Predicting Exercise Performance Using Machine Learning

Author: Muhamad Taopan

Date: 28/02/2025

Load Libraries

library(caret) library(randomForest) library(ggplot2) library(dplyr)

Load and Explore Data

train_url <- “https://d396qusza40orc.cloudfront.net/predmachlearn/pml-training.csv” test_url <- “https://d396qusza40orc.cloudfront.net/predmachlearn/pml-testing.csv”

train_data <- read.csv(train_url, na.strings = c(“NA”, "“,”#DIV/0!“)) test_data <- read.csv(test_url, na.strings = c(”NA“,”“,”#DIV/0!"))

str(train_data) summary(train_data)

Data Preprocessing

Remove columns with many missing values

train_data <- train_data[, colSums(is.na(train_data)) == 0]

Remove irrelevant columns (ID, timestamps, etc.)

train_data <- train_data %>% select(-c(1:7))

Convert classe to factor

train_data\(classe <- as.factor(train_data\)classe)

Split Data into Training and Validation Sets

set.seed(123) trainIndex <- createDataPartition(train_data$classe, p = 0.8, list = FALSE) train_set <- train_data[trainIndex, ] valid_set <- train_data[-trainIndex, ]

Train a Random Forest Model

set.seed(123) rf_model <- randomForest(classe ~ ., data = train_set, ntree = 100)

Model Evaluation

pred_valid <- predict(rf_model, valid_set) conf_matrix <- confusionMatrix(pred_valid, valid_set$classe) print(conf_matrix)

Prediction on Test Data

test_data <- test_data[, colnames(test_data) %in% colnames(train_set)] test_predictions <- predict(rf_model, test_data) print(test_predictions)

Conclusion

cat(“Random Forest performed well on the validation set.”) cat(“The model predicts the exercise performance with high accuracy.”) cat(“Predictions were made on 20 test cases.”)