Create a Standalone Model:Sonar Dataset Using Random Forest
Load packages
library(caret)
## Warning: package 'caret' was built under R version 4.2.1
## Loading required package: ggplot2
## Warning: package 'ggplot2' was built under R version 4.2.1
## Loading required package: lattice
library(mlbench)
## Warning: package 'mlbench' was built under R version 4.2.1
library(randomForest)
## Warning: package 'randomForest' was built under R version 4.2.2
## randomForest 4.7-1.1
## Type rfNews() to see new features/changes/bug fixes.
##
## Attaching package: 'randomForest'
## The following object is masked from 'package:ggplot2':
##
## margin
library(ggplot2)
library(rpart)
Load the Sonar dataset
data(Sonar)
set.seed(7)
head(Sonar)
## V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11
## 1 0.0200 0.0371 0.0428 0.0207 0.0954 0.0986 0.1539 0.1601 0.3109 0.2111 0.1609
## 2 0.0453 0.0523 0.0843 0.0689 0.1183 0.2583 0.2156 0.3481 0.3337 0.2872 0.4918
## 3 0.0262 0.0582 0.1099 0.1083 0.0974 0.2280 0.2431 0.3771 0.5598 0.6194 0.6333
## 4 0.0100 0.0171 0.0623 0.0205 0.0205 0.0368 0.1098 0.1276 0.0598 0.1264 0.0881
## 5 0.0762 0.0666 0.0481 0.0394 0.0590 0.0649 0.1209 0.2467 0.3564 0.4459 0.4152
## 6 0.0286 0.0453 0.0277 0.0174 0.0384 0.0990 0.1201 0.1833 0.2105 0.3039 0.2988
## V12 V13 V14 V15 V16 V17 V18 V19 V20 V21 V22
## 1 0.1582 0.2238 0.0645 0.0660 0.2273 0.3100 0.2999 0.5078 0.4797 0.5783 0.5071
## 2 0.6552 0.6919 0.7797 0.7464 0.9444 1.0000 0.8874 0.8024 0.7818 0.5212 0.4052
## 3 0.7060 0.5544 0.5320 0.6479 0.6931 0.6759 0.7551 0.8929 0.8619 0.7974 0.6737
## 4 0.1992 0.0184 0.2261 0.1729 0.2131 0.0693 0.2281 0.4060 0.3973 0.2741 0.3690
## 5 0.3952 0.4256 0.4135 0.4528 0.5326 0.7306 0.6193 0.2032 0.4636 0.4148 0.4292
## 6 0.4250 0.6343 0.8198 1.0000 0.9988 0.9508 0.9025 0.7234 0.5122 0.2074 0.3985
## V23 V24 V25 V26 V27 V28 V29 V30 V31 V32 V33
## 1 0.4328 0.5550 0.6711 0.6415 0.7104 0.8080 0.6791 0.3857 0.1307 0.2604 0.5121
## 2 0.3957 0.3914 0.3250 0.3200 0.3271 0.2767 0.4423 0.2028 0.3788 0.2947 0.1984
## 3 0.4293 0.3648 0.5331 0.2413 0.5070 0.8533 0.6036 0.8514 0.8512 0.5045 0.1862
## 4 0.5556 0.4846 0.3140 0.5334 0.5256 0.2520 0.2090 0.3559 0.6260 0.7340 0.6120
## 5 0.5730 0.5399 0.3161 0.2285 0.6995 1.0000 0.7262 0.4724 0.5103 0.5459 0.2881
## 6 0.5890 0.2872 0.2043 0.5782 0.5389 0.3750 0.3411 0.5067 0.5580 0.4778 0.3299
## V34 V35 V36 V37 V38 V39 V40 V41 V42 V43 V44
## 1 0.7547 0.8537 0.8507 0.6692 0.6097 0.4943 0.2744 0.0510 0.2834 0.2825 0.4256
## 2 0.2341 0.1306 0.4182 0.3835 0.1057 0.1840 0.1970 0.1674 0.0583 0.1401 0.1628
## 3 0.2709 0.4232 0.3043 0.6116 0.6756 0.5375 0.4719 0.4647 0.2587 0.2129 0.2222
## 4 0.3497 0.3953 0.3012 0.5408 0.8814 0.9857 0.9167 0.6121 0.5006 0.3210 0.3202
## 5 0.0981 0.1951 0.4181 0.4604 0.3217 0.2828 0.2430 0.1979 0.2444 0.1847 0.0841
## 6 0.2198 0.1407 0.2856 0.3807 0.4158 0.4054 0.3296 0.2707 0.2650 0.0723 0.1238
## V45 V46 V47 V48 V49 V50 V51 V52 V53 V54 V55
## 1 0.2641 0.1386 0.1051 0.1343 0.0383 0.0324 0.0232 0.0027 0.0065 0.0159 0.0072
## 2 0.0621 0.0203 0.0530 0.0742 0.0409 0.0061 0.0125 0.0084 0.0089 0.0048 0.0094
## 3 0.2111 0.0176 0.1348 0.0744 0.0130 0.0106 0.0033 0.0232 0.0166 0.0095 0.0180
## 4 0.4295 0.3654 0.2655 0.1576 0.0681 0.0294 0.0241 0.0121 0.0036 0.0150 0.0085
## 5 0.0692 0.0528 0.0357 0.0085 0.0230 0.0046 0.0156 0.0031 0.0054 0.0105 0.0110
## 6 0.1192 0.1089 0.0623 0.0494 0.0264 0.0081 0.0104 0.0045 0.0014 0.0038 0.0013
## V56 V57 V58 V59 V60 Class
## 1 0.0167 0.0180 0.0084 0.0090 0.0032 R
## 2 0.0191 0.0140 0.0049 0.0052 0.0044 R
## 3 0.0244 0.0316 0.0164 0.0095 0.0078 R
## 4 0.0073 0.0050 0.0044 0.0040 0.0117 R
## 5 0.0015 0.0072 0.0048 0.0107 0.0094 R
## 6 0.0089 0.0057 0.0027 0.0051 0.0062 R
str(Sonar)
## 'data.frame': 208 obs. of 61 variables:
## $ V1 : num 0.02 0.0453 0.0262 0.01 0.0762 0.0286 0.0317 0.0519 0.0223 0.0164 ...
## $ V2 : num 0.0371 0.0523 0.0582 0.0171 0.0666 0.0453 0.0956 0.0548 0.0375 0.0173 ...
## $ V3 : num 0.0428 0.0843 0.1099 0.0623 0.0481 ...
## $ V4 : num 0.0207 0.0689 0.1083 0.0205 0.0394 ...
## $ V5 : num 0.0954 0.1183 0.0974 0.0205 0.059 ...
## $ V6 : num 0.0986 0.2583 0.228 0.0368 0.0649 ...
## $ V7 : num 0.154 0.216 0.243 0.11 0.121 ...
## $ V8 : num 0.16 0.348 0.377 0.128 0.247 ...
## $ V9 : num 0.3109 0.3337 0.5598 0.0598 0.3564 ...
## $ V10 : num 0.211 0.287 0.619 0.126 0.446 ...
## $ V11 : num 0.1609 0.4918 0.6333 0.0881 0.4152 ...
## $ V12 : num 0.158 0.655 0.706 0.199 0.395 ...
## $ V13 : num 0.2238 0.6919 0.5544 0.0184 0.4256 ...
## $ V14 : num 0.0645 0.7797 0.532 0.2261 0.4135 ...
## $ V15 : num 0.066 0.746 0.648 0.173 0.453 ...
## $ V16 : num 0.227 0.944 0.693 0.213 0.533 ...
## $ V17 : num 0.31 1 0.6759 0.0693 0.7306 ...
## $ V18 : num 0.3 0.887 0.755 0.228 0.619 ...
## $ V19 : num 0.508 0.802 0.893 0.406 0.203 ...
## $ V20 : num 0.48 0.782 0.862 0.397 0.464 ...
## $ V21 : num 0.578 0.521 0.797 0.274 0.415 ...
## $ V22 : num 0.507 0.405 0.674 0.369 0.429 ...
## $ V23 : num 0.433 0.396 0.429 0.556 0.573 ...
## $ V24 : num 0.555 0.391 0.365 0.485 0.54 ...
## $ V25 : num 0.671 0.325 0.533 0.314 0.316 ...
## $ V26 : num 0.641 0.32 0.241 0.533 0.229 ...
## $ V27 : num 0.71 0.327 0.507 0.526 0.7 ...
## $ V28 : num 0.808 0.277 0.853 0.252 1 ...
## $ V29 : num 0.679 0.442 0.604 0.209 0.726 ...
## $ V30 : num 0.386 0.203 0.851 0.356 0.472 ...
## $ V31 : num 0.131 0.379 0.851 0.626 0.51 ...
## $ V32 : num 0.26 0.295 0.504 0.734 0.546 ...
## $ V33 : num 0.512 0.198 0.186 0.612 0.288 ...
## $ V34 : num 0.7547 0.2341 0.2709 0.3497 0.0981 ...
## $ V35 : num 0.854 0.131 0.423 0.395 0.195 ...
## $ V36 : num 0.851 0.418 0.304 0.301 0.418 ...
## $ V37 : num 0.669 0.384 0.612 0.541 0.46 ...
## $ V38 : num 0.61 0.106 0.676 0.881 0.322 ...
## $ V39 : num 0.494 0.184 0.537 0.986 0.283 ...
## $ V40 : num 0.274 0.197 0.472 0.917 0.243 ...
## $ V41 : num 0.051 0.167 0.465 0.612 0.198 ...
## $ V42 : num 0.2834 0.0583 0.2587 0.5006 0.2444 ...
## $ V43 : num 0.282 0.14 0.213 0.321 0.185 ...
## $ V44 : num 0.4256 0.1628 0.2222 0.3202 0.0841 ...
## $ V45 : num 0.2641 0.0621 0.2111 0.4295 0.0692 ...
## $ V46 : num 0.1386 0.0203 0.0176 0.3654 0.0528 ...
## $ V47 : num 0.1051 0.053 0.1348 0.2655 0.0357 ...
## $ V48 : num 0.1343 0.0742 0.0744 0.1576 0.0085 ...
## $ V49 : num 0.0383 0.0409 0.013 0.0681 0.023 0.0264 0.0507 0.0285 0.0777 0.0092 ...
## $ V50 : num 0.0324 0.0061 0.0106 0.0294 0.0046 0.0081 0.0159 0.0178 0.0439 0.0198 ...
## $ V51 : num 0.0232 0.0125 0.0033 0.0241 0.0156 0.0104 0.0195 0.0052 0.0061 0.0118 ...
## $ V52 : num 0.0027 0.0084 0.0232 0.0121 0.0031 0.0045 0.0201 0.0081 0.0145 0.009 ...
## $ V53 : num 0.0065 0.0089 0.0166 0.0036 0.0054 0.0014 0.0248 0.012 0.0128 0.0223 ...
## $ V54 : num 0.0159 0.0048 0.0095 0.015 0.0105 0.0038 0.0131 0.0045 0.0145 0.0179 ...
## $ V55 : num 0.0072 0.0094 0.018 0.0085 0.011 0.0013 0.007 0.0121 0.0058 0.0084 ...
## $ V56 : num 0.0167 0.0191 0.0244 0.0073 0.0015 0.0089 0.0138 0.0097 0.0049 0.0068 ...
## $ V57 : num 0.018 0.014 0.0316 0.005 0.0072 0.0057 0.0092 0.0085 0.0065 0.0032 ...
## $ V58 : num 0.0084 0.0049 0.0164 0.0044 0.0048 0.0027 0.0143 0.0047 0.0093 0.0035 ...
## $ V59 : num 0.009 0.0052 0.0095 0.004 0.0107 0.0051 0.0036 0.0048 0.0059 0.0056 ...
## $ V60 : num 0.0032 0.0044 0.0078 0.0117 0.0094 0.0062 0.0103 0.0053 0.0022 0.004 ...
## $ Class: Factor w/ 2 levels "M","R": 2 2 2 2 2 2 2 2 2 2 ...
Create 80%/20% for training and validation datasets
validationIndex<-createDataPartition(Sonar$Class,p=0.80, list=FALSE)
validation<-Sonar[-validationIndex, ]
Strain<-Sonar[validationIndex, ]
# Train a model and summarize the model
set.seed(7)
trainControl<-trainControl(method="repeatedcv", number=10, repeats=3)
fit.rf<-train(Class~ ., data=Strain, method="rf", metric="Accuracy",trControl=trainControl, ntree=2000)
print(fit.rf)
## Random Forest
##
## 167 samples
## 60 predictor
## 2 classes: 'M', 'R'
##
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times)
## Summary of sample sizes: 150, 150, 150, 151, 151, 150, ...
## Resampling results across tuning parameters:
##
## mtry Accuracy Kappa
## 2 0.8446078 0.6824883
## 31 0.8283088 0.6511811
## 60 0.8083333 0.6105439
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 2.
print(fit.rf$finalModel)
##
## Call:
## randomForest(x = x, y = y, ntree = 2000, mtry = min(param$mtry, ncol(x)))
## Type of random forest: classification
## Number of trees: 2000
## No. of variables tried at each split: 2
##
## OOB estimate of error rate: 14.37%
## Confusion matrix:
## M R class.error
## M 84 5 0.05617978
## R 19 59 0.24358974
Using the Random Forest algorithm and its configurations on the
Sonar dataset
Create Standalone Model using all training data
set.seed(7)
finalModel<-randomForest(Class~., Strain, mtry=2, ntrr=2000)
# Resampling results across tuning parameters
plot(fit.rf)
# Make predictions on "new data" using the final model
finalPredictions<-predict(finalModel, validation[, 1:60])
confusionMatrix(finalPredictions, validation$Class)
## Confusion Matrix and Statistics
##
## Reference
## Prediction M R
## M 19 3
## R 3 16
##
## Accuracy : 0.8537
## 95% CI : (0.7083, 0.9443)
## No Information Rate : 0.5366
## P-Value [Acc > NIR] : 1.883e-05
##
## Kappa : 0.7057
##
## Mcnemar's Test P-Value : 1
##
## Sensitivity : 0.8636
## Specificity : 0.8421
## Pos Pred Value : 0.8636
## Neg Pred Value : 0.8421
## Prevalence : 0.5366
## Detection Rate : 0.4634
## Detection Prevalence : 0.5366
## Balanced Accuracy : 0.8529
##
## 'Positive' Class : M
##
plot(finalModel)
