mask, r = 6, g = 5, b = 3, stretch = "hist")#vegetation
plotRGB(L8Sep2016_rad_PN_mask, r = 5, g = 6, b = 2, stretch = "hist")# brown
#Spectral index - Normalised Difference Water Index: NDWI = (green - nir)/(green + nir)
NDWI_may <- spectralIndices(L8May2016_rad_PN_mask, blue = "B2_tra", green = "B3_tra", red = "B4_tra",
nir = "B5_tra", swir2 = "B6_tra", swir3 = "B7_tra", indices = "NDWI")#
NDWI_sep <- spectralIndices(L8Sep2016_rad_PN_mask, blue = "B2_tra", green = "B3_tra", red = "B4_tra",
nir = "B5_tra", swir2 = "B6_tra", swir3 = "B7_tra", indices = "NDWI")#
NDVI_may <- spectralIndices(L8May2016_rad_PN_mask, blue = "B2_tra", green = "B3_tra", red = "B4_tra",
nir = "B5_tra", swir2 = "B6_tra", swir3 = "B7_tra", indices = "NDVI")#
NDVI_sep <- spectralIndices(L8Sep2016_rad_PN_mask, blue = "B2_tra", green = "B3_tra", red = "B4_tra",
nir = "B5_tra", swir2 = "B6_tra", swir3 = "B7_tra", indices = "NDVI")#
plot(NDWI_may)
plot(NDWI_sep)
plot(NDVI_may)
plot(NDVI_sep)
#join both datasets (sep - may)
L82016 <- stack(L8May2016_rad_PN_mask, L8Sep2016_rad_PN_mask)
L82016 <- L82016[[c(2,3,4,5,6,7,12,13,14,15,16,17)]] #subset - only optical radiometric bands
#join with spectral indices
L82016 <- stack(L82016,NDWI_may,NDWI_sep)
L82016 <- stack(L82016,NDVI_may,NDVI_sep)
############### training data #############
#read vector files for training dataset
train_2016 <- readOGR("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/TrainAreas", "TrainAreas_2016_8cat_v2")
## OGR data source with driver: ESRI Shapefile
## Source: "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/TrainAreas", layer: "TrainAreas_2016_8cat_v2"
## with 47 features
## It has 2 fields
## Integer64 fields read as strings: id
val_2016 <- readOGR("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/TrainAreas", "TestAreas_2016_8cat_v2")
## OGR data source with driver: ESRI Shapefile
## Source: "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/TrainAreas", layer: "TestAreas_2016_8cat_v2"
## with 50 features
## It has 2 fields
## Integer64 fields read as strings: id
######### classification procedures
library(caret)
library(randomForest)
library(party)
library(pls)
library(e1071)
library(kernlab)
library(adaptDA)
#ensemble of predictions
models <- c("svmPoly", "svmRadial", "svmLinear", "rf", "knn", "gbm", "pls", "mda", "amdai", "avNNet")
ensemble <- lapply (models, function(mod){
set.seed(5)
sc <- superClass(L82016, model= mod, trainData = train_2016,
responseCol = "class")
return(sc$map)
})
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 0.9248
## 2 1.5570 nan 0.1000 0.5633
## 3 1.2431 nan 0.1000 0.3443
## 4 1.0327 nan 0.1000 0.2737
## 5 0.8728 nan 0.1000 0.2078
## 6 0.7515 nan 0.1000 0.1735
## 7 0.6490 nan 0.1000 0.1294
## 8 0.5699 nan 0.1000 0.1032
## 9 0.5056 nan 0.1000 0.1047
## 10 0.4438 nan 0.1000 0.0742
## 20 0.1413 nan 0.1000 0.0203
## 40 0.0219 nan 0.1000 0.0005
## 60 0.0063 nan 0.1000 -0.0000
## 80 0.0025 nan 0.1000 0.0001
## 100 0.0007 nan 0.1000 0.0000
## 120 0.0003 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 150 0.0001 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 0.9687
## 2 1.4920 nan 0.1000 0.5519
## 3 1.1696 nan 0.1000 0.3615
## 4 0.9554 nan 0.1000 0.2726
## 5 0.7897 nan 0.1000 0.2077
## 6 0.6639 nan 0.1000 0.1861
## 7 0.5497 nan 0.1000 0.1431
## 8 0.4635 nan 0.1000 0.1079
## 9 0.3961 nan 0.1000 0.0925
## 10 0.3402 nan 0.1000 0.0785
## 20 0.0731 nan 0.1000 0.0137
## 40 0.0045 nan 0.1000 0.0002
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 1.0724
## 2 1.4318 nan 0.1000 0.5700
## 3 1.0969 nan 0.1000 0.3623
## 4 0.8799 nan 0.1000 0.2700
## 5 0.7220 nan 0.1000 0.1913
## 6 0.6062 nan 0.1000 0.1519
## 7 0.5095 nan 0.1000 0.1356
## 8 0.4291 nan 0.1000 0.1032
## 9 0.3656 nan 0.1000 0.0894
## 10 0.3086 nan 0.1000 0.0684
## 20 0.0658 nan 0.1000 0.0093
## 40 0.0045 nan 0.1000 0.0002
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 0.9429
## 2 1.5283 nan 0.1000 0.4805
## 3 1.2382 nan 0.1000 0.3448
## 4 1.0360 nan 0.1000 0.2650
## 5 0.8801 nan 0.1000 0.2055
## 6 0.7579 nan 0.1000 0.1684
## 7 0.6584 nan 0.1000 0.1281
## 8 0.5803 nan 0.1000 0.1236
## 9 0.5086 nan 0.1000 0.1051
## 10 0.4458 nan 0.1000 0.0830
## 20 0.1429 nan 0.1000 0.0195
## 40 0.0225 nan 0.1000 0.0015
## 60 0.0046 nan 0.1000 0.0003
## 80 0.0010 nan 0.1000 0.0001
## 100 0.0002 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 0.9328
## 2 1.4838 nan 0.1000 0.5206
## 3 1.1643 nan 0.1000 0.3513
## 4 0.9505 nan 0.1000 0.2578
## 5 0.7871 nan 0.1000 0.2085
## 6 0.6611 nan 0.1000 0.1660
## 7 0.5573 nan 0.1000 0.1483
## 8 0.4705 nan 0.1000 0.1162
## 9 0.3957 nan 0.1000 0.0904
## 10 0.3383 nan 0.1000 0.0871
## 20 0.0729 nan 0.1000 0.0117
## 40 0.0068 nan 0.1000 0.0007
## 60 0.0009 nan 0.1000 0.0001
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 1.0225
## 2 1.4583 nan 0.1000 0.5148
## 3 1.1474 nan 0.1000 0.3663
## 4 0.9322 nan 0.1000 0.2626
## 5 0.7690 nan 0.1000 0.2156
## 6 0.6387 nan 0.1000 0.1543
## 7 0.5417 nan 0.1000 0.1297
## 8 0.4586 nan 0.1000 0.1144
## 9 0.3851 nan 0.1000 0.0784
## 10 0.3325 nan 0.1000 0.0761
## 20 0.0720 nan 0.1000 0.0126
## 40 0.0044 nan 0.1000 0.0004
## 60 0.0004 nan 0.1000 0.0001
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 0.9611
## 2 1.5294 nan 0.1000 0.4573
## 3 1.2564 nan 0.1000 0.3707
## 4 1.0468 nan 0.1000 0.2696
## 5 0.8919 nan 0.1000 0.2275
## 6 0.7580 nan 0.1000 0.1631
## 7 0.6610 nan 0.1000 0.1454
## 8 0.5770 nan 0.1000 0.1071
## 9 0.5111 nan 0.1000 0.0868
## 10 0.4575 nan 0.1000 0.0788
## 20 0.1415 nan 0.1000 0.0176
## 40 0.0199 nan 0.1000 0.0018
## 60 0.0034 nan 0.1000 0.0003
## 80 0.0006 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 150 0.0000 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 1.0293
## 2 1.4578 nan 0.1000 0.5396
## 3 1.1401 nan 0.1000 0.3436
## 4 0.9335 nan 0.1000 0.2929
## 5 0.7565 nan 0.1000 0.2194
## 6 0.6243 nan 0.1000 0.1615
## 7 0.5262 nan 0.1000 0.1311
## 8 0.4460 nan 0.1000 0.1144
## 9 0.3766 nan 0.1000 0.0830
## 10 0.3242 nan 0.1000 0.0797
## 20 0.0660 nan 0.1000 0.0134
## 40 0.0043 nan 0.1000 0.0006
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 0.9502
## 2 1.4947 nan 0.1000 0.5400
## 3 1.1697 nan 0.1000 0.4054
## 4 0.9304 nan 0.1000 0.2558
## 5 0.7700 nan 0.1000 0.2233
## 6 0.6386 nan 0.1000 0.1902
## 7 0.5257 nan 0.1000 0.1358
## 8 0.4451 nan 0.1000 0.1118
## 9 0.3770 nan 0.1000 0.0965
## 10 0.3156 nan 0.1000 0.0650
## 20 0.0676 nan 0.1000 0.0100
## 40 0.0035 nan 0.1000 0.0004
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 0.9285
## 2 1.5463 nan 0.1000 0.4922
## 3 1.2512 nan 0.1000 0.3297
## 4 1.0531 nan 0.1000 0.2552
## 5 0.9016 nan 0.1000 0.2249
## 6 0.7716 nan 0.1000 0.1582
## 7 0.6735 nan 0.1000 0.1443
## 8 0.5859 nan 0.1000 0.0963
## 9 0.5221 nan 0.1000 0.1080
## 10 0.4555 nan 0.1000 0.0701
## 20 0.1487 nan 0.1000 0.0250
## 40 0.0218 nan 0.1000 0.0022
## 60 0.0045 nan 0.1000 0.0003
## 80 0.0009 nan 0.1000 0.0000
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 0.9810
## 2 1.4918 nan 0.1000 0.5451
## 3 1.1595 nan 0.1000 0.3880
## 4 0.9281 nan 0.1000 0.3004
## 5 0.7497 nan 0.1000 0.1869
## 6 0.6308 nan 0.1000 0.1745
## 7 0.5266 nan 0.1000 0.1423
## 8 0.4415 nan 0.1000 0.1053
## 9 0.3763 nan 0.1000 0.0870
## 10 0.3182 nan 0.1000 0.0730
## 20 0.0697 nan 0.1000 0.0097
## 40 0.0058 nan 0.1000 0.0006
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 1.0729
## 2 1.4424 nan 0.1000 0.4586
## 3 1.1551 nan 0.1000 0.3646
## 4 0.9224 nan 0.1000 0.2594
## 5 0.7602 nan 0.1000 0.1962
## 6 0.6346 nan 0.1000 0.1670
## 7 0.5337 nan 0.1000 0.1364
## 8 0.4504 nan 0.1000 0.0956
## 9 0.3878 nan 0.1000 0.0954
## 10 0.3290 nan 0.1000 0.0835
## 20 0.0698 nan 0.1000 0.0132
## 40 0.0044 nan 0.1000 0.0006
## 60 0.0004 nan 0.1000 0.0001
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 0.8437
## 2 1.5558 nan 0.1000 0.4971
## 3 1.2656 nan 0.1000 0.3680
## 4 1.0491 nan 0.1000 0.2528
## 5 0.8992 nan 0.1000 0.2173
## 6 0.7734 nan 0.1000 0.1657
## 7 0.6744 nan 0.1000 0.1455
## 8 0.5880 nan 0.1000 0.0938
## 9 0.5262 nan 0.1000 0.1037
## 10 0.4632 nan 0.1000 0.0815
## 20 0.1499 nan 0.1000 0.0261
## 40 0.0228 nan 0.1000 0.0013
## 60 0.0046 nan 0.1000 0.0002
## 80 0.0011 nan 0.1000 0.0000
## 100 0.0003 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 150 0.0000 nan 0.1000 0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 1.0516
## 2 1.4564 nan 0.1000 0.5423
## 3 1.1394 nan 0.1000 0.3966
## 4 0.9090 nan 0.1000 0.2606
## 5 0.7509 nan 0.1000 0.1990
## 6 0.6296 nan 0.1000 0.1767
## 7 0.5230 nan 0.1000 0.1293
## 8 0.4419 nan 0.1000 0.1103
## 9 0.3748 nan 0.1000 0.0958
## 10 0.3186 nan 0.1000 0.0803
## 20 0.0669 nan 0.1000 0.0087
## 40 0.0047 nan 0.1000 0.0006
## 60 0.0005 nan 0.1000 0.0001
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 1.0335
## 2 1.4669 nan 0.1000 0.5477
## 3 1.1488 nan 0.1000 0.3488
## 4 0.9448 nan 0.1000 0.2710
## 5 0.7722 nan 0.1000 0.2155
## 6 0.6426 nan 0.1000 0.1796
## 7 0.5344 nan 0.1000 0.1352
## 8 0.4515 nan 0.1000 0.0962
## 9 0.3910 nan 0.1000 0.1039
## 10 0.3261 nan 0.1000 0.0778
## 20 0.0739 nan 0.1000 0.0150
## 40 0.0039 nan 0.1000 0.0000
## 60 0.0003 nan 0.1000 -0.0001
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 2.0794 nan 0.1000 1.0651
## 2 1.4266 nan 0.1000 0.5564
## 3 1.0923 nan 0.1000 0.3421
## 4 0.8835 nan 0.1000 0.2898
## 5 0.7100 nan 0.1000 0.2128
## 6 0.5822 nan 0.1000 0.1566
## 7 0.4884 nan 0.1000 0.1290
## 8 0.4077 nan 0.1000 0.1063
## 9 0.3409 nan 0.1000 0.0875
## 10 0.2865 nan 0.1000 0.0723
## 20 0.0548 nan 0.1000 0.0104
## 40 0.0039 nan 0.1000 0.0004
## 60 0.0007 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0002
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 150 0.0000 nan 0.1000 -0.0000
##
## Fitting Repeat 1
##
## # weights: 33
## initial value 491.379180
## final value 216.000000
## converged
## Fitting Repeat 2
##
## # weights: 33
## initial value 421.982261
## final value 199.333333
## converged
## Fitting Repeat 3
##
## # weights: 33
## initial value 456.366755
## final value 216.000000
## converged
## Fitting Repeat 4
##
## # weights: 33
## initial value 456.423561
## final value 216.000000
## converged
## Fitting Repeat 5
##
## # weights: 33
## initial value 422.357115
## final value 216.000000
## converged
## Fitting Repeat 1
##
## # weights: 83
## initial value 436.639548
## iter 10 value 215.987768
## iter 20 value 215.980928
## iter 30 value 215.957685
## iter 40 value 200.325043
## final value 199.333340
## converged
## Fitting Repeat 2
##
## # weights: 83
## initial value 401.782638
## final value 216.000000
## converged
## Fitting Repeat 3
##
## # weights: 83
## initial value 349.203726
## final value 216.000000
## converged
## Fitting Repeat 4
##
## # weights: 83
## initial value 403.742790
## final value 215.999855
## converged
## Fitting Repeat 5
##
## # weights: 83
## initial value 392.071533
## final value 216.000000
## converged
## Fitting Repeat 1
##
## # weights: 133
## initial value 411.645833
## final value 216.000000
## converged
## Fitting Repeat 2
##
## # weights: 133
## initial value 472.945235
## final value 216.000000
## converged
## Fitting Repeat 3
##
## # weights: 133
## initial value 533.236959
## final value 216.000000
## converged
## Fitting Repeat 4
##
## # weights: 133
## initial value 588.349718
## final value 216.000000
## converged
## Fitting Repeat 5
##
## # weights: 133
## initial value 607.950705
## final value 216.000000
## converged
## Fitting Repeat 1
##
## # weights: 33
## initial value 523.341840
## iter 10 value 198.618606
## iter 20 value 184.696608
## iter 30 value 177.798786
## iter 40 value 166.289731
## iter 50 value 161.069878
## iter 60 value 159.689107
## iter 70 value 157.961787
## iter 80 value 155.642009
## iter 90 value 154.623812
## iter 100 value 154.605562
## final value 154.605562
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 33
## initial value 361.940820
## iter 10 value 202.160612
## iter 20 value 164.711021
## iter 30 value 160.203470
## iter 40 value 158.822160
## iter 50 value 158.331707
## iter 60 value 156.049495
## iter 70 value 154.733557
## iter 80 value 154.605431
## final value 154.605425
## converged
## Fitting Repeat 3
##
## # weights: 33
## initial value 477.842374
## iter 10 value 197.746044
## iter 20 value 184.586212
## iter 30 value 169.592675
## iter 40 value 159.415141
## iter 50 value 152.453741
## iter 60 value 151.187776
## iter 70 value 150.837281
## iter 80 value 150.509155
## final value 150.508121
## converged
## Fitting Repeat 4
##
## # weights: 33
## initial value 499.121314
## iter 10 value 208.686185
## iter 20 value 187.047272
## iter 30 value 184.272435
## iter 40 value 183.114191
## iter 50 value 182.802774
## iter 60 value 164.680016
## iter 70 value 163.543326
## iter 80 value 161.296862
## iter 90 value 160.381384
## iter 100 value 157.524651
## final value 157.524651
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 33
## initial value 464.021546
## iter 10 value 197.307274
## iter 20 value 166.769242
## iter 30 value 153.476880
## iter 40 value 152.144284
## iter 50 value 151.025154
## iter 60 value 150.615986
## iter 70 value 150.508127
## final value 150.508121
## converged
## Fitting Repeat 1
##
## # weights: 83
## initial value 552.189958
## iter 10 value 200.330284
## iter 20 value 184.725359
## iter 30 value 163.604835
## iter 40 value 139.325509
## iter 50 value 129.592472
## iter 60 value 123.022881
## iter 70 value 103.926631
## iter 80 value 88.834836
## iter 90 value 85.874287
## iter 100 value 84.641185
## final value 84.641185
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 484.519444
## iter 10 value 201.484898
## iter 20 value 191.080657
## iter 30 value 161.961364
## iter 40 value 149.350319
## iter 50 value 139.569982
## iter 60 value 134.233287
## iter 70 value 128.353305
## iter 80 value 126.610686
## iter 90 value 118.296888
## iter 100 value 98.532692
## final value 98.532692
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 453.091998
## iter 10 value 243.841222
## iter 20 value 186.007298
## iter 30 value 182.905337
## iter 40 value 182.105135
## iter 50 value 154.118654
## iter 60 value 138.137092
## iter 70 value 134.532585
## iter 80 value 119.616232
## iter 90 value 81.245923
## iter 100 value 73.500829
## final value 73.500829
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 83
## initial value 537.431089
## iter 10 value 207.727503
## iter 20 value 184.209459
## iter 30 value 177.121005
## iter 40 value 163.807125
## iter 50 value 161.533521
## iter 60 value 159.827017
## iter 70 value 159.438895
## iter 80 value 158.204561
## iter 90 value 151.326823
## iter 100 value 123.383334
## final value 123.383334
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 83
## initial value 459.124814
## iter 10 value 215.443813
## iter 20 value 183.667866
## iter 30 value 154.461012
## iter 40 value 151.454521
## iter 50 value 136.317315
## iter 60 value 133.836887
## iter 70 value 127.232597
## iter 80 value 108.893726
## iter 90 value 96.767792
## iter 100 value 93.862809
## final value 93.862809
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 474.124899
## iter 10 value 198.477743
## iter 20 value 184.542051
## iter 30 value 165.960111
## iter 40 value 159.077877
## iter 50 value 132.409953
## iter 60 value 120.661287
## iter 70 value 75.441274
## iter 80 value 63.915736
## iter 90 value 57.194501
## iter 100 value 47.292030
## final value 47.292030
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 478.448877
## iter 10 value 193.396873
## iter 20 value 182.643569
## iter 30 value 162.840849
## iter 40 value 152.240972
## iter 50 value 122.116541
## iter 60 value 114.216135
## iter 70 value 82.103484
## iter 80 value 69.461660
## iter 90 value 63.835080
## iter 100 value 61.393857
## final value 61.393857
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 430.554224
## iter 10 value 200.184882
## iter 20 value 190.772428
## iter 30 value 142.579522
## iter 40 value 121.644070
## iter 50 value 112.563383
## iter 60 value 102.749058
## iter 70 value 101.034383
## iter 80 value 98.383153
## iter 90 value 71.380027
## iter 100 value 62.508533
## final value 62.508533
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 492.057406
## iter 10 value 242.208777
## iter 20 value 186.139339
## iter 30 value 159.592822
## iter 40 value 155.944018
## iter 50 value 136.848839
## iter 60 value 113.524401
## iter 70 value 91.443243
## iter 80 value 78.100914
## iter 90 value 75.833309
## iter 100 value 59.417352
## final value 59.417352
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 540.098691
## iter 10 value 198.717331
## iter 20 value 186.882676
## iter 30 value 165.349410
## iter 40 value 147.540433
## iter 50 value 112.993530
## iter 60 value 103.970846
## iter 70 value 80.902582
## iter 80 value 67.338727
## iter 90 value 61.240491
## iter 100 value 43.267673
## final value 43.267673
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 33
## initial value 434.171219
## iter 10 value 216.121759
## iter 20 value 215.947508
## iter 30 value 211.708133
## iter 40 value 208.330374
## iter 50 value 208.303836
## iter 60 value 205.187741
## iter 70 value 205.070602
## iter 80 value 188.569218
## iter 90 value 188.469595
## iter 100 value 188.369578
## final value 188.369578
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 33
## initial value 434.817848
## iter 10 value 216.134828
## iter 20 value 216.133286
## iter 30 value 216.131585
## iter 40 value 216.129675
## iter 50 value 216.127481
## iter 60 value 216.124887
## iter 70 value 216.121697
## iter 80 value 216.117533
## iter 90 value 194.821985
## iter 100 value 190.423091
## final value 190.423091
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 33
## initial value 502.675885
## iter 10 value 218.389424
## iter 20 value 218.372792
## iter 30 value 218.350800
## iter 40 value 218.313038
## iter 50 value 218.178267
## iter 60 value 213.903366
## iter 70 value 194.860696
## iter 80 value 190.986829
## iter 90 value 189.905470
## iter 100 value 186.619095
## final value 186.619095
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 33
## initial value 460.985310
## iter 10 value 216.129172
## iter 20 value 216.126436
## iter 30 value 216.123096
## iter 40 value 216.118816
## iter 50 value 216.112947
## iter 60 value 216.104042
## iter 70 value 216.088099
## iter 80 value 216.048516
## iter 90 value 215.753004
## iter 100 value 199.458531
## final value 199.458531
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 33
## initial value 517.719653
## iter 10 value 200.249263
## iter 20 value 199.614838
## iter 30 value 188.364764
## iter 40 value 181.410813
## iter 50 value 181.066288
## iter 60 value 181.050363
## iter 70 value 174.731453
## iter 80 value 164.408114
## iter 90 value 163.998442
## iter 100 value 163.982782
## final value 163.982782
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 83
## initial value 413.753541
## iter 10 value 216.089259
## iter 20 value 184.998252
## iter 30 value 148.319886
## iter 40 value 142.283798
## iter 50 value 141.813845
## iter 60 value 141.733477
## iter 70 value 141.691629
## iter 80 value 141.604762
## iter 90 value 141.513550
## iter 100 value 141.117896
## final value 141.117896
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 517.333396
## iter 10 value 217.357947
## iter 20 value 217.351423
## iter 30 value 217.344577
## iter 40 value 217.337201
## iter 50 value 217.328877
## iter 60 value 217.318613
## iter 70 value 217.303350
## iter 80 value 217.266942
## iter 90 value 215.072513
## iter 100 value 200.156011
## final value 200.156011
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 539.779102
## iter 10 value 214.688814
## iter 20 value 182.611550
## iter 30 value 181.219858
## iter 40 value 181.078033
## iter 50 value 180.972617
## iter 60 value 179.255547
## iter 70 value 153.816135
## iter 80 value 146.617318
## iter 90 value 146.249378
## iter 100 value 146.217557
## final value 146.217557
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 83
## initial value 572.683608
## iter 10 value 213.325241
## iter 20 value 188.376562
## iter 30 value 179.144697
## iter 40 value 166.154225
## iter 50 value 158.015034
## iter 60 value 155.524083
## iter 70 value 155.273860
## iter 80 value 155.119497
## iter 90 value 152.990523
## iter 100 value 151.571674
## final value 151.571674
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 83
## initial value 514.346568
## iter 10 value 218.862734
## iter 20 value 218.841704
## iter 30 value 218.811246
## iter 40 value 218.742486
## iter 50 value 216.876457
## iter 60 value 201.886429
## iter 70 value 198.766231
## iter 80 value 165.585049
## iter 90 value 157.651173
## iter 100 value 148.382857
## final value 148.382857
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 466.510748
## iter 10 value 216.169710
## iter 20 value 199.577355
## iter 30 value 179.082337
## iter 40 value 177.198327
## iter 50 value 176.685823
## iter 60 value 176.255087
## iter 70 value 176.234583
## iter 80 value 167.623184
## iter 90 value 162.043949
## iter 100 value 144.049341
## final value 144.049341
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 562.063696
## iter 10 value 337.586386
## iter 20 value 332.604956
## iter 30 value 326.656901
## iter 40 value 269.517403
## iter 50 value 183.581575
## iter 60 value 181.272899
## iter 70 value 167.589891
## iter 80 value 150.977647
## iter 90 value 147.289530
## iter 100 value 143.718075
## final value 143.718075
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 433.477786
## iter 10 value 216.442997
## iter 20 value 215.031669
## iter 30 value 211.925557
## iter 40 value 211.557437
## iter 50 value 194.838035
## iter 60 value 188.945866
## iter 70 value 187.485081
## iter 80 value 182.998999
## iter 90 value 181.136654
## iter 100 value 171.282003
## final value 171.282003
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 465.838841
## iter 10 value 214.412677
## iter 20 value 212.652785
## iter 30 value 181.658035
## iter 40 value 177.484421
## iter 50 value 177.470955
## iter 60 value 174.048179
## iter 70 value 172.478479
## iter 80 value 172.269843
## iter 90 value 168.081241
## iter 100 value 167.494026
## final value 167.494026
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 472.412088
## iter 10 value 216.234766
## iter 20 value 212.728920
## iter 30 value 211.622933
## iter 40 value 208.687237
## iter 50 value 208.438428
## iter 60 value 192.376779
## iter 70 value 191.823878
## iter 80 value 187.562231
## iter 90 value 184.271855
## iter 100 value 184.109431
## final value 184.109431
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 33
## initial value 498.672637
## final value 214.000000
## converged
## Fitting Repeat 2
##
## # weights: 33
## initial value 466.034435
## final value 214.000000
## converged
## Fitting Repeat 3
##
## # weights: 33
## initial value 485.354517
## final value 213.999810
## converged
## Fitting Repeat 4
##
## # weights: 33
## initial value 462.464199
## final value 214.000000
## converged
## Fitting Repeat 5
##
## # weights: 33
## initial value 427.455995
## final value 214.000000
## converged
## Fitting Repeat 1
##
## # weights: 83
## initial value 367.020721
## final value 214.000000
## converged
## Fitting Repeat 2
##
## # weights: 83
## initial value 315.919018
## final value 214.000000
## converged
## Fitting Repeat 3
##
## # weights: 83
## initial value 421.787361
## final value 213.999981
## converged
## Fitting Repeat 4
##
## # weights: 83
## initial value 559.735676
## iter 10 value 193.546123
## iter 20 value 193.523631
## final value 193.523531
## converged
## Fitting Repeat 5
##
## # weights: 83
## initial value 459.981977
## final value 214.000000
## converged
## Fitting Repeat 1
##
## # weights: 133
## initial value 448.264437
## final value 214.000000
## converged
## Fitting Repeat 2
##
## # weights: 133
## initial value 455.238635
## final value 214.000000
## converged
## Fitting Repeat 3
##
## # weights: 133
## initial value 547.050849
## final value 197.733645
## converged
## Fitting Repeat 4
##
## # weights: 133
## initial value 388.702381
## final value 214.000000
## converged
## Fitting Repeat 5
##
## # weights: 133
## initial value 493.682056
## final value 214.000000
## converged
## Fitting Repeat 1
##
## # weights: 33
## initial value 392.084102
## iter 10 value 186.080646
## iter 20 value 181.412502
## iter 30 value 181.408386
## iter 40 value 178.713410
## iter 50 value 168.640233
## iter 60 value 162.694633
## iter 70 value 158.896295
## iter 80 value 156.330797
## iter 90 value 151.124381
## iter 100 value 148.714022
## final value 148.714022
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 33
## initial value 505.303583
## iter 10 value 185.367333
## iter 20 value 182.883629
## iter 30 value 172.769850
## iter 40 value 165.114989
## iter 50 value 161.342308
## iter 60 value 149.529803
## iter 70 value 148.286214
## iter 80 value 148.216886
## final value 148.216878
## converged
## Fitting Repeat 3
##
## # weights: 33
## initial value 463.541749
## iter 10 value 185.705924
## iter 20 value 183.022788
## iter 30 value 157.407582
## iter 40 value 152.312754
## iter 50 value 149.357714
## iter 60 value 148.827987
## iter 70 value 148.097110
## iter 80 value 144.400110
## iter 90 value 142.878465
## iter 100 value 142.717007
## final value 142.717007
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 33
## initial value 368.317011
## iter 10 value 187.605312
## iter 20 value 182.469870
## iter 30 value 158.782844
## iter 40 value 157.010592
## iter 50 value 156.132485
## iter 60 value 154.760335
## iter 70 value 151.028994
## iter 80 value 150.028683
## iter 90 value 149.732395
## final value 149.730935
## converged
## Fitting Repeat 5
##
## # weights: 33
## initial value 560.336753
## iter 10 value 184.490794
## iter 20 value 181.412315
## iter 30 value 181.341737
## iter 40 value 176.979750
## iter 50 value 164.876352
## iter 60 value 160.485735
## iter 70 value 159.526019
## iter 80 value 156.328656
## iter 90 value 149.671576
## iter 100 value 148.038276
## final value 148.038276
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 83
## initial value 606.108512
## iter 10 value 229.919739
## iter 20 value 181.830794
## iter 30 value 173.469764
## iter 40 value 160.476907
## iter 50 value 159.510091
## iter 60 value 154.741457
## iter 70 value 124.102931
## iter 80 value 99.619379
## iter 90 value 94.784895
## iter 100 value 92.600998
## final value 92.600998
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 534.948905
## iter 10 value 181.077352
## iter 20 value 174.091547
## iter 30 value 162.115747
## iter 40 value 150.398081
## iter 50 value 148.383468
## iter 60 value 119.377322
## iter 70 value 103.907554
## iter 80 value 100.083298
## iter 90 value 96.910419
## iter 100 value 93.825673
## final value 93.825673
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 502.559502
## iter 10 value 212.119152
## iter 20 value 182.300373
## iter 30 value 174.457478
## iter 40 value 149.664618
## iter 50 value 139.013221
## iter 60 value 130.711891
## iter 70 value 127.599556
## iter 80 value 109.562502
## iter 90 value 82.217761
## iter 100 value 74.698712
## final value 74.698712
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 83
## initial value 444.123999
## iter 10 value 184.394804
## iter 20 value 152.459193
## iter 30 value 149.343708
## iter 40 value 147.669160
## iter 50 value 146.953840
## iter 60 value 144.785102
## iter 70 value 134.809074
## iter 80 value 107.433969
## iter 90 value 88.988688
## iter 100 value 85.105677
## final value 85.105677
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 83
## initial value 462.609401
## iter 10 value 223.054853
## iter 20 value 191.757963
## iter 30 value 142.600726
## iter 40 value 120.243774
## iter 50 value 106.625559
## iter 60 value 100.721404
## iter 70 value 100.432604
## iter 80 value 98.311424
## iter 90 value 82.427525
## iter 100 value 76.068941
## final value 76.068941
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 440.903538
## iter 10 value 207.793178
## iter 20 value 169.557237
## iter 30 value 160.265534
## iter 40 value 138.048440
## iter 50 value 131.458885
## iter 60 value 120.898293
## iter 70 value 118.196882
## iter 80 value 117.170748
## iter 90 value 106.757399
## iter 100 value 87.222356
## final value 87.222356
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 544.669346
## iter 10 value 212.779113
## iter 20 value 184.396545
## iter 30 value 174.449504
## iter 40 value 152.831713
## iter 50 value 113.307211
## iter 60 value 85.196879
## iter 70 value 77.495807
## iter 80 value 67.288566
## iter 90 value 63.442443
## iter 100 value 61.631290
## final value 61.631290
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 516.735343
## iter 10 value 249.030933
## iter 20 value 192.870314
## iter 30 value 147.353331
## iter 40 value 129.766626
## iter 50 value 105.491534
## iter 60 value 80.668439
## iter 70 value 76.005571
## iter 80 value 67.378644
## iter 90 value 66.479401
## iter 100 value 65.075169
## final value 65.075169
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 574.190474
## iter 10 value 204.714678
## iter 20 value 202.575637
## iter 30 value 186.188007
## iter 40 value 158.861980
## iter 50 value 142.040176
## iter 60 value 127.246628
## iter 70 value 115.144950
## iter 80 value 109.262877
## iter 90 value 103.531924
## iter 100 value 102.683929
## final value 102.683929
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 505.500490
## iter 10 value 234.973606
## iter 20 value 183.045314
## iter 30 value 174.157764
## iter 40 value 164.450747
## iter 50 value 157.051611
## iter 60 value 130.940057
## iter 70 value 98.755586
## iter 80 value 79.673223
## iter 90 value 74.626483
## iter 100 value 53.922419
## final value 53.922419
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 33
## initial value 438.578930
## iter 10 value 201.922004
## iter 20 value 193.399572
## iter 30 value 173.699679
## iter 40 value 163.262393
## iter 50 value 157.221363
## iter 60 value 139.783621
## iter 70 value 130.916688
## iter 80 value 127.199658
## iter 90 value 122.562485
## iter 100 value 122.251234
## final value 122.251234
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 33
## initial value 512.988984
## iter 10 value 214.739738
## iter 20 value 211.998528
## iter 30 value 211.305762
## iter 40 value 197.792033
## iter 50 value 186.146056
## iter 60 value 184.663450
## iter 70 value 183.321865
## iter 80 value 181.574192
## iter 90 value 179.911908
## iter 100 value 179.870062
## final value 179.870062
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 33
## initial value 349.856580
## iter 10 value 214.020766
## iter 20 value 209.910579
## iter 30 value 209.888629
## iter 40 value 209.880575
## iter 50 value 209.860176
## iter 60 value 209.691032
## iter 70 value 194.940680
## iter 80 value 193.625421
## iter 90 value 193.431318
## iter 100 value 192.087359
## final value 192.087359
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 33
## initial value 435.870824
## iter 10 value 214.584512
## iter 20 value 198.578786
## iter 30 value 197.131009
## iter 40 value 193.627358
## iter 50 value 190.980626
## iter 60 value 186.078469
## iter 70 value 185.686467
## iter 80 value 184.436863
## iter 90 value 182.856302
## iter 100 value 182.593855
## final value 182.593855
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 33
## initial value 598.701322
## iter 10 value 214.107232
## iter 20 value 214.104079
## iter 30 value 214.100033
## iter 40 value 214.094490
## iter 50 value 214.086122
## iter 60 value 214.071350
## iter 70 value 214.036113
## iter 80 value 213.824706
## iter 90 value 197.840712
## iter 100 value 194.743384
## final value 194.743384
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 83
## initial value 379.180273
## iter 10 value 201.629985
## iter 20 value 192.079961
## iter 30 value 172.034025
## iter 40 value 171.669282
## iter 50 value 171.101883
## iter 60 value 171.070094
## iter 70 value 171.030726
## iter 80 value 167.030427
## iter 90 value 165.948068
## iter 100 value 165.927572
## final value 165.927572
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 506.516214
## iter 10 value 214.174722
## iter 20 value 214.140844
## iter 30 value 209.779007
## iter 40 value 209.571597
## iter 50 value 207.887474
## iter 60 value 192.293901
## iter 70 value 191.597756
## iter 80 value 191.583671
## iter 90 value 191.365799
## iter 100 value 187.825850
## final value 187.825850
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 404.382748
## iter 10 value 213.919769
## iter 20 value 195.523766
## iter 30 value 180.013304
## iter 40 value 174.549370
## iter 50 value 173.168990
## iter 60 value 173.041259
## iter 70 value 172.873580
## iter 80 value 172.513674
## iter 90 value 172.114870
## iter 100 value 170.560693
## final value 170.560693
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 83
## initial value 529.032720
## iter 10 value 213.618483
## iter 20 value 209.964184
## iter 30 value 179.671771
## final value 179.590237
## converged
## Fitting Repeat 5
##
## # weights: 83
## initial value 489.331434
## iter 10 value 216.767400
## iter 20 value 200.543314
## iter 30 value 195.937122
## iter 40 value 189.130686
## iter 50 value 185.410933
## iter 60 value 162.932388
## iter 70 value 159.536296
## iter 80 value 153.639628
## iter 90 value 148.280102
## iter 100 value 146.831265
## final value 146.831265
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 396.474570
## iter 10 value 212.983320
## iter 20 value 199.787755
## iter 30 value 196.460641
## iter 40 value 193.211079
## iter 50 value 185.451316
## iter 60 value 176.304256
## iter 70 value 173.626389
## iter 80 value 158.947722
## iter 90 value 154.905332
## iter 100 value 154.865031
## final value 154.865031
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 501.362229
## iter 10 value 214.190207
## iter 20 value 213.340755
## iter 30 value 213.274765
## iter 40 value 213.243090
## iter 50 value 212.368854
## iter 60 value 211.041898
## iter 70 value 211.002095
## iter 80 value 209.353119
## iter 90 value 197.287566
## iter 100 value 181.610697
## final value 181.610697
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 727.939670
## iter 10 value 214.393046
## iter 20 value 181.935451
## iter 30 value 179.675921
## iter 40 value 179.614440
## iter 50 value 154.297115
## iter 60 value 100.119997
## iter 70 value 89.709856
## iter 80 value 79.128730
## iter 90 value 71.659519
## iter 100 value 71.130234
## final value 71.130234
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 428.712804
## iter 10 value 220.293288
## iter 20 value 220.266954
## iter 30 value 220.240182
## iter 40 value 220.212473
## iter 50 value 220.182433
## iter 60 value 220.144142
## iter 70 value 220.003791
## iter 80 value 203.778225
## iter 90 value 195.454399
## iter 100 value 194.933742
## final value 194.933742
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 474.379367
## iter 10 value 193.932456
## iter 20 value 179.731981
## iter 30 value 179.632883
## iter 40 value 179.599131
## iter 50 value 149.737269
## iter 60 value 143.211993
## iter 70 value 142.324811
## iter 80 value 139.582891
## iter 90 value 138.022834
## iter 100 value 135.089575
## final value 135.089575
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 33
## initial value 385.825735
## final value 216.000000
## converged
## Fitting Repeat 2
##
## # weights: 33
## initial value 381.652163
## final value 216.000000
## converged
## Fitting Repeat 3
##
## # weights: 33
## initial value 411.125861
## final value 216.000000
## converged
## Fitting Repeat 4
##
## # weights: 33
## initial value 462.780248
## final value 216.000000
## converged
## Fitting Repeat 5
##
## # weights: 33
## initial value 433.247785
## final value 216.000000
## converged
## Fitting Repeat 1
##
## # weights: 83
## initial value 463.634618
## final value 216.000000
## converged
## Fitting Repeat 2
##
## # weights: 83
## initial value 507.855296
## final value 216.000000
## converged
## Fitting Repeat 3
##
## # weights: 83
## initial value 578.829927
## final value 216.000000
## converged
## Fitting Repeat 4
##
## # weights: 83
## initial value 604.225912
## final value 216.000000
## converged
## Fitting Repeat 5
##
## # weights: 83
## initial value 365.419714
## iter 10 value 199.884259
## iter 10 value 199.884259
## iter 10 value 199.884259
## final value 199.884259
## converged
## Fitting Repeat 1
##
## # weights: 133
## initial value 410.240162
## final value 215.999975
## converged
## Fitting Repeat 2
##
## # weights: 133
## initial value 403.836326
## iter 10 value 215.991507
## iter 20 value 215.990723
## iter 30 value 215.989780
## iter 40 value 215.988624
## iter 50 value 215.987174
## iter 60 value 215.985303
## iter 70 value 215.982797
## iter 80 value 215.979266
## iter 90 value 215.973928
## iter 100 value 215.964932
## final value 215.964932
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 441.870318
## final value 216.000000
## converged
## Fitting Repeat 4
##
## # weights: 133
## initial value 449.308696
## final value 216.000000
## converged
## Fitting Repeat 5
##
## # weights: 133
## initial value 441.919302
## final value 215.999956
## converged
## Fitting Repeat 1
##
## # weights: 33
## initial value 466.512392
## iter 10 value 208.630569
## iter 20 value 184.752321
## iter 30 value 168.775896
## iter 40 value 164.837045
## iter 50 value 160.210138
## iter 60 value 157.942053
## iter 70 value 156.969747
## iter 80 value 155.463702
## iter 90 value 154.242528
## final value 154.240762
## converged
## Fitting Repeat 2
##
## # weights: 33
## initial value 522.268593
## iter 10 value 200.625331
## iter 20 value 184.906499
## iter 30 value 182.246646
## iter 40 value 168.747043
## iter 50 value 166.654816
## iter 60 value 163.986476
## iter 70 value 163.033225
## iter 80 value 161.205933
## iter 90 value 158.368710
## iter 100 value 150.045072
## final value 150.045072
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 33
## initial value 433.231822
## iter 10 value 193.099442
## iter 20 value 183.190211
## iter 30 value 183.169988
## iter 40 value 183.007497
## iter 50 value 169.848167
## iter 60 value 165.294319
## iter 70 value 164.816162
## iter 80 value 158.992003
## iter 90 value 149.803534
## iter 100 value 149.418029
## final value 149.418029
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 33
## initial value 485.984654
## iter 10 value 191.448720
## iter 20 value 184.843456
## iter 30 value 181.388933
## iter 40 value 173.123904
## iter 50 value 168.167594
## iter 60 value 167.685515
## iter 70 value 166.608305
## iter 80 value 166.163310
## iter 90 value 165.867600
## iter 100 value 162.911548
## final value 162.911548
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 33
## initial value 437.913047
## iter 10 value 194.728000
## iter 20 value 185.464602
## iter 30 value 185.021811
## iter 40 value 184.723211
## iter 50 value 170.568707
## iter 60 value 165.497504
## iter 70 value 161.562371
## iter 80 value 158.772719
## iter 90 value 153.723074
## iter 100 value 151.180876
## final value 151.180876
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 83
## initial value 391.023861
## iter 10 value 202.586913
## iter 20 value 169.711362
## iter 30 value 157.473634
## iter 40 value 144.317308
## iter 50 value 138.890785
## iter 60 value 134.252960
## iter 70 value 98.378823
## iter 80 value 91.543960
## iter 90 value 90.803019
## iter 100 value 89.600502
## final value 89.600502
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 437.567626
## iter 10 value 204.807126
## iter 20 value 167.261516
## iter 30 value 161.717513
## iter 40 value 158.950738
## iter 50 value 156.071612
## iter 60 value 138.515127
## iter 70 value 110.267795
## iter 80 value 106.112783
## iter 90 value 103.257779
## iter 100 value 87.679834
## final value 87.679834
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 521.376415
## iter 10 value 212.317158
## iter 20 value 185.829659
## iter 30 value 180.795599
## iter 40 value 152.960746
## iter 50 value 148.119403
## iter 60 value 145.152494
## iter 70 value 140.410991
## iter 80 value 134.853831
## iter 90 value 115.586192
## iter 100 value 97.773190
## final value 97.773190
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 83
## initial value 443.793629
## iter 10 value 198.045299
## iter 20 value 181.108166
## iter 30 value 157.829345
## iter 40 value 156.380879
## iter 50 value 137.797531
## iter 60 value 127.222635
## iter 70 value 122.564217
## iter 80 value 120.241111
## iter 90 value 119.359432
## iter 100 value 119.154045
## final value 119.154045
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 83
## initial value 422.034305
## iter 10 value 197.770655
## iter 20 value 171.673581
## iter 30 value 158.328759
## iter 40 value 129.969328
## iter 50 value 120.846432
## iter 60 value 110.054496
## iter 70 value 107.064478
## iter 80 value 104.167143
## iter 90 value 102.953330
## iter 100 value 100.999008
## final value 100.999008
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 483.420423
## iter 10 value 212.682319
## iter 20 value 169.640768
## iter 30 value 160.213577
## iter 40 value 155.932068
## iter 50 value 142.545162
## iter 60 value 135.945239
## iter 70 value 128.281587
## iter 80 value 120.178393
## iter 90 value 94.754996
## iter 100 value 70.396982
## final value 70.396982
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 448.145618
## iter 10 value 245.126032
## iter 20 value 202.351883
## iter 30 value 183.478989
## iter 40 value 170.947941
## iter 50 value 162.126317
## iter 60 value 119.390290
## iter 70 value 113.774044
## iter 80 value 89.562601
## iter 90 value 77.734372
## iter 100 value 71.102709
## final value 71.102709
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 462.112315
## iter 10 value 216.350152
## iter 20 value 185.151012
## iter 30 value 178.211691
## iter 40 value 152.892934
## iter 50 value 139.339641
## iter 60 value 124.011541
## iter 70 value 81.102347
## iter 80 value 63.659145
## iter 90 value 60.537878
## iter 100 value 57.298814
## final value 57.298814
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 445.691442
## iter 10 value 296.205635
## iter 20 value 263.906795
## iter 30 value 195.469261
## iter 40 value 182.824951
## iter 50 value 163.180505
## iter 60 value 138.448035
## iter 70 value 110.645389
## iter 80 value 101.352478
## iter 90 value 90.323326
## iter 100 value 73.284346
## final value 73.284346
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 508.857473
## iter 10 value 213.734582
## iter 20 value 171.103707
## iter 30 value 161.209946
## iter 40 value 159.004254
## iter 50 value 127.700806
## iter 60 value 104.283941
## iter 70 value 88.629971
## iter 80 value 84.281690
## iter 90 value 75.705693
## iter 100 value 66.093789
## final value 66.093789
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 33
## initial value 489.984910
## iter 10 value 202.076671
## iter 20 value 181.452013
## iter 30 value 181.379816
## iter 40 value 181.277762
## iter 50 value 158.335670
## iter 60 value 154.007899
## iter 70 value 153.406281
## iter 80 value 153.363633
## iter 90 value 152.310319
## iter 100 value 151.780246
## final value 151.780246
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 33
## initial value 558.035904
## iter 10 value 216.170576
## iter 20 value 200.423839
## iter 30 value 187.474696
## iter 40 value 182.974498
## iter 50 value 181.532618
## iter 60 value 181.429696
## iter 70 value 181.414179
## iter 80 value 181.331786
## iter 90 value 158.020970
## iter 100 value 156.173993
## final value 156.173993
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 33
## initial value 428.826920
## iter 10 value 216.084779
## iter 20 value 216.076783
## iter 30 value 216.064364
## iter 40 value 216.040764
## iter 50 value 215.969144
## iter 60 value 211.505038
## iter 70 value 211.225471
## iter 80 value 204.917167
## iter 90 value 198.732821
## iter 100 value 196.312634
## final value 196.312634
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 33
## initial value 429.037504
## iter 10 value 214.644582
## iter 20 value 199.090045
## iter 30 value 192.119647
## iter 40 value 192.087610
## iter 50 value 190.286136
## iter 60 value 187.643243
## iter 70 value 185.946422
## iter 80 value 181.562209
## iter 90 value 181.374621
## final value 181.374607
## converged
## Fitting Repeat 5
##
## # weights: 33
## initial value 382.894400
## iter 10 value 201.646394
## iter 20 value 189.280174
## iter 30 value 186.274777
## iter 40 value 182.433065
## iter 50 value 181.420782
## iter 60 value 181.374228
## iter 60 value 181.374228
## iter 60 value 181.374228
## final value 181.374228
## converged
## Fitting Repeat 1
##
## # weights: 83
## initial value 521.890855
## iter 10 value 216.209141
## iter 20 value 213.141824
## iter 30 value 194.165273
## iter 40 value 193.038315
## iter 50 value 168.631535
## iter 60 value 161.309803
## iter 70 value 156.660584
## iter 80 value 156.302141
## iter 90 value 156.290655
## iter 100 value 156.156038
## final value 156.156038
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 431.863430
## iter 10 value 216.201551
## iter 20 value 199.990738
## iter 30 value 180.581778
## iter 40 value 179.758769
## iter 50 value 179.049979
## iter 60 value 178.650258
## iter 70 value 177.824785
## iter 80 value 172.805690
## iter 90 value 172.015312
## iter 100 value 171.744666
## final value 171.744666
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 477.780248
## iter 10 value 201.118554
## iter 20 value 183.862818
## iter 30 value 181.383292
## iter 40 value 179.712438
## iter 50 value 153.720689
## iter 60 value 151.623904
## iter 70 value 150.418452
## iter 80 value 150.374012
## iter 90 value 149.673904
## iter 100 value 149.487538
## final value 149.487538
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 83
## initial value 586.309164
## iter 10 value 207.116728
## iter 20 value 200.050842
## iter 30 value 194.128582
## iter 40 value 194.040100
## iter 50 value 192.446264
## iter 60 value 186.235097
## iter 70 value 186.174908
## iter 80 value 183.034284
## iter 90 value 181.613053
## iter 100 value 181.419122
## final value 181.419122
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 83
## initial value 454.345509
## iter 10 value 216.337607
## iter 20 value 216.142376
## iter 30 value 211.927436
## iter 40 value 181.723974
## iter 50 value 181.262659
## iter 60 value 167.618089
## iter 70 value 162.080047
## iter 80 value 161.992814
## iter 90 value 161.983443
## iter 100 value 161.961475
## final value 161.961475
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 562.100106
## iter 10 value 216.318118
## iter 20 value 213.257583
## iter 30 value 197.678430
## iter 40 value 195.566372
## iter 50 value 194.123992
## iter 60 value 189.876921
## iter 70 value 189.293108
## iter 80 value 184.986965
## iter 90 value 184.738418
## iter 100 value 181.690092
## final value 181.690092
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 396.787705
## iter 10 value 202.829308
## iter 20 value 198.772537
## iter 30 value 195.330093
## iter 40 value 192.203685
## iter 50 value 190.816392
## iter 60 value 190.771537
## iter 70 value 187.970676
## iter 80 value 187.554549
## iter 90 value 163.674900
## iter 100 value 161.089921
## final value 161.089921
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 398.042364
## iter 10 value 214.794187
## iter 20 value 163.946204
## iter 30 value 149.679038
## iter 40 value 115.890340
## iter 50 value 109.180462
## iter 60 value 93.249860
## iter 70 value 87.113256
## iter 80 value 86.933988
## iter 90 value 86.901225
## iter 100 value 86.866890
## final value 86.866890
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 473.965040
## iter 10 value 216.182333
## iter 20 value 186.880493
## iter 30 value 153.268929
## iter 40 value 146.066509
## iter 50 value 145.692297
## iter 60 value 145.543687
## iter 70 value 145.513835
## iter 80 value 144.817763
## iter 90 value 144.793983
## iter 100 value 144.791307
## final value 144.791307
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 480.239685
## iter 10 value 216.192545
## iter 20 value 195.044229
## iter 30 value 189.947708
## iter 40 value 169.030681
## iter 50 value 167.831109
## iter 60 value 163.521086
## iter 70 value 163.148694
## iter 80 value 162.990339
## iter 90 value 161.698800
## iter 100 value 152.874136
## final value 152.874136
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 33
## initial value 514.756540
## final value 216.000000
## converged
## Fitting Repeat 2
##
## # weights: 33
## initial value 366.170715
## final value 215.999631
## converged
## Fitting Repeat 3
##
## # weights: 33
## initial value 402.492999
## final value 216.000000
## converged
## Fitting Repeat 4
##
## # weights: 33
## initial value 460.417460
## iter 10 value 215.788526
## iter 20 value 199.973192
## final value 199.884259
## converged
## Fitting Repeat 5
##
## # weights: 33
## initial value 498.043365
## final value 215.999894
## converged
## Fitting Repeat 1
##
## # weights: 83
## initial value 640.854931
## final value 216.000000
## converged
## Fitting Repeat 2
##
## # weights: 83
## initial value 473.620671
## final value 215.999903
## converged
## Fitting Repeat 3
##
## # weights: 83
## initial value 413.508078
## final value 216.000000
## converged
## Fitting Repeat 4
##
## # weights: 83
## initial value 610.229709
## final value 216.000000
## converged
## Fitting Repeat 5
##
## # weights: 83
## initial value 328.136919
## final value 216.000000
## converged
## Fitting Repeat 1
##
## # weights: 133
## initial value 551.015720
## final value 216.000000
## converged
## Fitting Repeat 2
##
## # weights: 133
## initial value 505.473385
## final value 215.999640
## converged
## Fitting Repeat 3
##
## # weights: 133
## initial value 437.975658
## final value 216.000000
## converged
## Fitting Repeat 4
##
## # weights: 133
## initial value 367.451750
## iter 10 value 313.999011
## iter 20 value 313.998970
## iter 30 value 313.998926
## iter 40 value 313.998878
## iter 50 value 313.998826
## iter 60 value 313.998768
## iter 70 value 313.998704
## iter 80 value 313.998633
## iter 90 value 313.998555
## iter 100 value 313.998466
## final value 313.998466
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 539.782073
## final value 216.000000
## converged
## Fitting Repeat 1
##
## # weights: 33
## initial value 432.217682
## iter 10 value 191.342983
## iter 20 value 184.877935
## iter 30 value 184.604176
## iter 40 value 183.889822
## iter 50 value 179.714710
## iter 60 value 165.796962
## iter 70 value 165.290760
## iter 80 value 164.867897
## iter 90 value 158.947698
## iter 100 value 151.930978
## final value 151.930978
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 33
## initial value 344.234673
## iter 10 value 202.049450
## iter 20 value 185.149420
## iter 30 value 183.209117
## iter 40 value 183.201178
## iter 50 value 183.002809
## iter 60 value 167.320339
## iter 70 value 163.461780
## iter 80 value 161.772551
## iter 90 value 152.936264
## iter 100 value 149.635862
## final value 149.635862
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 33
## initial value 430.525527
## iter 10 value 189.975574
## iter 20 value 184.072651
## iter 30 value 167.514485
## iter 40 value 162.846275
## iter 50 value 162.477649
## iter 60 value 161.555946
## iter 70 value 158.940133
## iter 80 value 151.943548
## iter 90 value 151.232243
## iter 100 value 151.230811
## final value 151.230811
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 33
## initial value 459.941292
## iter 10 value 193.001591
## iter 20 value 183.849222
## iter 30 value 167.116841
## iter 40 value 166.018831
## iter 50 value 164.212980
## iter 60 value 163.788780
## iter 70 value 161.275712
## iter 80 value 156.381699
## iter 90 value 151.298050
## iter 100 value 149.713178
## final value 149.713178
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 33
## initial value 523.368505
## iter 10 value 196.243426
## iter 20 value 184.940546
## iter 30 value 184.877449
## iter 40 value 171.890905
## iter 50 value 167.117108
## iter 60 value 162.364284
## iter 70 value 159.646329
## iter 80 value 150.966096
## iter 90 value 148.977278
## final value 148.964541
## converged
## Fitting Repeat 1
##
## # weights: 83
## initial value 445.160737
## iter 10 value 229.385274
## iter 20 value 187.026408
## iter 30 value 173.824459
## iter 40 value 160.733107
## iter 50 value 157.512932
## iter 60 value 156.550402
## iter 70 value 153.638026
## iter 80 value 126.547825
## iter 90 value 121.131189
## iter 100 value 114.828766
## final value 114.828766
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 399.764140
## iter 10 value 205.575663
## iter 20 value 183.210243
## iter 30 value 168.740254
## iter 40 value 149.450051
## iter 50 value 139.071316
## iter 60 value 129.690869
## iter 70 value 126.348534
## iter 80 value 123.692959
## iter 90 value 101.927421
## iter 100 value 97.115455
## final value 97.115455
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 530.482909
## iter 10 value 203.984011
## iter 20 value 184.272322
## iter 30 value 162.439705
## iter 40 value 147.437982
## iter 50 value 124.264576
## iter 60 value 114.095093
## iter 70 value 100.152099
## iter 80 value 97.762655
## iter 90 value 92.655081
## iter 100 value 79.786052
## final value 79.786052
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 83
## initial value 480.985953
## iter 10 value 359.889854
## iter 20 value 166.263303
## iter 30 value 161.305424
## iter 40 value 145.149056
## iter 50 value 130.473183
## iter 60 value 127.861890
## iter 70 value 126.564418
## iter 80 value 124.457141
## iter 90 value 112.356188
## iter 100 value 91.573006
## final value 91.573006
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 83
## initial value 449.465503
## iter 10 value 215.476885
## iter 20 value 182.691594
## iter 30 value 168.267718
## iter 40 value 160.030790
## iter 50 value 135.015177
## iter 60 value 127.987872
## iter 70 value 123.783567
## iter 80 value 103.997382
## iter 90 value 95.672466
## iter 100 value 91.083553
## final value 91.083553
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 359.937096
## iter 10 value 236.643843
## iter 20 value 188.590848
## iter 30 value 185.725662
## iter 40 value 167.039677
## iter 50 value 161.261772
## iter 60 value 139.661906
## iter 70 value 100.119644
## iter 80 value 92.141047
## iter 90 value 88.833946
## iter 100 value 84.648895
## final value 84.648895
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 491.952228
## iter 10 value 212.942120
## iter 20 value 182.222544
## iter 30 value 159.918438
## iter 40 value 151.314084
## iter 50 value 146.502219
## iter 60 value 121.614256
## iter 70 value 110.942116
## iter 80 value 108.346651
## iter 90 value 96.681773
## iter 100 value 85.134161
## final value 85.134161
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 469.857931
## iter 10 value 225.072964
## iter 20 value 171.524015
## iter 30 value 146.120833
## iter 40 value 107.957823
## iter 50 value 90.218276
## iter 60 value 85.244529
## iter 70 value 78.067566
## iter 80 value 65.400965
## iter 90 value 52.477319
## iter 100 value 50.117995
## final value 50.117995
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 507.636422
## iter 10 value 203.423079
## iter 20 value 183.259600
## iter 30 value 137.683908
## iter 40 value 132.392190
## iter 50 value 110.568431
## iter 60 value 92.145307
## iter 70 value 75.195331
## iter 80 value 67.340412
## iter 90 value 60.477756
## iter 100 value 46.038419
## final value 46.038419
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 548.018961
## iter 10 value 218.938680
## iter 20 value 159.941534
## iter 30 value 152.262494
## iter 40 value 148.324974
## iter 50 value 120.735158
## iter 60 value 107.376417
## iter 70 value 104.096988
## iter 80 value 100.508012
## iter 90 value 99.215247
## iter 100 value 97.152457
## final value 97.152457
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 33
## initial value 475.741419
## iter 10 value 215.826919
## iter 20 value 199.974439
## iter 30 value 196.630722
## iter 40 value 196.101891
## iter 50 value 195.028574
## iter 60 value 194.918585
## iter 70 value 190.556094
## iter 80 value 189.939138
## iter 90 value 186.047931
## iter 100 value 184.436649
## final value 184.436649
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 33
## initial value 508.324594
## iter 10 value 215.732519
## iter 20 value 211.185153
## iter 30 value 192.157508
## iter 40 value 191.285120
## iter 50 value 165.721387
## iter 60 value 151.769787
## iter 70 value 150.465345
## iter 80 value 148.959509
## iter 90 value 146.341523
## iter 100 value 144.817171
## final value 144.817171
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 33
## initial value 397.901398
## iter 10 value 199.980990
## iter 20 value 199.446480
## iter 30 value 198.444791
## iter 40 value 196.778446
## iter 50 value 196.756528
## iter 60 value 193.535051
## iter 70 value 189.108156
## iter 80 value 183.875914
## iter 90 value 181.551699
## iter 100 value 181.542431
## final value 181.542431
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 33
## initial value 495.594389
## iter 10 value 216.119065
## iter 20 value 216.111376
## iter 30 value 216.099335
## iter 40 value 216.076065
## iter 50 value 216.003485
## iter 60 value 213.251634
## iter 70 value 211.132240
## iter 80 value 208.731562
## iter 90 value 193.755895
## iter 100 value 192.644352
## final value 192.644352
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 33
## initial value 480.983179
## iter 10 value 216.312701
## iter 20 value 200.423572
## iter 30 value 194.451496
## iter 40 value 182.654981
## iter 50 value 181.395057
## final value 181.383894
## converged
## Fitting Repeat 1
##
## # weights: 83
## initial value 363.341438
## iter 10 value 216.248572
## iter 20 value 216.075879
## iter 30 value 200.122955
## iter 40 value 198.484311
## iter 50 value 179.959866
## iter 60 value 177.294923
## iter 70 value 176.901385
## iter 80 value 176.445086
## iter 90 value 169.085638
## iter 100 value 168.929257
## final value 168.929257
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 386.379995
## iter 10 value 216.139519
## iter 20 value 212.602575
## iter 30 value 208.507281
## iter 40 value 208.374390
## iter 50 value 208.299823
## iter 60 value 192.227200
## iter 70 value 191.478767
## iter 80 value 186.048827
## iter 90 value 181.549931
## iter 100 value 181.462233
## final value 181.462233
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 410.191063
## iter 10 value 201.202862
## iter 20 value 200.322538
## iter 30 value 181.410529
## final value 181.381477
## converged
## Fitting Repeat 4
##
## # weights: 83
## initial value 398.332302
## iter 10 value 216.264900
## iter 20 value 216.177444
## iter 30 value 199.511339
## iter 40 value 180.696511
## iter 50 value 180.021183
## iter 60 value 179.926448
## iter 70 value 174.028327
## iter 80 value 173.854408
## iter 90 value 171.331569
## iter 100 value 161.477210
## final value 161.477210
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 83
## initial value 428.093939
## iter 10 value 193.917324
## iter 20 value 184.784950
## iter 30 value 182.078224
## iter 40 value 181.389299
## iter 50 value 181.383042
## iter 60 value 181.271862
## iter 70 value 179.052834
## iter 80 value 162.226360
## iter 90 value 157.436189
## iter 100 value 157.222995
## final value 157.222995
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 418.356411
## iter 10 value 219.362847
## iter 20 value 219.287511
## iter 30 value 203.239580
## iter 40 value 197.940937
## iter 50 value 187.141267
## iter 60 value 178.007748
## iter 70 value 177.543623
## iter 80 value 172.076559
## iter 90 value 169.929423
## iter 100 value 169.821213
## final value 169.821213
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 416.536631
## iter 10 value 215.899674
## iter 20 value 214.968215
## iter 30 value 198.942567
## iter 40 value 198.624614
## iter 50 value 196.762009
## iter 60 value 186.146107
## iter 70 value 163.788666
## iter 80 value 150.702567
## iter 90 value 140.388736
## iter 100 value 137.619654
## final value 137.619654
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 568.989790
## iter 10 value 216.934050
## iter 20 value 212.910828
## iter 30 value 187.875329
## iter 40 value 185.701767
## iter 50 value 183.418058
## iter 60 value 182.223128
## iter 70 value 179.663654
## iter 80 value 155.013525
## iter 90 value 152.259371
## iter 100 value 147.026869
## final value 147.026869
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 452.409435
## iter 10 value 211.579746
## iter 20 value 208.212994
## iter 30 value 192.272852
## iter 40 value 192.144874
## iter 50 value 191.878326
## iter 60 value 184.007536
## iter 70 value 181.554715
## iter 80 value 181.547415
## iter 90 value 181.511929
## iter 100 value 181.386076
## final value 181.386076
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 536.249363
## iter 10 value 217.627336
## iter 20 value 217.619642
## iter 30 value 217.611360
## iter 40 value 217.601782
## iter 50 value 214.156209
## iter 60 value 205.890580
## iter 70 value 205.688262
## iter 80 value 203.817362
## iter 90 value 187.034447
## iter 100 value 182.586935
## final value 182.586935
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 33
## initial value 416.504363
## final value 214.000000
## converged
## Fitting Repeat 2
##
## # weights: 33
## initial value 472.314951
## iter 10 value 213.988391
## iter 20 value 213.986878
## iter 30 value 213.984914
## iter 40 value 213.982261
## iter 50 value 213.978485
## iter 60 value 213.972685
## iter 70 value 213.962657
## iter 80 value 213.941257
## iter 90 value 213.866000
## iter 100 value 201.569070
## final value 201.569070
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 33
## initial value 514.690019
## final value 214.000000
## converged
## Fitting Repeat 4
##
## # weights: 33
## initial value 475.888566
## final value 214.000000
## converged
## Fitting Repeat 5
##
## # weights: 33
## initial value 390.498130
## final value 214.000000
## converged
## Fitting Repeat 1
##
## # weights: 83
## initial value 347.875317
## final value 214.000000
## converged
## Fitting Repeat 2
##
## # weights: 83
## initial value 421.471569
## final value 213.999900
## converged
## Fitting Repeat 3
##
## # weights: 83
## initial value 529.604863
## iter 10 value 213.829597
## final value 210.841121
## converged
## Fitting Repeat 4
##
## # weights: 83
## initial value 379.859823
## final value 214.000000
## converged
## Fitting Repeat 5
##
## # weights: 83
## initial value 430.426096
## final value 214.000000
## converged
## Fitting Repeat 1
##
## # weights: 133
## initial value 507.848450
## final value 214.000000
## converged
## Fitting Repeat 2
##
## # weights: 133
## initial value 481.323051
## final value 214.000000
## converged
## Fitting Repeat 3
##
## # weights: 133
## initial value 471.775915
## final value 214.000000
## converged
## Fitting Repeat 4
##
## # weights: 133
## initial value 721.349196
## final value 214.000000
## converged
## Fitting Repeat 5
##
## # weights: 133
## initial value 545.475352
## final value 214.000000
## converged
## Fitting Repeat 1
##
## # weights: 33
## initial value 462.679780
## iter 10 value 184.834332
## iter 20 value 173.266378
## iter 30 value 153.752555
## iter 40 value 151.676214
## iter 50 value 151.135453
## iter 60 value 150.668448
## iter 70 value 150.173701
## iter 80 value 149.820592
## iter 90 value 149.770648
## iter 100 value 149.017466
## final value 149.017466
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 33
## initial value 446.261528
## iter 10 value 201.421823
## iter 20 value 183.485153
## iter 30 value 178.121138
## iter 40 value 159.113261
## iter 50 value 156.842434
## iter 60 value 155.909098
## iter 70 value 155.740970
## iter 80 value 155.615995
## iter 90 value 155.555783
## iter 100 value 154.976504
## final value 154.976504
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 33
## initial value 428.115089
## iter 10 value 195.617191
## iter 20 value 177.695183
## iter 30 value 150.988999
## iter 40 value 148.598503
## iter 50 value 148.399892
## iter 60 value 148.376877
## iter 70 value 148.240711
## iter 80 value 145.077619
## iter 90 value 142.770792
## iter 100 value 142.557464
## final value 142.557464
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 33
## initial value 477.917560
## iter 10 value 186.327119
## iter 20 value 182.054696
## iter 30 value 181.425333
## iter 40 value 163.867818
## iter 50 value 157.530989
## iter 60 value 151.998037
## iter 70 value 151.095681
## iter 80 value 149.290976
## iter 90 value 148.663553
## iter 100 value 148.270747
## final value 148.270747
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 33
## initial value 434.112074
## iter 10 value 190.694900
## iter 20 value 183.594959
## iter 30 value 183.083833
## iter 40 value 181.725909
## iter 50 value 157.454033
## iter 60 value 151.743862
## iter 70 value 150.009762
## iter 80 value 149.260878
## iter 90 value 148.895356
## iter 100 value 148.463782
## final value 148.463782
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 83
## initial value 596.138803
## iter 10 value 195.652913
## iter 20 value 151.586883
## iter 30 value 136.927945
## iter 40 value 133.025274
## iter 50 value 94.756417
## iter 60 value 85.688904
## iter 70 value 83.700670
## iter 80 value 82.584127
## iter 90 value 81.177671
## iter 100 value 80.139545
## final value 80.139545
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 449.131931
## iter 10 value 202.467263
## iter 20 value 183.416676
## iter 30 value 167.926113
## iter 40 value 154.554652
## iter 50 value 150.799255
## iter 60 value 148.345487
## iter 70 value 115.107933
## iter 80 value 106.480172
## iter 90 value 104.146034
## iter 100 value 99.775802
## final value 99.775802
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 363.970209
## iter 10 value 207.693969
## iter 20 value 181.689010
## iter 30 value 180.569553
## iter 40 value 173.877915
## iter 50 value 152.239354
## iter 60 value 147.602778
## iter 70 value 147.065992
## iter 80 value 137.159439
## iter 90 value 124.618057
## iter 100 value 112.143081
## final value 112.143081
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 83
## initial value 429.736251
## iter 10 value 196.397650
## iter 20 value 182.651954
## iter 30 value 165.116279
## iter 40 value 146.580606
## iter 50 value 139.104346
## iter 60 value 134.340957
## iter 70 value 129.859120
## iter 80 value 127.293583
## iter 90 value 125.975820
## iter 100 value 122.451913
## final value 122.451913
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 83
## initial value 490.294755
## iter 10 value 185.912664
## iter 20 value 174.523155
## iter 30 value 150.966827
## iter 40 value 148.682372
## iter 50 value 147.669791
## iter 60 value 138.725621
## iter 70 value 131.324153
## iter 80 value 124.047778
## iter 90 value 122.849487
## iter 100 value 119.785852
## final value 119.785852
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 547.729684
## iter 10 value 195.351929
## iter 20 value 168.356704
## iter 30 value 161.999935
## iter 40 value 149.684476
## iter 50 value 119.512382
## iter 60 value 104.721622
## iter 70 value 95.561834
## iter 80 value 90.478774
## iter 90 value 84.495693
## iter 100 value 74.424804
## final value 74.424804
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 371.033762
## iter 10 value 206.049723
## iter 20 value 171.497032
## iter 30 value 156.033140
## iter 40 value 143.608620
## iter 50 value 128.563131
## iter 60 value 99.174950
## iter 70 value 89.224041
## iter 80 value 82.845084
## iter 90 value 66.703969
## iter 100 value 62.362445
## final value 62.362445
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 455.902902
## iter 10 value 176.086973
## iter 20 value 162.386875
## iter 30 value 149.528226
## iter 40 value 130.327134
## iter 50 value 125.219433
## iter 60 value 116.019641
## iter 70 value 93.268922
## iter 80 value 75.012409
## iter 90 value 59.651748
## iter 100 value 55.197311
## final value 55.197311
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 611.383112
## iter 10 value 208.734332
## iter 20 value 165.861620
## iter 30 value 147.615416
## iter 40 value 116.418854
## iter 50 value 88.112350
## iter 60 value 73.826354
## iter 70 value 69.855062
## iter 80 value 61.880510
## iter 90 value 54.610601
## iter 100 value 47.337552
## final value 47.337552
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 452.989927
## iter 10 value 184.409888
## iter 20 value 173.901116
## iter 30 value 165.770984
## iter 40 value 159.787910
## iter 50 value 149.695432
## iter 60 value 113.170743
## iter 70 value 101.446387
## iter 80 value 90.685149
## iter 90 value 86.474493
## iter 100 value 85.540364
## final value 85.540364
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 33
## initial value 399.896968
## iter 10 value 198.381669
## iter 20 value 194.918399
## iter 30 value 193.491676
## iter 40 value 186.972620
## iter 50 value 184.380922
## iter 60 value 183.624954
## iter 70 value 181.241497
## iter 80 value 181.220833
## iter 90 value 181.215960
## iter 100 value 180.200006
## final value 180.200006
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 33
## initial value 522.012856
## iter 10 value 214.272979
## iter 20 value 213.259175
## iter 30 value 209.858098
## iter 40 value 208.747966
## iter 50 value 208.489040
## iter 60 value 192.543606
## iter 70 value 192.018986
## iter 80 value 190.156607
## iter 90 value 187.874372
## iter 100 value 184.364342
## final value 184.364342
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 33
## initial value 478.714395
## iter 10 value 197.764336
## iter 20 value 194.402603
## iter 30 value 190.781341
## iter 40 value 189.640060
## iter 50 value 186.468383
## iter 60 value 184.732271
## iter 70 value 182.213815
## iter 80 value 181.656724
## iter 90 value 180.518707
## iter 100 value 180.363226
## final value 180.363226
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 33
## initial value 471.425399
## iter 10 value 213.924979
## iter 20 value 201.949511
## iter 30 value 192.123641
## iter 40 value 191.576476
## iter 50 value 187.525291
## iter 60 value 185.959447
## iter 70 value 184.368796
## iter 80 value 184.155490
## iter 90 value 180.002713
## iter 100 value 179.672640
## final value 179.672640
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 33
## initial value 459.514253
## iter 10 value 213.792197
## iter 20 value 198.208069
## iter 30 value 193.316770
## iter 40 value 190.156602
## iter 50 value 189.967290
## iter 60 value 187.528946
## iter 70 value 184.131737
## iter 80 value 184.069941
## iter 90 value 181.015519
## iter 100 value 180.922583
## final value 180.922583
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 83
## initial value 447.340570
## iter 10 value 214.307579
## iter 20 value 209.367359
## iter 30 value 198.024232
## iter 40 value 178.697736
## iter 50 value 167.925100
## iter 60 value 163.474438
## iter 70 value 163.379339
## iter 80 value 163.369288
## iter 90 value 163.224933
## iter 100 value 163.043763
## final value 163.043763
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 83
## initial value 501.128425
## iter 10 value 214.140854
## iter 20 value 214.137028
## iter 30 value 214.130597
## iter 40 value 214.115015
## iter 50 value 197.360042
## iter 60 value 193.420147
## iter 70 value 192.363257
## iter 80 value 151.199757
## iter 90 value 141.672227
## iter 100 value 140.977624
## final value 140.977624
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 83
## initial value 555.236710
## iter 10 value 214.211319
## iter 20 value 197.977089
## iter 30 value 196.315251
## iter 40 value 193.234336
## iter 50 value 190.717814
## iter 60 value 178.105003
## iter 70 value 177.416945
## iter 80 value 177.138818
## iter 90 value 175.743987
## iter 100 value 172.696154
## final value 172.696154
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 83
## initial value 429.850372
## iter 10 value 191.891506
## iter 20 value 179.725236
## iter 30 value 179.701667
## iter 40 value 165.826787
## iter 50 value 153.850255
## iter 60 value 149.650036
## iter 70 value 149.583107
## iter 80 value 149.514964
## iter 90 value 149.485964
## iter 100 value 149.410652
## final value 149.410652
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 83
## initial value 420.731848
## iter 10 value 214.099765
## iter 20 value 214.085233
## iter 30 value 214.023843
## iter 40 value 197.950550
## iter 50 value 197.755059
## iter 60 value 193.560961
## iter 70 value 193.351256
## iter 80 value 188.881281
## iter 90 value 188.859178
## iter 100 value 187.851794
## final value 187.851794
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 412.262684
## iter 10 value 213.529285
## iter 20 value 206.794606
## iter 30 value 206.716352
## iter 40 value 206.672231
## iter 50 value 190.577940
## iter 60 value 190.424512
## iter 70 value 187.948568
## iter 80 value 187.285584
## iter 90 value 187.251861
## iter 100 value 187.241656
## final value 187.241656
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 533.166165
## iter 10 value 214.245804
## iter 20 value 205.033883
## iter 30 value 191.680028
## iter 40 value 184.802578
## iter 50 value 182.473372
## iter 60 value 171.197243
## iter 70 value 143.413234
## iter 80 value 139.829801
## iter 90 value 139.602440
## iter 100 value 139.480723
## final value 139.480723
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 492.969718
## iter 10 value 214.252861
## iter 20 value 214.115395
## iter 30 value 197.887113
## iter 40 value 197.740358
## iter 50 value 190.735062
## iter 60 value 188.816475
## iter 70 value 181.109755
## iter 80 value 179.658666
## iter 90 value 179.645605
## iter 100 value 179.586897
## final value 179.586897
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 447.808632
## iter 10 value 213.445371
## iter 20 value 211.325797
## iter 30 value 202.854383
## iter 40 value 190.065246
## iter 50 value 189.131950
## iter 60 value 188.549801
## iter 70 value 184.396310
## iter 80 value 184.308299
## iter 90 value 180.087190
## iter 100 value 179.864499
## final value 179.864499
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 363.957074
## iter 10 value 216.336890
## iter 20 value 213.693077
## iter 30 value 203.538027
## iter 40 value 194.773055
## iter 50 value 193.599721
## iter 60 value 193.088409
## iter 70 value 191.001175
## iter 80 value 187.979782
## iter 90 value 172.384776
## iter 100 value 170.523151
## final value 170.523151
## stopped after 100 iterations
## Fitting Repeat 1
##
## # weights: 133
## initial value 525.639378
## iter 10 value 293.197961
## iter 20 value 225.452151
## iter 30 value 202.569226
## iter 40 value 172.331686
## iter 50 value 140.998711
## iter 60 value 128.637645
## iter 70 value 113.408537
## iter 80 value 106.174795
## iter 90 value 84.297501
## iter 100 value 69.215937
## final value 69.215937
## stopped after 100 iterations
## Fitting Repeat 2
##
## # weights: 133
## initial value 703.581902
## iter 10 value 288.723917
## iter 20 value 214.600747
## iter 30 value 172.773978
## iter 40 value 160.363943
## iter 50 value 157.814939
## iter 60 value 147.907896
## iter 70 value 126.790216
## iter 80 value 112.937847
## iter 90 value 87.772573
## iter 100 value 81.334401
## final value 81.334401
## stopped after 100 iterations
## Fitting Repeat 3
##
## # weights: 133
## initial value 698.192378
## iter 10 value 236.307965
## iter 20 value 220.007504
## iter 30 value 203.160717
## iter 40 value 161.532013
## iter 50 value 125.367528
## iter 60 value 116.355643
## iter 70 value 106.956815
## iter 80 value 95.078530
## iter 90 value 71.534282
## iter 100 value 50.869277
## final value 50.869277
## stopped after 100 iterations
## Fitting Repeat 4
##
## # weights: 133
## initial value 827.729449
## iter 10 value 295.551805
## iter 20 value 280.983187
## iter 30 value 241.293758
## iter 40 value 179.821420
## iter 50 value 167.149346
## iter 60 value 165.676518
## iter 70 value 162.151245
## iter 80 value 146.453329
## iter 90 value 112.602703
## iter 100 value 91.335870
## final value 91.335870
## stopped after 100 iterations
## Fitting Repeat 5
##
## # weights: 133
## initial value 706.643053
## iter 10 value 260.931750
## iter 20 value 230.545918
## iter 30 value 209.222416
## iter 40 value 191.252859
## iter 50 value 186.348680
## iter 60 value 184.196585
## iter 70 value 166.831992
## iter 80 value 160.738414
## iter 90 value 158.602899
## iter 100 value 155.005341
## final value 155.005341
## stopped after 100 iterations
prediction_stack <- stack(ensemble)
names(prediction_stack) <- models
plot(prediction_stack)
############### Accuracy assessment - confusion matrices - ####
models <- c("svmPoly", "svmRadial", "svmLinear", "rf", "knn", "gbm", "pls", "mda", "amdai", "avNNet", "Ens_SV", "Ens_WV")
mymodels <- data.frame(matrix (nrow=length(models), ncol= 7))
colnames (mymodels) <- c("Accuracy", "Kappa", "AccuracyLower", "AccuracyUpper",
"AccuracyNull", "AccuracyPValue", "McnemarPValue")
rownames(mymodels) <- models
#empty table for Producer's and user's accuracies
my.acc <- data.frame(matrix (nrow=length(levels(train_2016$class)), ncol= 3))
colnames (my.acc) <- c("PrA", "UrA", "alg")
rownames(my.acc) <- levels(train_2016$class)
myacc <- do.call("rbind", replicate(10, my.acc, simplify = F))
myacc$class <- levels(train_2016$class)
myacc$alg <- rep(models[1:10], each=length(levels(train_2016$class)))
#
uniqueClasses <- unique(train_2016$class)
set.seed(7)
xy_val <- lapply (uniqueClasses, function(class_i){
class_data <- subset(val_2016, class == class_i)
classpts <- spsample(class_data, type = "stratified", n = 100)
classpts$class <-rep(class_i, length(classpts))
return(classpts)
})
#rbind the spatialpointdataframe into asingle object
xy_val <- do.call("rbind", xy_val)
models <- c("svmPoly", "svmRadial", "svmLinear", "rf", "knn", "gbm", "pls", "mda", "amdai", "avNNet")
for (mod in models){
#extract predictions
pred <- extract(prediction_stack[[mod]], xy_val, cellnumbers=T)
#discard duplicates cells and 'cell' column
dup <- duplicated(pred)
pred <- pred[!dup,mod]
obs <- xy_val$class[!dup]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
valFactor <- uniqueClasses[pred]
head(valFactor)
mymodels[rownames(mymodels) %in% mod,] <- confusionMatrix(obs, reference = valFactor)[[3]]
table <- confusionMatrix(obs, reference = valFactor)[[2]]
PrA <- diag(table)/rowSums(table)
UrA <- diag(table)/colSums(table)
myacc[myacc$alg %in% mod,"PrA"] <- as.vector(PrA)
myacc[myacc$alg %in% mod,"UrA"] <- as.vector(UrA)
}
## validate the ensemble map
#simply voting ensemble procedure
Ensemble <- modal(prediction_stack[[c(1,3,4,5,8,9)]])
names(Ensemble) <- "Ens_SV"
pred <- extract(Ensemble, xy_val, cellnumbers=T)
#discard duplicates cells and 'cell' column
dup <- duplicated(pred)
pred <- pred[!dup,"Ens_SV"]
obs <- xy_val$class[!dup]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
valFactor <- uniqueClasses[pred]
head(valFactor)
## [1] Area Area Area Area Area Area
## 8 Levels: Area Areas queimadas Auga Bosque Carrizal Duna gris ... Vexetacion halofila
mymodels[rownames(mymodels) %in% "Ens_SV",] <-confusionMatrix(obs, reference = valFactor)[[3]]
table <- confusionMatrix(obs, reference = valFactor)[[2]]
PrA <- diag(table)/rowSums(table)
UrA <- diag(table)/colSums(table)
myacc_Ens_SV <- as.data.frame(cbind(PrA, UrA))
myacc_Ens_SV$alg <- "Ens_SV"
myacc_Ens_SV$class <- rownames(myacc_Ens_SV)
####save results
##weithed voting ensemnble procedure
Ensemble2 <- modal(stack(replicate(mymodels[rownames(mymodels)[1], "Accuracy"]*100, prediction_stack[[1]])),
stack(replicate(mymodels[rownames(mymodels)[3], "Accuracy"]*100, prediction_stack[[3]])),
stack(replicate(mymodels[rownames(mymodels)[4], "Accuracy"]*100, prediction_stack[[4]])),
stack(replicate(mymodels[rownames(mymodels)[5], "Accuracy"]*100, prediction_stack[[5]])),
stack(replicate(mymodels[rownames(mymodels)[8], "Accuracy"]*100, prediction_stack[[8]])),
stack(replicate(mymodels[rownames(mymodels)[9], "Accuracy"]*100, prediction_stack[[9]])))
names(Ensemble2) <- "Ens_Wv"
pred <- extract(Ensemble2, xy_val, cellnumbers=T)
#discard duplicates cells and 'cell' column
dup <- duplicated(pred)
pred <- pred[!dup,"Ens_Wv"]
obs <- xy_val$class[!dup]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
valFactor <- uniqueClasses[pred]
head(valFactor)
## [1] Area Area Area Area Area Area
## 8 Levels: Area Areas queimadas Auga Bosque Carrizal Duna gris ... Vexetacion halofila
mymodels[rownames(mymodels) %in% "Ens_WV",] <-confusionMatrix(obs, reference = valFactor)[[3]]
table <- confusionMatrix(obs, reference = valFactor)[[2]]
PrA <- diag(table)/rowSums(table)
UrA <- diag(table)/colSums(table)
myacc_Ens_WV <- as.data.frame(cbind(PrA, UrA))
myacc_Ens_WV$alg <- "Ens_WV"
myacc_Ens_WV$class <- rownames(myacc_Ens_WV)
####
myacc <- rbind(myacc, myacc_Ens_SV, myacc_Ens_WV)
#write.csv2(mymodels, "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/model.metrics2016_rev.csv")
#write.csv2(myacc, "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/acc.metrics2016_rev.csv")
#writeRaster(Ensemble, bylayer = T, suffix = 'names', filename = "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/Ens_SV_2016.tif", datatype = 'INT2S', overwrite=T, options=c("TFW=YES"))
#writeRaster(Ensemble2, filename = "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/Ens_WV_2016.tif", datatype = 'INT2S', overwrite=T, options=c("TFW=YES"))
#writeRaster(prediction_stack, bylayer = T, suffix = 'names', filename = "E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/Raster/LULCmap_2016.tif", datatype = 'INT2S', overwrite=T, options=c("TFW=YES"))
save.image("E://USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/ImageProcess2016_revision.RData")
##plot results
library(rasterVis)
library(ggplot2)
gplot(Ensemble) + geom_raster(aes(fill = value)) +
facet_wrap(~ variable) +
scale_fill_gradientn(name="Environmental units 2016",colours=c("grey90", "red2","blue3", "darkgreen" ,"yellow", "seagreen4","orange1","yellowgreen"),
breaks=c(1,2,3,4,5,6,7,8), na.value = "white", labels=c("Sand", "Burned areas", "Water", "Forest", "Reeds", "Grey dunes","Meadows and grasslands", "Halophyte vegetation")) +
theme(plot.margin = unit(c(0.001,0.001,0.001,0.001), "cm"), panel.grid.major = element_line(colour = "grey70", size = 0.2),
panel.grid.minor = element_blank(), panel.background = element_rect(fill = "white", colour = "white"))
gplot(Ensemble2) + geom_raster(aes(fill = value)) +
facet_wrap(~ variable) +
scale_fill_gradientn(name="Environmental units 2013",colours=c("grey90", "blue3", "darkgreen" ,"yellow", "seagreen4","orange1","yellowgreen"),
breaks=c(1,2,3,4,5,6,7), na.value = "white", labels=c("Sand", "Water", "Forest", "Reeds", "Grey Dunes","Meadows and grasslands", "Halophyte vegetation")) +
theme(plot.margin = unit(c(0.001,0.001,0.001,0.001), "cm"), panel.grid.major = element_line(colour = "grey70", size = 0.2),
panel.grid.minor = element_blank(), panel.background = element_rect(fill = "white", colour = "white"))
################################################################################
################ Mc Nemar's chi-squared test between pairs of algorithms #######
################################################################################
library(plyr)
library(reshape2)
library(ggplot2)
models <- c("svmPoly", "svmRadial", "svmLinear", "rf", "knn", "gbm", "pls", "mda", "amdai", "avNNet")
load("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results/ImageProcess2003.RData")
db <- as.data.frame(matrix(nrow=10,ncol=10))
colnames(db) <- models
rownames(db) <- models
options("scipen"=100, digits= 3)
for (i in models){
for (j in models){
pred <- extract(prediction_stack[[c(i)]], xy_val, cellnumbers=T)
dup <- duplicated(pred)
pred <- pred[!dup,i]
obs <- xy_val$class[!dup]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
alg1 <- uniqueClasses[pred]
head(alg1)
pred <- extract(prediction_stack[[c(j)]], xy_val, cellnumbers=T)
dup <- duplicated(pred)
pred <- pred[!dup, j]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
alg2 <- uniqueClasses[pred]
head(alg2)
tab <- cbind(obs, alg1, alg2)
m.freq <- count(tab, c("obs","alg1", "alg2"))
a <- sum(m.freq[m.freq$obs == m.freq$alg1 & m.freq$obs == m.freq$alg2, "freq"])
b <- sum(m.freq[m.freq$obs == m.freq$alg1 & m.freq$obs != m.freq$alg2, "freq"])
c <- sum(m.freq[m.freq$obs != m.freq$alg1 & m.freq$obs == m.freq$alg2, "freq"])
d <- sum(m.freq[m.freq$obs != m.freq$alg1 & m.freq$obs != m.freq$alg2, "freq"])
cont.tb <- as.table(matrix(c(a,b,c,d), ncol=2, byrow=T))
db[i,j] <- mcnemar.test(cont.tb)[3]
}
}
db[db < 0.01] <- 0.01
db[db < 0.05 & db > 0.01] <- 0.05
db[db > 0.05 & db < 0.1] <- 0.10
options(digits = 2)
#library(reshape2)
db <- as.matrix(db)
# Note that a correlation matrix has redundant information. We'll use the functions below to set half of it to NA.
get_upper_tri <- function(db){
db[lower.tri(db)]<- NA
return(db)
}
upper_tri <- get_upper_tri(db)
upper_tri
## svmPoly svmRadial svmLinear rf knn gbm pls mda amdai avNNet
## svmPoly NaN 1 0.68 1 0.45 1.00 0.01 0.37 0.68 0.01
## svmRadial NA NaN 1.00 1 0.22 0.68 0.01 0.68 1.00 0.01
## svmLinear NA NA NaN 1 0.10 0.25 0.01 1.00 1.00 0.01
## rf NA NA NA NaN 0.22 0.62 0.01 0.62 1.00 0.01
## knn NA NA NA NA NaN 0.72 0.01 0.10 0.18 0.10
## gbm NA NA NA NA NA NaN 0.01 0.13 0.37 0.05
## pls NA NA NA NA NA NA NaN 0.01 0.01 0.01
## mda NA NA NA NA NA NA NA NaN 1.00 0.01
## amdai NA NA NA NA NA NA NA NA NaN 0.01
## avNNet NA NA NA NA NA NA NA NA NA NaN
options(digits=2)
melted_db <- melt(upper_tri, na.rm = TRUE)
head(melted_db)
## Var1 Var2 value
## 11 svmPoly svmRadial 1.00
## 21 svmPoly svmLinear 0.68
## 22 svmRadial svmLinear 1.00
## 31 svmPoly rf 1.00
## 32 svmRadial rf 1.00
## 33 svmLinear rf 1.00
colnames(melted_db) <- c("Var1", "Var2", "value")
ggheatmap <- ggplot(melted_db, aes(Var2, Var1, fill = value))+
geom_tile(color = "white")+
scale_fill_gradient2(low = "red", high = "blue",
midpoint = 0.01, limit = c(0,1), space = "Lab",
name="McNemar Test (p-value)") +
theme_minimal() +
geom_text(aes(label = round(value, digits = 2)), color = "black", size = 4) +
theme(
axis.title.x = element_blank(),
axis.title.y = element_blank(),
panel.grid.major = element_blank(),
panel.border = element_blank(),
panel.background = element_blank(),
axis.ticks = element_blank(),
legend.justification = c(1, 0),
legend.position = c(0.6, 0.7),
legend.direction = "horizontal")+
guides(fill = guide_colorbar(barwidth = 7, barheight = 1,
title.position = "top", title.hjust = 0.5)) +
ggtitle ("Year 2003")
###year 2016
load("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results/ImageProcess2016.RData")
db <- as.data.frame(matrix(nrow=10,ncol=10))
colnames(db) <- models
rownames(db) <- models
options("scipen"=100, digits= 3)
for (i in models){
for (j in models){
pred <- extract(prediction_stack[[c(i)]], xy_val, cellnumbers=T)
dup <- duplicated(pred)
pred <- pred[!dup,i]
obs <- xy_val$class[!dup]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
alg1 <- uniqueClasses[pred]
head(alg1)
pred <- extract(prediction_stack[[c(j)]], xy_val, cellnumbers=T)
dup <- duplicated(pred)
pred <- pred[!dup, j]
#recode integers for predictions
uniqueClasses <- sort(uniqueClasses)
alg2 <- uniqueClasses[pred]
head(alg2)
tab <- cbind(obs, alg1, alg2)
m.freq <- count(tab, c("obs","alg1", "alg2"))
a <- sum(m.freq[m.freq$obs == m.freq$alg1 & m.freq$obs == m.freq$alg2, "freq"])
b <- sum(m.freq[m.freq$obs == m.freq$alg1 & m.freq$obs != m.freq$alg2, "freq"])
c <- sum(m.freq[m.freq$obs != m.freq$alg1 & m.freq$obs == m.freq$alg2, "freq"])
d <- sum(m.freq[m.freq$obs != m.freq$alg1 & m.freq$obs != m.freq$alg2, "freq"])
cont.tb <- as.table(matrix(c(a,b,c,d), ncol=2, byrow=T))
db[i,j] <- mcnemar.test(cont.tb)[3]
}
}
db[db < 0.01] <- 0.01
db[db < 0.05 & db > 0.01] <- 0.05
db[db > 0.05 & db < 0.1] <- 0.10
options(digits = 2)
#library(reshape2)
db <- as.matrix(db)
# Note that a correlation matrix has redundant information. We'll use the functions below to set half of it to NA.
get_upper_tri <- function(db){
db[lower.tri(db)]<- NA
return(db)
}
upper_tri <- get_upper_tri(db)
upper_tri
## svmPoly svmRadial svmLinear rf knn gbm pls mda amdai
## svmPoly NaN 0.13 1.00 1.00 0.48 0.22 0.01 1.00 0.62
## svmRadial NA NaN 0.05 0.05 0.05 1.00 0.01 0.13 0.37
## svmLinear NA NA NaN NaN 1.00 0.10 0.01 1.00 0.25
## rf NA NA NA NaN 1.00 0.10 0.01 1.00 0.25
## knn NA NA NA NA NaN 0.05 0.01 0.48 0.13
## gbm NA NA NA NA NA NaN 0.01 0.22 0.68
## pls NA NA NA NA NA NA NaN 0.01 0.01
## mda NA NA NA NA NA NA NA NaN 0.48
## amdai NA NA NA NA NA NA NA NA NaN
## avNNet NA NA NA NA NA NA NA NA NA
## avNNet
## svmPoly 0.01
## svmRadial 0.01
## svmLinear 0.01
## rf 0.01
## knn 0.01
## gbm 0.01
## pls 0.01
## mda 0.01
## amdai 0.01
## avNNet NaN
options(digits=2)
melted_db <- melt(upper_tri, na.rm = TRUE)
head(melted_db)
## Var1 Var2 value
## 11 svmPoly svmRadial 0.13
## 21 svmPoly svmLinear 1.00
## 22 svmRadial svmLinear 0.05
## 31 svmPoly rf 1.00
## 32 svmRadial rf 0.05
## 41 svmPoly knn 0.48
colnames(melted_db) <- c("Var1", "Var2", "value")
ggheatmap2 <- ggplot(melted_db, aes(Var2, Var1, fill = value))+
geom_tile(color = "white")+
scale_fill_gradient2(low = "red", high = "blue",
midpoint = 0.01, limit = c(0,1), space = "Lab",
name="McNemar Test (p-value)") +
theme_minimal() +
geom_text(aes(label = round(value, digits = 2)), color = "black", size = 4) +
theme(
axis.title.x = element_blank(),
axis.title.y = element_blank(),
panel.grid.major = element_blank(),
panel.border = element_blank(),
panel.background = element_blank(),
axis.ticks = element_blank(),
legend.justification = c(1, 0),
legend.position = c(0.6, 0.7),
legend.direction = "horizontal")+
guides(fill = guide_colorbar(barwidth = 7, barheight = 1,
title.position = "top", title.hjust = 0.5)) +
ggtitle ("Year 2016")
library("cowplot")
##
## Attaching package: 'cowplot'
## The following object is masked from 'package:ggplot2':
##
## ggsave
plot_grid(ggheatmap, ggheatmap2, ncol=2)
#########################################################################################
################# Read accuracy tables obtained from confusion matrices ##################
#########################################################################################
### User's and Producer's accuracies by algorithm and class
t1 <- read.csv2("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/acc.metrics2003_rev.csv")[,2:5]
t2 <- read.csv2("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/acc.metrics2016_rev.csv")[,2:5]
library(ggplot2)
library(reshape2)
myacc1 <- melt(t1)
## Using alg, class as id variables
myacc2 <- melt(t2)
## Using alg, class as id variables
myacc1$year <- "2003"
myacc2$year <- "2016"
levels(myacc1$class) <- c("Sand dunes", "Tidal areas", "Forest", "Reedbed","Sea dunes", "Grasslands", "Salt marshes")
levels(myacc2$class) <- c("Sand dunes", "Burned areas", "Tidal areas", "Forest", "Reedbed","Sea dunes", "Grasslands", "Salt marshes")
acc <- rbind(myacc1, myacc2)
#plot 8 x 5
myggplot1 <- ggplot(acc, aes(y=value, x=alg, colour=alg)) +
geom_point(stat="identity", size = 1) +
xlab("Classification method") +
ylab("Accuracy") +
ggtitle("") +
theme_light(base_size = 8) +
scale_colour_manual(values=colorRampPalette(c("grey", "blue"))(12)) +
scale_x_discrete(limits= c( "amdai", "avNNet", "gbm", "knn", "mda","pls", "rf", "svmPoly", "svmRadial", "svmLinear", "Ens_SV", "Ens_WV")) +
facet_grid (variable+year ~ class, scales = "free") + coord_flip()
print(myggplot1 +
theme(axis.text.x = element_text(angle = 45, vjust=1, hjust=1)))
## Warning: Removed 7 rows containing missing values (geom_point).
##### Kappa coef. and overall accuracy per year
t1 <- read.csv2("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/models.metrics2003_rev.csv")[,1:3]
t2 <- read.csv2("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/model.metrics2016_rev.csv")[,1:3]
myacc1 <- melt(t1)
## Using X as id variables
myacc2 <- melt(t2)
## Using X as id variables
myacc1$year <- "2003"
myacc2$year <- "2016"
acc <- rbind(myacc1, myacc2)
colnames(acc) <- c("alg", "variable", "value", "year")
###6 x 5
myggplot1 <- ggplot(acc, aes(y=value, x=year, fill=year)) +
geom_boxplot() +
xlab("Land cover class") +
theme(axis.text.x = element_text(angle = 90, vjust=0.5, hjust=1)) +
ylab("Year") +
ggtitle("") +
theme_light(base_size = 8) + geom_jitter(aes(colour = alg)) +
scale_fill_manual(values=colorRampPalette(c("grey", "blue"))(12)) +
scale_color_manual(values=c("yellow","grey60"," red1", "red3", "lightblue", "blue1", "blue4", "grey80", "green", "purple1", "purple3", "purple4")) +
facet_grid (~ variable, scales = "free")
print(myggplot1)
################################################################################
########################## Habitat changes analysis ############################
################################################################################
library(lulcc)
## Warning: package 'lulcc' was built under R version 3.4.2
setwd("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/Raster/")
datafiles <- Sys.glob("*.tif") #Or whatever identifies your files
r.stack <- stack()
for(i in 1:NROW(datafiles)){
tempraster <- raster(datafiles[i])
r.stack <- stack(r.stack,tempraster)
}
all_2003 <- raster::subset(r.stack, grep('2003', names(r.stack), value = T))
all_2016 <- raster::subset(r.stack, grep('2016', names(r.stack), value = T))
#reclasify to match habitat classes with year 2016
all_2003_reclass <- reclassify(all_2003,c(-Inf,1,1, 1,2,3, 2,3,4, 3,4,5, 4,5,6, 5,6,7, 6,7,8))
names(all_2003_reclass) <- c("Ens_SV", "Ens_WV", "amdai", "avNNet", "gbm", "knn", "mda", "pls", "rf","svmLinear", "svmPoly",
"svmRadial")
names(all_2016) <- c("Ens_SV", "Ens_WV", "amdai", "avNNet", "gbm", "knn", "mda", "pls", "rf","svmLinear", "svmPoly",
"svmRadial")
#reorder
all_2016 <- stack(all_2016[[3]],all_2016[[4]],all_2016[[5]],all_2016[[6]],all_2016[[7]],all_2016[[8]],
all_2016[[9]], all_2016[[10]],all_2016[[11]],all_2016[[12]], all_2016[[1]],all_2016[[2]])
all_2003_reclass <- stack(all_2003_reclass[[3]],all_2003_reclass[[4]],all_2003_reclass[[5]],all_2003_reclass[[6]],all_2003_reclass[[7]],all_2003_reclass[[8]],
all_2003_reclass[[9]], all_2003_reclass[[10]],all_2003_reclass[[11]], all_2003_reclass[[12]], all_2003_reclass[[1]],all_2003_reclass[[2]])
##plot maps
library(rasterVis)
library(ggplot2)
categories <- c("Sand dunes", "Burned areas", "Tidal areas", "Forest",
"Reedbed","Sea dunes", "Grasslands", "Salt marshes")
##14 x 12
gplot(all_2003_reclass) + geom_raster(aes(fill = value)) +
facet_wrap(~ variable) +
scale_fill_gradientn(name="Habitats 2003",colours=c("grey90", "red2","blue3", "darkgreen" ,"yellow", "seagreen4","orange1","yellowgreen"),
breaks=c(1,2,3,4,5,6,7,8), na.value = "white", labels=categories) +
theme(plot.margin = unit(c(0.001,0.001,0.001,0.001), "cm"), panel.grid.major = element_line(colour = "grey70", size = 0.2),
panel.grid.minor = element_blank(), panel.background = element_rect(fill = "white", colour = "white"))
gplot(all_2016) + geom_raster(aes(fill = value)) +
facet_wrap(~ variable) +
scale_fill_gradientn(name="Habitats 2016",colours=c("grey90", "red2","blue3", "darkgreen" ,"yellow", "seagreen4","orange1","yellowgreen"),
breaks=c(1,2,3,4,5,6,7,8), na.value = "white", labels=categories) +
theme(plot.margin = unit(c(0.001,0.001,0.001,0.001), "cm"), panel.grid.major = element_line(colour = "grey70", size = 0.2),
panel.grid.minor = element_blank(), panel.background = element_rect(fill = "white", colour = "white"))
#crostabulation
my.totals <- 0
for (my.alg in names(all_2016)[c(1,3:5,7:12)]){
Table <- crossTabulate(all_2003_reclass[[my.alg]], all_2016[[my.alg]], categories=(c(1,2,3,4,5,6,7,8)))
Table <- Table*0.09
rownames(Table) <- categories
colnames(Table) <- categories
#save
#write.csv2(Table, paste("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/ChangeAnalysis/CrossTab_", my.alg, ".csv", sep=""))
##total per category
total03 <- total(all_2003_reclass[[my.alg]])
total03 <- cbind(total03$total, 0)#add column empty for area burnt
total03 <- total03[c(1,8,2,3,4,5,6,7)]#reorder columns
total16 <- total(all_2016[[my.alg]])
totals <- as.data.frame(cbind(total03, t(total16$total)))
rownames(totals) <- categories
colnames(totals) <- c("2003", "2016")
totals$alg <- my.alg
my.totals <- rbind(my.totals, totals)
#write.csv2(totals,paste("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/ChangeAnalysis/Totales_", my.alg, ".csv", sep=""))
}
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
## Warning in total(all_2003_reclass[[my.alg]]): missing argument
## 'categories': getting categories from 'x'
## Warning in total(all_2016[[my.alg]]): missing argument 'categories':
## getting categories from 'x'
my.totals <- my.totals[2:81,]
#plots
library(ggplot2)
library(reshape)
##
## Attaching package: 'reshape'
## The following objects are masked from 'package:reshape2':
##
## colsplit, melt, recast
## The following object is masked from 'package:class':
##
## condense
## The following objects are masked from 'package:plyr':
##
## rename, round_any
db_totales <- melt(my.totals)
## Using alg as id variables
db_totales$LCT_categories <- categories
names(db_totales) <- c("alg", "year", "value", "Classes")
db_totales$Hectares <- (db_totales$value)*0.09 #30 x 30 meters pizel size
#plot 6 x 8
myggplot1 <- ggplot(db_totales, aes(x=Classes, y=Hectares, fill=Classes)) +
geom_boxplot() +
theme(axis.text.x = element_text(angle = 90, vjust=0.5, hjust=1)) +
ylab("Hectares") +
ggtitle("") +
theme_light(base_size = 8) + geom_jitter(aes(colour = alg),alpha=.3) +
scale_fill_brewer () +
scale_fill_manual(values=colorRampPalette(c("grey", "blue"))(8)) +
scale_color_manual(values=c("black"," red1", "red3", "black", "black", "black", "black","black","black","black","black")) +
facet_grid (~ year, scales = "free")
## Scale for 'fill' is already present. Adding another scale for 'fill',
## which will replace the existing scale.
print(myggplot1 +
theme(axis.text.x = element_text(angle = 45, vjust=1, hjust=1)) +
xlab("Habitat classes"))
#pct of change
my.totals$pct <- ((my.totals$`2016`-my.totals$`2003`)/my.totals$`2003`)*100
#write.csv2(my.totals,paste("E:/USC/OneDrive - Universidade de Santiago de Compostela/Corrubedo/Results_v2/ChangeAnalysis/my.totales_pct.csv", sep=""))
####### end