USArrests
Oved Ruiz - a01174435
2025-02-21
Contexto
La base de datos USArrests contiene estadÃsticas en arrestos por cada 100,000 residentes por agresión, asesinato y violación en cada uno de los 50 estados de EE.UU. En 1973.
Instalar paquetesy llamar librerias
library(cluster)
library(ggplot2)
library(factoextra)## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBalibrary(data.table)
library(dplyr)##
## Adjuntando el paquete: 'dplyr'## The following objects are masked from 'package:data.table':
##
## between, first, last## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(sf)## Linking to GEOS 3.13.0, GDAL 3.10.1, PROJ 9.5.1; sf_use_s2() is TRUElibrary(rnaturalearth)
library(rnaturalearthdata)##
## Adjuntando el paquete: 'rnaturalearthdata'## The following object is masked from 'package:rnaturalearth':
##
## countries110library(devtools)## Cargando paquete requerido: usethislibrary(caret)## Cargando paquete requerido: latticelibrary(datasets)
library(ggplot2)
library(lattice)
library(DataExplorer)Importar base de datos
df <- USArrests
summary(df)## Murder Assault UrbanPop Rape
## Min. : 0.800 Min. : 45.0 Min. :32.00 Min. : 7.30
## 1st Qu.: 4.075 1st Qu.:109.0 1st Qu.:54.50 1st Qu.:15.07
## Median : 7.250 Median :159.0 Median :66.00 Median :20.10
## Mean : 7.788 Mean :170.8 Mean :65.54 Mean :21.23
## 3rd Qu.:11.250 3rd Qu.:249.0 3rd Qu.:77.75 3rd Qu.:26.18
## Max. :17.400 Max. :337.0 Max. :91.00 Max. :46.00Clusters
# Scale the data
scaled_df <- scale(df)
# Generate the clusters
n_clusters = 4
kmean <- kmeans(scaled_df, centers = n_clusters)
# Assign the labels
labels <- cbind(df, cluster = kmean$cluster)
# Plot the clusters
fviz_cluster(kmean, data = df)
# Optimize the clusters
set.seed(123)
optimal <- clusGap(scaled_df, FUN = kmeans, nstart = 1, K.max = 10)
plot(optimal, xlab = 'Number of clusters')
# Metodo de la silueta
# fviz_nbclust(df, kmeans, method = 'wss') +
# ggtitle('Elbow method')# Compare the clusters
cluster_mean <- aggregate(labels, by = list(labels$cluster), FUN = mean)
cluster_mean## Group.1 Murder Assault UrbanPop Rape cluster
## 1 1 5.050 136.70 79.3 17.590 1
## 2 2 6.880 136.50 60.6 19.330 2
## 3 3 2.680 70.10 51.0 10.910 3
## 4 4 12.165 255.25 68.4 29.165 4table(labels$cluster)##
## 1 2 3 4
## 10 10 10 20new_cluster_names <- c("Safe State", "High Crime State", "Dangerous State", "Low Crime State")
labels <- labels %>%
mutate(cluster_name = case_when(
cluster == 1 ~ new_cluster_names[1],
cluster == 2 ~ new_cluster_names[2],
cluster == 3 ~ new_cluster_names[3],
cluster == 4 ~ new_cluster_names[4]
))
print(labels)## Murder Assault UrbanPop Rape cluster cluster_name
## Alabama 13.2 236 58 21.2 4 Low Crime State
## Alaska 10.0 263 48 44.5 4 Low Crime State
## Arizona 8.1 294 80 31.0 4 Low Crime State
## Arkansas 8.8 190 50 19.5 2 High Crime State
## California 9.0 276 91 40.6 4 Low Crime State
## Colorado 7.9 204 78 38.7 4 Low Crime State
## Connecticut 3.3 110 77 11.1 1 Safe State
## Delaware 5.9 238 72 15.8 1 Safe State
## Florida 15.4 335 80 31.9 4 Low Crime State
## Georgia 17.4 211 60 25.8 4 Low Crime State
## Hawaii 5.3 46 83 20.2 1 Safe State
## Idaho 2.6 120 54 14.2 3 Dangerous State
## Illinois 10.4 249 83 24.0 4 Low Crime State
## Indiana 7.2 113 65 21.0 2 High Crime State
## Iowa 2.2 56 57 11.3 3 Dangerous State
## Kansas 6.0 115 66 18.0 2 High Crime State
## Kentucky 9.7 109 52 16.3 2 High Crime State
## Louisiana 15.4 249 66 22.2 4 Low Crime State
## Maine 2.1 83 51 7.8 3 Dangerous State
## Maryland 11.3 300 67 27.8 4 Low Crime State
## Massachusetts 4.4 149 85 16.3 1 Safe State
## Michigan 12.1 255 74 35.1 4 Low Crime State
## Minnesota 2.7 72 66 14.9 3 Dangerous State
## Mississippi 16.1 259 44 17.1 4 Low Crime State
## Missouri 9.0 178 70 28.2 4 Low Crime State
## Montana 6.0 109 53 16.4 2 High Crime State
## Nebraska 4.3 102 62 16.5 2 High Crime State
## Nevada 12.2 252 81 46.0 4 Low Crime State
## New Hampshire 2.1 57 56 9.5 3 Dangerous State
## New Jersey 7.4 159 89 18.8 1 Safe State
## New Mexico 11.4 285 70 32.1 4 Low Crime State
## New York 11.1 254 86 26.1 4 Low Crime State
## North Carolina 13.0 337 45 16.1 4 Low Crime State
## North Dakota 0.8 45 44 7.3 3 Dangerous State
## Ohio 7.3 120 75 21.4 1 Safe State
## Oklahoma 6.6 151 68 20.0 2 High Crime State
## Oregon 4.9 159 67 29.3 2 High Crime State
## Pennsylvania 6.3 106 72 14.9 1 Safe State
## Rhode Island 3.4 174 87 8.3 1 Safe State
## South Carolina 14.4 279 48 22.5 4 Low Crime State
## South Dakota 3.8 86 45 12.8 3 Dangerous State
## Tennessee 13.2 188 59 26.9 4 Low Crime State
## Texas 12.7 201 80 25.5 4 Low Crime State
## Utah 3.2 120 80 22.9 1 Safe State
## Vermont 2.2 48 32 11.2 3 Dangerous State
## Virginia 8.5 156 63 20.7 2 High Crime State
## Washington 4.0 145 73 26.2 1 Safe State
## West Virginia 5.7 81 39 9.3 3 Dangerous State
## Wisconsin 2.6 53 66 10.8 3 Dangerous State
## Wyoming 6.8 161 60 15.6 2 High Crime StateModelo de Random Forest
labels <- labels %>%
mutate(cluster_name = as.factor(cluster_name)) %>%
select(-cluster)
print(labels)## Murder Assault UrbanPop Rape cluster_name
## Alabama 13.2 236 58 21.2 Low Crime State
## Alaska 10.0 263 48 44.5 Low Crime State
## Arizona 8.1 294 80 31.0 Low Crime State
## Arkansas 8.8 190 50 19.5 High Crime State
## California 9.0 276 91 40.6 Low Crime State
## Colorado 7.9 204 78 38.7 Low Crime State
## Connecticut 3.3 110 77 11.1 Safe State
## Delaware 5.9 238 72 15.8 Safe State
## Florida 15.4 335 80 31.9 Low Crime State
## Georgia 17.4 211 60 25.8 Low Crime State
## Hawaii 5.3 46 83 20.2 Safe State
## Idaho 2.6 120 54 14.2 Dangerous State
## Illinois 10.4 249 83 24.0 Low Crime State
## Indiana 7.2 113 65 21.0 High Crime State
## Iowa 2.2 56 57 11.3 Dangerous State
## Kansas 6.0 115 66 18.0 High Crime State
## Kentucky 9.7 109 52 16.3 High Crime State
## Louisiana 15.4 249 66 22.2 Low Crime State
## Maine 2.1 83 51 7.8 Dangerous State
## Maryland 11.3 300 67 27.8 Low Crime State
## Massachusetts 4.4 149 85 16.3 Safe State
## Michigan 12.1 255 74 35.1 Low Crime State
## Minnesota 2.7 72 66 14.9 Dangerous State
## Mississippi 16.1 259 44 17.1 Low Crime State
## Missouri 9.0 178 70 28.2 Low Crime State
## Montana 6.0 109 53 16.4 High Crime State
## Nebraska 4.3 102 62 16.5 High Crime State
## Nevada 12.2 252 81 46.0 Low Crime State
## New Hampshire 2.1 57 56 9.5 Dangerous State
## New Jersey 7.4 159 89 18.8 Safe State
## New Mexico 11.4 285 70 32.1 Low Crime State
## New York 11.1 254 86 26.1 Low Crime State
## North Carolina 13.0 337 45 16.1 Low Crime State
## North Dakota 0.8 45 44 7.3 Dangerous State
## Ohio 7.3 120 75 21.4 Safe State
## Oklahoma 6.6 151 68 20.0 High Crime State
## Oregon 4.9 159 67 29.3 High Crime State
## Pennsylvania 6.3 106 72 14.9 Safe State
## Rhode Island 3.4 174 87 8.3 Safe State
## South Carolina 14.4 279 48 22.5 Low Crime State
## South Dakota 3.8 86 45 12.8 Dangerous State
## Tennessee 13.2 188 59 26.9 Low Crime State
## Texas 12.7 201 80 25.5 Low Crime State
## Utah 3.2 120 80 22.9 Safe State
## Vermont 2.2 48 32 11.2 Dangerous State
## Virginia 8.5 156 63 20.7 High Crime State
## Washington 4.0 145 73 26.2 Safe State
## West Virginia 5.7 81 39 9.3 Dangerous State
## Wisconsin 2.6 53 66 10.8 Dangerous State
## Wyoming 6.8 161 60 15.6 High Crime State# split the data
set.seed(123)
training <- createDataPartition(labels$cluster_name, p = 0.8, list = FALSE)
training_data <- labels[training, ]
test_data <- labels[-training, ]model <- train(
cluster_name ~ .,
data = training_data,
method = 'nnet',
preProcess = c('scale', 'center'),
trControl = trainControl(method = 'cv', number = 10)
)## # weights: 13
## initial value 52.116221
## iter 10 value 22.979921
## iter 20 value 21.617726
## iter 30 value 21.611760
## iter 40 value 21.610775
## iter 50 value 21.610593
## iter 50 value 21.610593
## iter 50 value 21.610593
## final value 21.610593
## converged
## # weights: 31
## initial value 54.099065
## iter 10 value 4.995589
## iter 20 value 0.009486
## final value 0.000054
## converged
## # weights: 49
## initial value 52.120979
## iter 10 value 9.977961
## iter 20 value 0.036501
## final value 0.000090
## converged
## # weights: 13
## initial value 51.411675
## iter 10 value 32.892405
## iter 20 value 30.207433
## final value 30.207382
## converged
## # weights: 31
## initial value 64.458832
## iter 10 value 20.208545
## iter 20 value 19.008376
## iter 30 value 18.851746
## iter 40 value 18.693471
## iter 50 value 18.683157
## iter 50 value 18.683157
## iter 50 value 18.683157
## final value 18.683157
## converged
## # weights: 49
## initial value 56.581586
## iter 10 value 18.197468
## iter 20 value 16.426749
## iter 30 value 16.239299
## iter 40 value 16.238199
## final value 16.238198
## converged
## # weights: 13
## initial value 51.716739
## iter 10 value 23.147390
## iter 20 value 17.631757
## iter 30 value 16.282374
## iter 40 value 11.912752
## iter 50 value 9.980716
## iter 60 value 9.826101
## iter 70 value 9.695089
## iter 80 value 9.197012
## iter 90 value 9.185900
## iter 100 value 9.175619
## final value 9.175619
## stopped after 100 iterations
## # weights: 31
## initial value 49.520737
## iter 10 value 9.795186
## iter 20 value 3.739103
## iter 30 value 3.382503
## iter 40 value 3.127599
## iter 50 value 2.325352
## iter 60 value 0.536733
## iter 70 value 0.342782
## iter 80 value 0.320620
## iter 90 value 0.284845
## iter 100 value 0.202199
## final value 0.202199
## stopped after 100 iterations
## # weights: 49
## initial value 59.413279
## iter 10 value 3.579442
## iter 20 value 0.177062
## iter 30 value 0.148812
## iter 40 value 0.129814
## iter 50 value 0.120345
## iter 60 value 0.116334
## iter 70 value 0.109206
## iter 80 value 0.103204
## iter 90 value 0.100500
## iter 100 value 0.097175
## final value 0.097175
## stopped after 100 iterations
## # weights: 13
## initial value 49.316975
## iter 10 value 22.618526
## iter 20 value 18.284076
## iter 30 value 15.304232
## iter 40 value 15.046297
## iter 50 value 14.298623
## iter 60 value 8.992678
## iter 70 value 7.586123
## iter 80 value 6.909568
## iter 90 value 6.856355
## iter 100 value 6.725461
## final value 6.725461
## stopped after 100 iterations
## # weights: 31
## initial value 52.449550
## iter 10 value 13.182943
## iter 20 value 0.264222
## iter 30 value 0.009333
## iter 40 value 0.002762
## final value 0.000073
## converged
## # weights: 49
## initial value 55.403389
## iter 10 value 5.876817
## iter 20 value 0.080420
## iter 30 value 0.000923
## final value 0.000073
## converged
## # weights: 13
## initial value 56.021994
## iter 10 value 31.178608
## iter 20 value 29.929985
## final value 29.929457
## converged
## # weights: 31
## initial value 55.157000
## iter 10 value 19.657673
## iter 20 value 18.415518
## iter 30 value 18.414324
## final value 18.414323
## converged
## # weights: 49
## initial value 54.316000
## iter 10 value 21.729740
## iter 20 value 16.319620
## iter 30 value 16.115091
## iter 40 value 16.113531
## final value 16.113528
## converged
## # weights: 13
## initial value 50.498615
## iter 10 value 30.035011
## iter 20 value 22.867407
## iter 30 value 22.848975
## iter 40 value 22.772774
## iter 50 value 22.416569
## iter 60 value 22.244525
## iter 70 value 22.201195
## iter 80 value 22.159986
## iter 90 value 22.147912
## iter 100 value 22.144711
## final value 22.144711
## stopped after 100 iterations
## # weights: 31
## initial value 65.534658
## iter 10 value 6.565414
## iter 20 value 0.192389
## iter 30 value 0.164371
## iter 40 value 0.129280
## iter 50 value 0.120841
## iter 60 value 0.114705
## iter 70 value 0.110305
## iter 80 value 0.107986
## iter 90 value 0.106719
## iter 100 value 0.105150
## final value 0.105150
## stopped after 100 iterations
## # weights: 49
## initial value 60.188524
## iter 10 value 2.873263
## iter 20 value 0.172720
## iter 30 value 0.150986
## iter 40 value 0.126915
## iter 50 value 0.121971
## iter 60 value 0.112863
## iter 70 value 0.105100
## iter 80 value 0.100685
## iter 90 value 0.095399
## iter 100 value 0.092388
## final value 0.092388
## stopped after 100 iterations
## # weights: 13
## initial value 51.075551
## iter 10 value 23.059438
## iter 20 value 18.798521
## iter 30 value 17.720069
## iter 40 value 17.711311
## iter 50 value 17.697112
## iter 60 value 17.617307
## iter 70 value 17.598133
## iter 80 value 17.593245
## iter 90 value 17.549367
## iter 100 value 17.546575
## final value 17.546575
## stopped after 100 iterations
## # weights: 31
## initial value 50.189915
## iter 10 value 5.702968
## iter 20 value 0.041499
## iter 30 value 0.000178
## iter 30 value 0.000100
## iter 30 value 0.000100
## final value 0.000100
## converged
## # weights: 49
## initial value 48.945589
## iter 10 value 3.399431
## iter 20 value 0.164070
## iter 30 value 0.004924
## iter 40 value 0.002668
## final value 0.000096
## converged
## # weights: 13
## initial value 57.508878
## iter 10 value 29.950906
## iter 20 value 29.687476
## final value 29.687410
## converged
## # weights: 31
## initial value 56.922655
## iter 10 value 20.450118
## iter 20 value 17.956605
## iter 30 value 17.903606
## iter 40 value 17.858701
## final value 17.853085
## converged
## # weights: 49
## initial value 56.117893
## iter 10 value 18.393147
## iter 20 value 15.977309
## iter 30 value 15.644858
## iter 40 value 15.639555
## iter 50 value 15.606812
## iter 60 value 15.486600
## iter 70 value 15.485916
## final value 15.485916
## converged
## # weights: 13
## initial value 51.542641
## iter 10 value 24.275276
## iter 20 value 21.484878
## iter 30 value 21.108215
## iter 40 value 21.016805
## iter 50 value 20.995176
## iter 60 value 20.983845
## iter 70 value 20.963701
## iter 80 value 20.860117
## iter 90 value 20.839022
## iter 100 value 19.583835
## final value 19.583835
## stopped after 100 iterations
## # weights: 31
## initial value 55.587875
## iter 10 value 14.733351
## iter 20 value 11.481733
## iter 30 value 11.034365
## iter 40 value 10.795005
## iter 50 value 10.629401
## iter 60 value 6.261132
## iter 70 value 0.489179
## iter 80 value 0.387801
## iter 90 value 0.358990
## iter 100 value 0.315604
## final value 0.315604
## stopped after 100 iterations
## # weights: 49
## initial value 46.432638
## iter 10 value 5.217843
## iter 20 value 0.416876
## iter 30 value 0.271250
## iter 40 value 0.226659
## iter 50 value 0.189875
## iter 60 value 0.148685
## iter 70 value 0.124372
## iter 80 value 0.111494
## iter 90 value 0.104530
## iter 100 value 0.101146
## final value 0.101146
## stopped after 100 iterations
## # weights: 13
## initial value 59.465164
## iter 10 value 23.837208
## iter 20 value 21.972129
## iter 30 value 21.926459
## iter 40 value 21.921458
## final value 21.921457
## converged
## # weights: 31
## initial value 55.518870
## iter 10 value 6.115283
## iter 20 value 2.803667
## iter 30 value 0.638613
## iter 40 value 0.101044
## iter 50 value 0.029303
## iter 60 value 0.010704
## iter 70 value 0.005386
## iter 80 value 0.002542
## iter 90 value 0.001554
## iter 100 value 0.001350
## final value 0.001350
## stopped after 100 iterations
## # weights: 49
## initial value 46.680663
## iter 10 value 1.013195
## iter 20 value 0.002391
## final value 0.000063
## converged
## # weights: 13
## initial value 49.751622
## iter 10 value 35.664867
## iter 20 value 30.893747
## iter 30 value 30.842907
## iter 40 value 30.841431
## final value 30.841410
## converged
## # weights: 31
## initial value 52.598224
## iter 10 value 20.560187
## iter 20 value 18.909314
## iter 30 value 18.821225
## final value 18.821219
## converged
## # weights: 49
## initial value 50.872298
## iter 10 value 18.422817
## iter 20 value 16.655003
## iter 30 value 16.585178
## iter 40 value 16.413468
## iter 50 value 16.412497
## final value 16.412496
## converged
## # weights: 13
## initial value 57.217155
## iter 10 value 24.902720
## iter 20 value 24.178928
## iter 30 value 24.176246
## iter 40 value 24.173377
## iter 50 value 24.169297
## iter 60 value 24.113955
## iter 70 value 23.892903
## iter 80 value 22.431672
## iter 90 value 19.942788
## iter 100 value 14.776878
## final value 14.776878
## stopped after 100 iterations
## # weights: 31
## initial value 57.149411
## iter 10 value 10.113007
## iter 20 value 6.650184
## iter 30 value 6.305432
## iter 40 value 5.139439
## iter 50 value 4.324924
## iter 60 value 4.012281
## iter 70 value 3.981113
## iter 80 value 3.817072
## iter 90 value 3.743945
## iter 100 value 3.690590
## final value 3.690590
## stopped after 100 iterations
## # weights: 49
## initial value 52.042206
## iter 10 value 3.678868
## iter 20 value 0.285262
## iter 30 value 0.248392
## iter 40 value 0.204152
## iter 50 value 0.160979
## iter 60 value 0.141652
## iter 70 value 0.134840
## iter 80 value 0.122514
## iter 90 value 0.115861
## iter 100 value 0.106892
## final value 0.106892
## stopped after 100 iterations
## # weights: 13
## initial value 56.375956
## iter 10 value 24.765656
## iter 20 value 24.125931
## final value 24.124665
## converged
## # weights: 31
## initial value 52.052573
## iter 10 value 17.165314
## iter 20 value 6.655472
## iter 30 value 2.841610
## iter 40 value 2.533361
## iter 50 value 2.507732
## iter 60 value 2.502126
## iter 70 value 2.493355
## iter 80 value 2.450227
## iter 90 value 2.333923
## iter 100 value 2.060373
## final value 2.060373
## stopped after 100 iterations
## # weights: 49
## initial value 59.165306
## iter 10 value 6.559046
## iter 20 value 0.015291
## final value 0.000079
## converged
## # weights: 13
## initial value 49.949119
## iter 10 value 31.200649
## iter 20 value 29.803881
## final value 29.780093
## converged
## # weights: 31
## initial value 54.060467
## iter 10 value 23.385542
## iter 20 value 18.646394
## iter 30 value 18.528779
## final value 18.528627
## converged
## # weights: 49
## initial value 54.799240
## iter 10 value 18.988505
## iter 20 value 17.381968
## iter 30 value 17.147115
## iter 40 value 17.007255
## iter 50 value 16.986250
## iter 60 value 16.986155
## final value 16.986152
## converged
## # weights: 13
## initial value 51.481757
## iter 10 value 23.379796
## iter 20 value 21.499050
## iter 30 value 20.573314
## iter 40 value 19.976979
## iter 50 value 16.006588
## iter 60 value 10.840780
## iter 70 value 10.436921
## iter 80 value 9.971905
## iter 90 value 9.960733
## iter 100 value 9.959128
## final value 9.959128
## stopped after 100 iterations
## # weights: 31
## initial value 54.058446
## iter 10 value 17.630572
## iter 20 value 3.047147
## iter 30 value 0.157937
## iter 40 value 0.142202
## iter 50 value 0.131654
## iter 60 value 0.117311
## iter 70 value 0.113007
## iter 80 value 0.110438
## iter 90 value 0.109481
## iter 100 value 0.107759
## final value 0.107759
## stopped after 100 iterations
## # weights: 49
## initial value 56.749507
## iter 10 value 4.085875
## iter 20 value 0.245387
## iter 30 value 0.183887
## iter 40 value 0.146488
## iter 50 value 0.129128
## iter 60 value 0.119442
## iter 70 value 0.107908
## iter 80 value 0.100516
## iter 90 value 0.096734
## iter 100 value 0.094596
## final value 0.094596
## stopped after 100 iterations
## # weights: 13
## initial value 51.545718
## iter 10 value 23.065084
## iter 20 value 22.180652
## iter 30 value 20.761207
## iter 40 value 20.133806
## iter 50 value 19.840173
## iter 60 value 19.721684
## iter 70 value 19.423660
## iter 80 value 19.300545
## iter 90 value 19.256965
## iter 100 value 19.233888
## final value 19.233888
## stopped after 100 iterations
## # weights: 31
## initial value 51.166218
## iter 10 value 8.854028
## iter 20 value 5.598661
## iter 30 value 3.748796
## iter 40 value 3.177309
## iter 50 value 3.019161
## iter 60 value 3.014512
## iter 70 value 3.014449
## iter 80 value 3.014398
## iter 90 value 3.014347
## final value 3.014346
## converged
## # weights: 49
## initial value 51.385594
## iter 10 value 3.864726
## iter 20 value 0.023973
## iter 30 value 0.000550
## final value 0.000082
## converged
## # weights: 13
## initial value 58.498018
## iter 10 value 29.814176
## iter 20 value 29.618570
## final value 29.618484
## converged
## # weights: 31
## initial value 53.253606
## iter 10 value 21.683680
## iter 20 value 18.745500
## iter 30 value 18.734290
## final value 18.733684
## converged
## # weights: 49
## initial value 52.963155
## iter 10 value 17.326626
## iter 20 value 15.840120
## iter 30 value 15.525514
## iter 40 value 15.507347
## iter 50 value 15.507236
## final value 15.507236
## converged
## # weights: 13
## initial value 48.202119
## iter 10 value 23.594806
## iter 20 value 22.345142
## iter 30 value 22.273959
## iter 40 value 22.192792
## iter 50 value 22.172968
## iter 60 value 22.111989
## iter 70 value 21.380158
## iter 80 value 20.845710
## iter 90 value 20.806068
## iter 100 value 19.980391
## final value 19.980391
## stopped after 100 iterations
## # weights: 31
## initial value 51.630029
## iter 10 value 9.836435
## iter 20 value 0.531847
## iter 30 value 0.371597
## iter 40 value 0.321157
## iter 50 value 0.280553
## iter 60 value 0.259706
## iter 70 value 0.242709
## iter 80 value 0.231569
## iter 90 value 0.221853
## iter 100 value 0.215153
## final value 0.215153
## stopped after 100 iterations
## # weights: 49
## initial value 52.307769
## iter 10 value 4.045411
## iter 20 value 0.204075
## iter 30 value 0.176379
## iter 40 value 0.156087
## iter 50 value 0.143211
## iter 60 value 0.126212
## iter 70 value 0.117100
## iter 80 value 0.110159
## iter 90 value 0.107309
## iter 100 value 0.103566
## final value 0.103566
## stopped after 100 iterations
## # weights: 13
## initial value 50.458978
## iter 10 value 23.181762
## iter 20 value 23.057675
## iter 30 value 23.037111
## iter 40 value 22.999354
## iter 50 value 22.798011
## iter 60 value 21.998726
## iter 70 value 21.945189
## iter 80 value 21.918283
## iter 90 value 21.133511
## iter 100 value 19.272280
## final value 19.272280
## stopped after 100 iterations
## # weights: 31
## initial value 55.515363
## iter 10 value 11.673394
## iter 20 value 2.871300
## iter 30 value 0.003099
## final value 0.000091
## converged
## # weights: 49
## initial value 49.858083
## iter 10 value 1.775548
## iter 20 value 0.000401
## final value 0.000071
## converged
## # weights: 13
## initial value 50.349839
## iter 10 value 29.287836
## iter 20 value 28.948251
## final value 28.948219
## converged
## # weights: 31
## initial value 50.477634
## iter 10 value 26.096557
## iter 20 value 18.366878
## iter 30 value 18.146232
## iter 40 value 18.142578
## final value 18.142578
## converged
## # weights: 49
## initial value 70.266878
## iter 10 value 18.199665
## iter 20 value 16.175907
## iter 30 value 16.148424
## iter 40 value 16.143947
## final value 16.143919
## converged
## # weights: 13
## initial value 49.686192
## iter 10 value 23.234192
## iter 20 value 20.062437
## iter 30 value 18.663716
## iter 40 value 17.359470
## iter 50 value 16.048058
## iter 60 value 10.719124
## iter 70 value 9.664989
## iter 80 value 9.266331
## iter 90 value 8.988284
## iter 100 value 8.559374
## final value 8.559374
## stopped after 100 iterations
## # weights: 31
## initial value 54.171408
## iter 10 value 13.656563
## iter 20 value 6.386345
## iter 30 value 5.460039
## iter 40 value 3.709205
## iter 50 value 2.130715
## iter 60 value 1.492281
## iter 70 value 1.347943
## iter 80 value 1.210905
## iter 90 value 1.003687
## iter 100 value 0.971483
## final value 0.971483
## stopped after 100 iterations
## # weights: 49
## initial value 52.069662
## iter 10 value 0.655843
## iter 20 value 0.354074
## iter 30 value 0.240498
## iter 40 value 0.169816
## iter 50 value 0.147729
## iter 60 value 0.124697
## iter 70 value 0.119114
## iter 80 value 0.114547
## iter 90 value 0.110633
## iter 100 value 0.108335
## final value 0.108335
## stopped after 100 iterations
## # weights: 13
## initial value 57.589874
## iter 10 value 33.376929
## iter 20 value 29.104331
## iter 30 value 28.537574
## iter 40 value 28.499295
## iter 50 value 28.435001
## iter 60 value 28.080424
## iter 70 value 27.972488
## iter 80 value 27.838201
## iter 90 value 27.809540
## iter 100 value 27.765989
## final value 27.765989
## stopped after 100 iterations
## # weights: 31
## initial value 50.413803
## iter 10 value 15.685293
## iter 20 value 0.110239
## iter 30 value 0.000248
## final value 0.000067
## converged
## # weights: 49
## initial value 50.658089
## iter 10 value 2.318984
## iter 20 value 0.005450
## final value 0.000055
## converged
## # weights: 13
## initial value 56.924422
## iter 10 value 30.831132
## iter 20 value 30.250194
## final value 30.250189
## converged
## # weights: 31
## initial value 57.771461
## iter 10 value 21.235261
## iter 20 value 18.872212
## iter 30 value 18.705789
## iter 40 value 18.700743
## final value 18.700742
## converged
## # weights: 49
## initial value 55.297053
## iter 10 value 18.061170
## iter 20 value 16.466768
## iter 30 value 16.399129
## iter 40 value 16.335166
## iter 50 value 16.271119
## iter 60 value 16.270876
## final value 16.270875
## converged
## # weights: 13
## initial value 58.712642
## iter 10 value 23.873448
## iter 20 value 17.735656
## iter 30 value 12.071993
## iter 40 value 9.619071
## iter 50 value 9.131800
## iter 60 value 9.078221
## iter 70 value 9.069428
## iter 80 value 9.063154
## iter 90 value 9.055510
## iter 100 value 9.044493
## final value 9.044493
## stopped after 100 iterations
## # weights: 31
## initial value 49.320478
## iter 10 value 9.065647
## iter 20 value 3.261085
## iter 30 value 1.782577
## iter 40 value 0.695241
## iter 50 value 0.594693
## iter 60 value 0.477195
## iter 70 value 0.458350
## iter 80 value 0.393243
## iter 90 value 0.338720
## iter 100 value 0.305230
## final value 0.305230
## stopped after 100 iterations
## # weights: 49
## initial value 50.093008
## iter 10 value 4.725724
## iter 20 value 0.330928
## iter 30 value 0.304852
## iter 40 value 0.243937
## iter 50 value 0.184527
## iter 60 value 0.149030
## iter 70 value 0.138952
## iter 80 value 0.131202
## iter 90 value 0.124699
## iter 100 value 0.119725
## final value 0.119725
## stopped after 100 iterations
## # weights: 13
## initial value 48.808703
## iter 10 value 23.436771
## iter 20 value 20.178103
## iter 30 value 15.622456
## iter 40 value 11.444742
## iter 50 value 10.149950
## iter 60 value 9.242817
## iter 70 value 8.674975
## iter 80 value 8.243298
## iter 90 value 7.999979
## iter 100 value 7.791685
## final value 7.791685
## stopped after 100 iterations
## # weights: 31
## initial value 44.808279
## iter 10 value 3.908462
## iter 20 value 0.020993
## final value 0.000064
## converged
## # weights: 49
## initial value 53.921382
## iter 10 value 4.221689
## iter 20 value 0.014770
## iter 30 value 0.002208
## final value 0.000054
## converged
## # weights: 13
## initial value 52.344561
## iter 10 value 31.908573
## iter 20 value 29.417846
## final value 29.387985
## converged
## # weights: 31
## initial value 60.535716
## iter 10 value 23.492196
## iter 20 value 17.473166
## iter 30 value 17.297074
## final value 17.296388
## converged
## # weights: 49
## initial value 57.494544
## iter 10 value 16.535061
## iter 20 value 15.272767
## iter 30 value 15.213974
## iter 40 value 15.209630
## final value 15.209626
## converged
## # weights: 13
## initial value 56.045316
## iter 10 value 24.561951
## iter 20 value 18.639107
## iter 30 value 15.418322
## iter 40 value 10.684061
## iter 50 value 9.830400
## iter 60 value 9.632803
## iter 70 value 9.533287
## iter 80 value 9.223434
## iter 90 value 9.203076
## iter 100 value 9.199413
## final value 9.199413
## stopped after 100 iterations
## # weights: 31
## initial value 56.377866
## iter 10 value 2.592824
## iter 20 value 0.420096
## iter 30 value 0.271593
## iter 40 value 0.221900
## iter 50 value 0.159712
## iter 60 value 0.137396
## iter 70 value 0.128155
## iter 80 value 0.121056
## iter 90 value 0.109916
## iter 100 value 0.105751
## final value 0.105751
## stopped after 100 iterations
## # weights: 49
## initial value 47.569864
## iter 10 value 3.318375
## iter 20 value 0.302141
## iter 30 value 0.266062
## iter 40 value 0.232458
## iter 50 value 0.197361
## iter 60 value 0.169139
## iter 70 value 0.146873
## iter 80 value 0.134597
## iter 90 value 0.126511
## iter 100 value 0.114335
## final value 0.114335
## stopped after 100 iterations
## # weights: 13
## initial value 58.188528
## iter 10 value 24.387616
## iter 20 value 24.126265
## iter 30 value 24.124680
## final value 24.124660
## converged
## # weights: 31
## initial value 51.526223
## iter 10 value 8.398731
## iter 20 value 4.963183
## iter 30 value 3.867587
## iter 40 value 2.925045
## iter 50 value 2.478015
## iter 60 value 2.381370
## iter 70 value 2.374012
## iter 80 value 2.371618
## iter 90 value 2.329656
## iter 100 value 2.288486
## final value 2.288486
## stopped after 100 iterations
## # weights: 49
## initial value 53.611894
## iter 10 value 6.933767
## iter 20 value 0.030238
## iter 30 value 0.000550
## final value 0.000087
## converged
## # weights: 13
## initial value 50.463447
## iter 10 value 32.362995
## iter 20 value 30.607819
## final value 30.607712
## converged
## # weights: 31
## initial value 55.119665
## iter 10 value 20.515404
## iter 20 value 18.947805
## iter 30 value 18.452973
## iter 40 value 18.407001
## final value 18.406843
## converged
## # weights: 49
## initial value 53.051331
## iter 10 value 18.548364
## iter 20 value 16.429410
## iter 30 value 15.976858
## iter 40 value 15.962644
## iter 50 value 15.962335
## final value 15.962335
## converged
## # weights: 13
## initial value 49.753849
## iter 10 value 24.053460
## iter 20 value 21.847185
## iter 30 value 12.885010
## iter 40 value 8.399066
## iter 50 value 7.972040
## iter 60 value 7.891578
## iter 70 value 7.843990
## iter 80 value 7.822940
## iter 90 value 7.818793
## iter 100 value 7.808103
## final value 7.808103
## stopped after 100 iterations
## # weights: 31
## initial value 58.887796
## iter 10 value 7.272140
## iter 20 value 0.202101
## iter 30 value 0.168480
## iter 40 value 0.149096
## iter 50 value 0.136488
## iter 60 value 0.128016
## iter 70 value 0.125784
## iter 80 value 0.123931
## iter 90 value 0.121345
## iter 100 value 0.119671
## final value 0.119671
## stopped after 100 iterations
## # weights: 49
## initial value 51.880379
## iter 10 value 3.656291
## iter 20 value 0.211031
## iter 30 value 0.182190
## iter 40 value 0.135686
## iter 50 value 0.115796
## iter 60 value 0.101491
## iter 70 value 0.098736
## iter 80 value 0.095314
## iter 90 value 0.093418
## iter 100 value 0.091782
## final value 0.091782
## stopped after 100 iterations
## # weights: 49
## initial value 71.621878
## iter 10 value 22.337349
## iter 20 value 18.616792
## iter 30 value 18.321087
## iter 40 value 18.303398
## iter 50 value 18.297871
## iter 60 value 18.297708
## final value 18.297708
## convergedtraining_results <- predict(model, training_data)
test_results <- predict(model, test_data)
# Confusion matrix for training data
cmtr <- confusionMatrix(training_results, training_data$cluster_name)
print(cmtr)## Confusion Matrix and Statistics
##
## Reference
## Prediction Dangerous State High Crime State Low Crime State Safe State
## Dangerous State 8 0 0 0
## High Crime State 0 8 0 0
## Low Crime State 0 0 16 0
## Safe State 0 0 0 8
##
## Overall Statistics
##
## Accuracy : 1
## 95% CI : (0.9119, 1)
## No Information Rate : 0.4
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: Dangerous State Class: High Crime State
## Sensitivity 1.0 1.0
## Specificity 1.0 1.0
## Pos Pred Value 1.0 1.0
## Neg Pred Value 1.0 1.0
## Prevalence 0.2 0.2
## Detection Rate 0.2 0.2
## Detection Prevalence 0.2 0.2
## Balanced Accuracy 1.0 1.0
## Class: Low Crime State Class: Safe State
## Sensitivity 1.0 1.0
## Specificity 1.0 1.0
## Pos Pred Value 1.0 1.0
## Neg Pred Value 1.0 1.0
## Prevalence 0.4 0.2
## Detection Rate 0.4 0.2
## Detection Prevalence 0.4 0.2
## Balanced Accuracy 1.0 1.0# Confusion matrix for testing data
cmts <- confusionMatrix(test_results, test_data$cluster_name)
print(cmts)## Confusion Matrix and Statistics
##
## Reference
## Prediction Dangerous State High Crime State Low Crime State Safe State
## Dangerous State 2 0 0 0
## High Crime State 0 2 0 0
## Low Crime State 0 0 4 0
## Safe State 0 0 0 2
##
## Overall Statistics
##
## Accuracy : 1
## 95% CI : (0.6915, 1)
## No Information Rate : 0.4
## P-Value [Acc > NIR] : 0.0001049
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: Dangerous State Class: High Crime State
## Sensitivity 1.0 1.0
## Specificity 1.0 1.0
## Pos Pred Value 1.0 1.0
## Neg Pred Value 1.0 1.0
## Prevalence 0.2 0.2
## Detection Rate 0.2 0.2
## Detection Prevalence 0.2 0.2
## Balanced Accuracy 1.0 1.0
## Class: Low Crime State Class: Safe State
## Sensitivity 1.0 1.0
## Specificity 1.0 1.0
## Pos Pred Value 1.0 1.0
## Neg Pred Value 1.0 1.0
## Prevalence 0.4 0.2
## Detection Rate 0.4 0.2
## Detection Prevalence 0.4 0.2
## Balanced Accuracy 1.0 1.0LS0tDQp0aXRsZTogIlVTQXJyZXN0cyINCmF1dGhvcjogJ092ZWQgUnVpeiAtIGEwMTE3NDQzNScNCmRhdGU6ICIyMDI1LTAyLTIxIg0Kb3V0cHV0OiANCiAgaHRtbF9kb2N1bWVudDoNCiAgICAgIHRvYzogVFJVRQ0KICAgICAgdG9jX2Zsb2F0OiBUUlVFDQogICAgICBjb2RlX2Rvd25sb2FkOiBUUlVFDQogICAgICB0aGVtZTogJ2pvdXJuYWwnDQotLS0NCg0KIVtdKEM6XFxVc2Vyc1xcQUNFUlxcRG93bmxvYWRzXFxPSVAgKDEpLmpwZykNCg0KIyA8c3BhbiBzdHlsZT0iY29sb3I6IEJsdWU7Ij5Db250ZXh0bzwvc3Bhbj4NCg0KDQpMYSBiYXNlIGRlIGRhdG9zICoqVVNBcnJlc3RzKiogY29udGllbmUgZXN0YWTDrXN0aWNhcyBlbiBhcnJlc3RvcyBwb3IgY2FkYSAxMDAsMDAwIHJlc2lkZW50ZXMgcG9yIGFncmVzacOzbiwgYXNlc2luYXRvIHkgdmlvbGFjacOzbiBlbiBjYWRhIHVubyBkZSBsb3MgNTAgZXN0YWRvcyBkZSBFRS5VVS4gRW4gMTk3My4gIA0KDQojIDxzcGFuIHN0eWxlPSJjb2xvcjogQmx1ZTsiPkluc3RhbGFyIHBhcXVldGVzeSBsbGFtYXIgbGlicmVyaWFzPC9zcGFuPg0KDQpgYGB7cn0NCmxpYnJhcnkoY2x1c3RlcikNCmxpYnJhcnkoZ2dwbG90MikNCmxpYnJhcnkoZmFjdG9leHRyYSkNCmxpYnJhcnkoZGF0YS50YWJsZSkNCmxpYnJhcnkoZHBseXIpDQpsaWJyYXJ5KHNmKQ0KbGlicmFyeShybmF0dXJhbGVhcnRoKQ0KbGlicmFyeShybmF0dXJhbGVhcnRoZGF0YSkNCmxpYnJhcnkoZGV2dG9vbHMpDQpsaWJyYXJ5KGNhcmV0KQ0KbGlicmFyeShkYXRhc2V0cykNCmxpYnJhcnkoZ2dwbG90MikNCmxpYnJhcnkobGF0dGljZSkNCmxpYnJhcnkoRGF0YUV4cGxvcmVyKQ0KYGBgDQoNCiMgPHNwYW4gc3R5bGU9ImNvbG9yOiBCbHVlOyI+SW1wb3J0YXIgYmFzZSBkZSBkYXRvczwvc3Bhbj4NCg0KYGBge3J9DQpkZiA8LSBVU0FycmVzdHMNCnN1bW1hcnkoZGYpDQpgYGANCg0KIyA8c3BhbiBzdHlsZT0iY29sb3I6IEJsdWU7Ij5DbHVzdGVyczwvc3Bhbj4NCg0KYGBge3J9DQojIFNjYWxlIHRoZSBkYXRhDQpzY2FsZWRfZGYgPC0gc2NhbGUoZGYpDQojIEdlbmVyYXRlIHRoZSBjbHVzdGVycw0Kbl9jbHVzdGVycyA9IDQNCmttZWFuIDwtIGttZWFucyhzY2FsZWRfZGYsIGNlbnRlcnMgPSBuX2NsdXN0ZXJzKQ0KIyBBc3NpZ24gdGhlIGxhYmVscw0KbGFiZWxzIDwtIGNiaW5kKGRmLCBjbHVzdGVyID0ga21lYW4kY2x1c3RlcikNCiMgUGxvdCB0aGUgY2x1c3RlcnMNCmZ2aXpfY2x1c3RlcihrbWVhbiwgZGF0YSA9IGRmKQ0KYGBgDQoNCmBgYHtyfQ0KIyBPcHRpbWl6ZSB0aGUgY2x1c3RlcnMNCnNldC5zZWVkKDEyMykNCm9wdGltYWwgPC0gY2x1c0dhcChzY2FsZWRfZGYsIEZVTiA9IGttZWFucywgbnN0YXJ0ID0gMSwgSy5tYXggPSAxMCkNCnBsb3Qob3B0aW1hbCwgeGxhYiA9ICdOdW1iZXIgb2YgY2x1c3RlcnMnKQ0KIyBNZXRvZG8gZGUgbGEgc2lsdWV0YQ0KIyBmdml6X25iY2x1c3QoZGYsIGttZWFucywgbWV0aG9kID0gJ3dzcycpICsNCiMgICBnZ3RpdGxlKCdFbGJvdyBtZXRob2QnKQ0KYGBgDQoNCmBgYHtyfQ0KIyBDb21wYXJlIHRoZSBjbHVzdGVycw0KY2x1c3Rlcl9tZWFuIDwtIGFnZ3JlZ2F0ZShsYWJlbHMsIGJ5ID0gbGlzdChsYWJlbHMkY2x1c3RlciksIEZVTiA9IG1lYW4pDQpjbHVzdGVyX21lYW4NCnRhYmxlKGxhYmVscyRjbHVzdGVyKQ0KYGBgDQoNCmBgYHtyfQ0KbmV3X2NsdXN0ZXJfbmFtZXMgPC0gYygiU2FmZSBTdGF0ZSIsICJIaWdoIENyaW1lIFN0YXRlIiwgIkRhbmdlcm91cyBTdGF0ZSIsICJMb3cgQ3JpbWUgU3RhdGUiKQ0KDQpsYWJlbHMgPC0gbGFiZWxzICU+JQ0KICBtdXRhdGUoY2x1c3Rlcl9uYW1lID0gY2FzZV93aGVuKA0KICAgIGNsdXN0ZXIgPT0gMSB+IG5ld19jbHVzdGVyX25hbWVzWzFdLA0KICAgIGNsdXN0ZXIgPT0gMiB+IG5ld19jbHVzdGVyX25hbWVzWzJdLA0KICAgIGNsdXN0ZXIgPT0gMyB+IG5ld19jbHVzdGVyX25hbWVzWzNdLA0KICAgIGNsdXN0ZXIgPT0gNCB+IG5ld19jbHVzdGVyX25hbWVzWzRdDQogICkpDQpwcmludChsYWJlbHMpDQoNCmBgYA0KDQojIDxzcGFuIHN0eWxlPSJjb2xvcjogQmx1ZTsiPk1vZGVsbyBkZSBSYW5kb20gRm9yZXN0PC9zcGFuPg0KDQpgYGB7cn0NCmxhYmVscyA8LSBsYWJlbHMgJT4lDQogIG11dGF0ZShjbHVzdGVyX25hbWUgPSBhcy5mYWN0b3IoY2x1c3Rlcl9uYW1lKSkgJT4lDQogIHNlbGVjdCgtY2x1c3RlcikNCnByaW50KGxhYmVscykNCmBgYA0KDQpgYGB7cn0NCiMgc3BsaXQgdGhlIGRhdGEgDQpzZXQuc2VlZCgxMjMpDQp0cmFpbmluZyA8LSBjcmVhdGVEYXRhUGFydGl0aW9uKGxhYmVscyRjbHVzdGVyX25hbWUsIHAgPSAwLjgsIGxpc3QgPSBGQUxTRSkNCnRyYWluaW5nX2RhdGEgPC0gbGFiZWxzW3RyYWluaW5nLCBdDQp0ZXN0X2RhdGEgPC0gbGFiZWxzWy10cmFpbmluZywgXQ0KYGBgDQoNCmBgYHtyfQ0KbW9kZWwgPC0gdHJhaW4oDQogIGNsdXN0ZXJfbmFtZSB+IC4sIA0KICBkYXRhID0gdHJhaW5pbmdfZGF0YSwNCiAgbWV0aG9kID0gJ25uZXQnLA0KICBwcmVQcm9jZXNzID0gYygnc2NhbGUnLCAnY2VudGVyJyksDQogIHRyQ29udHJvbCA9IHRyYWluQ29udHJvbChtZXRob2QgPSAnY3YnLCBudW1iZXIgPSAxMCkNCikNCg0KdHJhaW5pbmdfcmVzdWx0cyA8LSBwcmVkaWN0KG1vZGVsLCB0cmFpbmluZ19kYXRhKQ0KdGVzdF9yZXN1bHRzIDwtIHByZWRpY3QobW9kZWwsIHRlc3RfZGF0YSkNCg0KIyBDb25mdXNpb24gbWF0cml4IGZvciB0cmFpbmluZyBkYXRhDQpjbXRyIDwtIGNvbmZ1c2lvbk1hdHJpeCh0cmFpbmluZ19yZXN1bHRzLCB0cmFpbmluZ19kYXRhJGNsdXN0ZXJfbmFtZSkNCnByaW50KGNtdHIpDQoNCiMgQ29uZnVzaW9uIG1hdHJpeCBmb3IgdGVzdGluZyBkYXRhDQpjbXRzIDwtIGNvbmZ1c2lvbk1hdHJpeCh0ZXN0X3Jlc3VsdHMsIHRlc3RfZGF0YSRjbHVzdGVyX25hbWUpDQpwcmludChjbXRzKQ0KYGBgDQoNCg==