Project-Report.html

---
title: "MachineLearning"
author: "Reynaldo"
date: "25 de septiembre de 2017"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```
## step 1: download zip file from website to new folder call: data
```{r, echo=FALSE}
getwd()
if(!file.exists("./MLearning")) dir.create("./MLearning")
fileUrl <- "https://d396qusza40orc.cloudfront.net/predmachlearn/pml-training.csv"
download.file(fileUrl, destfile = "./Mlearning/TrainingData.csv")
fileUrl <- "https://d396qusza40orc.cloudfront.net/predmachlearn/pml-testing.csv"
download.file(fileUrl, destfile = "./Mlearning/TestingData.csv")
```
## step 2: load data into R and get dimension of every new read
```{r, echo=FALSE}
rm(list=ls()) 
TrD <- read.csv("./MLearning/TrainingData.csv",na.strings=c('','NA'))
TrD1<-TrD[,!apply(TrD,2,function(x) any(is.na(x)) )]
TrD2<-TrD1[,-c(1:7)]
TtD <- read.csv("./MLearning/TestingData.csv")
dim(TrD)
dim(TrD2)
head(TrD2)
dim(TtD)
```
## step3: Load Packages
```{r, echo=FALSE}
library(caret)
library(rpart)
library(rpart.plot)
library(randomForest)
library(corrplot)
library(rattle)
library(tidyverse)
```
##Step4: Create a partition with the training dataset 
```{r, echo=FALSE}
inTrain<- createDataPartition(TrD2$classe, p=0.7, list=FALSE)
TrainSet <- TrD2[inTrain, ]
TestSet  <- TrD2[-inTrain, ]
dim(TrainSet)
dim(TestSet)
```
### remove identification only variables (columns 1 to 5)
```{r, echo=FALSE}
TrainSet <- TrainSet[, -(1:5)]
TestSet  <- TestSet[, -(1:5)]
dim(TrainSet)
dim(TestSet)
```
##Step5: Correlation
```{r Correlation, echo=true}
corMatrix <- cor(TrainSet[, -48])
corrplot(corMatrix, order = "FPC", method = "color", type = "lower",title = 'Correlation among Traits', tl.cex = 0.8, tl.col = rgb(0, 0, 0))
```
##Step6: Prediction Model
###A.- Randon Forest 
Model fit
```{r RF, echo=true}
set.seed(12345)
Control.RF <- trainControl(method="cv", number=3, verboseIter=FALSE)
FitRF <- train(classe ~ ., data=TrainSet, method="rf",
                          trControl=Control.RF)
FitRF$finalModel
```
# prediction on Test dataset
```{r Confusion.Matrix RF, echo=true}
Predict.RF <- predict(FitRF, newdata=TestSet)
Confusion.Matrix.RF <- confusionMatrix(Predict.RF, TestSet$classe)
Confusion.Matrix.RF
```
### Plot matrix results
```{r plot ConfMat, echo=true}
plot(Confusion.Matrix.RF$table, col = Confusion.Matrix.RF$byClass, 
     main = paste("Accuracy for Random Forest Model =",
                  round(Confusion.Matrix.RF$overall['Accuracy'], 2)))
```
###B.- Method: Decision Trees
model fit
```{r plot DT, echo=true}
set.seed(12345)
Fit.DT <- rpart(classe ~ ., data=TrainSet, method="class")
fancyRpartPlot(Fit.DT)
```
Prediction: Test dataset
```{r Confusion.Matrix.DT, echo=true}
Prediction.DT <- predict(Fit.DT, newdata=TestSet, type="class")
Confusion.Matrix.DT <- confusionMatrix(Prediction.DT, TestSet$classe)
Confusion.Matrix.DT
```

```{r Plot Confusion.Matrix.DT, echo=true}
plot(Confusion.Matrix.DT$table, col = Confusion.Matrix.DT$byClass, 
     main = paste("Accuracy for Desicion Tree =",
                  round(Confusion.Matrix.DT$overall['Accuracy'], 2)))
```
###C.- Method: Generalized Boosted Model
model fit
```{r GBM , echo=true}
set.seed(12345)
Control.GBM <- trainControl(method = "repeatedcv", number = 5, repeats = 1)
Fit.GBM  <- train(classe ~ ., data=TrainSet, method = "gbm",
                    trControl = Control.GBM, verbose = FALSE)
Fit.GBM$finalModel
```

Prediction Test dataset
```{r Prediction GBM , echo=true}
Predict.GBM <- predict(Fit.GBM, newdata=TestSet)
Confusion.Matrix.GBM <- confusionMatrix(Predict.GBM, TestSet$classe)
Confusion.Matrix.GBM
```

plot matrix results
```{r Plot Prediction GBM , echo=true}
plot(Confusion.Matrix.GBM$table, col =Confusion.Matrix.GBM$byClass, 
     main = paste("Accuracy for GBM =", round(Confusion.Matrix.GBM$overall['Accuracy'], 2)))
```
## Step 7: Selected Model to the Test Data
```{r Select Model , echo=true}
Predict.Test <- predict(FitRF, newdata=TtD)
Predict.Test
```