The objetive of this R markdown document is to show two different analysis for predictions for the data set “pml” by the metodology of Random Forest and Regression trees
For this analysis i used the librarys of: Caret, rio, randomForest
library(rio)
library(caret)
## Warning: package 'caret' was built under R version 4.3.2
## Loading required package: ggplot2
## Warning: package 'ggplot2' was built under R version 4.3.2
## Loading required package: lattice
## Warning: package 'lattice' was built under R version 4.3.2
library(randomForest)
## Warning: package 'randomForest' was built under R version 4.3.2
## 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(rattle)
## Warning: package 'rattle' was built under R version 4.3.2
## Loading required package: tibble
## Loading required package: bitops
## Rattle: A free graphical interface for data science with R.
## Version 5.5.1 Copyright (c) 2006-2021 Togaware Pty Ltd.
## Type 'rattle()' to shake, rattle, and roll your data.
##
## Attaching package: 'rattle'
## The following object is masked from 'package:randomForest':
##
## importance
training <- import("data/pml-training.csv")
testing <- import("data/pml-testing.csv")
For improve this process i had to remove the columns in the database that dont have any information
training_names <- colnames(training)[!colSums(is.na(training))>0]
training_names <- training_names[8:length(training_names)]
training <- training[training_names]
testing_names <- colnames(testing)[!colSums(is.na(testing))>0]
testing_names <- testing_names[8:length(testing_names)]
testing <- testing[testing_names]
rf_model <- train(classe ~., data = training, method = "rf")
predict_model <- predict(rf_model, newdata = testing)
testing$classe <- predict_model
training$classe <- factor(training$classe)
confusionMatrix(testing$classe, predict_model)
## Confusion Matrix and Statistics
##
## Reference
## Prediction A B C D E
## A 7 0 0 0 0
## B 0 8 0 0 0
## C 0 0 1 0 0
## D 0 0 0 1 0
## E 0 0 0 0 3
##
## Overall Statistics
##
## Accuracy : 1
## 95% CI : (0.8316, 1)
## No Information Rate : 0.4
## P-Value [Acc > NIR] : 1.1e-08
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: A Class: B Class: C Class: D Class: E
## Sensitivity 1.00 1.0 1.00 1.00 1.00
## Specificity 1.00 1.0 1.00 1.00 1.00
## Pos Pred Value 1.00 1.0 1.00 1.00 1.00
## Neg Pred Value 1.00 1.0 1.00 1.00 1.00
## Prevalence 0.35 0.4 0.05 0.05 0.15
## Detection Rate 0.35 0.4 0.05 0.05 0.15
## Detection Prevalence 0.35 0.4 0.05 0.05 0.15
## Balanced Accuracy 1.00 1.0 1.00 1.00 1.00
modFit <- train(classe~., method = "rpart", data = training)
print(modFit$finalModel)
## n= 19622
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 19622 14042 A (0.28 0.19 0.17 0.16 0.18)
## 2) roll_belt< 130.5 17977 12411 A (0.31 0.21 0.19 0.18 0.11)
## 4) pitch_forearm< -33.95 1578 10 A (0.99 0.0063 0 0 0) *
## 5) pitch_forearm>=-33.95 16399 12401 A (0.24 0.23 0.21 0.2 0.12)
## 10) magnet_dumbbell_y< 439.5 13870 9953 A (0.28 0.18 0.24 0.19 0.11)
## 20) roll_forearm< 123.5 8643 5131 A (0.41 0.18 0.18 0.17 0.061) *
## 21) roll_forearm>=123.5 5227 3500 C (0.077 0.18 0.33 0.23 0.18) *
## 11) magnet_dumbbell_y>=439.5 2529 1243 B (0.032 0.51 0.043 0.22 0.19) *
## 3) roll_belt>=130.5 1645 14 E (0.0085 0 0 0 0.99) *
plot(modFit$finalModel, uniform = T, main = "Decision Tree")
text(modFit$finalModel, use.n = T, all = T, cex = 0.8)
fancyRpartPlot(modFit$finalModel)