Practical Machine Learning Project for Weight Lifting Exercise Dataset
Terence Lim Zheng Wei
26 January 2016
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).
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
Load Dataset
This section downloads the dataset and stores them into two dataframes, training and testing.
library(caret)
library(ggplot2)
library(dplyr)
set.seed(333)
filenames <- c("pml-training.csv","pml-testing.csv")
if(sum(list.files() %in% filenames)==0){
download.file("https://d396qusza40orc.cloudfront.net/predmachlearn/
pml-training.csv","pml-training.csv")
download.file("https://d396qusza40orc.cloudfront.net/predmachlearn/
pml-testing.csv","pml-testing.csv")
}
training <- tbl_df(read.csv("pml-training.csv",header=TRUE,na.strings=c("NA","")))
testing <- tbl_df(read.csv("pml-testing.csv",header=TRUE,na.strings=c("NA","")))
names(training)## [1] "X" "user_name"
## [3] "raw_timestamp_part_1" "raw_timestamp_part_2"
## [5] "cvtd_timestamp" "new_window"
## [7] "num_window" "roll_belt"
## [9] "pitch_belt" "yaw_belt"
## [11] "total_accel_belt" "kurtosis_roll_belt"
## [13] "kurtosis_picth_belt" "kurtosis_yaw_belt"
## [15] "skewness_roll_belt" "skewness_roll_belt.1"
## [17] "skewness_yaw_belt" "max_roll_belt"
## [19] "max_picth_belt" "max_yaw_belt"
## [21] "min_roll_belt" "min_pitch_belt"
## [23] "min_yaw_belt" "amplitude_roll_belt"
## [25] "amplitude_pitch_belt" "amplitude_yaw_belt"
## [27] "var_total_accel_belt" "avg_roll_belt"
## [29] "stddev_roll_belt" "var_roll_belt"
## [31] "avg_pitch_belt" "stddev_pitch_belt"
## [33] "var_pitch_belt" "avg_yaw_belt"
## [35] "stddev_yaw_belt" "var_yaw_belt"
## [37] "gyros_belt_x" "gyros_belt_y"
## [39] "gyros_belt_z" "accel_belt_x"
## [41] "accel_belt_y" "accel_belt_z"
## [43] "magnet_belt_x" "magnet_belt_y"
## [45] "magnet_belt_z" "roll_arm"
## [47] "pitch_arm" "yaw_arm"
## [49] "total_accel_arm" "var_accel_arm"
## [51] "avg_roll_arm" "stddev_roll_arm"
## [53] "var_roll_arm" "avg_pitch_arm"
## [55] "stddev_pitch_arm" "var_pitch_arm"
## [57] "avg_yaw_arm" "stddev_yaw_arm"
## [59] "var_yaw_arm" "gyros_arm_x"
## [61] "gyros_arm_y" "gyros_arm_z"
## [63] "accel_arm_x" "accel_arm_y"
## [65] "accel_arm_z" "magnet_arm_x"
## [67] "magnet_arm_y" "magnet_arm_z"
## [69] "kurtosis_roll_arm" "kurtosis_picth_arm"
## [71] "kurtosis_yaw_arm" "skewness_roll_arm"
## [73] "skewness_pitch_arm" "skewness_yaw_arm"
## [75] "max_roll_arm" "max_picth_arm"
## [77] "max_yaw_arm" "min_roll_arm"
## [79] "min_pitch_arm" "min_yaw_arm"
## [81] "amplitude_roll_arm" "amplitude_pitch_arm"
## [83] "amplitude_yaw_arm" "roll_dumbbell"
## [85] "pitch_dumbbell" "yaw_dumbbell"
## [87] "kurtosis_roll_dumbbell" "kurtosis_picth_dumbbell"
## [89] "kurtosis_yaw_dumbbell" "skewness_roll_dumbbell"
## [91] "skewness_pitch_dumbbell" "skewness_yaw_dumbbell"
## [93] "max_roll_dumbbell" "max_picth_dumbbell"
## [95] "max_yaw_dumbbell" "min_roll_dumbbell"
## [97] "min_pitch_dumbbell" "min_yaw_dumbbell"
## [99] "amplitude_roll_dumbbell" "amplitude_pitch_dumbbell"
## [101] "amplitude_yaw_dumbbell" "total_accel_dumbbell"
## [103] "var_accel_dumbbell" "avg_roll_dumbbell"
## [105] "stddev_roll_dumbbell" "var_roll_dumbbell"
## [107] "avg_pitch_dumbbell" "stddev_pitch_dumbbell"
## [109] "var_pitch_dumbbell" "avg_yaw_dumbbell"
## [111] "stddev_yaw_dumbbell" "var_yaw_dumbbell"
## [113] "gyros_dumbbell_x" "gyros_dumbbell_y"
## [115] "gyros_dumbbell_z" "accel_dumbbell_x"
## [117] "accel_dumbbell_y" "accel_dumbbell_z"
## [119] "magnet_dumbbell_x" "magnet_dumbbell_y"
## [121] "magnet_dumbbell_z" "roll_forearm"
## [123] "pitch_forearm" "yaw_forearm"
## [125] "kurtosis_roll_forearm" "kurtosis_picth_forearm"
## [127] "kurtosis_yaw_forearm" "skewness_roll_forearm"
## [129] "skewness_pitch_forearm" "skewness_yaw_forearm"
## [131] "max_roll_forearm" "max_picth_forearm"
## [133] "max_yaw_forearm" "min_roll_forearm"
## [135] "min_pitch_forearm" "min_yaw_forearm"
## [137] "amplitude_roll_forearm" "amplitude_pitch_forearm"
## [139] "amplitude_yaw_forearm" "total_accel_forearm"
## [141] "var_accel_forearm" "avg_roll_forearm"
## [143] "stddev_roll_forearm" "var_roll_forearm"
## [145] "avg_pitch_forearm" "stddev_pitch_forearm"
## [147] "var_pitch_forearm" "avg_yaw_forearm"
## [149] "stddev_yaw_forearm" "var_yaw_forearm"
## [151] "gyros_forearm_x" "gyros_forearm_y"
## [153] "gyros_forearm_z" "accel_forearm_x"
## [155] "accel_forearm_y" "accel_forearm_z"
## [157] "magnet_forearm_x" "magnet_forearm_y"
## [159] "magnet_forearm_z" "classe"We will be using the data available to predict the classe variable.
Pre-process data
Remove first 7 columns of data as they do not assist in predicting classe based on physical movements
training<-training[,-c(1:7)]
testing<-testing[,-c(1:7)]Remove columns which have greater than 80% of N.A values
num_na <- colSums(is.na(training))
low_na_col <- num_na < 0.8 * nrow(training)
training <- training[,low_na_col]
testing <- testing[,low_na_col]Check whether there are columns with near zero variance as they do not assist in prediction
nsv <- nearZeroVar(training,saveMetrics = TRUE)
nsv## freqRatio percentUnique zeroVar nzv
## roll_belt 1.101904 6.7781062 FALSE FALSE
## pitch_belt 1.036082 9.3772296 FALSE FALSE
## yaw_belt 1.058480 9.9734991 FALSE FALSE
## total_accel_belt 1.063160 0.1477933 FALSE FALSE
## gyros_belt_x 1.058651 0.7134849 FALSE FALSE
## gyros_belt_y 1.144000 0.3516461 FALSE FALSE
## gyros_belt_z 1.066214 0.8612782 FALSE FALSE
## accel_belt_x 1.055412 0.8357966 FALSE FALSE
## accel_belt_y 1.113725 0.7287738 FALSE FALSE
## accel_belt_z 1.078767 1.5237998 FALSE FALSE
## magnet_belt_x 1.090141 1.6664968 FALSE FALSE
## magnet_belt_y 1.099688 1.5187035 FALSE FALSE
## magnet_belt_z 1.006369 2.3290184 FALSE FALSE
## roll_arm 52.338462 13.5256345 FALSE FALSE
## pitch_arm 87.256410 15.7323412 FALSE FALSE
## yaw_arm 33.029126 14.6570176 FALSE FALSE
## total_accel_arm 1.024526 0.3363572 FALSE FALSE
## gyros_arm_x 1.015504 3.2769341 FALSE FALSE
## gyros_arm_y 1.454369 1.9162165 FALSE FALSE
## gyros_arm_z 1.110687 1.2638875 FALSE FALSE
## accel_arm_x 1.017341 3.9598410 FALSE FALSE
## accel_arm_y 1.140187 2.7367241 FALSE FALSE
## accel_arm_z 1.128000 4.0362858 FALSE FALSE
## magnet_arm_x 1.000000 6.8239731 FALSE FALSE
## magnet_arm_y 1.056818 4.4439914 FALSE FALSE
## magnet_arm_z 1.036364 6.4468454 FALSE FALSE
## roll_dumbbell 1.022388 84.2065029 FALSE FALSE
## pitch_dumbbell 2.277372 81.7449801 FALSE FALSE
## yaw_dumbbell 1.132231 83.4828254 FALSE FALSE
## total_accel_dumbbell 1.072634 0.2191418 FALSE FALSE
## gyros_dumbbell_x 1.003268 1.2282132 FALSE FALSE
## gyros_dumbbell_y 1.264957 1.4167771 FALSE FALSE
## gyros_dumbbell_z 1.060100 1.0498420 FALSE FALSE
## accel_dumbbell_x 1.018018 2.1659362 FALSE FALSE
## accel_dumbbell_y 1.053061 2.3748853 FALSE FALSE
## accel_dumbbell_z 1.133333 2.0894914 FALSE FALSE
## magnet_dumbbell_x 1.098266 5.7486495 FALSE FALSE
## magnet_dumbbell_y 1.197740 4.3012945 FALSE FALSE
## magnet_dumbbell_z 1.020833 3.4451126 FALSE FALSE
## roll_forearm 11.589286 11.0895933 FALSE FALSE
## pitch_forearm 65.983051 14.8557741 FALSE FALSE
## yaw_forearm 15.322835 10.1467740 FALSE FALSE
## total_accel_forearm 1.128928 0.3567424 FALSE FALSE
## gyros_forearm_x 1.059273 1.5187035 FALSE FALSE
## gyros_forearm_y 1.036554 3.7763735 FALSE FALSE
## gyros_forearm_z 1.122917 1.5645704 FALSE FALSE
## accel_forearm_x 1.126437 4.0464784 FALSE FALSE
## accel_forearm_y 1.059406 5.1116094 FALSE FALSE
## accel_forearm_z 1.006250 2.9558659 FALSE FALSE
## magnet_forearm_x 1.012346 7.7667924 FALSE FALSE
## magnet_forearm_y 1.246914 9.5403119 FALSE FALSE
## magnet_forearm_z 1.000000 8.5771073 FALSE FALSE
## classe 1.469581 0.0254816 FALSE FALSEPrediction
Split the dataset into the training set and cross validation set.
inTrain <- createDataPartition(training$classe,p=0.6,list=FALSE)
train_data <- training[inTrain,]
cv_data <- training[-inTrain,]Set the training controls to use 3 fold cross validation
fitControl <- trainControl(method="cv", number=3, verboseIter=F)Use a CART Model for prediction. This model results in low accuracy and thus we will use random forests to see whether it improves performance.
tree_fit <- train(classe~.,method="rpart",data=train_data,
trControl = fitControl)
tree_pred <- predict(tree_fit,cv_data)
confusionMatrix(tree_pred,cv_data$classe)$overall## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.4977058 0.3430350 0.4865813 0.5088321 0.2844762
## AccuracyPValue McnemarPValue
## 0.0000000 NaNUse a Random Forest Model for prediction. This model achieves high accuracy when predicted against the cross validation set. We will use this model to predict against the testing dataset.
tree_fit <- train(classe~.,method="rf",data=train_data,
trControl = fitControl, allowParallel=TRUE)
tree_pred <- predict(tree_fit,cv_data)
confusionMatrix(tree_pred,cv_data$classe)$overall## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.9931175 0.9912929 0.9910293 0.9948256 0.2844762
## AccuracyPValue McnemarPValue
## 0.0000000 NaNUsing the random forest model against the cross validation set, the out of sample error is 0.0068825
Variable Importance
ggplot(varImp(tree_fit),aes(y=importance))+geom_bar(stat="identity")
From this we can see the relative importance of variable used in deriving the model. For computational sake, this can be used for dimensionality reduction to decide which variables to use in the model.
Prediction on Test Set
test_pred <- predict(tree_fit,testing[,-53])
test_pred## [1] B A B A A E D B A A B C B A E E A B B B
## Levels: A B C D E