Random Forest Classifier
naema winde
2025-03-12
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.
library(mlbench)## Warning: package 'mlbench' was built under R version 4.4.3data("BreastCancer")
str(BreastCancer) ## 'data.frame': 699 obs. of 11 variables:
## $ Id : chr "1000025" "1002945" "1015425" "1016277" ...
## $ Cl.thickness : Ord.factor w/ 10 levels "1"<"2"<"3"<"4"<..: 5 5 3 6 4 8 1 2 2 4 ...
## $ Cell.size : Ord.factor w/ 10 levels "1"<"2"<"3"<"4"<..: 1 4 1 8 1 10 1 1 1 2 ...
## $ Cell.shape : Ord.factor w/ 10 levels "1"<"2"<"3"<"4"<..: 1 4 1 8 1 10 1 2 1 1 ...
## $ Marg.adhesion : Ord.factor w/ 10 levels "1"<"2"<"3"<"4"<..: 1 5 1 1 3 8 1 1 1 1 ...
## $ Epith.c.size : Ord.factor w/ 10 levels "1"<"2"<"3"<"4"<..: 2 7 2 3 2 7 2 2 2 2 ...
## $ Bare.nuclei : Factor w/ 10 levels "1","2","3","4",..: 1 10 2 4 1 10 10 1 1 1 ...
## $ Bl.cromatin : Factor w/ 10 levels "1","2","3","4",..: 3 3 3 3 3 9 3 3 1 2 ...
## $ Normal.nucleoli: Factor w/ 10 levels "1","2","3","4",..: 1 2 1 7 1 7 1 1 1 1 ...
## $ Mitoses : Factor w/ 9 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 5 1 ...
## $ Class : Factor w/ 2 levels "benign","malignant": 1 1 1 1 1 2 1 1 1 1 ...levels(BreastCancer$Class)## [1] "benign" "malignant"summary(BreastCancer)## Id Cl.thickness Cell.size Cell.shape Marg.adhesion
## Length:699 1 :145 1 :384 1 :353 1 :407
## Class :character 5 :130 10 : 67 2 : 59 2 : 58
## Mode :character 3 :108 3 : 52 10 : 58 3 : 58
## 4 : 80 2 : 45 3 : 56 10 : 55
## 10 : 69 4 : 40 4 : 44 4 : 33
## 2 : 50 5 : 30 5 : 34 8 : 25
## (Other):117 (Other): 81 (Other): 95 (Other): 63
## Epith.c.size Bare.nuclei Bl.cromatin Normal.nucleoli Mitoses
## 2 :386 1 :402 2 :166 1 :443 1 :579
## 3 : 72 10 :132 3 :165 10 : 61 2 : 35
## 4 : 48 2 : 30 1 :152 3 : 44 3 : 33
## 1 : 47 5 : 30 7 : 73 2 : 36 10 : 14
## 6 : 41 3 : 28 4 : 40 8 : 24 4 : 12
## 5 : 39 (Other): 61 5 : 34 6 : 22 7 : 9
## (Other): 66 NA's : 16 (Other): 69 (Other): 69 (Other): 17
## Class
## benign :458
## malignant:241
##
##
##
##
## library(mice)## Warning: package 'mice' was built under R version 4.4.3##
## Attaching package: 'mice'## The following object is masked from 'package:stats':
##
## filter## The following objects are masked from 'package:base':
##
## cbind, rbindlibrary(caret)## Warning: package 'caret' was built under R version 4.4.3## Loading required package: ggplot2## Loading required package: latticedataset_impute <- mice(BreastCancer[,2:10], print = FALSE)
BreastCancer <- cbind(BreastCancer[,11, drop = FALSE], mice::complete(dataset_impute, 1))summary(BreastCancer)## Class Cl.thickness Cell.size Cell.shape Marg.adhesion
## benign :458 1 :145 1 :384 1 :353 1 :407
## malignant:241 5 :130 10 : 67 2 : 59 2 : 58
## 3 :108 3 : 52 10 : 58 3 : 58
## 4 : 80 2 : 45 3 : 56 10 : 55
## 10 : 69 4 : 40 4 : 44 4 : 33
## 2 : 50 5 : 30 5 : 34 8 : 25
## (Other):117 (Other): 81 (Other): 95 (Other): 63
## Epith.c.size Bare.nuclei Bl.cromatin Normal.nucleoli Mitoses
## 2 :386 1 :413 2 :166 1 :443 1 :579
## 3 : 72 10 :133 3 :165 10 : 61 2 : 35
## 4 : 48 2 : 31 1 :152 3 : 44 3 : 33
## 1 : 47 5 : 30 7 : 73 2 : 36 10 : 14
## 6 : 41 3 : 28 4 : 40 8 : 24 4 : 12
## 5 : 39 8 : 21 5 : 34 6 : 22 7 : 9
## (Other): 66 (Other): 43 (Other): 69 (Other): 69 (Other): 17library(caTools)## Warning: package 'caTools' was built under R version 4.4.3set.seed(150)
split=sample.split(BreastCancer, SplitRatio = 0.7)
training_set=subset(BreastCancer,split==TRUE)
test_set=subset(BreastCancer,split==FALSE) dim(training_set)## [1] 490 10dim(test_set)## [1] 209 10topredict_set<-test_set[2:10]
dim(topredict_set)## [1] 209 9library(randomForest)## Warning: package 'randomForest' was built under R version 4.4.3## randomForest 4.7-1.2## Type rfNews() to see new features/changes/bug fixes.##
## Attaching package: 'randomForest'## The following object is masked from 'package:ggplot2':
##
## marginmodel_rf <- randomForest(Class ~ ., data = training_set, importance=TRUE, ntree = 5)
preds_rf <- predict(model_rf, topredict_set)
(conf_matrix_forest <- table(preds_rf, test_set$Class))##
## preds_rf benign malignant
## benign 125 2
## malignant 10 72confusionMatrix(conf_matrix_forest)## Confusion Matrix and Statistics
##
##
## preds_rf benign malignant
## benign 125 2
## malignant 10 72
##
## Accuracy : 0.9426
## 95% CI : (0.9019, 0.97)
## No Information Rate : 0.6459
## P-Value [Acc > NIR] : < 2e-16
##
## Kappa : 0.8775
##
## Mcnemar's Test P-Value : 0.04331
##
## Sensitivity : 0.9259
## Specificity : 0.9730
## Pos Pred Value : 0.9843
## Neg Pred Value : 0.8780
## Prevalence : 0.6459
## Detection Rate : 0.5981
## Detection Prevalence : 0.6077
## Balanced Accuracy : 0.9494
##
## 'Positive' Class : benign
## library(rpart)## Warning: package 'rpart' was built under R version 4.4.3model_dtree<- rpart(Class ~ ., data=training_set)
preds_dtree <- predict(model_dtree,newdata=topredict_set, type = "class")
(conf_matrix_dtree <- table(preds_dtree, test_set$Class))##
## preds_dtree benign malignant
## benign 127 5
## malignant 8 69confusionMatrix(conf_matrix_dtree)## Confusion Matrix and Statistics
##
##
## preds_dtree benign malignant
## benign 127 5
## malignant 8 69
##
## Accuracy : 0.9378
## 95% CI : (0.896, 0.9665)
## No Information Rate : 0.6459
## P-Value [Acc > NIR] : <2e-16
##
## Kappa : 0.8652
##
## Mcnemar's Test P-Value : 0.5791
##
## Sensitivity : 0.9407
## Specificity : 0.9324
## Pos Pred Value : 0.9621
## Neg Pred Value : 0.8961
## Prevalence : 0.6459
## Detection Rate : 0.6077
## Detection Prevalence : 0.6316
## Balanced Accuracy : 0.9366
##
## 'Positive' Class : benign
##