library(caret)## Loading required package: lattice## Warning: package 'lattice' was built under R version 3.6.3## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 3.6.3data= read.csv('pml-training.csv', stringsAsFactors= F)
str(data)## 'data.frame': 19622 obs. of 160 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ user_name : chr "carlitos" "carlitos" "carlitos" "carlitos" ...
## $ 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 : chr "05/12/2011 11:23" "05/12/2011 11:23" "05/12/2011 11:23" "05/12/2011 11:23" ...
## $ new_window : chr "no" "no" "no" "no" ...
## $ 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 : chr "" "" "" "" ...
## $ kurtosis_picth_belt : chr "" "" "" "" ...
## $ kurtosis_yaw_belt : chr "" "" "" "" ...
## $ skewness_roll_belt : chr "" "" "" "" ...
## $ skewness_roll_belt.1 : chr "" "" "" "" ...
## $ skewness_yaw_belt : chr "" "" "" "" ...
## $ max_roll_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ max_picth_belt : int NA NA NA NA NA NA NA NA NA NA ...
## $ max_yaw_belt : chr "" "" "" "" ...
## $ min_roll_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ min_pitch_belt : int NA NA NA NA NA NA NA NA NA NA ...
## $ min_yaw_belt : chr "" "" "" "" ...
## $ amplitude_roll_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ amplitude_pitch_belt : int NA NA NA NA NA NA NA NA NA NA ...
## $ amplitude_yaw_belt : chr "" "" "" "" ...
## $ var_total_accel_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ avg_roll_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ stddev_roll_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ var_roll_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ avg_pitch_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ stddev_pitch_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ var_pitch_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ avg_yaw_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ stddev_yaw_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ var_yaw_belt : num NA NA NA NA NA NA NA NA NA NA ...
## $ gyros_belt_x : num 0 0.02 0 0.02 0.02 0.02 0.02 0.02 0.02 0.03 ...
## $ gyros_belt_y : num 0 0 0 0 0.02 0 0 0 0 0 ...
## $ gyros_belt_z : num -0.02 -0.02 -0.02 -0.03 -0.02 -0.02 -0.02 -0.02 -0.02 0 ...
## $ accel_belt_x : int -21 -22 -20 -22 -21 -21 -22 -22 -20 -21 ...
## $ accel_belt_y : int 4 4 5 3 2 4 3 4 2 4 ...
## $ accel_belt_z : int 22 22 23 21 24 21 21 21 24 22 ...
## $ magnet_belt_x : int -3 -7 -2 -6 -6 0 -4 -2 1 -3 ...
## $ magnet_belt_y : int 599 608 600 604 600 603 599 603 602 609 ...
## $ magnet_belt_z : int -313 -311 -305 -310 -302 -312 -311 -313 -312 -308 ...
## $ roll_arm : num -128 -128 -128 -128 -128 -128 -128 -128 -128 -128 ...
## $ pitch_arm : num 22.5 22.5 22.5 22.1 22.1 22 21.9 21.8 21.7 21.6 ...
## $ yaw_arm : num -161 -161 -161 -161 -161 -161 -161 -161 -161 -161 ...
## $ total_accel_arm : int 34 34 34 34 34 34 34 34 34 34 ...
## $ var_accel_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ avg_roll_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ stddev_roll_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ var_roll_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ avg_pitch_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ stddev_pitch_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ var_pitch_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ avg_yaw_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ stddev_yaw_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ var_yaw_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ gyros_arm_x : num 0 0.02 0.02 0.02 0 0.02 0 0.02 0.02 0.02 ...
## $ gyros_arm_y : num 0 -0.02 -0.02 -0.03 -0.03 -0.03 -0.03 -0.02 -0.03 -0.03 ...
## $ gyros_arm_z : num -0.02 -0.02 -0.02 0.02 0 0 0 0 -0.02 -0.02 ...
## $ accel_arm_x : int -288 -290 -289 -289 -289 -289 -289 -289 -288 -288 ...
## $ accel_arm_y : int 109 110 110 111 111 111 111 111 109 110 ...
## $ accel_arm_z : int -123 -125 -126 -123 -123 -122 -125 -124 -122 -124 ...
## $ magnet_arm_x : int -368 -369 -368 -372 -374 -369 -373 -372 -369 -376 ...
## $ magnet_arm_y : int 337 337 344 344 337 342 336 338 341 334 ...
## $ magnet_arm_z : int 516 513 513 512 506 513 509 510 518 516 ...
## $ kurtosis_roll_arm : chr "" "" "" "" ...
## $ kurtosis_picth_arm : chr "" "" "" "" ...
## $ kurtosis_yaw_arm : chr "" "" "" "" ...
## $ skewness_roll_arm : chr "" "" "" "" ...
## $ skewness_pitch_arm : chr "" "" "" "" ...
## $ skewness_yaw_arm : chr "" "" "" "" ...
## $ max_roll_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ max_picth_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ max_yaw_arm : int NA NA NA NA NA NA NA NA NA NA ...
## $ min_roll_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ min_pitch_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ min_yaw_arm : int NA NA NA NA NA NA NA NA NA NA ...
## $ amplitude_roll_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ amplitude_pitch_arm : num NA NA NA NA NA NA NA NA NA NA ...
## $ amplitude_yaw_arm : int NA NA NA NA NA NA NA NA NA NA ...
## $ roll_dumbbell : num 13.1 13.1 12.9 13.4 13.4 ...
## $ pitch_dumbbell : num -70.5 -70.6 -70.3 -70.4 -70.4 ...
## $ yaw_dumbbell : num -84.9 -84.7 -85.1 -84.9 -84.9 ...
## $ kurtosis_roll_dumbbell : chr "" "" "" "" ...
## $ kurtosis_picth_dumbbell : chr "" "" "" "" ...
## $ kurtosis_yaw_dumbbell : chr "" "" "" "" ...
## $ skewness_roll_dumbbell : chr "" "" "" "" ...
## $ skewness_pitch_dumbbell : chr "" "" "" "" ...
## $ skewness_yaw_dumbbell : chr "" "" "" "" ...
## $ max_roll_dumbbell : num NA NA NA NA NA NA NA NA NA NA ...
## $ max_picth_dumbbell : num NA NA NA NA NA NA NA NA NA NA ...
## $ max_yaw_dumbbell : chr "" "" "" "" ...
## $ min_roll_dumbbell : num NA NA NA NA NA NA NA NA NA NA ...
## $ min_pitch_dumbbell : num NA NA NA NA NA NA NA NA NA NA ...
## $ min_yaw_dumbbell : chr "" "" "" "" ...
## $ amplitude_roll_dumbbell : num NA NA NA NA NA NA NA NA NA NA ...
## [list output truncated]# Removing the first 7 columns as they are unnecessary
v= c(-1,-2, -3, -4, -5, -6, -7)
data= data[, v]
# Changing the variable type to numeric and replacing NAs with 0
v1= 2:152
data[,v1]= sapply(data[,v1], as.numeric)## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coerciondata = replace(data, is.na(data),0)intrain= createDataPartition(y= data$classe, p=.7, list=F)
training= data[intrain,]
testing= data[-intrain,]library(parallel)
library(doParallel)## Warning: package 'doParallel' was built under R version 3.6.3## Loading required package: foreach## Loading required package: iteratorscluster <- makeCluster(detectCores() - 1)
registerDoParallel(cluster)Random forest is chosen because it has high predictive accuracy in general, and intrerpretability is not our main concern here.
The classe varaible is to be predicted and it depends on all the remaining variables. Random forest is used with 5-fold cross validation. Cross validation reduces overfitting on the training data and hence the model should perform better on the test data.
fitControl = trainControl(method = "cv", number = 5, allowParallel = TRUE)
mod= train(classe~., method= 'rf', data=training, trControl= fitControl)
stopCluster(cluster)
registerDoSEQ()
# Viewing the results
mod## Random Forest
##
## 13737 samples
## 152 predictor
## 5 classes: 'A', 'B', 'C', 'D', 'E'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold)
## Summary of sample sizes: 10990, 10989, 10990, 10990, 10989
## Resampling results across tuning parameters:
##
## mtry Accuracy Kappa
## 2 0.8404311 0.7957442
## 77 0.9923565 0.9903315
## 152 0.9881344 0.9849899
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 77.mod$resample## Accuracy Kappa Resample
## 1 0.9945395 0.9930918 Fold1
## 2 0.9923553 0.9903317 Fold3
## 3 0.9909025 0.9884933 Fold2
## 4 0.9923581 0.9903329 Fold5
## 5 0.9916272 0.9894076 Fold4confusionMatrix.train(mod)## Cross-Validated (5 fold) Confusion Matrix
##
## (entries are percentual average cell counts across resamples)
##
## Reference
## Prediction A B C D E
## A 28.4 0.2 0.0 0.0 0.0
## B 0.0 19.1 0.1 0.0 0.0
## C 0.0 0.1 17.3 0.2 0.0
## D 0.0 0.0 0.1 16.2 0.1
## E 0.0 0.0 0.0 0.0 18.3
##
## Accuracy (average) : 0.9924Greater than 99% accuracy is attained on training data, which is satisfactory.
p1= predict(mod, testing)
testing$classe = as.factor(testing$classe)
confusionMatrix(p1, testing$classe)## Confusion Matrix and Statistics
##
## Reference
## Prediction A B C D E
## A 1669 5 0 0 0
## B 4 1133 4 0 2
## C 1 1 1022 5 2
## D 0 0 0 957 0
## E 0 0 0 2 1078
##
## Overall Statistics
##
## Accuracy : 0.9956
## 95% CI : (0.9935, 0.9971)
## No Information Rate : 0.2845
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.9944
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: A Class: B Class: C Class: D Class: E
## Sensitivity 0.9970 0.9947 0.9961 0.9927 0.9963
## Specificity 0.9988 0.9979 0.9981 1.0000 0.9996
## Pos Pred Value 0.9970 0.9913 0.9913 1.0000 0.9981
## Neg Pred Value 0.9988 0.9987 0.9992 0.9986 0.9992
## Prevalence 0.2845 0.1935 0.1743 0.1638 0.1839
## Detection Rate 0.2836 0.1925 0.1737 0.1626 0.1832
## Detection Prevalence 0.2845 0.1942 0.1752 0.1626 0.1835
## Balanced Accuracy 0.9979 0.9963 0.9971 0.9964 0.9979The accuracy on the testing data is also greater than 99 percent. Out-of-sample error (< 1%) is slightly lesser than in-sample error. The model does better on the test data.
# Applying same processing steps to the new data
valid= read.csv('pml-testing.csv', stringsAsFactors= F)
valid= valid[, v]
valid[,v1]= sapply(valid[,v1], as.numeric)
valid = replace(valid, is.na(valid),0)
# Results
p2= predict(mod, valid)
p2## [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