ML Prediction
Janus
Wednesday, December 23, 2015
Background
Using devices such as Jawbone Up, Nike FuelBand, and Fitbit it is now possible to collect a large amount of data about personal activity relatively inexpensively. These type of devices are part of the quantified self movement - a group of enthusiasts who take measurements about themselves regularly to improve their health, to find patterns in their behavior, or because they are tech geeks. One thing that people regularly do is quantify how much of a particular activity they do, but they rarely quantify how well they do it. In this project, your goal will be to use data from accelerometers on the belt, forearm, arm, and dumbell of 6 participants. They were asked to perform barbell lifts correctly and incorrectly in 5 different ways. More information is available from the website here: http://groupware.les.inf.puc-rio.br/har (see the section on the Weight Lifting Exercise Dataset).
Data
The training data for this project are available here:
https://d396qusza40orc.cloudfront.net/predmachlearn/pml-training.csv
The test data are available here:
https://d396qusza40orc.cloudfront.net/predmachlearn/pml-testing.csv
The data for this project come from this source: http://groupware.les.inf.puc-rio.br/har. If you use the document you create for this class for any purpose please cite them as they have been very generous in allowing their data to be used for this kind of assignment.
Data Cleaning
#Loading data
setwd("C:/Users/ITSUPPORT/Desktop/R/M8")
training <- read.csv("pml-training.csv", na.strings = c("NA", "#DIV/0!", ""))
testing <- read.csv("pml-testing.csv", na.strings = c("NA", "#DIV/0!", ""))## 'data.frame': 19622 obs. of 160 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ user_name : Factor w/ 6 levels "adelmo","carlitos",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ raw_timestamp_part_1 : int 1323084231 1323084231 1323084231 1323084232 1323084232 1323084232 1323084232 1323084232 1323084232 1323084232 ...
## $ raw_timestamp_part_2 : int 788290 808298 820366 120339 196328 304277 368296 440390 484323 484434 ...
## $ cvtd_timestamp : Factor w/ 20 levels "02/12/2011 13:32",..: 9 9 9 9 9 9 9 9 9 9 ...
## $ new_window : Factor w/ 2 levels "no","yes": 1 1 1 1 1 1 1 1 1 1 ...
## $ num_window : int 11 11 11 12 12 12 12 12 12 12 ...
## $ roll_belt : num 1.41 1.41 1.42 1.48 1.48 1.45 1.42 1.42 1.43 1.45 ...
## $ pitch_belt : num 8.07 8.07 8.07 8.05 8.07 8.06 8.09 8.13 8.16 8.17 ...
## $ yaw_belt : num -94.4 -94.4 -94.4 -94.4 -94.4 -94.4 -94.4 -94.4 -94.4 -94.4 ...
## $ total_accel_belt : int 3 3 3 3 3 3 3 3 3 3 ...
## $ kurtosis_roll_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ kurtosis_picth_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ kurtosis_yaw_belt : logi NA NA NA NA NA NA ...
## $ skewness_roll_belt : num NA NA NA NA NA NA NA NA NA NA ...
## [list output truncated]table(training$classe)##
## A B C D E
## 5580 3797 3422 3216 3607prop.table(table(training$user_name, training$classe), 1)##
## A B C D E
## adelmo 0.2993320 0.1993834 0.1927030 0.1323227 0.1762590
## carlitos 0.2679949 0.2217224 0.1584190 0.1561697 0.1956941
## charles 0.2542421 0.2106900 0.1524321 0.1815611 0.2010747
## eurico 0.2817590 0.1928339 0.1592834 0.1895765 0.1765472
## jeremy 0.3459730 0.1437390 0.1916520 0.1534392 0.1651969
## pedro 0.2452107 0.1934866 0.1911877 0.1796935 0.1904215prop.table(table(training$classe))##
## A B C D E
## 0.2843747 0.1935073 0.1743961 0.1638977 0.1838243training <- training[, 7:160]
testing <- testing[, 7:160]is_data <- apply(!is.na(training), 2, sum) > 19621 # which is the number of observations
training <- training[, is_data]
testing <- testing[, is_data]Here to split the training set into two for cross validation purposes. We randomly subsample 60% of the set for training purposes (actual model building), while the 40% remainder will be used only for testing, evaluation and accuracy measurement.
library(caret)## Warning: package 'caret' was built under R version 3.2.2## Loading required package: lattice
## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 3.2.2set.seed(3141592)
inTrain <- createDataPartition(y=training$classe, p=0.60, list=FALSE)
train1 <- training[inTrain,]
train2 <- training[-inTrain,]
dim(train1)## [1] 11776 54dim(train2)## [1] 7846 54The [i] identify the “zero covariates”" from train1 and [ii] remove these “zero covariates”" from both train1 and train2:
nzv_cols <- nearZeroVar(train1)
if(length(nzv_cols) > 0) {
train1 <- train1[, -nzv_cols]
train2 <- train2[, -nzv_cols]
}
dim(train1)## [1] 11776 54dim(train2)## [1] 7846 54library(randomForest)## Warning: package 'randomForest' was built under R version 3.2.2## randomForest 4.6-12
## Type rfNews() to see new features/changes/bug fixes.set.seed(3141592)
fitModel <- randomForest(classe~., data=train1, importance=TRUE, ntree=100)
varImpPlot(fitModel)
correl = cor(train1[,c("yaw_belt","roll_belt","num_window","pitch_belt","magnet_dumbbell_z","magnet_dumbbell_y","pitch_forearm","accel_dumbbell_y","roll_arm","roll_forearm")])
diag(correl) <- 0
which(abs(correl)>0.75, arr.ind=TRUE)## row col
## roll_belt 2 1
## yaw_belt 1 2cor(train1$roll_belt, train1$yaw_belt)## [1] 0.8152349The quick tree classifier selects roll_belt as the first discriminant among all 53 covariates
library(rpart.plot)## Warning: package 'rpart.plot' was built under R version 3.2.3## Loading required package: rpart## Warning: package 'rpart' was built under R version 3.2.3fitModel <- rpart(classe~., data=train1, method="class")
prp(fitModel)
Mideling
Here to using a Random Forest algorithm, using the train() function from the caret package.
set.seed(3141592)
fitModel <- train(classe~roll_belt+num_window+pitch_belt+magnet_dumbbell_y+magnet_dumbbell_z+pitch_forearm+accel_dumbbell_y+roll_arm+roll_forearm,
data=train1,
method="rf",
trControl=trainControl(method="cv",number=2),
prox=TRUE,
verbose=TRUE,
allowParallel=TRUE)saveRDS(fitModel, "modelRF.Rds")fitModel <- readRDS("modelRF.Rds")predictions <- predict(fitModel, newdata=train2)
confusionMat <- confusionMatrix(predictions, train2$classe)
confusionMat## Confusion Matrix and Statistics
##
## Reference
## Prediction A B C D E
## A 2231 0 0 0 0
## B 1 1517 1 0 2
## C 0 0 1367 6 1
## D 0 1 0 1280 4
## E 0 0 0 0 1435
##
## Overall Statistics
##
## Accuracy : 0.998
## 95% CI : (0.9967, 0.9988)
## No Information Rate : 0.2845
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.9974
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: A Class: B Class: C Class: D Class: E
## Sensitivity 0.9996 0.9993 0.9993 0.9953 0.9951
## Specificity 1.0000 0.9994 0.9989 0.9992 1.0000
## Pos Pred Value 1.0000 0.9974 0.9949 0.9961 1.0000
## Neg Pred Value 0.9998 0.9998 0.9998 0.9991 0.9989
## Prevalence 0.2845 0.1935 0.1744 0.1639 0.1838
## Detection Rate 0.2843 0.1933 0.1742 0.1631 0.1829
## Detection Prevalence 0.2843 0.1939 0.1751 0.1638 0.1829
## Balanced Accuracy 0.9998 0.9994 0.9991 0.9973 0.9976missClass = function(values, predicted) {
sum(predicted != values) / length(values)
}
OOS_errRate = missClass(train2$classe, predictions)
OOS_errRate## [1] 0.002039256Final submission
predictions <- predict(fitModel, newdata=testing)
testing$classe <- predictions
submit <- data.frame(problem_id = testing$problem_id, classe = predictions)
write.csv(submit, file = "coursera-submission.csv", row.names = FALSE)
answers = testing$classe
write_files = function(x){
n = length(x)
for(i in 1:n){
filename = paste0("problem_",i,".txt")
write.table(x[i], file=filename, quote=FALSE, row.names=FALSE, col.names=FALSE)
}
}
write_files(answers)