Prediction Assignment Writeup

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.   :120.00

Including 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(caret) library(gbm) # For Gradient Boosted Machines (decision tree-based) library(dplyr) library(corrplot) # For correlation analysis

Create data folder

if(!file.exists(“data”)) dir.create(“data”)

Download files

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

download.file(train_url, “./data/pml-training.csv”) download.file(test_url, “./data/pml-testing.csv”)

Load data (treat empty strings, #DIV/0!, and NA as NA)

training <- read.csv(“./data/pml-training.csv”, na.strings = c(“NA”, “#DIV/0!”, "“)) testing <- read.csv(”./data/pml-testing.csv“, na.strings = c(”NA“,”#DIV/0!“,”"))

Remove columns with >95% NA

mostlyNA <- sapply(training, function(x) mean(is.na(x))) > 0.95 training <- training[, mostlyNA == FALSE] testing <- testing[, mostlyNA == FALSE]

Remove near-zero variance variables

nzv <- nearZeroVar(training) training <- training[, -nzv] testing <- testing[, -nzv]

Remove identification columns (first 5 columns: timestamps, user names, etc.)

training <- training[, -(1:5)] testing <- testing[, -(1:5)]

dim(training) # Should be 19622 x 54

Select numeric variables (exclude classe)

numeric_vars <- sapply(training, is.numeric) corr_matrix <- cor(training[, numeric_vars])

Plot correlation matrix (figure 1 of <5)

corrplot(corr_matrix, method = “color”, type = “lower”, tl.cex = 0.4, tl.srt = 45, title = “Correlation Matrix of Numeric Predictors”, mar = c(0,0,1,0))

set.seed(12345) inTrain <- createDataPartition(training$classe, p = 0.7, list = FALSE) train_set <- training[inTrain, ] valid_set <- training[-inTrain, ]

control <- trainControl(method = “repeatedcv”, number = 3, repeats = 1, verboseIter = FALSE)

model_gbm <- train(classe ~ ., data = train_set, method = “gbm”, trControl = control, verbose = FALSE)

model_gbm

pred_valid <- predict(model_gbm, valid_set) cm <- confusionMatrix(pred_valid, valid_set$classe) cm

Plot top 10 important variables (figure 2 of <5)

varImp_gbm <- varImp(model_gbm) plot(varImp_gbm, top = 10, main = “Top 10 Important Variables in GBM”)

final_predictions <- predict(model_gbm, testing) final_predictions

pml_write_files <- function(x) { n <- length(x) path <- “./predictions” if(!file.exists(path)) dir.create(path) for(i in 1:n){ filename <- paste0(“problem_id_”, i, “.txt”) write.table(x[i], file = file.path(path, filename), quote = FALSE, row.names = FALSE, col.names = FALSE) } }

pml_write_files(final_predictions)

rmarkdown::render(“Prediction Assignment Writeup.Rmd”)