keras and caret
library(tidyverse)## -- Attaching packages ----------------------------------------------------------------------------------------- tidyverse 1.2.1 --## v ggplot2 3.2.1 v purrr 0.3.2
## v tibble 2.1.3 v dplyr 0.8.3
## v tidyr 1.0.0 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.4.0## -- Conflicts -------------------------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(caret)## Loading required package: lattice##
## Attaching package: 'caret'## The following object is masked from 'package:purrr':
##
## liftlibrary(keras)
library(datasets)
library(GGally)## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2##
## Attaching package: 'GGally'## The following object is masked from 'package:dplyr':
##
## nasalibrary(janitor)##
## Attaching package: 'janitor'## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.testlibrary(broom)
theme_set(theme_light())iris <- datasets::iris
iris <- clean_names(as_tibble(iris))Summary of data
ggpairs(iris, aes(colour = species))## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Split data
set.seed(777)
split <- createDataPartition(iris$species, p = 0.75, list = F)
train <- iris[split,]
test <- iris[-split,]Caret
Create model using KNN
fit1 <- train(species ~ ., data= train, method ="knn")
fit1## k-Nearest Neighbors
##
## 114 samples
## 4 predictor
## 3 classes: 'setosa', 'versicolor', 'virginica'
##
## No pre-processing
## Resampling: Bootstrapped (25 reps)
## Summary of sample sizes: 114, 114, 114, 114, 114, 114, ...
## Resampling results across tuning parameters:
##
## k Accuracy Kappa
## 5 0.9759876 0.9634918
## 7 0.9749680 0.9619386
## 9 0.9743473 0.9610629
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was k = 5.Use it to predict values
On training data:
train_predict1 <- predict(fit1, train)
confusionMatrix(train$species, train_predict1)## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 38 0 0
## versicolor 0 37 1
## virginica 0 1 37
##
## Overall Statistics
##
## Accuracy : 0.9825
## 95% CI : (0.9381, 0.9979)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.9737
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 0.9737 0.9737
## Specificity 1.0000 0.9868 0.9868
## Pos Pred Value 1.0000 0.9737 0.9737
## Neg Pred Value 1.0000 0.9868 0.9868
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3246 0.3246
## Detection Prevalence 0.3333 0.3333 0.3333
## Balanced Accuracy 1.0000 0.9803 0.9803And test data
test_predict1 <- predict(fit1, test)
confusionMatrix(test$species, test_predict1)## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 12 0 0
## versicolor 0 11 1
## virginica 0 0 12
##
## Overall Statistics
##
## Accuracy : 0.9722
## 95% CI : (0.8547, 0.9993)
## No Information Rate : 0.3611
## P-Value [Acc > NIR] : 7.69e-15
##
## Kappa : 0.9583
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 0.9231
## Specificity 1.0000 0.9600 1.0000
## Pos Pred Value 1.0000 0.9167 1.0000
## Neg Pred Value 1.0000 1.0000 0.9583
## Prevalence 0.3333 0.3056 0.3611
## Detection Rate 0.3333 0.3056 0.3333
## Detection Prevalence 0.3333 0.3333 0.3333
## Balanced Accuracy 1.0000 0.9800 0.9615Create model using nnet
fit2 <- train(species ~ ., data= train, method ="nnet")## # weights: 11
## initial value 128.834685
## iter 10 value 56.156075
## iter 20 value 17.215995
## iter 30 value 0.558362
## iter 40 value 0.021187
## iter 50 value 0.018792
## iter 60 value 0.009935
## iter 70 value 0.005286
## iter 80 value 0.005055
## iter 90 value 0.004974
## iter 100 value 0.004845
## final value 0.004845
## stopped after 100 iterations
## # weights: 27
## initial value 150.528326
## iter 10 value 120.909460
## iter 20 value 70.635175
## iter 30 value 0.524330
## iter 40 value 0.008568
## final value 0.000051
## converged
## # weights: 43
## initial value 140.834476
## iter 10 value 52.648161
## iter 20 value 3.292173
## iter 30 value 0.003616
## final value 0.000060
## converged
## # weights: 11
## initial value 121.196561
## iter 10 value 52.385520
## iter 20 value 45.807214
## final value 45.805213
## converged
## # weights: 27
## initial value 144.238980
## iter 10 value 83.404005
## iter 20 value 54.004775
## iter 30 value 20.827616
## iter 40 value 19.383124
## iter 50 value 19.381333
## final value 19.381332
## converged
## # weights: 43
## initial value 137.160389
## iter 10 value 58.860903
## iter 20 value 26.084408
## iter 30 value 18.859326
## iter 40 value 18.377446
## iter 50 value 17.900398
## iter 60 value 17.502672
## iter 70 value 17.487170
## iter 80 value 17.482248
## iter 90 value 17.478979
## iter 100 value 17.474341
## final value 17.474341
## stopped after 100 iterations
## # weights: 11
## initial value 124.582720
## iter 10 value 54.544121
## iter 20 value 46.483535
## iter 30 value 12.477915
## iter 40 value 1.337035
## iter 50 value 1.226492
## iter 60 value 1.205734
## iter 70 value 1.203475
## iter 80 value 1.194828
## iter 90 value 1.193958
## iter 100 value 1.193623
## final value 1.193623
## stopped after 100 iterations
## # weights: 27
## initial value 126.988509
## iter 10 value 52.543874
## iter 20 value 52.204044
## iter 30 value 52.194651
## iter 40 value 52.159418
## iter 50 value 52.045611
## iter 60 value 51.860889
## iter 70 value 11.822222
## iter 80 value 1.376330
## iter 90 value 1.275814
## iter 100 value 1.234768
## final value 1.234768
## stopped after 100 iterations
## # weights: 43
## initial value 163.417357
## iter 10 value 51.245211
## iter 20 value 7.073992
## iter 30 value 0.543711
## iter 40 value 0.435148
## iter 50 value 0.354256
## iter 60 value 0.240120
## iter 70 value 0.194210
## iter 80 value 0.187460
## iter 90 value 0.168031
## iter 100 value 0.148234
## final value 0.148234
## stopped after 100 iterations
## # weights: 11
## initial value 134.797035
## iter 10 value 57.472254
## iter 20 value 38.641695
## iter 30 value 11.533377
## iter 40 value 3.677375
## iter 50 value 1.876063
## iter 60 value 1.493978
## iter 70 value 0.106482
## iter 80 value 0.077738
## iter 90 value 0.069663
## iter 100 value 0.066312
## final value 0.066312
## stopped after 100 iterations
## # weights: 27
## initial value 139.688132
## iter 10 value 124.866458
## iter 20 value 62.499600
## iter 30 value 7.288096
## iter 40 value 0.739898
## iter 50 value 0.001080
## final value 0.000053
## converged
## # weights: 43
## initial value 155.450313
## iter 10 value 39.474328
## iter 20 value 0.745934
## iter 30 value 0.000749
## iter 40 value 0.000182
## final value 0.000077
## converged
## # weights: 11
## initial value 148.489144
## iter 10 value 125.180382
## iter 20 value 71.480044
## iter 30 value 53.570585
## iter 40 value 44.447370
## final value 44.447211
## converged
## # weights: 27
## initial value 137.617237
## iter 10 value 51.484572
## iter 20 value 24.485544
## iter 30 value 22.083442
## iter 40 value 22.080661
## iter 50 value 21.888858
## iter 60 value 19.887600
## final value 19.849976
## converged
## # weights: 43
## initial value 144.274348
## iter 10 value 42.530779
## iter 20 value 22.537894
## iter 30 value 20.291316
## iter 40 value 19.541792
## iter 50 value 19.324035
## iter 60 value 19.218453
## iter 70 value 19.002876
## iter 80 value 18.945919
## final value 18.940126
## converged
## # weights: 11
## initial value 126.551198
## iter 10 value 49.986307
## iter 20 value 13.434406
## iter 30 value 2.493839
## iter 40 value 2.031275
## iter 50 value 1.964060
## iter 60 value 1.874886
## iter 70 value 1.870593
## iter 80 value 1.868199
## iter 90 value 1.865859
## iter 100 value 1.864964
## final value 1.864964
## stopped after 100 iterations
## # weights: 27
## initial value 130.281853
## iter 10 value 37.265404
## iter 20 value 11.778438
## iter 30 value 4.891750
## iter 40 value 3.566889
## iter 50 value 3.283138
## iter 60 value 3.202821
## iter 70 value 2.202461
## iter 80 value 2.166235
## iter 90 value 1.864967
## iter 100 value 1.833127
## final value 1.833127
## stopped after 100 iterations
## # weights: 43
## initial value 188.399622
## iter 10 value 54.975995
## iter 20 value 49.077712
## iter 30 value 1.650153
## iter 40 value 0.209324
## iter 50 value 0.199574
## iter 60 value 0.193291
## iter 70 value 0.178288
## iter 80 value 0.173947
## iter 90 value 0.170654
## iter 100 value 0.169723
## final value 0.169723
## stopped after 100 iterations
## # weights: 11
## initial value 126.098348
## iter 10 value 50.043535
## iter 10 value 50.043535
## iter 10 value 50.043535
## final value 50.043535
## converged
## # weights: 27
## initial value 124.963588
## iter 10 value 51.295784
## iter 20 value 50.046351
## iter 30 value 50.043656
## final value 50.043536
## converged
## # weights: 43
## initial value 138.910266
## iter 10 value 50.830587
## iter 20 value 27.227997
## iter 30 value 2.238286
## iter 40 value 0.007321
## iter 50 value 0.000101
## iter 50 value 0.000100
## iter 50 value 0.000030
## final value 0.000030
## converged
## # weights: 11
## initial value 140.516944
## iter 10 value 59.760390
## iter 20 value 54.839304
## iter 30 value 45.051547
## final value 45.051056
## converged
## # weights: 27
## initial value 140.489017
## iter 10 value 78.772352
## iter 20 value 55.417608
## iter 30 value 25.535900
## iter 40 value 18.857376
## iter 50 value 18.366792
## final value 18.366786
## converged
## # weights: 43
## initial value 122.343278
## iter 10 value 49.153558
## iter 20 value 20.700096
## iter 30 value 18.074046
## iter 40 value 17.562037
## iter 50 value 17.154366
## iter 60 value 17.108051
## iter 70 value 16.975644
## final value 16.975527
## converged
## # weights: 11
## initial value 144.989765
## iter 10 value 52.127792
## iter 20 value 50.094892
## iter 30 value 50.091430
## iter 40 value 50.089360
## iter 50 value 48.655060
## iter 60 value 15.318470
## iter 70 value 1.180048
## iter 80 value 1.089689
## iter 90 value 1.074558
## iter 100 value 1.073353
## final value 1.073353
## stopped after 100 iterations
## # weights: 27
## initial value 134.173814
## iter 10 value 19.530101
## iter 20 value 0.412156
## iter 30 value 0.314625
## iter 40 value 0.275691
## iter 50 value 0.248163
## iter 60 value 0.222478
## iter 70 value 0.202304
## iter 80 value 0.187731
## iter 90 value 0.162410
## iter 100 value 0.138829
## final value 0.138829
## stopped after 100 iterations
## # weights: 43
## initial value 132.609414
## iter 10 value 60.107330
## iter 20 value 0.576171
## iter 30 value 0.280480
## iter 40 value 0.264940
## iter 50 value 0.228229
## iter 60 value 0.164001
## iter 70 value 0.143683
## iter 80 value 0.137882
## iter 90 value 0.127361
## iter 100 value 0.122754
## final value 0.122754
## stopped after 100 iterations
## # weights: 11
## initial value 155.374505
## iter 10 value 124.556877
## iter 20 value 124.547922
## final value 124.547915
## converged
## # weights: 27
## initial value 150.304582
## iter 10 value 45.168392
## iter 20 value 12.169710
## iter 30 value 7.789886
## iter 40 value 7.780574
## iter 50 value 7.780486
## iter 50 value 7.780486
## iter 50 value 7.780486
## final value 7.780486
## converged
## # weights: 43
## initial value 138.923213
## iter 10 value 52.926701
## iter 20 value 0.176695
## iter 30 value 0.008617
## iter 40 value 0.000428
## final value 0.000089
## converged
## # weights: 11
## initial value 129.205347
## iter 10 value 96.496454
## iter 20 value 49.588250
## iter 30 value 44.638942
## final value 44.636873
## converged
## # weights: 27
## initial value 122.164496
## iter 10 value 31.620004
## iter 20 value 19.599030
## iter 30 value 18.506400
## iter 40 value 18.218763
## iter 50 value 18.210149
## final value 18.210148
## converged
## # weights: 43
## initial value 130.800718
## iter 10 value 37.300984
## iter 20 value 18.759130
## iter 30 value 17.287645
## iter 40 value 16.940661
## iter 50 value 16.274556
## iter 60 value 15.673250
## iter 70 value 15.627545
## iter 80 value 15.627302
## final value 15.627300
## converged
## # weights: 11
## initial value 123.907762
## iter 10 value 54.374315
## iter 20 value 54.322471
## iter 30 value 54.302537
## iter 40 value 51.564041
## iter 50 value 12.719348
## iter 60 value 1.614602
## iter 70 value 0.982662
## iter 80 value 0.980464
## iter 90 value 0.975819
## iter 100 value 0.975564
## final value 0.975564
## stopped after 100 iterations
## # weights: 27
## initial value 148.395053
## iter 10 value 54.690322
## iter 20 value 34.603060
## iter 30 value 0.386322
## iter 40 value 0.318262
## iter 50 value 0.265261
## iter 60 value 0.214252
## iter 70 value 0.177578
## iter 80 value 0.153422
## iter 90 value 0.128194
## iter 100 value 0.121817
## final value 0.121817
## stopped after 100 iterations
## # weights: 43
## initial value 166.609493
## iter 10 value 54.654423
## iter 20 value 54.326166
## iter 30 value 7.569432
## iter 40 value 0.220933
## iter 50 value 0.202936
## iter 60 value 0.176985
## iter 70 value 0.157177
## iter 80 value 0.099241
## iter 90 value 0.096628
## iter 100 value 0.087657
## final value 0.087657
## stopped after 100 iterations
## # weights: 11
## initial value 130.132319
## iter 10 value 42.803951
## iter 20 value 36.532809
## iter 30 value 8.842198
## iter 40 value 0.682450
## iter 50 value 0.032238
## iter 60 value 0.018521
## iter 70 value 0.015334
## iter 80 value 0.013454
## iter 90 value 0.008655
## iter 100 value 0.007892
## final value 0.007892
## stopped after 100 iterations
## # weights: 27
## initial value 147.314743
## iter 10 value 103.858861
## iter 20 value 0.749867
## iter 30 value 0.000922
## final value 0.000059
## converged
## # weights: 43
## initial value 130.006858
## iter 10 value 43.358527
## iter 20 value 41.653110
## iter 30 value 2.638726
## iter 40 value 0.012949
## iter 50 value 0.000147
## iter 50 value 0.000074
## iter 50 value 0.000074
## final value 0.000074
## converged
## # weights: 11
## initial value 123.137562
## iter 10 value 47.039763
## iter 20 value 41.876665
## iter 30 value 41.858302
## final value 41.858300
## converged
## # weights: 27
## initial value 129.532853
## iter 10 value 69.120792
## iter 20 value 45.024087
## iter 30 value 23.617729
## iter 40 value 20.307744
## iter 50 value 19.222513
## iter 60 value 18.136120
## iter 70 value 16.547339
## iter 80 value 16.524010
## final value 16.524009
## converged
## # weights: 43
## initial value 132.655539
## iter 10 value 53.608226
## iter 20 value 25.923010
## iter 30 value 17.217113
## iter 40 value 17.090454
## iter 50 value 16.242300
## iter 60 value 15.524174
## iter 70 value 15.017990
## iter 80 value 14.917251
## final value 14.917242
## converged
## # weights: 11
## initial value 124.490361
## iter 10 value 52.116352
## iter 20 value 43.474190
## iter 30 value 43.459204
## iter 40 value 43.436945
## iter 50 value 43.416285
## iter 60 value 43.385607
## iter 70 value 43.353459
## iter 80 value 43.351717
## iter 90 value 43.094771
## iter 100 value 29.847838
## final value 29.847838
## stopped after 100 iterations
## # weights: 27
## initial value 129.836872
## iter 10 value 48.628960
## iter 20 value 41.684071
## iter 30 value 0.731636
## iter 40 value 0.309020
## iter 50 value 0.228221
## iter 60 value 0.161171
## iter 70 value 0.110173
## iter 80 value 0.103493
## iter 90 value 0.100371
## iter 100 value 0.096700
## final value 0.096700
## stopped after 100 iterations
## # weights: 43
## initial value 148.941987
## iter 10 value 2.838661
## iter 20 value 0.551023
## iter 30 value 0.317360
## iter 40 value 0.193343
## iter 50 value 0.153326
## iter 60 value 0.141196
## iter 70 value 0.127237
## iter 80 value 0.119007
## iter 90 value 0.110820
## iter 100 value 0.105460
## final value 0.105460
## stopped after 100 iterations
## # weights: 11
## initial value 129.911203
## iter 10 value 107.931464
## iter 20 value 35.384276
## iter 30 value 4.282505
## iter 40 value 0.038854
## iter 50 value 0.018847
## iter 60 value 0.013483
## iter 70 value 0.009454
## iter 80 value 0.009342
## iter 90 value 0.008983
## iter 100 value 0.008868
## final value 0.008868
## stopped after 100 iterations
## # weights: 27
## initial value 142.558893
## iter 10 value 55.400427
## iter 20 value 55.395781
## final value 55.395696
## converged
## # weights: 43
## initial value 131.140739
## iter 10 value 57.680269
## iter 20 value 2.484071
## iter 30 value 0.033881
## iter 40 value 0.000259
## final value 0.000046
## converged
## # weights: 11
## initial value 128.843773
## iter 10 value 64.341489
## iter 20 value 47.985462
## final value 46.773717
## converged
## # weights: 27
## initial value 165.048324
## iter 10 value 43.739636
## iter 20 value 19.998873
## iter 30 value 19.831843
## final value 19.831496
## converged
## # weights: 43
## initial value 181.052290
## iter 10 value 79.728113
## iter 20 value 44.872418
## iter 30 value 26.475194
## iter 40 value 21.489624
## iter 50 value 20.654254
## iter 60 value 20.062306
## iter 70 value 19.702817
## iter 80 value 19.443565
## iter 90 value 19.289756
## iter 100 value 18.731606
## final value 18.731606
## stopped after 100 iterations
## # weights: 11
## initial value 132.856806
## iter 10 value 55.874610
## iter 20 value 55.452283
## iter 30 value 55.450229
## iter 40 value 55.444399
## iter 50 value 53.460539
## iter 60 value 39.701548
## iter 70 value 8.091531
## iter 80 value 2.170184
## iter 90 value 1.903514
## iter 100 value 1.850561
## final value 1.850561
## stopped after 100 iterations
## # weights: 27
## initial value 127.422637
## iter 10 value 65.250551
## iter 20 value 55.592166
## iter 30 value 55.480899
## iter 40 value 55.429257
## iter 50 value 5.677708
## iter 60 value 0.827432
## iter 70 value 0.217143
## iter 80 value 0.209129
## iter 90 value 0.193636
## iter 100 value 0.186620
## final value 0.186620
## stopped after 100 iterations
## # weights: 43
## initial value 144.199630
## iter 10 value 86.042162
## iter 20 value 8.616521
## iter 30 value 0.279510
## iter 40 value 0.241477
## iter 50 value 0.225218
## iter 60 value 0.214275
## iter 70 value 0.206395
## iter 80 value 0.198201
## iter 90 value 0.184922
## iter 100 value 0.175948
## final value 0.175948
## stopped after 100 iterations
## # weights: 11
## initial value 123.779795
## iter 10 value 60.652573
## iter 20 value 11.692060
## iter 30 value 1.005027
## iter 40 value 0.873137
## iter 50 value 0.737134
## iter 60 value 0.636811
## iter 70 value 0.477114
## iter 80 value 0.447001
## iter 90 value 0.385198
## iter 100 value 0.171852
## final value 0.171852
## stopped after 100 iterations
## # weights: 27
## initial value 154.443311
## iter 10 value 55.643274
## iter 20 value 55.637146
## final value 55.637072
## converged
## # weights: 43
## initial value 129.585992
## iter 10 value 44.421384
## iter 20 value 0.084717
## iter 30 value 0.000297
## final value 0.000082
## converged
## # weights: 11
## initial value 143.585241
## iter 10 value 74.364543
## iter 20 value 44.355015
## iter 30 value 44.338937
## final value 44.338923
## converged
## # weights: 27
## initial value 137.701292
## iter 10 value 79.326703
## iter 20 value 34.676394
## iter 30 value 27.029369
## iter 40 value 20.786323
## iter 50 value 19.293789
## iter 60 value 18.905368
## iter 70 value 18.741316
## final value 18.741312
## converged
## # weights: 43
## initial value 145.204929
## iter 10 value 32.841975
## iter 20 value 18.706972
## iter 30 value 17.928660
## iter 40 value 17.626982
## iter 50 value 17.458201
## iter 60 value 17.384110
## iter 70 value 17.375477
## iter 80 value 17.375283
## final value 17.375278
## converged
## # weights: 11
## initial value 124.395788
## iter 10 value 56.176039
## iter 20 value 15.023921
## iter 30 value 3.638184
## iter 40 value 2.228763
## iter 50 value 1.784504
## iter 60 value 1.770083
## iter 70 value 1.742850
## iter 80 value 1.720545
## iter 90 value 1.711344
## iter 100 value 1.701082
## final value 1.701082
## stopped after 100 iterations
## # weights: 27
## initial value 138.990976
## iter 10 value 22.194135
## iter 20 value 3.796016
## iter 30 value 2.133249
## iter 40 value 1.982661
## iter 50 value 1.890907
## iter 60 value 1.852129
## iter 70 value 1.770999
## iter 80 value 1.535774
## iter 90 value 1.141362
## iter 100 value 1.010150
## final value 1.010150
## stopped after 100 iterations
## # weights: 43
## initial value 150.164996
## iter 10 value 45.785059
## iter 20 value 3.919325
## iter 30 value 0.846193
## iter 40 value 0.747735
## iter 50 value 0.679515
## iter 60 value 0.515911
## iter 70 value 0.384690
## iter 80 value 0.368072
## iter 90 value 0.339890
## iter 100 value 0.285313
## final value 0.285313
## stopped after 100 iterations
## # weights: 11
## initial value 126.412107
## iter 10 value 51.587259
## iter 20 value 51.430936
## iter 30 value 13.913705
## iter 40 value 3.939073
## iter 50 value 0.431354
## iter 60 value 0.202292
## iter 70 value 0.157757
## iter 80 value 0.131896
## iter 90 value 0.100047
## iter 100 value 0.093507
## final value 0.093507
## stopped after 100 iterations
## # weights: 27
## initial value 148.225523
## iter 10 value 47.480748
## iter 20 value 20.422174
## iter 30 value 2.043025
## iter 40 value 0.005362
## final value 0.000053
## converged
## # weights: 43
## initial value 156.499762
## iter 10 value 40.242784
## iter 20 value 0.375741
## iter 30 value 0.000821
## final value 0.000071
## converged
## # weights: 11
## initial value 131.328381
## iter 10 value 68.118052
## iter 20 value 61.764983
## iter 30 value 55.839606
## iter 40 value 42.659021
## final value 42.648486
## converged
## # weights: 27
## initial value 130.424336
## iter 10 value 55.242082
## iter 20 value 32.838683
## iter 30 value 23.798410
## iter 40 value 19.589430
## iter 50 value 19.237047
## iter 60 value 19.010073
## iter 70 value 19.007645
## final value 19.007508
## converged
## # weights: 43
## initial value 143.484622
## iter 10 value 50.993616
## iter 20 value 18.893417
## iter 30 value 17.877331
## iter 40 value 17.664217
## iter 50 value 16.746469
## iter 60 value 16.684871
## final value 16.684870
## converged
## # weights: 11
## initial value 125.205377
## iter 10 value 48.158324
## iter 20 value 9.407643
## iter 30 value 2.357828
## iter 40 value 1.644087
## iter 50 value 1.503127
## iter 60 value 1.462424
## iter 70 value 1.409956
## iter 80 value 1.370500
## iter 90 value 1.362405
## iter 100 value 1.361103
## final value 1.361103
## stopped after 100 iterations
## # weights: 27
## initial value 138.466842
## iter 10 value 79.901886
## iter 20 value 51.954623
## iter 30 value 51.864166
## iter 40 value 48.956990
## iter 50 value 13.085044
## iter 60 value 4.349833
## iter 70 value 1.776326
## iter 80 value 1.466151
## iter 90 value 1.450404
## iter 100 value 1.282561
## final value 1.282561
## stopped after 100 iterations
## # weights: 43
## initial value 126.944066
## iter 10 value 49.948787
## iter 20 value 0.607146
## iter 30 value 0.387235
## iter 40 value 0.350716
## iter 50 value 0.301026
## iter 60 value 0.240642
## iter 70 value 0.228872
## iter 80 value 0.208109
## iter 90 value 0.200837
## iter 100 value 0.182591
## final value 0.182591
## stopped after 100 iterations
## # weights: 11
## initial value 125.949527
## iter 10 value 69.565889
## iter 20 value 7.590551
## iter 30 value 1.156597
## iter 40 value 0.678397
## iter 50 value 0.591646
## iter 60 value 0.470305
## iter 70 value 0.396315
## iter 80 value 0.193973
## iter 90 value 0.151077
## iter 100 value 0.124863
## final value 0.124863
## stopped after 100 iterations
## # weights: 27
## initial value 132.892973
## iter 10 value 61.345841
## iter 20 value 54.557785
## iter 30 value 54.548380
## final value 54.548370
## converged
## # weights: 43
## initial value 177.799950
## iter 10 value 54.605981
## iter 20 value 54.406360
## iter 30 value 5.682116
## iter 40 value 0.250655
## iter 50 value 0.001111
## final value 0.000085
## converged
## # weights: 11
## initial value 129.395649
## iter 10 value 66.167378
## iter 20 value 62.405938
## iter 30 value 55.035125
## iter 40 value 44.513378
## final value 44.511783
## converged
## # weights: 27
## initial value 147.258304
## iter 10 value 64.667974
## iter 20 value 32.561246
## iter 30 value 22.635691
## iter 40 value 19.887480
## iter 50 value 19.645020
## iter 60 value 19.566583
## iter 70 value 18.922893
## iter 80 value 18.760886
## final value 18.760882
## converged
## # weights: 43
## initial value 129.125396
## iter 10 value 68.041780
## iter 20 value 22.807955
## iter 30 value 21.000791
## iter 40 value 20.198269
## iter 50 value 19.087167
## iter 60 value 18.667255
## iter 70 value 18.506863
## iter 80 value 17.960694
## iter 90 value 17.756087
## iter 100 value 17.431386
## final value 17.431386
## stopped after 100 iterations
## # weights: 11
## initial value 118.741468
## iter 10 value 53.400641
## iter 20 value 53.192937
## iter 30 value 53.144467
## iter 40 value 53.094744
## iter 50 value 53.029852
## iter 60 value 52.696767
## iter 70 value 37.524043
## iter 80 value 5.928502
## iter 90 value 2.860042
## iter 100 value 2.408220
## final value 2.408220
## stopped after 100 iterations
## # weights: 27
## initial value 129.602678
## iter 10 value 54.688757
## iter 20 value 53.067430
## iter 30 value 52.814841
## iter 40 value 46.192258
## iter 50 value 15.029190
## iter 60 value 4.419943
## iter 70 value 1.908051
## iter 80 value 1.626181
## iter 90 value 1.534292
## iter 100 value 1.515448
## final value 1.515448
## stopped after 100 iterations
## # weights: 43
## initial value 138.090611
## iter 10 value 59.383821
## iter 20 value 34.745019
## iter 30 value 0.595499
## iter 40 value 0.366319
## iter 50 value 0.270693
## iter 60 value 0.243379
## iter 70 value 0.195284
## iter 80 value 0.158666
## iter 90 value 0.151244
## iter 100 value 0.147856
## final value 0.147856
## stopped after 100 iterations
## # weights: 11
## initial value 130.412988
## iter 10 value 58.237619
## iter 20 value 56.830023
## iter 30 value 43.184648
## iter 40 value 3.164133
## iter 50 value 0.716527
## iter 60 value 0.448196
## iter 70 value 0.220712
## iter 80 value 0.098271
## iter 90 value 0.069516
## iter 100 value 0.067414
## final value 0.067414
## stopped after 100 iterations
## # weights: 27
## initial value 128.022329
## iter 10 value 58.506349
## iter 20 value 56.839488
## iter 30 value 56.838070
## final value 56.838069
## converged
## # weights: 43
## initial value 127.032005
## iter 10 value 0.283053
## iter 20 value 0.001574
## final value 0.000091
## converged
## # weights: 11
## initial value 131.685276
## iter 10 value 123.933265
## iter 20 value 67.716038
## iter 30 value 45.921618
## final value 45.898983
## converged
## # weights: 27
## initial value 155.088933
## iter 10 value 59.902117
## iter 20 value 33.431881
## iter 30 value 21.769891
## iter 40 value 20.923765
## iter 50 value 19.481591
## iter 60 value 18.929792
## iter 70 value 18.644443
## iter 80 value 18.629203
## final value 18.629203
## converged
## # weights: 43
## initial value 139.503521
## iter 10 value 47.875774
## iter 20 value 18.797214
## iter 30 value 17.776687
## iter 40 value 17.207632
## iter 50 value 16.678701
## iter 60 value 16.515423
## iter 70 value 16.398852
## iter 80 value 16.333924
## iter 90 value 16.315481
## iter 100 value 16.285730
## final value 16.285730
## stopped after 100 iterations
## # weights: 11
## initial value 131.930200
## iter 10 value 61.242817
## iter 20 value 57.027610
## iter 30 value 12.001413
## iter 40 value 1.734016
## iter 50 value 1.375338
## iter 60 value 1.261994
## iter 70 value 1.179729
## iter 80 value 1.170366
## iter 90 value 1.157937
## iter 100 value 1.154190
## final value 1.154190
## stopped after 100 iterations
## # weights: 27
## initial value 128.515642
## iter 10 value 86.706150
## iter 20 value 14.573344
## iter 30 value 0.239400
## iter 40 value 0.203296
## iter 50 value 0.147047
## iter 60 value 0.126415
## iter 70 value 0.122546
## iter 80 value 0.115405
## iter 90 value 0.105340
## iter 100 value 0.100515
## final value 0.100515
## stopped after 100 iterations
## # weights: 43
## initial value 132.662556
## iter 10 value 57.117139
## iter 20 value 14.451354
## iter 30 value 0.585803
## iter 40 value 0.373992
## iter 50 value 0.268075
## iter 60 value 0.223549
## iter 70 value 0.166470
## iter 80 value 0.131704
## iter 90 value 0.120006
## iter 100 value 0.110995
## final value 0.110995
## stopped after 100 iterations
## # weights: 11
## initial value 125.846838
## iter 10 value 116.143591
## iter 20 value 19.400885
## iter 30 value 7.201541
## iter 40 value 3.072062
## iter 50 value 0.079302
## iter 60 value 0.032834
## iter 70 value 0.021008
## iter 80 value 0.020834
## iter 90 value 0.018322
## iter 100 value 0.016463
## final value 0.016463
## stopped after 100 iterations
## # weights: 27
## initial value 146.517660
## iter 10 value 35.212365
## iter 20 value 0.522789
## iter 30 value 0.001992
## iter 40 value 0.000960
## final value 0.000062
## converged
## # weights: 43
## initial value 121.761118
## iter 10 value 52.949313
## iter 20 value 51.926197
## iter 30 value 51.869207
## iter 40 value 33.363137
## iter 50 value 11.460710
## iter 60 value 0.953798
## iter 70 value 0.586586
## iter 80 value 0.020522
## iter 90 value 0.015075
## iter 100 value 0.014858
## final value 0.014858
## stopped after 100 iterations
## # weights: 11
## initial value 125.885143
## iter 10 value 86.755317
## iter 20 value 59.607534
## iter 30 value 46.209730
## final value 46.205285
## converged
## # weights: 27
## initial value 127.516216
## iter 10 value 59.894310
## iter 20 value 32.002135
## iter 30 value 21.108010
## iter 40 value 19.820531
## iter 50 value 19.735439
## iter 60 value 19.651468
## iter 70 value 19.583064
## final value 19.583048
## converged
## # weights: 43
## initial value 147.254639
## iter 10 value 60.266769
## iter 20 value 28.364290
## iter 30 value 19.677806
## iter 40 value 18.377179
## iter 50 value 17.786857
## iter 60 value 17.568603
## iter 70 value 17.529031
## iter 80 value 17.524918
## final value 17.524059
## converged
## # weights: 11
## initial value 128.519433
## iter 10 value 51.993728
## iter 20 value 51.970377
## iter 30 value 51.956295
## iter 40 value 49.352495
## iter 50 value 8.635551
## iter 60 value 1.708762
## iter 70 value 1.660152
## iter 80 value 1.632677
## iter 90 value 1.615923
## iter 100 value 1.611663
## final value 1.611663
## stopped after 100 iterations
## # weights: 27
## initial value 136.962770
## iter 10 value 52.152514
## iter 20 value 52.081367
## iter 30 value 52.004500
## iter 40 value 51.985072
## iter 50 value 50.420914
## iter 60 value 6.768547
## iter 70 value 0.364995
## iter 80 value 0.336622
## iter 90 value 0.313770
## iter 100 value 0.234848
## final value 0.234848
## stopped after 100 iterations
## # weights: 43
## initial value 139.466520
## iter 10 value 14.169215
## iter 20 value 11.768935
## iter 30 value 1.170465
## iter 40 value 0.543021
## iter 50 value 0.477815
## iter 60 value 0.440572
## iter 70 value 0.412175
## iter 80 value 0.248705
## iter 90 value 0.172786
## iter 100 value 0.165493
## final value 0.165493
## stopped after 100 iterations
## # weights: 11
## initial value 129.094397
## iter 10 value 50.110151
## iter 20 value 14.260353
## iter 30 value 0.988551
## iter 40 value 0.058519
## iter 50 value 0.038302
## iter 60 value 0.036103
## iter 70 value 0.035158
## iter 80 value 0.031644
## iter 90 value 0.027225
## iter 100 value 0.026901
## final value 0.026901
## stopped after 100 iterations
## # weights: 27
## initial value 145.004021
## iter 10 value 98.616706
## iter 20 value 8.664428
## iter 30 value 0.053132
## final value 0.000072
## converged
## # weights: 43
## initial value 140.227679
## iter 10 value 30.458627
## iter 20 value 3.043083
## iter 30 value 0.040378
## iter 40 value 0.000252
## final value 0.000051
## converged
## # weights: 11
## initial value 134.223119
## iter 10 value 72.812635
## iter 20 value 45.808863
## iter 30 value 45.009104
## final value 45.006113
## converged
## # weights: 27
## initial value 131.987342
## iter 10 value 72.512244
## iter 20 value 51.057949
## iter 30 value 38.010862
## iter 40 value 22.616618
## iter 50 value 19.513904
## iter 60 value 18.749389
## iter 70 value 18.715749
## iter 80 value 18.714815
## final value 18.714814
## converged
## # weights: 43
## initial value 160.473963
## iter 10 value 59.316545
## iter 20 value 35.695580
## iter 30 value 23.642412
## iter 40 value 19.251361
## iter 50 value 18.338195
## iter 60 value 18.280366
## iter 70 value 18.237079
## iter 80 value 18.116106
## iter 90 value 17.736053
## iter 100 value 17.469912
## final value 17.469912
## stopped after 100 iterations
## # weights: 11
## initial value 130.511787
## iter 10 value 124.904007
## final value 124.903846
## converged
## # weights: 27
## initial value 129.538858
## iter 10 value 50.041019
## iter 20 value 49.957136
## iter 30 value 49.765505
## iter 40 value 48.924676
## iter 50 value 48.530468
## iter 60 value 38.107181
## iter 70 value 7.882460
## iter 80 value 3.658012
## iter 90 value 2.383607
## iter 100 value 2.062181
## final value 2.062181
## stopped after 100 iterations
## # weights: 43
## initial value 135.010551
## iter 10 value 5.353186
## iter 20 value 0.339475
## iter 30 value 0.319803
## iter 40 value 0.272969
## iter 50 value 0.245978
## iter 60 value 0.226648
## iter 70 value 0.204383
## iter 80 value 0.197555
## iter 90 value 0.190309
## iter 100 value 0.177932
## final value 0.177932
## stopped after 100 iterations
## # weights: 11
## initial value 126.473660
## iter 10 value 75.450395
## iter 20 value 50.518959
## iter 30 value 48.154689
## iter 40 value 33.523326
## iter 50 value 6.540908
## iter 60 value 2.509322
## iter 70 value 1.675215
## iter 80 value 0.498709
## iter 90 value 0.382443
## iter 100 value 0.069648
## final value 0.069648
## stopped after 100 iterations
## # weights: 27
## initial value 144.588808
## iter 10 value 56.918478
## iter 20 value 55.263609
## iter 30 value 33.001548
## iter 40 value 6.309333
## iter 50 value 1.107876
## iter 60 value 0.010383
## iter 70 value 0.000267
## final value 0.000067
## converged
## # weights: 43
## initial value 129.243149
## iter 10 value 56.845151
## iter 20 value 5.083844
## iter 30 value 0.101394
## iter 40 value 0.000383
## final value 0.000029
## converged
## # weights: 11
## initial value 132.398713
## iter 10 value 106.205813
## iter 20 value 47.665896
## final value 47.265873
## converged
## # weights: 27
## initial value 140.098645
## iter 10 value 71.770663
## iter 20 value 23.237960
## iter 30 value 19.706867
## iter 40 value 19.512214
## iter 50 value 19.483921
## final value 19.482937
## converged
## # weights: 43
## initial value 143.148081
## iter 10 value 49.355438
## iter 20 value 22.548772
## iter 30 value 20.429605
## iter 40 value 19.336454
## iter 50 value 18.776083
## iter 60 value 18.240724
## iter 70 value 18.051495
## iter 80 value 17.943284
## final value 17.942473
## converged
## # weights: 11
## initial value 149.797549
## iter 10 value 56.792112
## iter 20 value 56.240080
## iter 30 value 28.762583
## iter 40 value 8.673770
## iter 50 value 1.804405
## iter 60 value 1.788935
## iter 70 value 1.777819
## iter 80 value 1.757778
## iter 90 value 1.755818
## iter 100 value 1.755266
## final value 1.755266
## stopped after 100 iterations
## # weights: 27
## initial value 129.994587
## iter 10 value 57.487632
## iter 20 value 56.891336
## iter 30 value 56.823420
## iter 40 value 56.815236
## iter 50 value 56.805308
## iter 60 value 52.472275
## iter 70 value 14.089221
## iter 80 value 0.929401
## iter 90 value 0.837568
## iter 100 value 0.608295
## final value 0.608295
## stopped after 100 iterations
## # weights: 43
## initial value 122.805912
## iter 10 value 14.287670
## iter 20 value 0.270113
## iter 30 value 0.247850
## iter 40 value 0.223025
## iter 50 value 0.192928
## iter 60 value 0.182050
## iter 70 value 0.179296
## iter 80 value 0.175442
## iter 90 value 0.164020
## iter 100 value 0.160975
## final value 0.160975
## stopped after 100 iterations
## # weights: 11
## initial value 126.743132
## iter 10 value 38.143595
## iter 20 value 7.247891
## iter 30 value 2.088055
## iter 40 value 1.151003
## iter 50 value 0.734450
## iter 60 value 0.633737
## iter 70 value 0.474597
## iter 80 value 0.439390
## iter 90 value 0.359654
## iter 100 value 0.349651
## final value 0.349651
## stopped after 100 iterations
## # weights: 27
## initial value 124.506255
## iter 10 value 49.224292
## iter 20 value 6.718882
## iter 30 value 0.553842
## iter 40 value 0.000788
## final value 0.000068
## converged
## # weights: 43
## initial value 160.459229
## iter 10 value 32.257024
## iter 20 value 2.072376
## iter 30 value 0.007969
## iter 40 value 0.000274
## final value 0.000095
## converged
## # weights: 11
## initial value 129.987564
## iter 10 value 115.285501
## iter 20 value 59.723103
## iter 30 value 46.091030
## iter 40 value 46.001436
## final value 46.001374
## converged
## # weights: 27
## initial value 146.655323
## iter 10 value 52.816055
## iter 20 value 21.047278
## iter 30 value 20.373820
## iter 40 value 20.365404
## iter 50 value 20.364753
## final value 20.364749
## converged
## # weights: 43
## initial value 135.814909
## iter 10 value 56.533676
## iter 20 value 22.152576
## iter 30 value 19.613089
## iter 40 value 19.279532
## iter 50 value 19.267454
## iter 60 value 19.252823
## final value 19.252803
## converged
## # weights: 11
## initial value 134.871226
## iter 10 value 52.090220
## iter 20 value 51.380210
## iter 30 value 51.371215
## iter 40 value 49.864016
## iter 50 value 47.168888
## iter 60 value 12.917924
## iter 70 value 3.617963
## iter 80 value 2.225638
## iter 90 value 2.130665
## iter 100 value 2.053285
## final value 2.053285
## stopped after 100 iterations
## # weights: 27
## initial value 137.476164
## iter 10 value 60.955035
## iter 20 value 51.417002
## iter 30 value 51.390034
## iter 40 value 49.032995
## iter 50 value 23.685900
## iter 60 value 3.743909
## iter 70 value 2.188563
## iter 80 value 2.070221
## iter 90 value 2.023614
## iter 100 value 1.913824
## final value 1.913824
## stopped after 100 iterations
## # weights: 43
## initial value 135.622421
## iter 10 value 10.208792
## iter 20 value 0.332165
## iter 30 value 0.313105
## iter 40 value 0.250724
## iter 50 value 0.232342
## iter 60 value 0.228732
## iter 70 value 0.198055
## iter 80 value 0.193416
## iter 90 value 0.184233
## iter 100 value 0.173992
## final value 0.173992
## stopped after 100 iterations
## # weights: 11
## initial value 126.349436
## iter 10 value 125.148671
## iter 20 value 51.974200
## iter 30 value 15.544098
## iter 40 value 0.711336
## iter 50 value 0.102398
## iter 60 value 0.025343
## iter 70 value 0.001225
## iter 80 value 0.001034
## iter 90 value 0.001007
## iter 100 value 0.000990
## final value 0.000990
## stopped after 100 iterations
## # weights: 27
## initial value 123.611872
## iter 10 value 51.927405
## final value 51.926023
## converged
## # weights: 43
## initial value 156.560243
## iter 10 value 28.059030
## iter 20 value 0.032527
## iter 30 value 0.002827
## iter 40 value 0.000262
## final value 0.000023
## converged
## # weights: 11
## initial value 137.895825
## iter 10 value 125.594046
## iter 20 value 94.625085
## iter 30 value 44.013095
## final value 43.849885
## converged
## # weights: 27
## initial value 124.338400
## iter 10 value 58.274134
## iter 20 value 47.713148
## iter 30 value 44.729850
## iter 40 value 26.936056
## iter 50 value 19.594689
## iter 60 value 18.818781
## iter 70 value 17.600515
## final value 17.594502
## converged
## # weights: 43
## initial value 129.675592
## iter 10 value 63.310776
## iter 20 value 30.599084
## iter 30 value 17.782329
## iter 40 value 16.777177
## iter 50 value 16.461585
## iter 60 value 16.173774
## iter 70 value 15.940197
## iter 80 value 15.936999
## final value 15.936998
## converged
## # weights: 11
## initial value 126.951507
## iter 10 value 43.851987
## iter 20 value 4.616169
## iter 30 value 1.678184
## iter 40 value 1.327115
## iter 50 value 1.251548
## iter 60 value 1.197451
## iter 70 value 1.181665
## iter 80 value 1.177081
## iter 90 value 1.170311
## iter 100 value 1.161786
## final value 1.161786
## stopped after 100 iterations
## # weights: 27
## initial value 146.870813
## iter 10 value 52.945746
## iter 20 value 52.380090
## iter 30 value 2.177965
## iter 40 value 0.417938
## iter 50 value 0.282489
## iter 60 value 0.186264
## iter 70 value 0.148774
## iter 80 value 0.142382
## iter 90 value 0.130250
## iter 100 value 0.104738
## final value 0.104738
## stopped after 100 iterations
## # weights: 43
## initial value 271.311130
## iter 10 value 74.281195
## iter 20 value 0.643024
## iter 30 value 0.408422
## iter 40 value 0.368762
## iter 50 value 0.318295
## iter 60 value 0.290187
## iter 70 value 0.241934
## iter 80 value 0.207991
## iter 90 value 0.191870
## iter 100 value 0.171193
## final value 0.171193
## stopped after 100 iterations
## # weights: 11
## initial value 123.012348
## iter 10 value 73.650293
## iter 20 value 59.079931
## iter 30 value 58.533261
## iter 40 value 58.444634
## iter 50 value 58.440572
## iter 60 value 58.439807
## iter 70 value 58.439027
## final value 58.438861
## converged
## # weights: 27
## initial value 235.028157
## iter 10 value 72.173680
## iter 20 value 0.381737
## iter 30 value 0.000332
## final value 0.000084
## converged
## # weights: 43
## initial value 121.634535
## iter 10 value 45.508669
## iter 20 value 26.276593
## iter 30 value 6.093393
## iter 40 value 0.092644
## iter 50 value 0.004378
## iter 60 value 0.000199
## final value 0.000079
## converged
## # weights: 11
## initial value 148.020148
## iter 10 value 123.058917
## iter 20 value 122.495104
## iter 30 value 55.946724
## iter 40 value 45.410599
## final value 45.367768
## converged
## # weights: 27
## initial value 128.551965
## iter 10 value 44.625633
## iter 20 value 21.253188
## iter 30 value 20.519497
## iter 40 value 19.466590
## iter 50 value 18.875056
## iter 60 value 18.867094
## iter 60 value 18.867094
## iter 60 value 18.867094
## final value 18.867094
## converged
## # weights: 43
## initial value 139.733384
## iter 10 value 47.550968
## iter 20 value 20.754379
## iter 30 value 18.619272
## iter 40 value 18.147637
## iter 50 value 17.884133
## iter 60 value 17.303088
## iter 70 value 17.190781
## iter 80 value 17.096757
## iter 90 value 17.077928
## iter 100 value 17.069300
## final value 17.069300
## stopped after 100 iterations
## # weights: 11
## initial value 136.143090
## iter 10 value 122.430493
## final value 122.427936
## converged
## # weights: 27
## initial value 120.805116
## iter 10 value 59.182510
## iter 20 value 5.259036
## iter 30 value 0.134277
## iter 40 value 0.123526
## iter 50 value 0.121470
## iter 60 value 0.118086
## iter 70 value 0.116296
## iter 80 value 0.114842
## iter 90 value 0.113316
## iter 100 value 0.112518
## final value 0.112518
## stopped after 100 iterations
## # weights: 43
## initial value 131.741457
## iter 10 value 18.591871
## iter 20 value 0.164112
## iter 30 value 0.149771
## iter 40 value 0.140878
## iter 50 value 0.133660
## iter 60 value 0.125187
## iter 70 value 0.122231
## iter 80 value 0.116296
## iter 90 value 0.114341
## iter 100 value 0.111104
## final value 0.111104
## stopped after 100 iterations
## # weights: 11
## initial value 128.146840
## iter 10 value 49.171243
## iter 20 value 47.243487
## iter 30 value 47.122727
## iter 40 value 47.102294
## iter 50 value 47.101748
## iter 60 value 47.093062
## iter 70 value 47.077585
## iter 80 value 46.623796
## iter 90 value 44.492471
## iter 100 value 44.190344
## final value 44.190344
## stopped after 100 iterations
## # weights: 27
## initial value 122.511542
## iter 10 value 35.382517
## iter 20 value 0.157076
## iter 30 value 0.000370
## final value 0.000059
## converged
## # weights: 43
## initial value 130.476856
## iter 10 value 53.653119
## iter 20 value 26.618378
## iter 30 value 0.080247
## iter 40 value 0.000152
## final value 0.000072
## converged
## # weights: 11
## initial value 133.435412
## iter 10 value 110.956459
## iter 20 value 48.587231
## iter 30 value 45.496265
## final value 45.495977
## converged
## # weights: 27
## initial value 143.954160
## iter 10 value 107.871935
## iter 20 value 23.133092
## iter 30 value 19.578933
## iter 40 value 18.489631
## iter 50 value 18.371956
## iter 60 value 18.340849
## iter 70 value 18.318778
## final value 18.318764
## converged
## # weights: 43
## initial value 130.467192
## iter 10 value 62.375879
## iter 20 value 27.980063
## iter 30 value 18.591806
## iter 40 value 17.979504
## iter 50 value 17.780429
## iter 60 value 17.248861
## iter 70 value 16.809341
## iter 80 value 16.787360
## iter 90 value 16.779486
## iter 100 value 16.777647
## final value 16.777647
## stopped after 100 iterations
## # weights: 11
## initial value 134.808545
## iter 10 value 50.500991
## iter 20 value 50.017476
## iter 30 value 49.966979
## iter 40 value 46.928587
## iter 50 value 8.821101
## iter 60 value 1.879220
## iter 70 value 1.585865
## iter 80 value 1.405264
## iter 90 value 1.390154
## iter 100 value 1.373107
## final value 1.373107
## stopped after 100 iterations
## # weights: 27
## initial value 125.800912
## iter 10 value 62.287829
## iter 20 value 5.962954
## iter 30 value 2.766370
## iter 40 value 2.618623
## iter 50 value 2.159733
## iter 60 value 1.760093
## iter 70 value 1.576728
## iter 80 value 1.232711
## iter 90 value 0.863428
## iter 100 value 0.706625
## final value 0.706625
## stopped after 100 iterations
## # weights: 43
## initial value 134.249118
## iter 10 value 51.755332
## iter 20 value 32.550842
## iter 30 value 0.252612
## iter 40 value 0.162398
## iter 50 value 0.134158
## iter 60 value 0.128202
## iter 70 value 0.119551
## iter 80 value 0.114414
## iter 90 value 0.105884
## iter 100 value 0.102105
## final value 0.102105
## stopped after 100 iterations
## # weights: 11
## initial value 133.079361
## iter 10 value 21.774854
## iter 20 value 5.848730
## iter 30 value 0.526580
## iter 40 value 0.123912
## iter 50 value 0.114386
## iter 60 value 0.105034
## iter 70 value 0.058520
## iter 80 value 0.051178
## iter 90 value 0.032870
## iter 100 value 0.032277
## final value 0.032277
## stopped after 100 iterations
## # weights: 27
## initial value 130.290215
## iter 10 value 49.883689
## iter 20 value 0.047698
## final value 0.000055
## converged
## # weights: 43
## initial value 145.448857
## iter 10 value 53.364381
## iter 20 value 0.282012
## iter 30 value 0.008737
## iter 40 value 0.003501
## iter 50 value 0.000458
## iter 60 value 0.000133
## iter 60 value 0.000093
## iter 60 value 0.000092
## final value 0.000092
## converged
## # weights: 11
## initial value 127.258631
## iter 10 value 93.958859
## iter 20 value 43.927441
## final value 43.830848
## converged
## # weights: 27
## initial value 132.807538
## iter 10 value 63.604324
## iter 20 value 19.538277
## iter 30 value 17.339214
## iter 40 value 17.244814
## iter 50 value 17.243005
## iter 50 value 17.243004
## iter 50 value 17.243004
## final value 17.243004
## converged
## # weights: 43
## initial value 122.171173
## iter 10 value 40.803583
## iter 20 value 18.959010
## iter 30 value 16.334765
## iter 40 value 15.684485
## iter 50 value 15.129684
## iter 60 value 15.069790
## final value 15.069750
## converged
## # weights: 11
## initial value 126.344137
## iter 10 value 116.213438
## iter 20 value 12.562576
## iter 30 value 7.302202
## iter 40 value 6.206892
## iter 50 value 4.870586
## iter 60 value 4.343619
## iter 70 value 2.009102
## iter 80 value 1.802184
## iter 90 value 1.436772
## iter 100 value 1.225676
## final value 1.225676
## stopped after 100 iterations
## # weights: 27
## initial value 155.324686
## iter 10 value 54.323729
## iter 20 value 25.376700
## iter 30 value 0.161243
## iter 40 value 0.127704
## iter 50 value 0.118726
## iter 60 value 0.110353
## iter 70 value 0.094061
## iter 80 value 0.090562
## iter 90 value 0.088668
## iter 100 value 0.086082
## final value 0.086082
## stopped after 100 iterations
## # weights: 43
## initial value 180.529979
## iter 10 value 50.973116
## iter 20 value 12.114120
## iter 30 value 0.225924
## iter 40 value 0.185754
## iter 50 value 0.161980
## iter 60 value 0.150972
## iter 70 value 0.133409
## iter 80 value 0.115084
## iter 90 value 0.099438
## iter 100 value 0.091639
## final value 0.091639
## stopped after 100 iterations
## # weights: 11
## initial value 142.728973
## iter 10 value 70.413749
## iter 20 value 48.660409
## iter 30 value 47.874199
## final value 47.158071
## converged
## # weights: 27
## initial value 132.403114
## iter 10 value 48.876436
## iter 20 value 48.109800
## iter 30 value 27.853634
## iter 40 value 3.930871
## iter 50 value 0.013890
## iter 60 value 0.000243
## final value 0.000089
## converged
## # weights: 43
## initial value 133.411971
## iter 10 value 39.147615
## iter 20 value 1.399631
## iter 30 value 0.002667
## final value 0.000086
## converged
## # weights: 11
## initial value 140.885363
## iter 10 value 122.504520
## iter 20 value 107.588600
## iter 30 value 82.498422
## iter 40 value 49.211164
## iter 50 value 44.349479
## final value 44.349478
## converged
## # weights: 27
## initial value 170.883632
## iter 10 value 58.009050
## iter 20 value 35.003163
## iter 30 value 18.149286
## iter 40 value 17.657978
## iter 50 value 17.501268
## iter 60 value 17.501020
## iter 60 value 17.501020
## iter 60 value 17.501020
## final value 17.501020
## converged
## # weights: 43
## initial value 145.070587
## iter 10 value 74.116619
## iter 20 value 24.325458
## iter 30 value 17.100184
## iter 40 value 16.454775
## iter 50 value 16.039798
## iter 60 value 15.849855
## iter 70 value 15.845903
## iter 80 value 15.845731
## iter 90 value 15.845568
## final value 15.845565
## converged
## # weights: 11
## initial value 129.220149
## iter 10 value 59.745477
## iter 20 value 34.360340
## iter 30 value 16.522524
## iter 40 value 3.387631
## iter 50 value 1.239806
## iter 60 value 0.998043
## iter 70 value 0.913425
## iter 80 value 0.890567
## iter 90 value 0.880495
## iter 100 value 0.859721
## final value 0.859721
## stopped after 100 iterations
## # weights: 27
## initial value 125.372898
## iter 10 value 43.294504
## iter 20 value 0.597189
## iter 30 value 0.153814
## iter 40 value 0.129438
## iter 50 value 0.124595
## iter 60 value 0.117244
## iter 70 value 0.114800
## iter 80 value 0.112129
## iter 90 value 0.110931
## iter 100 value 0.109722
## final value 0.109722
## stopped after 100 iterations
## # weights: 43
## initial value 122.303890
## iter 10 value 54.249220
## iter 20 value 47.740932
## iter 30 value 0.282094
## iter 40 value 0.254518
## iter 50 value 0.238303
## iter 60 value 0.195713
## iter 70 value 0.149366
## iter 80 value 0.108057
## iter 90 value 0.093159
## iter 100 value 0.090972
## final value 0.090972
## stopped after 100 iterations
## # weights: 11
## initial value 131.829808
## iter 10 value 54.067098
## iter 20 value 51.689532
## iter 30 value 51.658874
## iter 40 value 51.583497
## iter 50 value 50.813738
## iter 60 value 49.756013
## iter 70 value 42.930581
## iter 80 value 39.805994
## iter 90 value 33.168085
## iter 100 value 14.645313
## final value 14.645313
## stopped after 100 iterations
## # weights: 27
## initial value 132.904151
## iter 10 value 46.097268
## iter 20 value 6.774073
## iter 30 value 0.065951
## iter 40 value 0.007996
## iter 50 value 0.002292
## iter 60 value 0.000359
## final value 0.000091
## converged
## # weights: 43
## initial value 132.573609
## iter 10 value 37.592651
## iter 20 value 0.054357
## final value 0.000088
## converged
## # weights: 11
## initial value 127.684652
## iter 10 value 72.664373
## iter 20 value 61.464897
## iter 30 value 52.662795
## iter 40 value 44.971401
## final value 44.970993
## converged
## # weights: 27
## initial value 127.134112
## iter 10 value 64.541810
## iter 20 value 25.511045
## iter 30 value 18.646068
## iter 40 value 18.397258
## iter 50 value 18.367380
## iter 50 value 18.367380
## iter 50 value 18.367380
## final value 18.367380
## converged
## # weights: 43
## initial value 161.652766
## iter 10 value 62.605205
## iter 20 value 25.030069
## iter 30 value 19.173039
## iter 40 value 18.358337
## iter 50 value 18.140126
## iter 60 value 18.002962
## iter 70 value 17.959151
## iter 80 value 17.956519
## iter 90 value 17.955510
## iter 100 value 17.953085
## final value 17.953085
## stopped after 100 iterations
## # weights: 11
## initial value 137.131661
## iter 10 value 59.845742
## iter 20 value 49.840568
## iter 30 value 38.240394
## iter 40 value 12.519257
## iter 50 value 3.462623
## iter 60 value 2.460124
## iter 70 value 1.418957
## iter 80 value 1.366792
## iter 90 value 1.267299
## iter 100 value 1.259822
## final value 1.259822
## stopped after 100 iterations
## # weights: 27
## initial value 172.404329
## iter 10 value 92.444788
## iter 20 value 3.844847
## iter 30 value 0.694742
## iter 40 value 0.602203
## iter 50 value 0.394827
## iter 60 value 0.294508
## iter 70 value 0.264030
## iter 80 value 0.179629
## iter 90 value 0.141971
## iter 100 value 0.127391
## final value 0.127391
## stopped after 100 iterations
## # weights: 43
## initial value 125.173741
## iter 10 value 52.404861
## iter 20 value 52.358331
## iter 30 value 52.343193
## iter 40 value 10.433989
## iter 50 value 0.270249
## iter 60 value 0.246834
## iter 70 value 0.229458
## iter 80 value 0.202362
## iter 90 value 0.142578
## iter 100 value 0.128389
## final value 0.128389
## stopped after 100 iterations
## # weights: 11
## initial value 131.513194
## iter 10 value 114.193882
## iter 20 value 59.702812
## iter 30 value 53.249369
## iter 40 value 50.151643
## iter 50 value 47.629653
## iter 60 value 43.259943
## iter 70 value 38.763366
## iter 80 value 17.275316
## iter 90 value 1.230047
## iter 100 value 0.805593
## final value 0.805593
## stopped after 100 iterations
## # weights: 27
## initial value 140.633627
## iter 10 value 43.632486
## iter 20 value 29.920690
## iter 30 value 18.098861
## iter 40 value 3.649838
## iter 50 value 0.030781
## iter 60 value 0.001048
## iter 70 value 0.000985
## iter 80 value 0.000939
## final value 0.000068
## converged
## # weights: 43
## initial value 175.105835
## iter 10 value 45.794187
## iter 20 value 0.198146
## iter 30 value 0.000455
## final value 0.000060
## converged
## # weights: 11
## initial value 126.937176
## iter 10 value 62.618756
## iter 20 value 57.873786
## iter 30 value 47.886346
## final value 47.824175
## converged
## # weights: 27
## initial value 132.068938
## iter 10 value 87.564535
## iter 20 value 45.923854
## iter 30 value 26.402336
## iter 40 value 20.036190
## iter 50 value 19.738974
## iter 60 value 19.538591
## iter 70 value 19.354129
## iter 80 value 19.350024
## final value 19.350024
## converged
## # weights: 43
## initial value 151.533273
## iter 10 value 60.446648
## iter 20 value 38.768512
## iter 30 value 19.060627
## iter 40 value 18.726354
## iter 50 value 18.261874
## iter 60 value 17.375279
## iter 70 value 17.272874
## final value 17.272708
## converged
## # weights: 11
## initial value 124.240545
## iter 10 value 31.793757
## iter 20 value 2.518988
## iter 30 value 1.350434
## iter 40 value 1.278471
## iter 50 value 1.254587
## iter 60 value 1.250558
## iter 70 value 1.244589
## iter 80 value 1.241666
## iter 90 value 1.239132
## iter 100 value 1.238853
## final value 1.238853
## stopped after 100 iterations
## # weights: 27
## initial value 140.657042
## iter 10 value 68.608771
## iter 20 value 2.508125
## iter 30 value 0.155276
## iter 40 value 0.148941
## iter 50 value 0.135824
## iter 60 value 0.132117
## iter 70 value 0.120360
## iter 80 value 0.117594
## iter 90 value 0.111091
## iter 100 value 0.106654
## final value 0.106654
## stopped after 100 iterations
## # weights: 43
## initial value 131.474392
## iter 10 value 51.095077
## iter 20 value 4.258064
## iter 30 value 0.294087
## iter 40 value 0.240637
## iter 50 value 0.147708
## iter 60 value 0.130220
## iter 70 value 0.113449
## iter 80 value 0.105525
## iter 90 value 0.103452
## iter 100 value 0.102410
## final value 0.102410
## stopped after 100 iterations
## # weights: 11
## initial value 126.941216
## iter 10 value 50.201180
## iter 20 value 11.377953
## iter 30 value 0.833648
## iter 40 value 0.477354
## iter 50 value 0.393074
## iter 60 value 0.284497
## iter 70 value 0.179477
## iter 80 value 0.166860
## iter 90 value 0.136371
## iter 100 value 0.128704
## final value 0.128704
## stopped after 100 iterations
## # weights: 27
## initial value 163.512923
## iter 10 value 55.154305
## iter 20 value 30.099208
## iter 30 value 13.086336
## iter 40 value 1.564899
## iter 50 value 0.005150
## final value 0.000095
## converged
## # weights: 43
## initial value 165.986685
## iter 10 value 8.262906
## iter 20 value 0.287275
## iter 30 value 0.008530
## iter 40 value 0.000507
## final value 0.000060
## converged
## # weights: 11
## initial value 130.781547
## iter 10 value 64.016066
## iter 20 value 59.377091
## iter 30 value 46.305158
## final value 46.233545
## converged
## # weights: 27
## initial value 123.746583
## iter 10 value 64.169097
## iter 20 value 26.583969
## iter 30 value 23.288764
## iter 40 value 22.830961
## iter 50 value 22.658310
## iter 60 value 21.784170
## iter 70 value 19.521219
## iter 80 value 19.490079
## final value 19.490077
## converged
## # weights: 43
## initial value 129.032554
## iter 10 value 54.958299
## iter 20 value 30.089499
## iter 30 value 18.907607
## iter 40 value 18.642735
## iter 50 value 18.546593
## iter 60 value 18.482161
## iter 70 value 17.688529
## iter 80 value 17.517222
## iter 90 value 17.417797
## iter 100 value 17.383272
## final value 17.383272
## stopped after 100 iterations
## # weights: 11
## initial value 140.324350
## iter 10 value 102.545835
## iter 20 value 52.785556
## iter 30 value 52.761902
## iter 40 value 52.747449
## iter 50 value 52.739524
## iter 60 value 52.568751
## iter 70 value 47.522194
## iter 80 value 19.059520
## iter 90 value 2.297552
## iter 100 value 1.569365
## final value 1.569365
## stopped after 100 iterations
## # weights: 27
## initial value 136.066985
## iter 10 value 47.572753
## iter 20 value 2.669588
## iter 30 value 0.266704
## iter 40 value 0.242218
## iter 50 value 0.227691
## iter 60 value 0.181758
## iter 70 value 0.170911
## iter 80 value 0.162433
## iter 90 value 0.150295
## iter 100 value 0.138600
## final value 0.138600
## stopped after 100 iterations
## # weights: 43
## initial value 126.990370
## iter 10 value 42.020605
## iter 20 value 1.070532
## iter 30 value 0.150235
## iter 40 value 0.142362
## iter 50 value 0.135815
## iter 60 value 0.124701
## iter 70 value 0.115094
## iter 80 value 0.112376
## iter 90 value 0.110873
## iter 100 value 0.107998
## final value 0.107998
## stopped after 100 iterations
## # weights: 11
## initial value 125.517046
## iter 10 value 54.133213
## iter 20 value 54.039954
## final value 54.039844
## converged
## # weights: 27
## initial value 134.527176
## iter 10 value 63.325998
## iter 20 value 54.051174
## iter 30 value 54.039863
## final value 54.039837
## converged
## # weights: 43
## initial value 125.263169
## iter 10 value 8.369145
## iter 20 value 0.088437
## iter 30 value 0.000121
## iter 30 value 0.000071
## iter 30 value 0.000071
## final value 0.000071
## converged
## # weights: 11
## initial value 132.702757
## iter 10 value 121.259965
## iter 20 value 69.502372
## iter 30 value 60.884744
## iter 40 value 46.142000
## final value 46.110662
## converged
## # weights: 27
## initial value 129.165179
## iter 10 value 74.138320
## iter 20 value 48.194396
## iter 30 value 37.098861
## iter 40 value 19.611843
## iter 50 value 19.082309
## iter 60 value 19.055437
## iter 70 value 19.050432
## final value 19.050432
## converged
## # weights: 43
## initial value 147.643825
## iter 10 value 65.812789
## iter 20 value 29.416666
## iter 30 value 20.987004
## iter 40 value 18.799604
## iter 50 value 17.612592
## iter 60 value 17.180220
## iter 70 value 17.027069
## iter 80 value 16.949303
## iter 90 value 16.913852
## final value 16.899568
## converged
## # weights: 11
## initial value 137.878410
## iter 10 value 125.136531
## iter 20 value 125.135366
## iter 30 value 116.103410
## iter 40 value 50.084316
## iter 50 value 13.176241
## iter 60 value 1.871320
## iter 70 value 1.801871
## iter 80 value 1.732016
## iter 90 value 1.723453
## iter 100 value 1.717232
## final value 1.717232
## stopped after 100 iterations
## # weights: 27
## initial value 125.065096
## iter 10 value 55.246466
## iter 20 value 54.134106
## iter 30 value 54.128013
## iter 40 value 54.122799
## iter 50 value 54.093246
## iter 60 value 3.100612
## iter 70 value 0.212589
## iter 80 value 0.193410
## iter 90 value 0.190607
## iter 100 value 0.178396
## final value 0.178396
## stopped after 100 iterations
## # weights: 43
## initial value 128.788133
## iter 10 value 21.882046
## iter 20 value 1.768992
## iter 30 value 0.997501
## iter 40 value 0.570841
## iter 50 value 0.521656
## iter 60 value 0.471935
## iter 70 value 0.379924
## iter 80 value 0.335013
## iter 90 value 0.308309
## iter 100 value 0.269105
## final value 0.269105
## stopped after 100 iterations
## # weights: 11
## initial value 148.798489
## iter 10 value 125.163753
## final value 125.163520
## converged
## # weights: 27
## initial value 156.683229
## iter 10 value 85.974008
## iter 20 value 53.380396
## iter 30 value 53.313970
## final value 53.313877
## converged
## # weights: 43
## initial value 134.909579
## iter 10 value 1.586914
## iter 20 value 0.004237
## final value 0.000065
## converged
## # weights: 11
## initial value 135.593278
## iter 10 value 123.159070
## iter 20 value 51.523802
## iter 30 value 44.209709
## final value 44.208617
## converged
## # weights: 27
## initial value 138.808578
## iter 10 value 52.715702
## iter 20 value 33.298180
## iter 30 value 23.420879
## iter 40 value 18.210789
## iter 50 value 18.028104
## iter 60 value 18.002660
## iter 70 value 17.996770
## final value 17.996769
## converged
## # weights: 43
## initial value 123.981926
## iter 10 value 48.997938
## iter 20 value 22.674930
## iter 30 value 18.116109
## iter 40 value 17.381232
## iter 50 value 17.162984
## iter 60 value 16.913799
## iter 70 value 16.098548
## iter 80 value 15.850984
## final value 15.850977
## converged
## # weights: 11
## initial value 132.462571
## iter 10 value 125.149477
## iter 20 value 76.258209
## iter 30 value 50.897050
## iter 40 value 49.176872
## iter 50 value 29.379829
## iter 60 value 3.097808
## iter 70 value 1.453442
## iter 80 value 1.229379
## iter 90 value 1.098936
## iter 100 value 1.054294
## final value 1.054294
## stopped after 100 iterations
## # weights: 27
## initial value 139.613490
## iter 10 value 54.463500
## iter 20 value 53.406579
## iter 30 value 53.380180
## iter 40 value 52.510927
## iter 50 value 17.329180
## iter 60 value 1.108532
## iter 70 value 0.989261
## iter 80 value 0.983728
## iter 90 value 0.981261
## iter 100 value 0.981098
## final value 0.981098
## stopped after 100 iterations
## # weights: 43
## initial value 133.854004
## iter 10 value 2.565113
## iter 20 value 0.113211
## iter 30 value 0.104765
## iter 40 value 0.099607
## iter 50 value 0.091713
## iter 60 value 0.087966
## iter 70 value 0.085927
## iter 80 value 0.084539
## iter 90 value 0.082760
## iter 100 value 0.080892
## final value 0.080892
## stopped after 100 iterations
## # weights: 11
## initial value 128.564670
## iter 10 value 88.307556
## iter 20 value 39.172909
## iter 30 value 7.116214
## iter 40 value 3.691777
## iter 50 value 1.440942
## iter 60 value 0.747253
## iter 70 value 0.561263
## iter 80 value 0.468124
## iter 90 value 0.367579
## iter 100 value 0.350213
## final value 0.350213
## stopped after 100 iterations
## # weights: 27
## initial value 127.353724
## iter 10 value 37.626698
## iter 20 value 4.934642
## iter 30 value 2.864189
## iter 40 value 0.251006
## iter 50 value 0.011183
## final value 0.000086
## converged
## # weights: 43
## initial value 137.331514
## iter 10 value 48.049286
## iter 20 value 1.601438
## iter 30 value 0.000673
## final value 0.000077
## converged
## # weights: 11
## initial value 127.036046
## iter 10 value 49.716049
## iter 20 value 45.046852
## iter 30 value 44.999388
## final value 44.999250
## converged
## # weights: 27
## initial value 128.350838
## iter 10 value 63.463053
## iter 20 value 35.283754
## iter 30 value 23.704586
## iter 40 value 23.289025
## iter 50 value 22.846703
## iter 60 value 20.537374
## iter 70 value 20.477194
## final value 20.477176
## converged
## # weights: 43
## initial value 150.865565
## iter 10 value 67.742017
## iter 20 value 25.690311
## iter 30 value 21.070661
## iter 40 value 20.295155
## iter 50 value 19.507446
## iter 60 value 18.909876
## iter 70 value 18.497307
## iter 80 value 18.430471
## iter 90 value 18.418077
## iter 100 value 18.413372
## final value 18.413372
## stopped after 100 iterations
## # weights: 11
## initial value 134.399327
## iter 10 value 20.911414
## iter 20 value 4.195200
## iter 30 value 2.103994
## iter 40 value 2.048915
## iter 50 value 1.993776
## iter 60 value 1.990088
## iter 70 value 1.985887
## iter 80 value 1.985468
## iter 90 value 1.985342
## iter 100 value 1.985247
## final value 1.985247
## stopped after 100 iterations
## # weights: 27
## initial value 147.884859
## iter 10 value 33.734448
## iter 20 value 0.655722
## iter 30 value 0.242184
## iter 40 value 0.233739
## iter 50 value 0.211285
## iter 60 value 0.204011
## iter 70 value 0.197594
## iter 80 value 0.193342
## iter 90 value 0.186475
## iter 100 value 0.177945
## final value 0.177945
## stopped after 100 iterations
## # weights: 43
## initial value 113.076507
## iter 10 value 36.928804
## iter 20 value 0.509703
## iter 30 value 0.279841
## iter 40 value 0.233891
## iter 50 value 0.204863
## iter 60 value 0.193274
## iter 70 value 0.179341
## iter 80 value 0.170747
## iter 90 value 0.164184
## iter 100 value 0.157898
## final value 0.157898
## stopped after 100 iterations
## # weights: 27
## initial value 153.208074
## iter 10 value 38.129789
## iter 20 value 23.359486
## iter 30 value 22.171744
## iter 40 value 19.942348
## iter 50 value 19.292547
## iter 60 value 19.290461
## final value 19.290450
## convergedfit2## Neural Network
##
## 114 samples
## 4 predictor
## 3 classes: 'setosa', 'versicolor', 'virginica'
##
## No pre-processing
## Resampling: Bootstrapped (25 reps)
## Summary of sample sizes: 114, 114, 114, 114, 114, 114, ...
## Resampling results across tuning parameters:
##
## size decay Accuracy Kappa
## 1 0e+00 0.8524464 0.7840269
## 1 1e-04 0.9144437 0.8810990
## 1 1e-01 0.9632655 0.9443577
## 3 0e+00 0.8689832 0.8053334
## 3 1e-04 0.9705782 0.9555730
## 3 1e-01 0.9765072 0.9644706
## 5 0e+00 0.9705025 0.9553993
## 5 1e-04 0.9764515 0.9643741
## 5 1e-01 0.9765072 0.9644706
##
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were size = 3 and decay = 0.1.Use it to predict values
On training data:
train_predict2 <- predict(fit2, train)
confusionMatrix(train$species, train_predict2)## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 38 0 0
## versicolor 0 38 0
## virginica 0 0 38
##
## Overall Statistics
##
## Accuracy : 1
## 95% CI : (0.9682, 1)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 1.0000
## Specificity 1.0000 1.0000 1.0000
## Pos Pred Value 1.0000 1.0000 1.0000
## Neg Pred Value 1.0000 1.0000 1.0000
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.3333
## Detection Prevalence 0.3333 0.3333 0.3333
## Balanced Accuracy 1.0000 1.0000 1.0000And test data
test_predict2 <- predict(fit2, test)
confusionMatrix(test$species, test_predict2)## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 12 0 0
## versicolor 0 10 2
## virginica 0 0 12
##
## Overall Statistics
##
## Accuracy : 0.9444
## 95% CI : (0.8134, 0.9932)
## No Information Rate : 0.3889
## P-Value [Acc > NIR] : 2.763e-12
##
## Kappa : 0.9167
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 0.8571
## Specificity 1.0000 0.9231 1.0000
## Pos Pred Value 1.0000 0.8333 1.0000
## Neg Pred Value 1.0000 1.0000 0.9167
## Prevalence 0.3333 0.2778 0.3889
## Detection Rate 0.3333 0.2778 0.3333
## Detection Prevalence 0.3333 0.3333 0.3333
## Balanced Accuracy 1.0000 0.9615 0.9286Create model using bayesglm
fit3 <- train(species ~ ., data= train, method ="bayesglm")
fit3## Bayesian Generalized Linear Model
##
## 114 samples
## 4 predictor
## 3 classes: 'setosa', 'versicolor', 'virginica'
##
## No pre-processing
## Resampling: Bootstrapped (25 reps)
## Summary of sample sizes: 114, 114, 114, 114, 114, 114, ...
## Resampling results:
##
## Accuracy Kappa
## 0.6764353 0.5085229Use it to predict values
On training data:
train_predict3 <- predict(fit3, train)
confusionMatrix(train$species, train_predict3)## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 38 0 0
## versicolor 0 38 0
## virginica 0 38 0
##
## Overall Statistics
##
## Accuracy : 0.6667
## 95% CI : (0.5723, 0.7522)
## No Information Rate : 0.6667
## P-Value [Acc > NIR] : 0.5439
##
## Kappa : 0.5
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 0.5000 NA
## Specificity 1.0000 1.0000 0.6667
## Pos Pred Value 1.0000 1.0000 NA
## Neg Pred Value 1.0000 0.5000 NA
## Prevalence 0.3333 0.6667 0.0000
## Detection Rate 0.3333 0.3333 0.0000
## Detection Prevalence 0.3333 0.3333 0.3333
## Balanced Accuracy 1.0000 0.7500 NAAnd test data
test_predict3 <- predict(fit3, test)
confusionMatrix(test$species, test_predict3)## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 12 0 0
## versicolor 0 12 0
## virginica 0 12 0
##
## Overall Statistics
##
## Accuracy : 0.6667
## 95% CI : (0.4903, 0.8144)
## No Information Rate : 0.6667
## P-Value [Acc > NIR] : 0.5775
##
## Kappa : 0.5
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 0.5000 NA
## Specificity 1.0000 1.0000 0.6667
## Pos Pred Value 1.0000 1.0000 NA
## Neg Pred Value 1.0000 0.5000 NA
## Prevalence 0.3333 0.6667 0.0000
## Detection Rate 0.3333 0.3333 0.0000
## Detection Prevalence 0.3333 0.3333 0.3333
## Balanced Accuracy 1.0000 0.7500 NASimple KNN to determine sepal length
fit4 <- train(sepal_length ~ ., data= train, method ="knn")
train_predict4 <- predict(fit4, train)
blah <- cbind(train, train_predict4)
blah %>%
select(sepal_length, train_predict4) %>%
ggplot() +
geom_point(aes(sepal_length, train_predict4)) +
geom_abline() +
expand_limits(x = 0, y = 0) +
ylim(c(0,8))
Simple LM to determine sepal length
fit5 <- train(sepal_length ~ ., data= train, method ="lm")
train_predict5 <- predict(fit5, train)
blah2 <- cbind(train, train_predict5)
summary(fit5)##
## Call:
## lm(formula = .outcome ~ ., data = dat)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.89020 -0.19714 0.01149 0.18649 0.69654
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.12889 0.31172 6.830 5.21e-10 ***
## sepal_width 0.47875 0.09591 4.992 2.31e-06 ***
## petal_length 0.86921 0.07681 11.316 < 2e-16 ***
## petal_width -0.19129 0.17061 -1.121 0.264679
## speciesversicolor -0.89947 0.26383 -3.409 0.000917 ***
## speciesvirginica -1.40257 0.36502 -3.842 0.000206 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2962 on 108 degrees of freedom
## Multiple R-squared: 0.8772, Adjusted R-squared: 0.8715
## F-statistic: 154.3 on 5 and 108 DF, p-value: < 2.2e-16blah2 %>%
select(sepal_length, train_predict5) %>%
ggplot() +
geom_point(aes(sepal_length, train_predict5)) +
geom_abline() +
expand_limits(x = 0, y = 0) +
ylim(c(0,8))
What happens if I use CV?
Nothing apparently! Both produce the same results
fitControl <- trainControl(method = "cv",
number = 100,
repeats = 100)## Warning: `repeats` has no meaning for this resampling method.fit6 <- train(sepal_length ~ ., data= train, method ="lm", trcontrol = fitControl)## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregarded
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'trcontrol' will be disregardedtrain_predict6 <- predict(fit6, train)
blah3 <- cbind(train_predict5, train_predict6)Keras
Set up data
Seperate into X and Y
Xtrain <- train[1:4]
Ytrain <- train[5]
Xtest <- test[1:4]
Ytest <- test[5]OHE of targets
Ytraincat <- to_categorical(as.numeric(Ytrain$species) -1)
Ytestcat <- to_categorical(as.numeric(Ytest$species) -1) As matrix
Should have done this first!!!
Xtrain <- as.matrix(Xtrain)
Xtest <- as.matrix(Xtest)
Ytraincat <- as.matrix(Ytraincat)
Ytestcat <- as.matrix(Ytestcat)Construct model
# Initialize a sequential model
model <- keras_model_sequential()
# Add layers to the model
model %>%
layer_dense(units = 8, activation = 'relu', input_shape = c(4)) %>%
layer_dense(units = 3, activation = 'softmax')Compile Model
model %>% compile(
loss = 'categorical_crossentropy',
optimizer = 'adam',
metrics = 'accuracy'
)Fit Model
# Store the fitting history in `history`
history <- model %>% fit(
Xtrain,
Ytraincat,
epochs = 200,
batch_size = 5,
validation_split = 0.2
)
# Plot the history
plot(history)
Confusion Matrx
I should have kept a numeric version of the targets so had to convert here
classes <- model %>% predict_classes(Xtest)
table(as.numeric(Ytest$species) -1, classes)## classes
## 0 1 2
## 0 12 0 0
## 1 0 11 1
## 2 0 2 10classes2 <- model %>% predict_classes(Xtrain)
table(as.numeric(Ytrain$species) -1, classes2)## classes2
## 0 1 2
## 0 38 0 0
## 1 0 38 0
## 2 0 5 33Evaluate Model
On test
testscore <- model %>% evaluate(Xtest, Ytestcat)
testscore## $loss
## [1] 0.1536488
##
## $accuracy
## [1] 0.9166667On train
trainscore <- model %>% evaluate(Xtrain, Ytraincat)
trainscore## $loss
## [1] 0.1256034
##
## $accuracy
## [1] 0.9561403