Project
Spiros Paraskevas
9 Νοεμβρίου 2015
Loading libraries and the data and performing Preprocessing to define strategy.
library(caret)## Loading required package: lattice
## Loading required package: ggplot2library(data.table)
library(rpart)
library(rpart.plot)
library(RColorBrewer)
library(rattle)## Loading required package: RGtk2
## Rattle: A free graphical interface for data mining with R.
## Version 3.5.0 Copyright (c) 2006-2015 Togaware Pty Ltd.
## Type 'rattle()' to shake, rattle, and roll your data.library(randomForest)## randomForest 4.6-12
## Type rfNews() to see new features/changes/bug fixes.library(knitr)
library(mice)## Loading required package: Rcpp
## mice 2.22 2014-06-10library(ROCR)## Loading required package: gplots
##
## Attaching package: 'gplots'
##
## The following object is masked from 'package:stats':
##
## lowesslibrary(outliers)##
## Attaching package: 'outliers'
##
## The following object is masked from 'package:randomForest':
##
## outlierlibrary(plyr)
library(boot)##
## Attaching package: 'boot'
##
## The following object is masked from 'package:lattice':
##
## melanoma###
training <- read.csv("train.csv", sep=",") ##Having inspected the dataset, the columns are seperated with comas.
validation <- read.csv("test.csv", sep=",")
summary(training)
summary(validation)
lapply(training,class)
lapply(validation,class)Data Quality, Sanity checks & Exploratory Data Analysis(pt1).
Appropriate transformations and feature engineering on both datasets. Exploratory data analysis to reveal skweness, outliers etc.
##PassengerID is an ID variable, hence it must be removed.
training <- training[,-1]
validation <- validation[,-1]
##Survived is a categorical variable, its class should be transformed to factor class.
class(training$Survived) ##Jesus, its an integer## [1] "integer"training$Survived <- as.factor(training$Survived)
table(training$Survived)##
## 0 1
## 549 342sum(is.na(training$Survived))/length(training$Survived)#No NAs## [1] 0##Pclass is a categorical variable, its class should be transformed to factor.
##Training set
class(training$Pclass)## [1] "integer"training$Pclass <- as.factor(training$Pclass)
table(training$Pclass)##
## 1 2 3
## 216 184 491sum(is.na(training$Pclass))/length(training$Pclass) #No NAs## [1] 0##Validation set
class(validation$Pclass)## [1] "integer"validation$Pclass <- as.factor(validation$Pclass)
table(validation$Pclass)##
## 1 2 3
## 107 93 218sum(is.na(validation$Pclass))/length(validation$Pclass) #No NAs## [1] 0##Name variable is useless, hence it gets removed from both datasets
training <- training[,-3]
validation <- validation[,-2]
##Sex variable is categorical, and its class should be factor.
class(training$Sex) #Aleeady of a factor type, no transformation necessary.## [1] "factor"table(training$Sex)##
## female male
## 314 577sum(is.na(training$Sex))/length(is.na(training$Sex))#No NAs## [1] 0class(validation$Sex) #Aleeady of a factor type, no transformation necessary.## [1] "factor"table(validation$Sex)##
## female male
## 152 266sum(is.na(training$Sex))/length(is.na(training$Sex))#No NAs## [1] 0##Age variable should be numeric, which is so already, hence no action needed
class(training$Age) #Already of a numeric type, no transormation necessary## [1] "numeric"summary(training$Age, na.rm=TRUE)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.42 20.12 28.00 29.70 38.00 80.00 177hist(training$Age) #Slightly rightly skewed, nothing to worry about.
boxplot(training$Age) #Few outliers, no big deal
sum(is.na(training$Age))/length(training$Age) # 20% missing values. We will check against CV accuracy the removal, NA imputation, or just complete row removal.## [1] 0.1986532class(validation$Age) #Already of a numeric type, no transormation necessary## [1] "numeric"summary(validation$Age, na.rm=TRUE)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.17 21.00 27.00 30.27 39.00 76.00 86hist(training$Age) #Slightly rightly skewed, nothing to worry about.
boxplot(training$Age) #Few outliers, no big deal
sum(is.na(training$Age))/length(training$Age) # 20% missing values. We will check against CV accuracy the removal, NA imputation, or just complete row removal.## [1] 0.1986532##SibSp is of a integer class, which is already
class(training$SibSp)## [1] "integer"table(training$SibSp)##
## 0 1 2 3 4 5 8
## 608 209 28 16 18 5 7sum(is.na(training$SibSp))/length(is.na(training$SibSp))#No NAs## [1] 0class(validation$SibSp)## [1] "integer"table(validation$SibSp)##
## 0 1 2 3 4 5 8
## 283 110 14 4 4 1 2sum(is.na(validation$SibSp))/length(is.na(validation$SibSp))#No NAs## [1] 0##Parch is of an integer class, which is already, hence no action necessary
class(training$Parch) #Alreadof the correct type, no transformation necessary## [1] "integer"table(training$Parch)##
## 0 1 2 3 4 5 6
## 678 118 80 5 4 5 1sum(is.na(training$Parch))/length(training$Parch) #No NAs## [1] 0class(validation$Parch) #Alreadof the correct type, no transformation necessary## [1] "integer"table(training$Parch)##
## 0 1 2 3 4 5 6
## 678 118 80 5 4 5 1sum(is.na(validation$Parch))/length(validation$Parch) #No NAs## [1] 0####Ticket variable is useless. Hence it gets removed.
training <- training[,-7]
validation <- validation[,-6]
##Fare variable is
class(training$Fare) #already registerd as numeric class, hence no action necessary## [1] "numeric"summary(training$Fare)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 7.91 14.45 32.20 31.00 512.30hist(training$Fare) #Heavily skewed, maybe a logarithmic transformation could prove usefull. Will check against CV accuracy.
boxplot(training$Fare) #One outlier, that is considerably, out of normal. Will remove this datapoint.
sum(is.na(training$Fare))/length(training$Fare)#No NAs## [1] 0which.max(training$Fare)## [1] 259training$Fare[259]## [1] 512.3292class(validation$Fare) #already registerd as numeric class, hence no action necessary## [1] "numeric"summary(validation$Fare)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.000 7.896 14.450 35.630 31.500 512.300 1hist(validation$Fare) #Heavily skewed, maybe a logarithmic transformation could prove usefull. Will check against CV accuracy.
boxplot(validation$Fare) #One outlier, that is considerably, out of normal. Will remove this datapoint.
sum(is.na(training$Fare))/length(training$Fare)#No NAs## [1] 0which.max(validation$Fare)## [1] 344validation$Fare[344]## [1] 512.3292##Cabin variable should be transformed to provide ie discrimination among those who had cabin and those who did not. Hence, we transform the variable in a binary one with 0,1 levels.
class(training$Cabin)## [1] "factor"training$Cabin <- as.character(training$Cabin)
training$Cabin[training$Cabin==""] <- 0
training$Cabin[!training$Cabin==0] <- 1
training$Cabin <- as.factor(training$Cabin)
table(training$Cabin)##
## 0 1
## 687 204sum(is.na(training$Cabin))/length(training$Cabin)#No NAs## [1] 0class(validation$Cabin)## [1] "factor"validation$Cabin <- as.character(validation$Cabin)
validation$Cabin[validation$Cabin==""] <- 0
validation$Cabin[!validation$Cabin==0] <- 1
validation$Cabin <- as.factor(validation$Cabin)
table(validation$Cabin)##
## 0 1
## 327 91sum(is.na(validation$Cabin))/length(validation$Cabin)#No NAs## [1] 0##Embarked
class(training$Embarked) # Already of a factor type, no transformation necessary## [1] "factor"table(training$Embarked) # NAs were considered as a factor level, transformation need##
## C Q S
## 2 168 77 644training$Embarked[training$Embarked==""] <- 0## Warning in `[<-.factor`(`*tmp*`, training$Embarked == "", value =
## structure(c(4L, : invalid factor level, NA generatedsum(is.na(training$Embarked))/length(training$Embarked) ##Very few NAs## [1] 0.002244669class(validation$Embarked) # Already of a factor type, no transformation necessary## [1] "factor"table(validation$Embarked)##
## C Q S
## 102 46 270sum(is.na(validation$Embarked))/length(validation$Embarked) ##No NAs## [1] 0Data Quality, Sanity & Exploratory Data Analysis (pt2)
Here, duplicated records are checked for
##Let's check for duplicate records by counting how many are there, if any.
sum(duplicated(training)==TRUE)##Ohh, significant number of duplicate records## [1] 107The amount of duplicate records is 107, which is significant. The duplicate records must be removed from the training dataset.
training_unique <- unique(training)
rm(training)##The initial training set is no longer needed.Based on the summary results we see that missing values exist. Most NAs are found at the Age variable. Two strategies are checked. The first will be to impute missing values in Age variable with the variable mean value, and then perform omition of rows containing NAs. The second will be to delete all rows with missing values.
##Imputing Age
training_Age <- training_unique
training_Age$Age[is.na(training_unique$Age)] <- mean(training_unique$Age,na.rm=TRUE)
training_Age <- na.omit(training_Age)
validation_Age <- validation
validation_Age$Age[is.na(validation_Age$Age)] <- mean(validation_Age$Age,na.rm=TRUE)
validation_Age <- na.omit(validation_Age)
training_na <- na.omit(training_unique)
validation_na <- na.omit(validation)All following checks will be held on training_Age. Final checks will include training_na
Correlations
#Numeric attributes
cor(training_Age[,c(4,5,6,7)]) # Some correlation, but no action will be employed## Age SibSp Parch Fare
## Age 1.00000000 -0.2799495 -0.1873354 0.08639407
## SibSp -0.27994952 1.0000000 0.3810158 0.13650684
## Parch -0.18733541 0.3810158 1.0000000 0.19329489
## Fare 0.08639407 0.1365068 0.1932949 1.00000000#Factor attributes, nothing interestingModeling approaches
5-fold Cross Validation on accuracy, averaged over 5 repetitions will be the strategy to select the best possible model.
##Let's define a trainControl setting, that will remain the same for all applied models thereon
fitControl <- trainControl(## 10-fold CV
method = "repeatedcv",
number = 5,
#classProbs = TRUE,
## repeated ten times
repeats = 5)Let’s set the formula including all variables
##Set the formula
formula <- Survived~Pclass+Sex+Age+SibSp+Parch+Fare+Cabin+EmbarkedThe criterion is a models Accuracy = (TF+TP)/(TF+FF+FP+TP) ,which we opt to maximize. Under this criterion we shall compare a number of classifiers using the excellent “caret” package.
Generalized Linear model (Binomial family)
set.seed(1000)
logisticReg <- train(formula,
data = training_Age,
method = "glm",
#metric = "ROC",
trControl = fitControl)## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleadinglogisticReg## Generalized Linear Model
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 625, ...
## Resampling results
##
## Accuracy Kappa Accuracy SD Kappa SD
## 0.7813753 0.5437916 0.03270276 0.06892272
##
## ##Accuracy 0.7813753 Accuracy (Stand.Dev 0.03270276) Bayesian Logistic Regression trees
set.seed(1000)
BayesianLogReg <- train(formula,
data = training_Age,
method = "bayesglm",
trControl = fitControl)## Loading required package: arm
## Loading required package: MASS
## Loading required package: Matrix
## Loading required package: lme4
##
## arm (Version 1.8-6, built: 2015-7-7)
##
## Working directory is D:/Data_Science_Projects/Kaggle/Titanic
##
##
## Attaching package: 'arm'
##
## The following object is masked from 'package:boot':
##
## logitBayesianLogReg## Bayesian Generalized Linear Model
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 625, ...
## Resampling results
##
## Accuracy Kappa Accuracy SD Kappa SD
## 0.7821429 0.5453747 0.03264758 0.06862032
##
## ##Accuracy 0.7821429 (Stand.Dev 0.03264758) Classification and regression trees CART
set.seed(1000)
##tuning for complexity parameter (cp)
rpartTune1 <- train(training_Age[,c(2,3,4,5,6,7,8,9)], training_Age$Survived,
method = "rpart",
tuneLength = 10,
trControl = fitControl)
plot(rpartTune1)
rpartTune1## CART
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 625, ...
## Resampling results across tuning parameters:
##
## cp Accuracy Kappa Accuracy SD Kappa SD
## 0.00000000 0.7713981 0.5195163 0.03267479 0.06791937
## 0.04811353 0.7634656 0.5013339 0.02769522 0.06197579
## 0.09622707 0.7673117 0.5120282 0.03082519 0.06651355
## 0.14434060 0.7673117 0.5120282 0.03082519 0.06651355
## 0.19245414 0.7673117 0.5120282 0.03082519 0.06651355
## 0.24056767 0.7673117 0.5120282 0.03082519 0.06651355
## 0.28868120 0.7673117 0.5120282 0.03082519 0.06651355
## 0.33679474 0.7673117 0.5120282 0.03082519 0.06651355
## 0.38490827 0.7673117 0.5120282 0.03082519 0.06651355
## 0.43302181 0.6697641 0.2403141 0.07970959 0.23704117
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was cp = 0.##Accuracy 0.7769606 (Stand.Dev. 0.02825927)
##tuning for maximum node depth (maxdepth)
rpartTune2 <- train(training_Age[,c(2,3,4,5,6,7,8,9)], training_Age$Survived,
method = "rpart2",
tuneLength = 10,
trControl = fitControl)## note: only 8 possible values of the max tree depth from the initial fit.
## Truncating the grid to 8 .plot(rpartTune2)
rpartTune2## CART
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 626, 625, 626, 625, 626, ...
## Resampling results across tuning parameters:
##
## maxdepth Accuracy Kappa Accuracy SD Kappa SD
## 1 0.7672775 0.5118670 0.02998430 0.06530389
## 3 0.7770015 0.5238072 0.02521525 0.05919326
## 4 0.7749600 0.5158499 0.02649617 0.05981048
## 7 0.7767353 0.5233229 0.02513619 0.05227189
## 12 0.7757064 0.5220013 0.02583147 0.05357595
## 16 0.7757064 0.5220013 0.02583147 0.05357595
## 20 0.7757064 0.5220013 0.02583147 0.05357595
## 21 0.7757064 0.5220013 0.02583147 0.05357595
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was maxdepth = 3.##Accuracy 0.7759268 (Stand.Dev. 0.02634301)Random Forest
set.seed(1000)
rfGrid = expand.grid(.mtry = c(1,2,3,4,5))
randomForestFit = train(x = training_Age[,c(2,3,4,5,6,7,8,9)],
y = training_Age$Survived,
method = "rf",
trControl = fitControl,
tuneGrid = rfGrid,
ntree=30)
plot(randomForestFit)
randomForestFit## Random Forest
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 625, ...
## Resampling results across tuning parameters:
##
## mtry Accuracy Kappa Accuracy SD Kappa SD
## 1 0.7762926 0.5168517 0.03526116 0.07769250
## 2 0.7931474 0.5612414 0.03202731 0.06974171
## 3 0.7967534 0.5713995 0.03508362 0.07558851
## 4 0.7885857 0.5560803 0.03391657 0.07259389
## 5 0.7793679 0.5377080 0.03684067 0.07889677
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 3.varImp(randomForestFit)## rf variable importance
##
## Overall
## Sex 100.0000
## Age 77.5436
## Fare 76.6489
## Pclass 23.5638
## Cabin 5.0015
## SibSp 3.1171
## Parch 0.4259
## Embarked 0.0000##Accuracy 0.7967534 (Stand.Dev. 0.03508362)GBM
gbmGrid <- expand.grid(interaction.depth = c(1, 2, 3),
n.trees = (1:10)*5,
shrinkage = (1:3)*0.1,
n.minobsinnode = (1:3)*10)
gbmFit <- train(formula, data = training_Age,
method = "gbm",
trControl = fitControl,
## This last option is actually one
## for gbm() that passes through
verbose = FALSE,
tuneGrid = gbmGrid)## Loading required package: gbm
## Loading required package: survival
##
## Attaching package: 'survival'
##
## The following object is masked from 'package:boot':
##
## aml
##
## The following object is masked from 'package:caret':
##
## cluster
##
## Loading required package: splines
## Loading required package: parallel
## Loaded gbm 2.1.1gbmFit## Stochastic Gradient Boosting
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 626, ...
## Resampling results across tuning parameters:
##
## shrinkage interaction.depth n.minobsinnode n.trees Accuracy
## 0.1 1 10 5 0.7659847
## 0.1 1 10 10 0.7672586
## 0.1 1 10 15 0.7672586
## 0.1 1 10 20 0.7664894
## 0.1 1 10 25 0.7675150
## 0.1 1 10 30 0.7695582
## 0.1 1 10 35 0.7675232
## 0.1 1 10 40 0.7739139
## 0.1 1 10 45 0.7759521
## 0.1 1 10 50 0.7797966
## 0.1 1 20 5 0.7652139
## 0.1 1 20 10 0.7662395
## 0.1 1 20 15 0.7659847
## 0.1 1 20 20 0.7659847
## 0.1 1 20 25 0.7664976
## 0.1 1 20 30 0.7687987
## 0.1 1 20 35 0.7690503
## 0.1 1 20 40 0.7675151
## 0.1 1 20 45 0.7693034
## 0.1 1 20 50 0.7744267
## 0.1 1 30 5 0.7659766
## 0.1 1 30 10 0.7670022
## 0.1 1 30 15 0.7672586
## 0.1 1 30 20 0.7672586
## 0.1 1 30 25 0.7652139
## 0.1 1 30 30 0.7664878
## 0.1 1 30 35 0.7685391
## 0.1 1 30 40 0.7698227
## 0.1 1 30 45 0.7718675
## 0.1 1 30 50 0.7741752
## 0.1 2 10 5 0.7762152
## 0.1 2 10 10 0.7652106
## 0.1 2 10 15 0.7723771
## 0.1 2 10 20 0.7813221
## 0.1 2 10 25 0.7882337
## 0.1 2 10 30 0.7913172
## 0.1 2 10 35 0.7936167
## 0.1 2 10 40 0.8002687
## 0.1 2 10 45 0.8000058
## 0.1 2 10 50 0.8000009
## 0.1 2 20 5 0.7762152
## 0.1 2 20 10 0.7682762
## 0.1 2 20 15 0.7636739
## 0.1 2 20 20 0.7644349
## 0.1 2 20 25 0.7741508
## 0.1 2 20 30 0.7782599
## 0.1 2 20 35 0.7815867
## 0.1 2 20 40 0.7841362
## 0.1 2 20 45 0.7900238
## 0.1 2 20 50 0.7923250
## 0.1 2 30 5 0.7762152
## 0.1 2 30 10 0.7700630
## 0.1 2 30 15 0.7667572
## 0.1 2 30 20 0.7667491
## 0.1 2 30 25 0.7733962
## 0.1 2 30 30 0.7787645
## 0.1 2 30 35 0.7795354
## 0.1 2 30 40 0.7800433
## 0.1 2 30 45 0.7823493
## 0.1 2 30 50 0.7849200
## 0.1 3 10 5 0.7769828
## 0.1 3 10 10 0.7779971
## 0.1 3 10 15 0.7833784
## 0.1 3 10 20 0.7897804
## 0.1 3 10 25 0.7977079
## 0.1 3 10 30 0.7977080
## 0.1 3 10 35 0.8010396
## 0.1 3 10 40 0.8018072
## 0.1 3 10 45 0.8015459
## 0.1 3 10 50 0.8041051
## 0.1 3 20 5 0.7762152
## 0.1 3 20 10 0.7736478
## 0.1 3 20 15 0.7792953
## 0.1 3 20 20 0.7820913
## 0.1 3 20 25 0.7882419
## 0.1 3 20 30 0.7879823
## 0.1 3 20 35 0.7949004
## 0.1 3 20 40 0.7933604
## 0.1 3 20 45 0.7933604
## 0.1 3 20 50 0.7956485
## 0.1 3 30 5 0.7762152
## 0.1 3 30 10 0.7744203
## 0.1 3 30 15 0.7739204
## 0.1 3 30 20 0.7813253
## 0.1 3 30 25 0.7797787
## 0.1 3 30 30 0.7800368
## 0.1 3 30 35 0.7869534
## 0.1 3 30 40 0.7856729
## 0.1 3 30 45 0.7851634
## 0.1 3 30 50 0.7838846
## 0.2 1 10 5 0.7621419
## 0.2 1 10 10 0.7670071
## 0.2 1 10 15 0.7698146
## 0.2 1 10 20 0.7716144
## 0.2 1 10 25 0.7826302
## 0.2 1 10 30 0.7856957
## 0.2 1 10 35 0.7874743
## 0.2 1 10 40 0.7902997
## 0.2 1 10 45 0.7884999
## 0.2 1 10 50 0.7890209
## 0.2 1 20 5 0.7680230
## 0.2 1 20 10 0.7659766
## 0.2 1 20 15 0.7646978
## 0.2 1 20 20 0.7716078
## 0.2 1 20 25 0.7723852
## 0.2 1 20 30 0.7764845
## 0.2 1 20 35 0.7808337
## 0.2 1 20 40 0.7867067
## 0.2 1 20 45 0.7861939
## 0.2 1 20 50 0.7867100
## 0.2 1 30 5 0.7649575
## 0.2 1 30 10 0.7664959
## 0.2 1 30 15 0.7682810
## 0.2 1 30 20 0.7708435
## 0.2 1 30 25 0.7762102
## 0.2 1 30 30 0.7754459
## 0.2 1 30 35 0.7759604
## 0.2 1 30 40 0.7756990
## 0.2 1 30 45 0.7792953
## 0.2 1 30 50 0.7772473
## 0.2 2 10 5 0.7695728
## 0.2 2 10 10 0.7803192
## 0.2 2 10 15 0.7946213
## 0.2 2 10 20 0.8007620
## 0.2 2 10 25 0.8012944
## 0.2 2 10 30 0.8005220
## 0.2 2 10 35 0.7977128
## 0.2 2 10 40 0.8002607
## 0.2 2 10 45 0.7984707
## 0.2 2 10 50 0.8005072
## 0.2 2 20 5 0.7687841
## 0.2 2 20 10 0.7716160
## 0.2 2 20 15 0.7823673
## 0.2 2 20 20 0.7882419
## 0.2 2 20 25 0.7920799
## 0.2 2 20 30 0.7920815
## 0.2 2 20 35 0.7951520
## 0.2 2 20 40 0.7969322
## 0.2 2 20 45 0.7948874
## 0.2 2 20 50 0.7954002
## 0.2 2 30 5 0.7692970
## 0.2 2 30 10 0.7721191
## 0.2 2 30 15 0.7698114
## 0.2 2 30 20 0.7782533
## 0.2 2 30 25 0.7833847
## 0.2 2 30 30 0.7841361
## 0.2 2 30 35 0.7818350
## 0.2 2 30 40 0.7836184
## 0.2 2 30 45 0.7892496
## 0.2 2 30 50 0.7925862
## 0.2 3 10 5 0.7754541
## 0.2 3 10 10 0.7887596
## 0.2 3 10 15 0.7961809
## 0.2 3 10 20 0.7948939
## 0.2 3 10 25 0.7989933
## 0.2 3 10 30 0.8020473
## 0.2 3 10 35 0.8002720
## 0.2 3 10 40 0.8020523
## 0.2 3 10 45 0.8025618
## 0.2 3 10 50 0.8038439
## 0.2 3 20 5 0.7690600
## 0.2 3 20 10 0.7831252
## 0.2 3 20 15 0.7869453
## 0.2 3 20 20 0.7933474
## 0.2 3 20 25 0.7915509
## 0.2 3 20 30 0.7943730
## 0.2 3 20 35 0.7920686
## 0.2 3 20 40 0.7959033
## 0.2 3 20 45 0.7935989
## 0.2 3 20 50 0.7974402
## 0.2 3 30 5 0.7705774
## 0.2 3 30 10 0.7736641
## 0.2 3 30 15 0.7805578
## 0.2 3 30 20 0.7856713
## 0.2 3 30 25 0.7912862
## 0.2 3 30 30 0.7900123
## 0.2 3 30 35 0.7902574
## 0.2 3 30 40 0.7941035
## 0.2 3 30 45 0.7961564
## 0.2 3 30 50 0.7969240
## 0.3 1 10 5 0.7675150
## 0.3 1 10 10 0.7700677
## 0.3 1 10 15 0.7736542
## 0.3 1 10 20 0.7744202
## 0.3 1 10 25 0.7823591
## 0.3 1 10 30 0.7823689
## 0.3 1 10 35 0.7844137
## 0.3 1 10 40 0.7897917
## 0.3 1 10 45 0.7810852
## 0.3 1 10 50 0.7818610
## 0.3 1 20 5 0.7657365
## 0.3 1 20 10 0.7669989
## 0.3 1 20 15 0.7736591
## 0.3 1 20 20 0.7757104
## 0.3 1 20 25 0.7780213
## 0.3 1 20 30 0.7823771
## 0.3 1 20 35 0.7831349
## 0.3 1 20 40 0.7849281
## 0.3 1 20 45 0.7877405
## 0.3 1 20 50 0.7913221
## 0.3 1 30 5 0.7667491
## 0.3 1 30 10 0.7693116
## 0.3 1 30 15 0.7736656
## 0.3 1 30 20 0.7728948
## 0.3 1 30 25 0.7754524
## 0.3 1 30 30 0.7821060
## 0.3 1 30 35 0.7813286
## 0.3 1 30 40 0.7805562
## 0.3 1 30 45 0.7795370
## 0.3 1 30 50 0.7785195
## 0.3 2 10 5 0.7736429
## 0.3 2 10 10 0.7895142
## 0.3 2 10 15 0.7971756
## 0.3 2 10 20 0.8030714
## 0.3 2 10 25 0.8012814
## 0.3 2 10 30 0.8015329
## 0.3 2 10 35 0.7966676
## 0.3 2 10 40 0.7987124
## 0.3 2 10 45 0.8007507
## 0.3 2 10 50 0.7994800
## 0.3 2 20 5 0.7667540
## 0.3 2 20 10 0.7805692
## 0.3 2 20 15 0.7892659
## 0.3 2 20 20 0.7930925
## 0.3 2 20 25 0.7994768
## 0.3 2 20 30 0.7966660
## 0.3 2 20 35 0.7958854
## 0.3 2 20 40 0.7941116
## 0.3 2 20 45 0.7984462
## 0.3 2 20 50 0.7969176
## 0.3 2 30 5 0.7639287
## 0.3 2 30 10 0.7693068
## 0.3 2 30 15 0.7802998
## 0.3 2 30 20 0.7805643
## 0.3 2 30 25 0.7846360
## 0.3 2 30 30 0.7846375
## 0.3 2 30 35 0.7856779
## 0.3 2 30 40 0.7941149
## 0.3 2 30 45 0.7918170
## 0.3 2 30 50 0.7933506
## 0.3 3 10 5 0.7803144
## 0.3 3 10 10 0.7956632
## 0.3 3 10 15 0.8023054
## 0.3 3 10 20 0.8015426
## 0.3 3 10 25 0.8015443
## 0.3 3 10 30 0.8028149
## 0.3 3 10 35 0.8025699
## 0.3 3 10 40 0.7999993
## 0.3 3 10 45 0.7943925
## 0.3 3 10 50 0.7997657
## 0.3 3 20 5 0.7774907
## 0.3 3 20 10 0.7925781
## 0.3 3 20 15 0.7918154
## 0.3 3 20 20 0.7977112
## 0.3 3 20 25 0.8000075
## 0.3 3 20 30 0.8017942
## 0.3 3 20 35 0.7974548
## 0.3 3 20 40 0.7969354
## 0.3 3 20 45 0.8043323
## 0.3 3 20 50 0.8061287
## 0.3 3 30 5 0.7734125
## 0.3 3 30 10 0.7821126
## 0.3 3 30 15 0.7915574
## 0.3 3 30 20 0.7846490
## 0.3 3 30 25 0.7897723
## 0.3 3 30 30 0.7895191
## 0.3 3 30 35 0.7923250
## 0.3 3 30 40 0.7948988
## 0.3 3 30 45 0.7931023
## 0.3 3 30 50 0.7943795
## Kappa Accuracy SD Kappa SD
## 0.5068990 0.02989148 0.06320075
## 0.5116754 0.03049068 0.06346941
## 0.5122267 0.03049068 0.06344830
## 0.5099611 0.02948566 0.06079232
## 0.5128053 0.03036620 0.06321439
## 0.5167000 0.03125230 0.06447723
## 0.5121230 0.03134333 0.06508044
## 0.5264767 0.02909830 0.05868774
## 0.5316101 0.03017819 0.06184828
## 0.5402722 0.02910022 0.05994546
## 0.5039342 0.02776113 0.05596537
## 0.5087632 0.02990394 0.06239219
## 0.5090396 0.02989148 0.06230063
## 0.5090396 0.02989148 0.06230063
## 0.5101743 0.03039883 0.06358601
## 0.5156691 0.03260019 0.06835429
## 0.5155470 0.02893755 0.05940530
## 0.5129674 0.02814021 0.05789075
## 0.5164180 0.02620867 0.05247451
## 0.5278479 0.02636268 0.05332780
## 0.5078179 0.03023477 0.06384033
## 0.5109710 0.02999089 0.06112310
## 0.5122267 0.03049068 0.06344830
## 0.5122267 0.03049068 0.06344830
## 0.5070237 0.02924455 0.05991361
## 0.5104608 0.03079029 0.06334470
## 0.5138546 0.03046889 0.06339141
## 0.5183164 0.02969520 0.06182831
## 0.5221668 0.03191171 0.06711851
## 0.5277807 0.03098311 0.06419363
## 0.5003228 0.01943130 0.04543021
## 0.4876053 0.02805329 0.05555898
## 0.5083940 0.03128839 0.06185535
## 0.5291644 0.03282362 0.06747275
## 0.5447690 0.03282961 0.06938786
## 0.5524133 0.02483552 0.05327124
## 0.5580691 0.02424531 0.05201645
## 0.5729243 0.02191954 0.04712153
## 0.5731354 0.02195673 0.04752952
## 0.5747671 0.02251967 0.04722950
## 0.5003228 0.01943130 0.04543021
## 0.4909829 0.02522061 0.05143022
## 0.4885601 0.02326584 0.04555953
## 0.4939438 0.03013584 0.06018546
## 0.5142870 0.02734693 0.05734199
## 0.5240661 0.02964560 0.06225099
## 0.5313803 0.03038308 0.06422843
## 0.5393379 0.02891215 0.06225570
## 0.5533187 0.02424764 0.05181633
## 0.5588020 0.02938789 0.06293289
## 0.5003228 0.01943130 0.04543021
## 0.4935595 0.02555045 0.05146750
## 0.4946169 0.03018342 0.06177469
## 0.4966534 0.02983784 0.06149704
## 0.5116707 0.02858429 0.05836913
## 0.5234695 0.02768109 0.05730050
## 0.5279118 0.03053069 0.06479479
## 0.5297229 0.03088374 0.06587760
## 0.5349552 0.03198181 0.06821559
## 0.5414414 0.02713213 0.05687380
## 0.5025879 0.01980548 0.04635923
## 0.5097134 0.02248619 0.05092485
## 0.5277655 0.02539061 0.05826005
## 0.5477875 0.02564416 0.05743698
## 0.5665746 0.02388304 0.05304513
## 0.5682688 0.02716449 0.06075609
## 0.5764466 0.02656016 0.05838217
## 0.5792110 0.02717506 0.05886332
## 0.5794138 0.02455545 0.05321545
## 0.5852808 0.02485300 0.05329289
## 0.5003228 0.01943130 0.04543021
## 0.4997695 0.02255565 0.05173043
## 0.5185328 0.02346828 0.05354928
## 0.5289593 0.02458976 0.05261948
## 0.5430550 0.02372909 0.05118290
## 0.5444704 0.02727598 0.05917280
## 0.5611766 0.02576930 0.05545747
## 0.5596960 0.02379788 0.05124839
## 0.5602221 0.02422032 0.05201502
## 0.5663037 0.02748152 0.05951490
## 0.5003228 0.01943130 0.04543021
## 0.4972711 0.01881778 0.04425143
## 0.5072300 0.02783253 0.05655506
## 0.5272299 0.02945697 0.06193121
## 0.5272033 0.02724902 0.05744290
## 0.5284531 0.03037383 0.06574787
## 0.5446295 0.02888876 0.06078796
## 0.5426307 0.03154473 0.06574049
## 0.5427859 0.02930526 0.06203585
## 0.5410170 0.03066654 0.06346243
## 0.4969020 0.02905763 0.06313107
## 0.5106325 0.03024207 0.06293365
## 0.5168493 0.03116431 0.06384049
## 0.5222493 0.03337429 0.06958435
## 0.5454766 0.03015808 0.06215687
## 0.5520518 0.02897665 0.05979709
## 0.5560712 0.02809719 0.05785234
## 0.5624375 0.02555621 0.05248440
## 0.5585148 0.02528132 0.05253832
## 0.5601679 0.02210160 0.04590014
## 0.5127959 0.03098242 0.06365961
## 0.5087470 0.02908016 0.06020368
## 0.5053047 0.03154475 0.06602654
## 0.5204837 0.03094083 0.06430366
## 0.5233665 0.03058057 0.06259138
## 0.5327456 0.02685929 0.05464271
## 0.5416816 0.02432870 0.04958532
## 0.5548815 0.02144464 0.04366260
## 0.5531995 0.02263922 0.04633041
## 0.5538997 0.02375048 0.04851069
## 0.5045487 0.02884121 0.05936438
## 0.5093319 0.03012906 0.06297748
## 0.5132175 0.02956596 0.06185566
## 0.5203602 0.03395988 0.07195817
## 0.5316613 0.02748804 0.05628281
## 0.5295998 0.02172159 0.04344300
## 0.5313039 0.02844610 0.05961419
## 0.5304756 0.02666457 0.05625595
## 0.5381902 0.02321282 0.04736218
## 0.5343281 0.02483476 0.05045475
## 0.4950654 0.02584843 0.05095010
## 0.5249029 0.02943062 0.05776693
## 0.5596901 0.02325698 0.04757517
## 0.5760927 0.02614172 0.05533125
## 0.5789276 0.02754474 0.05934038
## 0.5776058 0.02813928 0.06052737
## 0.5731894 0.02487932 0.05158207
## 0.5783795 0.02812301 0.06029140
## 0.5745024 0.02609011 0.05635277
## 0.5789149 0.02455203 0.05181259
## 0.4921559 0.02713570 0.05104730
## 0.5054420 0.03044131 0.06086967
## 0.5317215 0.03013853 0.06154400
## 0.5471720 0.03156888 0.06771020
## 0.5587298 0.02930018 0.06162407
## 0.5586091 0.03139512 0.06613766
## 0.5664189 0.03054368 0.06530382
## 0.5714003 0.02600282 0.05390575
## 0.5661670 0.02418800 0.05110142
## 0.5689763 0.02760907 0.05800245
## 0.4970240 0.02383458 0.04804574
## 0.5065992 0.02652028 0.05409472
## 0.5056798 0.02643911 0.05383536
## 0.5262018 0.02581677 0.05358491
## 0.5393275 0.02626151 0.05419982
## 0.5419764 0.02693321 0.05582672
## 0.5383184 0.02563819 0.05284795
## 0.5429392 0.02824805 0.05835249
## 0.5548746 0.02950318 0.06118314
## 0.5623431 0.02559582 0.05337077
## 0.5066489 0.02106890 0.04680100
## 0.5455886 0.02430075 0.05307135
## 0.5638722 0.02435777 0.05385935
## 0.5635308 0.02491793 0.05411678
## 0.5748122 0.02782335 0.05975369
## 0.5825965 0.02557957 0.05436915
## 0.5791112 0.02454043 0.05319673
## 0.5832853 0.02413513 0.05164381
## 0.5846561 0.02703984 0.05727037
## 0.5871523 0.02751466 0.05762595
## 0.4910376 0.02483772 0.05246725
## 0.5317716 0.03188216 0.06673153
## 0.5444316 0.02748041 0.05758297
## 0.5607694 0.02621358 0.05720106
## 0.5585958 0.02332011 0.05095746
## 0.5655117 0.02412584 0.05008549
## 0.5609522 0.02602048 0.05473449
## 0.5692131 0.02638864 0.05591078
## 0.5647448 0.02825116 0.05980830
## 0.5730702 0.02697304 0.05724702
## 0.4905673 0.02551313 0.05556197
## 0.5099487 0.02642500 0.05573226
## 0.5298149 0.02655870 0.05549651
## 0.5442780 0.02265255 0.04689895
## 0.5564607 0.02433550 0.05103039
## 0.5549483 0.02707553 0.05652122
## 0.5556731 0.02853002 0.05880285
## 0.5641275 0.02534519 0.05256388
## 0.5690210 0.02856476 0.05971621
## 0.5713791 0.02817817 0.05873615
## 0.5113058 0.02991173 0.06577079
## 0.5161516 0.02975794 0.06212736
## 0.5269481 0.03001907 0.06092161
## 0.5288953 0.03094444 0.06308286
## 0.5455104 0.02486484 0.05045012
## 0.5461805 0.02793851 0.05701533
## 0.5503732 0.02707467 0.05620419
## 0.5615423 0.02693005 0.05658118
## 0.5441289 0.02880323 0.05894892
## 0.5455595 0.02783118 0.05841053
## 0.5062034 0.02973347 0.06351429
## 0.5121327 0.03649630 0.07636107
## 0.5256620 0.03469460 0.06969554
## 0.5319991 0.03271957 0.06703400
## 0.5361551 0.02515516 0.05087471
## 0.5450275 0.02727182 0.05862499
## 0.5469076 0.02362591 0.04850026
## 0.5502612 0.02254087 0.04526951
## 0.5567018 0.02411068 0.04955774
## 0.5642937 0.02431196 0.04961548
## 0.5094269 0.03108580 0.06472619
## 0.5153240 0.02816689 0.05575237
## 0.5263178 0.02699728 0.05483013
## 0.5249356 0.02908962 0.05930803
## 0.5300506 0.02158561 0.04509479
## 0.5452791 0.02465576 0.04990347
## 0.5435970 0.02165604 0.04440491
## 0.5420138 0.02402749 0.04941061
## 0.5386598 0.02284500 0.04615461
## 0.5372723 0.02400847 0.04941306
## 0.5127404 0.02427860 0.05337630
## 0.5487454 0.02708556 0.05414822
## 0.5688673 0.02953122 0.06202047
## 0.5828046 0.02271731 0.04856831
## 0.5792530 0.02406788 0.05166909
## 0.5799759 0.02757551 0.05880047
## 0.5710994 0.02739864 0.05858402
## 0.5752218 0.02801623 0.05887613
## 0.5797910 0.02736330 0.05786494
## 0.5784495 0.02738766 0.05714912
## 0.4980699 0.03015008 0.06043332
## 0.5300725 0.03233429 0.06820843
## 0.5526998 0.03001324 0.06255075
## 0.5620874 0.02576839 0.05248620
## 0.5756971 0.02585228 0.05459968
## 0.5701116 0.02972990 0.06305907
## 0.5690775 0.02989518 0.06404186
## 0.5660351 0.02730382 0.05734733
## 0.5749226 0.02660593 0.05676162
## 0.5712990 0.02367713 0.05067415
## 0.4874785 0.02613835 0.05460939
## 0.5068663 0.03292139 0.07033958
## 0.5329821 0.03167851 0.06582253
## 0.5361748 0.03143679 0.06528534
## 0.5448641 0.02817413 0.05978375
## 0.5443156 0.02691208 0.05659360
## 0.5474512 0.02827260 0.05958969
## 0.5649149 0.02536301 0.05359065
## 0.5602842 0.02554563 0.05421837
## 0.5640671 0.02426604 0.05123815
## 0.5266237 0.02638660 0.05811096
## 0.5652257 0.02428825 0.05160268
## 0.5830309 0.02098591 0.04438336
## 0.5815659 0.02868528 0.05904744
## 0.5825131 0.02949765 0.06168518
## 0.5856772 0.02850845 0.05899529
## 0.5848333 0.02366155 0.04900259
## 0.5793287 0.02372010 0.04804921
## 0.5682937 0.02716170 0.05544241
## 0.5798493 0.02645018 0.05472741
## 0.5199651 0.02581712 0.05476589
## 0.5581072 0.02730160 0.05883057
## 0.5574222 0.02729231 0.05923644
## 0.5706626 0.02468845 0.05323286
## 0.5773610 0.02761652 0.05903879
## 0.5817431 0.02674297 0.05708867
## 0.5729509 0.02880149 0.06086004
## 0.5723672 0.02656655 0.05625026
## 0.5878010 0.02499278 0.05241269
## 0.5912440 0.02472564 0.05325086
## 0.5059979 0.02431065 0.05129652
## 0.5312242 0.02560560 0.05338802
## 0.5557316 0.02649882 0.05721655
## 0.5438182 0.02877293 0.06077471
## 0.5558637 0.02568464 0.05398612
## 0.5550227 0.02543186 0.05520704
## 0.5606423 0.02714567 0.05887034
## 0.5666388 0.02716689 0.05676868
## 0.5630442 0.02595302 0.05452447
## 0.5658454 0.03034492 0.06401267
##
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were n.trees = 50, interaction.depth
## = 3, shrinkage = 0.3 and n.minobsinnode = 20.trellis.par.set(caretTheme())
plot(gbmFit)
ggplot(gbmFit)
##Accuracy 0.8079415 (Stand.Dev. 0.02443083)Model selection procedure.
logisticReg #Accuracy 0.7813753 (Stand.Dev. 0.03270276) ## Generalized Linear Model
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 625, ...
## Resampling results
##
## Accuracy Kappa Accuracy SD Kappa SD
## 0.7813753 0.5437916 0.03270276 0.06892272
##
## BayesianLogReg #Accuracy 0.7821429 (Stand.Dev. 0.03264758) ## Bayesian Generalized Linear Model
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 625, ...
## Resampling results
##
## Accuracy Kappa Accuracy SD Kappa SD
## 0.7821429 0.5453747 0.03264758 0.06862032
##
## rpartTune1 #Accuracy 0.7769606 (Stand.Dev. 0.02825927)## CART
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 625, ...
## Resampling results across tuning parameters:
##
## cp Accuracy Kappa Accuracy SD Kappa SD
## 0.00000000 0.7713981 0.5195163 0.03267479 0.06791937
## 0.04811353 0.7634656 0.5013339 0.02769522 0.06197579
## 0.09622707 0.7673117 0.5120282 0.03082519 0.06651355
## 0.14434060 0.7673117 0.5120282 0.03082519 0.06651355
## 0.19245414 0.7673117 0.5120282 0.03082519 0.06651355
## 0.24056767 0.7673117 0.5120282 0.03082519 0.06651355
## 0.28868120 0.7673117 0.5120282 0.03082519 0.06651355
## 0.33679474 0.7673117 0.5120282 0.03082519 0.06651355
## 0.38490827 0.7673117 0.5120282 0.03082519 0.06651355
## 0.43302181 0.6697641 0.2403141 0.07970959 0.23704117
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was cp = 0.rpartTune2 #Accuracy 0.7759268 (Stand.Dev. 0.02634301)## CART
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 626, 625, 626, 625, 626, ...
## Resampling results across tuning parameters:
##
## maxdepth Accuracy Kappa Accuracy SD Kappa SD
## 1 0.7672775 0.5118670 0.02998430 0.06530389
## 3 0.7770015 0.5238072 0.02521525 0.05919326
## 4 0.7749600 0.5158499 0.02649617 0.05981048
## 7 0.7767353 0.5233229 0.02513619 0.05227189
## 12 0.7757064 0.5220013 0.02583147 0.05357595
## 16 0.7757064 0.5220013 0.02583147 0.05357595
## 20 0.7757064 0.5220013 0.02583147 0.05357595
## 21 0.7757064 0.5220013 0.02583147 0.05357595
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was maxdepth = 3.randomForestFit #Accuracy 0.7967534 (Stand.Dev. 0.03508362)## Random Forest
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 625, ...
## Resampling results across tuning parameters:
##
## mtry Accuracy Kappa Accuracy SD Kappa SD
## 1 0.7762926 0.5168517 0.03526116 0.07769250
## 2 0.7931474 0.5612414 0.03202731 0.06974171
## 3 0.7967534 0.5713995 0.03508362 0.07558851
## 4 0.7885857 0.5560803 0.03391657 0.07259389
## 5 0.7793679 0.5377080 0.03684067 0.07889677
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 3.gbmFit #Accuracy 0.8079415 (Stand.Dev. 0.02443083)## Stochastic Gradient Boosting
##
## 782 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 626, 624, 626, 626, 626, 626, ...
## Resampling results across tuning parameters:
##
## shrinkage interaction.depth n.minobsinnode n.trees Accuracy
## 0.1 1 10 5 0.7659847
## 0.1 1 10 10 0.7672586
## 0.1 1 10 15 0.7672586
## 0.1 1 10 20 0.7664894
## 0.1 1 10 25 0.7675150
## 0.1 1 10 30 0.7695582
## 0.1 1 10 35 0.7675232
## 0.1 1 10 40 0.7739139
## 0.1 1 10 45 0.7759521
## 0.1 1 10 50 0.7797966
## 0.1 1 20 5 0.7652139
## 0.1 1 20 10 0.7662395
## 0.1 1 20 15 0.7659847
## 0.1 1 20 20 0.7659847
## 0.1 1 20 25 0.7664976
## 0.1 1 20 30 0.7687987
## 0.1 1 20 35 0.7690503
## 0.1 1 20 40 0.7675151
## 0.1 1 20 45 0.7693034
## 0.1 1 20 50 0.7744267
## 0.1 1 30 5 0.7659766
## 0.1 1 30 10 0.7670022
## 0.1 1 30 15 0.7672586
## 0.1 1 30 20 0.7672586
## 0.1 1 30 25 0.7652139
## 0.1 1 30 30 0.7664878
## 0.1 1 30 35 0.7685391
## 0.1 1 30 40 0.7698227
## 0.1 1 30 45 0.7718675
## 0.1 1 30 50 0.7741752
## 0.1 2 10 5 0.7762152
## 0.1 2 10 10 0.7652106
## 0.1 2 10 15 0.7723771
## 0.1 2 10 20 0.7813221
## 0.1 2 10 25 0.7882337
## 0.1 2 10 30 0.7913172
## 0.1 2 10 35 0.7936167
## 0.1 2 10 40 0.8002687
## 0.1 2 10 45 0.8000058
## 0.1 2 10 50 0.8000009
## 0.1 2 20 5 0.7762152
## 0.1 2 20 10 0.7682762
## 0.1 2 20 15 0.7636739
## 0.1 2 20 20 0.7644349
## 0.1 2 20 25 0.7741508
## 0.1 2 20 30 0.7782599
## 0.1 2 20 35 0.7815867
## 0.1 2 20 40 0.7841362
## 0.1 2 20 45 0.7900238
## 0.1 2 20 50 0.7923250
## 0.1 2 30 5 0.7762152
## 0.1 2 30 10 0.7700630
## 0.1 2 30 15 0.7667572
## 0.1 2 30 20 0.7667491
## 0.1 2 30 25 0.7733962
## 0.1 2 30 30 0.7787645
## 0.1 2 30 35 0.7795354
## 0.1 2 30 40 0.7800433
## 0.1 2 30 45 0.7823493
## 0.1 2 30 50 0.7849200
## 0.1 3 10 5 0.7769828
## 0.1 3 10 10 0.7779971
## 0.1 3 10 15 0.7833784
## 0.1 3 10 20 0.7897804
## 0.1 3 10 25 0.7977079
## 0.1 3 10 30 0.7977080
## 0.1 3 10 35 0.8010396
## 0.1 3 10 40 0.8018072
## 0.1 3 10 45 0.8015459
## 0.1 3 10 50 0.8041051
## 0.1 3 20 5 0.7762152
## 0.1 3 20 10 0.7736478
## 0.1 3 20 15 0.7792953
## 0.1 3 20 20 0.7820913
## 0.1 3 20 25 0.7882419
## 0.1 3 20 30 0.7879823
## 0.1 3 20 35 0.7949004
## 0.1 3 20 40 0.7933604
## 0.1 3 20 45 0.7933604
## 0.1 3 20 50 0.7956485
## 0.1 3 30 5 0.7762152
## 0.1 3 30 10 0.7744203
## 0.1 3 30 15 0.7739204
## 0.1 3 30 20 0.7813253
## 0.1 3 30 25 0.7797787
## 0.1 3 30 30 0.7800368
## 0.1 3 30 35 0.7869534
## 0.1 3 30 40 0.7856729
## 0.1 3 30 45 0.7851634
## 0.1 3 30 50 0.7838846
## 0.2 1 10 5 0.7621419
## 0.2 1 10 10 0.7670071
## 0.2 1 10 15 0.7698146
## 0.2 1 10 20 0.7716144
## 0.2 1 10 25 0.7826302
## 0.2 1 10 30 0.7856957
## 0.2 1 10 35 0.7874743
## 0.2 1 10 40 0.7902997
## 0.2 1 10 45 0.7884999
## 0.2 1 10 50 0.7890209
## 0.2 1 20 5 0.7680230
## 0.2 1 20 10 0.7659766
## 0.2 1 20 15 0.7646978
## 0.2 1 20 20 0.7716078
## 0.2 1 20 25 0.7723852
## 0.2 1 20 30 0.7764845
## 0.2 1 20 35 0.7808337
## 0.2 1 20 40 0.7867067
## 0.2 1 20 45 0.7861939
## 0.2 1 20 50 0.7867100
## 0.2 1 30 5 0.7649575
## 0.2 1 30 10 0.7664959
## 0.2 1 30 15 0.7682810
## 0.2 1 30 20 0.7708435
## 0.2 1 30 25 0.7762102
## 0.2 1 30 30 0.7754459
## 0.2 1 30 35 0.7759604
## 0.2 1 30 40 0.7756990
## 0.2 1 30 45 0.7792953
## 0.2 1 30 50 0.7772473
## 0.2 2 10 5 0.7695728
## 0.2 2 10 10 0.7803192
## 0.2 2 10 15 0.7946213
## 0.2 2 10 20 0.8007620
## 0.2 2 10 25 0.8012944
## 0.2 2 10 30 0.8005220
## 0.2 2 10 35 0.7977128
## 0.2 2 10 40 0.8002607
## 0.2 2 10 45 0.7984707
## 0.2 2 10 50 0.8005072
## 0.2 2 20 5 0.7687841
## 0.2 2 20 10 0.7716160
## 0.2 2 20 15 0.7823673
## 0.2 2 20 20 0.7882419
## 0.2 2 20 25 0.7920799
## 0.2 2 20 30 0.7920815
## 0.2 2 20 35 0.7951520
## 0.2 2 20 40 0.7969322
## 0.2 2 20 45 0.7948874
## 0.2 2 20 50 0.7954002
## 0.2 2 30 5 0.7692970
## 0.2 2 30 10 0.7721191
## 0.2 2 30 15 0.7698114
## 0.2 2 30 20 0.7782533
## 0.2 2 30 25 0.7833847
## 0.2 2 30 30 0.7841361
## 0.2 2 30 35 0.7818350
## 0.2 2 30 40 0.7836184
## 0.2 2 30 45 0.7892496
## 0.2 2 30 50 0.7925862
## 0.2 3 10 5 0.7754541
## 0.2 3 10 10 0.7887596
## 0.2 3 10 15 0.7961809
## 0.2 3 10 20 0.7948939
## 0.2 3 10 25 0.7989933
## 0.2 3 10 30 0.8020473
## 0.2 3 10 35 0.8002720
## 0.2 3 10 40 0.8020523
## 0.2 3 10 45 0.8025618
## 0.2 3 10 50 0.8038439
## 0.2 3 20 5 0.7690600
## 0.2 3 20 10 0.7831252
## 0.2 3 20 15 0.7869453
## 0.2 3 20 20 0.7933474
## 0.2 3 20 25 0.7915509
## 0.2 3 20 30 0.7943730
## 0.2 3 20 35 0.7920686
## 0.2 3 20 40 0.7959033
## 0.2 3 20 45 0.7935989
## 0.2 3 20 50 0.7974402
## 0.2 3 30 5 0.7705774
## 0.2 3 30 10 0.7736641
## 0.2 3 30 15 0.7805578
## 0.2 3 30 20 0.7856713
## 0.2 3 30 25 0.7912862
## 0.2 3 30 30 0.7900123
## 0.2 3 30 35 0.7902574
## 0.2 3 30 40 0.7941035
## 0.2 3 30 45 0.7961564
## 0.2 3 30 50 0.7969240
## 0.3 1 10 5 0.7675150
## 0.3 1 10 10 0.7700677
## 0.3 1 10 15 0.7736542
## 0.3 1 10 20 0.7744202
## 0.3 1 10 25 0.7823591
## 0.3 1 10 30 0.7823689
## 0.3 1 10 35 0.7844137
## 0.3 1 10 40 0.7897917
## 0.3 1 10 45 0.7810852
## 0.3 1 10 50 0.7818610
## 0.3 1 20 5 0.7657365
## 0.3 1 20 10 0.7669989
## 0.3 1 20 15 0.7736591
## 0.3 1 20 20 0.7757104
## 0.3 1 20 25 0.7780213
## 0.3 1 20 30 0.7823771
## 0.3 1 20 35 0.7831349
## 0.3 1 20 40 0.7849281
## 0.3 1 20 45 0.7877405
## 0.3 1 20 50 0.7913221
## 0.3 1 30 5 0.7667491
## 0.3 1 30 10 0.7693116
## 0.3 1 30 15 0.7736656
## 0.3 1 30 20 0.7728948
## 0.3 1 30 25 0.7754524
## 0.3 1 30 30 0.7821060
## 0.3 1 30 35 0.7813286
## 0.3 1 30 40 0.7805562
## 0.3 1 30 45 0.7795370
## 0.3 1 30 50 0.7785195
## 0.3 2 10 5 0.7736429
## 0.3 2 10 10 0.7895142
## 0.3 2 10 15 0.7971756
## 0.3 2 10 20 0.8030714
## 0.3 2 10 25 0.8012814
## 0.3 2 10 30 0.8015329
## 0.3 2 10 35 0.7966676
## 0.3 2 10 40 0.7987124
## 0.3 2 10 45 0.8007507
## 0.3 2 10 50 0.7994800
## 0.3 2 20 5 0.7667540
## 0.3 2 20 10 0.7805692
## 0.3 2 20 15 0.7892659
## 0.3 2 20 20 0.7930925
## 0.3 2 20 25 0.7994768
## 0.3 2 20 30 0.7966660
## 0.3 2 20 35 0.7958854
## 0.3 2 20 40 0.7941116
## 0.3 2 20 45 0.7984462
## 0.3 2 20 50 0.7969176
## 0.3 2 30 5 0.7639287
## 0.3 2 30 10 0.7693068
## 0.3 2 30 15 0.7802998
## 0.3 2 30 20 0.7805643
## 0.3 2 30 25 0.7846360
## 0.3 2 30 30 0.7846375
## 0.3 2 30 35 0.7856779
## 0.3 2 30 40 0.7941149
## 0.3 2 30 45 0.7918170
## 0.3 2 30 50 0.7933506
## 0.3 3 10 5 0.7803144
## 0.3 3 10 10 0.7956632
## 0.3 3 10 15 0.8023054
## 0.3 3 10 20 0.8015426
## 0.3 3 10 25 0.8015443
## 0.3 3 10 30 0.8028149
## 0.3 3 10 35 0.8025699
## 0.3 3 10 40 0.7999993
## 0.3 3 10 45 0.7943925
## 0.3 3 10 50 0.7997657
## 0.3 3 20 5 0.7774907
## 0.3 3 20 10 0.7925781
## 0.3 3 20 15 0.7918154
## 0.3 3 20 20 0.7977112
## 0.3 3 20 25 0.8000075
## 0.3 3 20 30 0.8017942
## 0.3 3 20 35 0.7974548
## 0.3 3 20 40 0.7969354
## 0.3 3 20 45 0.8043323
## 0.3 3 20 50 0.8061287
## 0.3 3 30 5 0.7734125
## 0.3 3 30 10 0.7821126
## 0.3 3 30 15 0.7915574
## 0.3 3 30 20 0.7846490
## 0.3 3 30 25 0.7897723
## 0.3 3 30 30 0.7895191
## 0.3 3 30 35 0.7923250
## 0.3 3 30 40 0.7948988
## 0.3 3 30 45 0.7931023
## 0.3 3 30 50 0.7943795
## Kappa Accuracy SD Kappa SD
## 0.5068990 0.02989148 0.06320075
## 0.5116754 0.03049068 0.06346941
## 0.5122267 0.03049068 0.06344830
## 0.5099611 0.02948566 0.06079232
## 0.5128053 0.03036620 0.06321439
## 0.5167000 0.03125230 0.06447723
## 0.5121230 0.03134333 0.06508044
## 0.5264767 0.02909830 0.05868774
## 0.5316101 0.03017819 0.06184828
## 0.5402722 0.02910022 0.05994546
## 0.5039342 0.02776113 0.05596537
## 0.5087632 0.02990394 0.06239219
## 0.5090396 0.02989148 0.06230063
## 0.5090396 0.02989148 0.06230063
## 0.5101743 0.03039883 0.06358601
## 0.5156691 0.03260019 0.06835429
## 0.5155470 0.02893755 0.05940530
## 0.5129674 0.02814021 0.05789075
## 0.5164180 0.02620867 0.05247451
## 0.5278479 0.02636268 0.05332780
## 0.5078179 0.03023477 0.06384033
## 0.5109710 0.02999089 0.06112310
## 0.5122267 0.03049068 0.06344830
## 0.5122267 0.03049068 0.06344830
## 0.5070237 0.02924455 0.05991361
## 0.5104608 0.03079029 0.06334470
## 0.5138546 0.03046889 0.06339141
## 0.5183164 0.02969520 0.06182831
## 0.5221668 0.03191171 0.06711851
## 0.5277807 0.03098311 0.06419363
## 0.5003228 0.01943130 0.04543021
## 0.4876053 0.02805329 0.05555898
## 0.5083940 0.03128839 0.06185535
## 0.5291644 0.03282362 0.06747275
## 0.5447690 0.03282961 0.06938786
## 0.5524133 0.02483552 0.05327124
## 0.5580691 0.02424531 0.05201645
## 0.5729243 0.02191954 0.04712153
## 0.5731354 0.02195673 0.04752952
## 0.5747671 0.02251967 0.04722950
## 0.5003228 0.01943130 0.04543021
## 0.4909829 0.02522061 0.05143022
## 0.4885601 0.02326584 0.04555953
## 0.4939438 0.03013584 0.06018546
## 0.5142870 0.02734693 0.05734199
## 0.5240661 0.02964560 0.06225099
## 0.5313803 0.03038308 0.06422843
## 0.5393379 0.02891215 0.06225570
## 0.5533187 0.02424764 0.05181633
## 0.5588020 0.02938789 0.06293289
## 0.5003228 0.01943130 0.04543021
## 0.4935595 0.02555045 0.05146750
## 0.4946169 0.03018342 0.06177469
## 0.4966534 0.02983784 0.06149704
## 0.5116707 0.02858429 0.05836913
## 0.5234695 0.02768109 0.05730050
## 0.5279118 0.03053069 0.06479479
## 0.5297229 0.03088374 0.06587760
## 0.5349552 0.03198181 0.06821559
## 0.5414414 0.02713213 0.05687380
## 0.5025879 0.01980548 0.04635923
## 0.5097134 0.02248619 0.05092485
## 0.5277655 0.02539061 0.05826005
## 0.5477875 0.02564416 0.05743698
## 0.5665746 0.02388304 0.05304513
## 0.5682688 0.02716449 0.06075609
## 0.5764466 0.02656016 0.05838217
## 0.5792110 0.02717506 0.05886332
## 0.5794138 0.02455545 0.05321545
## 0.5852808 0.02485300 0.05329289
## 0.5003228 0.01943130 0.04543021
## 0.4997695 0.02255565 0.05173043
## 0.5185328 0.02346828 0.05354928
## 0.5289593 0.02458976 0.05261948
## 0.5430550 0.02372909 0.05118290
## 0.5444704 0.02727598 0.05917280
## 0.5611766 0.02576930 0.05545747
## 0.5596960 0.02379788 0.05124839
## 0.5602221 0.02422032 0.05201502
## 0.5663037 0.02748152 0.05951490
## 0.5003228 0.01943130 0.04543021
## 0.4972711 0.01881778 0.04425143
## 0.5072300 0.02783253 0.05655506
## 0.5272299 0.02945697 0.06193121
## 0.5272033 0.02724902 0.05744290
## 0.5284531 0.03037383 0.06574787
## 0.5446295 0.02888876 0.06078796
## 0.5426307 0.03154473 0.06574049
## 0.5427859 0.02930526 0.06203585
## 0.5410170 0.03066654 0.06346243
## 0.4969020 0.02905763 0.06313107
## 0.5106325 0.03024207 0.06293365
## 0.5168493 0.03116431 0.06384049
## 0.5222493 0.03337429 0.06958435
## 0.5454766 0.03015808 0.06215687
## 0.5520518 0.02897665 0.05979709
## 0.5560712 0.02809719 0.05785234
## 0.5624375 0.02555621 0.05248440
## 0.5585148 0.02528132 0.05253832
## 0.5601679 0.02210160 0.04590014
## 0.5127959 0.03098242 0.06365961
## 0.5087470 0.02908016 0.06020368
## 0.5053047 0.03154475 0.06602654
## 0.5204837 0.03094083 0.06430366
## 0.5233665 0.03058057 0.06259138
## 0.5327456 0.02685929 0.05464271
## 0.5416816 0.02432870 0.04958532
## 0.5548815 0.02144464 0.04366260
## 0.5531995 0.02263922 0.04633041
## 0.5538997 0.02375048 0.04851069
## 0.5045487 0.02884121 0.05936438
## 0.5093319 0.03012906 0.06297748
## 0.5132175 0.02956596 0.06185566
## 0.5203602 0.03395988 0.07195817
## 0.5316613 0.02748804 0.05628281
## 0.5295998 0.02172159 0.04344300
## 0.5313039 0.02844610 0.05961419
## 0.5304756 0.02666457 0.05625595
## 0.5381902 0.02321282 0.04736218
## 0.5343281 0.02483476 0.05045475
## 0.4950654 0.02584843 0.05095010
## 0.5249029 0.02943062 0.05776693
## 0.5596901 0.02325698 0.04757517
## 0.5760927 0.02614172 0.05533125
## 0.5789276 0.02754474 0.05934038
## 0.5776058 0.02813928 0.06052737
## 0.5731894 0.02487932 0.05158207
## 0.5783795 0.02812301 0.06029140
## 0.5745024 0.02609011 0.05635277
## 0.5789149 0.02455203 0.05181259
## 0.4921559 0.02713570 0.05104730
## 0.5054420 0.03044131 0.06086967
## 0.5317215 0.03013853 0.06154400
## 0.5471720 0.03156888 0.06771020
## 0.5587298 0.02930018 0.06162407
## 0.5586091 0.03139512 0.06613766
## 0.5664189 0.03054368 0.06530382
## 0.5714003 0.02600282 0.05390575
## 0.5661670 0.02418800 0.05110142
## 0.5689763 0.02760907 0.05800245
## 0.4970240 0.02383458 0.04804574
## 0.5065992 0.02652028 0.05409472
## 0.5056798 0.02643911 0.05383536
## 0.5262018 0.02581677 0.05358491
## 0.5393275 0.02626151 0.05419982
## 0.5419764 0.02693321 0.05582672
## 0.5383184 0.02563819 0.05284795
## 0.5429392 0.02824805 0.05835249
## 0.5548746 0.02950318 0.06118314
## 0.5623431 0.02559582 0.05337077
## 0.5066489 0.02106890 0.04680100
## 0.5455886 0.02430075 0.05307135
## 0.5638722 0.02435777 0.05385935
## 0.5635308 0.02491793 0.05411678
## 0.5748122 0.02782335 0.05975369
## 0.5825965 0.02557957 0.05436915
## 0.5791112 0.02454043 0.05319673
## 0.5832853 0.02413513 0.05164381
## 0.5846561 0.02703984 0.05727037
## 0.5871523 0.02751466 0.05762595
## 0.4910376 0.02483772 0.05246725
## 0.5317716 0.03188216 0.06673153
## 0.5444316 0.02748041 0.05758297
## 0.5607694 0.02621358 0.05720106
## 0.5585958 0.02332011 0.05095746
## 0.5655117 0.02412584 0.05008549
## 0.5609522 0.02602048 0.05473449
## 0.5692131 0.02638864 0.05591078
## 0.5647448 0.02825116 0.05980830
## 0.5730702 0.02697304 0.05724702
## 0.4905673 0.02551313 0.05556197
## 0.5099487 0.02642500 0.05573226
## 0.5298149 0.02655870 0.05549651
## 0.5442780 0.02265255 0.04689895
## 0.5564607 0.02433550 0.05103039
## 0.5549483 0.02707553 0.05652122
## 0.5556731 0.02853002 0.05880285
## 0.5641275 0.02534519 0.05256388
## 0.5690210 0.02856476 0.05971621
## 0.5713791 0.02817817 0.05873615
## 0.5113058 0.02991173 0.06577079
## 0.5161516 0.02975794 0.06212736
## 0.5269481 0.03001907 0.06092161
## 0.5288953 0.03094444 0.06308286
## 0.5455104 0.02486484 0.05045012
## 0.5461805 0.02793851 0.05701533
## 0.5503732 0.02707467 0.05620419
## 0.5615423 0.02693005 0.05658118
## 0.5441289 0.02880323 0.05894892
## 0.5455595 0.02783118 0.05841053
## 0.5062034 0.02973347 0.06351429
## 0.5121327 0.03649630 0.07636107
## 0.5256620 0.03469460 0.06969554
## 0.5319991 0.03271957 0.06703400
## 0.5361551 0.02515516 0.05087471
## 0.5450275 0.02727182 0.05862499
## 0.5469076 0.02362591 0.04850026
## 0.5502612 0.02254087 0.04526951
## 0.5567018 0.02411068 0.04955774
## 0.5642937 0.02431196 0.04961548
## 0.5094269 0.03108580 0.06472619
## 0.5153240 0.02816689 0.05575237
## 0.5263178 0.02699728 0.05483013
## 0.5249356 0.02908962 0.05930803
## 0.5300506 0.02158561 0.04509479
## 0.5452791 0.02465576 0.04990347
## 0.5435970 0.02165604 0.04440491
## 0.5420138 0.02402749 0.04941061
## 0.5386598 0.02284500 0.04615461
## 0.5372723 0.02400847 0.04941306
## 0.5127404 0.02427860 0.05337630
## 0.5487454 0.02708556 0.05414822
## 0.5688673 0.02953122 0.06202047
## 0.5828046 0.02271731 0.04856831
## 0.5792530 0.02406788 0.05166909
## 0.5799759 0.02757551 0.05880047
## 0.5710994 0.02739864 0.05858402
## 0.5752218 0.02801623 0.05887613
## 0.5797910 0.02736330 0.05786494
## 0.5784495 0.02738766 0.05714912
## 0.4980699 0.03015008 0.06043332
## 0.5300725 0.03233429 0.06820843
## 0.5526998 0.03001324 0.06255075
## 0.5620874 0.02576839 0.05248620
## 0.5756971 0.02585228 0.05459968
## 0.5701116 0.02972990 0.06305907
## 0.5690775 0.02989518 0.06404186
## 0.5660351 0.02730382 0.05734733
## 0.5749226 0.02660593 0.05676162
## 0.5712990 0.02367713 0.05067415
## 0.4874785 0.02613835 0.05460939
## 0.5068663 0.03292139 0.07033958
## 0.5329821 0.03167851 0.06582253
## 0.5361748 0.03143679 0.06528534
## 0.5448641 0.02817413 0.05978375
## 0.5443156 0.02691208 0.05659360
## 0.5474512 0.02827260 0.05958969
## 0.5649149 0.02536301 0.05359065
## 0.5602842 0.02554563 0.05421837
## 0.5640671 0.02426604 0.05123815
## 0.5266237 0.02638660 0.05811096
## 0.5652257 0.02428825 0.05160268
## 0.5830309 0.02098591 0.04438336
## 0.5815659 0.02868528 0.05904744
## 0.5825131 0.02949765 0.06168518
## 0.5856772 0.02850845 0.05899529
## 0.5848333 0.02366155 0.04900259
## 0.5793287 0.02372010 0.04804921
## 0.5682937 0.02716170 0.05544241
## 0.5798493 0.02645018 0.05472741
## 0.5199651 0.02581712 0.05476589
## 0.5581072 0.02730160 0.05883057
## 0.5574222 0.02729231 0.05923644
## 0.5706626 0.02468845 0.05323286
## 0.5773610 0.02761652 0.05903879
## 0.5817431 0.02674297 0.05708867
## 0.5729509 0.02880149 0.06086004
## 0.5723672 0.02656655 0.05625026
## 0.5878010 0.02499278 0.05241269
## 0.5912440 0.02472564 0.05325086
## 0.5059979 0.02431065 0.05129652
## 0.5312242 0.02560560 0.05338802
## 0.5557316 0.02649882 0.05721655
## 0.5438182 0.02877293 0.06077471
## 0.5558637 0.02568464 0.05398612
## 0.5550227 0.02543186 0.05520704
## 0.5606423 0.02714567 0.05887034
## 0.5666388 0.02716689 0.05676868
## 0.5630442 0.02595302 0.05452447
## 0.5658454 0.03034492 0.06401267
##
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were n.trees = 50, interaction.depth
## = 3, shrinkage = 0.3 and n.minobsinnode = 20.##gfbfit fits bestBased on the accuracy results, the best modeling approach is gbm (Tuning n.trees = 40, interaction.depth = 5, shrinkage = 0.1 and n.minobsinnode = 10).
Altered solution
Using the training_na dataset and removing Cabin variable, we refit the data to gbm modelling approach.
Modeling approaches
5-fold Cross Validation on accuracy, averaged over 5 repetitions will be the strategy to select the best possible model.
##Let's define a trainControl setting, that will remain the same for all applied models thereon
fitControl <- trainControl(## 10-fold CV
method = "repeatedcv",
number = 5,
#classProbs = TRUE,
## repeated ten times
repeats = 5)Let’s set the formula including all variables
##Set the formula
formula <- Survived~Pclass+Sex+Age+SibSp+Parch+Fare+EmbarkedThe criterion is a models Accuracy = (TF+TP)/(TF+FF+FP+TP) ,which we opt to maximize. Under this criterion we shall compare a number of classifiers using the excellent “caret” package.
Generalized Linear model (Binomial family)
set.seed(1000)
logisticReg <- train(formula,
data = training_na,
method = "glm",
#metric = "ROC",
trControl = fitControl)## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleadinglogisticReg## Generalized Linear Model
##
## 676 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 540, 541, 541, 541, 541, 541, ...
## Resampling results
##
## Accuracy Kappa Accuracy SD Kappa SD
## 0.7887516 0.5613619 0.03060581 0.0632509
##
## ##Accuracy 0.7887516 (Stand.Dev 0.03060581) Bayesian Logistic Regression trees
set.seed(1000)
BayesianLogReg <- train(formula,
data = training_na,
method = "bayesglm",
trControl = fitControl)
BayesianLogReg## Bayesian Generalized Linear Model
##
## 676 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 540, 541, 541, 541, 541, 541, ...
## Resampling results
##
## Accuracy Kappa Accuracy SD Kappa SD
## 0.7896339 0.5629991 0.03101783 0.06455036
##
## ##Accuracy 0.7896339 (Stand.Dev 0.03101783) Classification and regression trees CART
set.seed(1000)
##tuning for complexity parameter (cp)
rpartTune1 <- train(training_na[,c(2,3,4,5,6,7,9)], training_na$Survived,
method = "rpart",
tuneLength = 10,
trControl = fitControl)
plot(rpartTune1)
rpartTune1## CART
##
## 676 samples
## 7 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 540, 541, 541, 541, 541, 541, ...
## Resampling results across tuning parameters:
##
## cp Accuracy Kappa Accuracy SD Kappa SD
## 0.00000000 0.7831285 0.5484498 0.03036959 0.06272175
## 0.04964539 0.7635967 0.5025345 0.02416022 0.05098645
## 0.09929078 0.7692133 0.5186312 0.02783123 0.05781905
## 0.14893617 0.7692133 0.5186312 0.02783123 0.05781905
## 0.19858156 0.7692133 0.5186312 0.02783123 0.05781905
## 0.24822695 0.7692133 0.5186312 0.02783123 0.05781905
## 0.29787234 0.7692133 0.5186312 0.02783123 0.05781905
## 0.34751773 0.7692133 0.5186312 0.02783123 0.05781905
## 0.39716312 0.7692133 0.5186312 0.02783123 0.05781905
## 0.44680851 0.6766599 0.2684261 0.08554935 0.24454961
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was cp = 0.##Accuracy 0.7872922 (Stand.Dev. 0.03179111)
##tuning for maximum node depth (maxdepth)
rpartTune2 <- train(training_na[,c(2,3,4,5,6,7,9)], training_na$Survived,
method = "rpart2",
tuneLength = 10,
trControl = fitControl)## note: only 7 possible values of the max tree depth from the initial fit.
## Truncating the grid to 7 .plot(rpartTune2)
rpartTune2## CART
##
## 676 samples
## 7 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 540, 541, 541, 541, 540, ...
## Resampling results across tuning parameters:
##
## maxdepth Accuracy Kappa Accuracy SD Kappa SD
## 1 0.7692321 0.5183231 0.03458839 0.07405691
## 2 0.7733913 0.5182442 0.03141861 0.06554766
## 4 0.7825918 0.5401786 0.03562312 0.07510554
## 5 0.7831889 0.5416102 0.03793152 0.08119068
## 9 0.7873044 0.5509052 0.03261511 0.06941881
## 10 0.7873044 0.5509052 0.03261511 0.06941881
## 16 0.7873044 0.5509052 0.03261511 0.06941881
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was maxdepth = 9.##Accuracy 0.7884292 (Stand.Dev. 0.03934454)Random Forest
set.seed(1000)
rfGrid = expand.grid(.mtry = c(1,2,3,4,5))
randomForestFit = train(x = training_na[,c(2,3,4,5,6,7,9)],
y = training_na$Survived,
method = "rf",
trControl = fitControl,
tuneGrid = rfGrid,
ntree=30)
plot(randomForestFit)
randomForestFit## Random Forest
##
## 676 samples
## 7 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 540, 541, 541, 541, 541, 541, ...
## Resampling results across tuning parameters:
##
## mtry Accuracy Kappa Accuracy SD Kappa SD
## 1 0.7914380 0.5574521 0.03347622 0.06811380
## 2 0.8006145 0.5827785 0.03956907 0.08074349
## 3 0.8011962 0.5855667 0.03848834 0.07869026
## 4 0.7872856 0.5600704 0.02946737 0.06110196
## 5 0.7837233 0.5532518 0.03291143 0.06590668
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 3.varImp(randomForestFit)## rf variable importance
##
## Overall
## Sex 100.000
## Age 96.147
## Fare 93.730
## Pclass 27.275
## SibSp 8.639
## Parch 2.492
## Embarked 0.000##Accuracy 0.8011962 (Stand.Dev. 0.03848834)GBM
gbmGrid <- expand.grid(interaction.depth = c(1, 2, 3,4,5),
n.trees = (1:10)*5,
shrinkage = (1:3)*0.1,
n.minobsinnode = (1:3)*10)
gbmFit <- train(formula, data = training_na,
method = "gbm",
trControl = fitControl,
## This last option is actually one
## for gbm() that passes through
verbose = FALSE,
tuneGrid = gbmGrid)
gbmFit## Stochastic Gradient Boosting
##
## 676 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 541, 540, 540, 542, 540, ...
## Resampling results across tuning parameters:
##
## shrinkage interaction.depth n.minobsinnode n.trees Accuracy
## 0.1 1 10 5 0.7692200
## 0.1 1 10 10 0.7692200
## 0.1 1 10 15 0.7692200
## 0.1 1 10 20 0.7692200
## 0.1 1 10 25 0.7695163
## 0.1 1 10 30 0.7704052
## 0.1 1 10 35 0.7742549
## 0.1 1 10 40 0.7730763
## 0.1 1 10 45 0.7771961
## 0.1 1 10 50 0.7825339
## 0.1 1 20 5 0.7671459
## 0.1 1 20 10 0.7692200
## 0.1 1 20 15 0.7692200
## 0.1 1 20 20 0.7692200
## 0.1 1 20 25 0.7668562
## 0.1 1 20 30 0.7709956
## 0.1 1 20 35 0.7712897
## 0.1 1 20 40 0.7689325
## 0.1 1 20 45 0.7703964
## 0.1 1 20 50 0.7786775
## 0.1 1 30 5 0.7671459
## 0.1 1 30 10 0.7692200
## 0.1 1 30 15 0.7692200
## 0.1 1 30 20 0.7692200
## 0.1 1 30 25 0.7695207
## 0.1 1 30 30 0.7686318
## 0.1 1 30 35 0.7638932
## 0.1 1 30 40 0.7627080
## 0.1 1 30 45 0.7653616
## 0.1 1 30 50 0.7700827
## 0.1 2 10 5 0.7825295
## 0.1 2 10 10 0.7804619
## 0.1 2 10 15 0.7834294
## 0.1 2 10 20 0.7946757
## 0.1 2 10 25 0.7976300
## 0.1 2 10 30 0.7988194
## 0.1 2 10 35 0.7991202
## 0.1 2 10 40 0.8005864
## 0.1 2 10 45 0.7996996
## 0.1 2 10 50 0.8005907
## 0.1 2 20 5 0.7825295
## 0.1 2 20 10 0.7774924
## 0.1 2 20 15 0.7810458
## 0.1 2 20 20 0.7840088
## 0.1 2 20 25 0.7840022
## 0.1 2 20 30 0.7899195
## 0.1 2 20 35 0.7902224
## 0.1 2 20 40 0.7940655
## 0.1 2 20 45 0.7976234
## 0.1 2 20 50 0.7979153
## 0.1 2 30 5 0.7825295
## 0.1 2 30 10 0.7783725
## 0.1 2 30 15 0.7715707
## 0.1 2 30 20 0.7736645
## 0.1 2 30 25 0.7792722
## 0.1 2 30 30 0.7789956
## 0.1 2 30 35 0.7795838
## 0.1 2 30 40 0.7810588
## 0.1 2 30 45 0.7810566
## 0.1 2 30 50 0.7831285
## 0.1 3 10 5 0.7831199
## 0.1 3 10 10 0.7825185
## 0.1 3 10 15 0.7914010
## 0.1 3 10 20 0.8044230
## 0.1 3 10 25 0.8035559
## 0.1 3 10 30 0.8032486
## 0.1 3 10 35 0.8020743
## 0.1 3 10 40 0.8035428
## 0.1 3 10 45 0.8008849
## 0.1 3 10 50 0.8020810
## 0.1 3 20 5 0.7825295
## 0.1 3 20 10 0.7822419
## 0.1 3 20 15 0.7819413
## 0.1 3 20 20 0.7878607
## 0.1 3 20 25 0.7979393
## 0.1 3 20 30 0.8005974
## 0.1 3 20 35 0.8011944
## 0.1 3 20 40 0.8020920
## 0.1 3 20 45 0.8020833
## 0.1 3 20 50 0.8038589
## 0.1 3 30 5 0.7825295
## 0.1 3 30 10 0.7825295
## 0.1 3 30 15 0.7774990
## 0.1 3 30 20 0.7801504
## 0.1 3 30 25 0.7810546
## 0.1 3 30 30 0.7795731
## 0.1 3 30 35 0.7807539
## 0.1 3 30 40 0.7837169
## 0.1 3 30 45 0.7852071
## 0.1 3 30 50 0.7890372
## 0.1 4 10 5 0.7813486
## 0.1 4 10 10 0.7917169
## 0.1 4 10 15 0.7985209
## 0.1 4 10 20 0.8071422
## 0.1 4 10 25 0.8044734
## 0.1 4 10 30 0.8062316
## 0.1 4 10 35 0.8065345
## 0.1 4 10 40 0.8065212
## 0.1 4 10 45 0.8038655
## 0.1 4 10 50 0.8059221
## 0.1 4 20 5 0.7825295
## 0.1 4 20 10 0.7816428
## 0.1 4 20 15 0.7858085
## 0.1 4 20 20 0.7869740
## 0.1 4 20 25 0.7970285
## 0.1 4 20 30 0.8017868
## 0.1 4 20 35 0.8035449
## 0.1 4 20 40 0.8020744
## 0.1 4 20 45 0.8079918
## 0.1 4 20 50 0.8103557
## 0.1 4 30 5 0.7825295
## 0.1 4 30 10 0.7822332
## 0.1 4 30 15 0.7816514
## 0.1 4 30 20 0.7801612
## 0.1 4 30 25 0.7825273
## 0.1 4 30 30 0.7860895
## 0.1 4 30 35 0.7869653
## 0.1 4 30 40 0.7922943
## 0.1 4 30 45 0.7943553
## 0.1 4 30 50 0.7964272
## 0.1 5 10 5 0.7875577
## 0.1 5 10 10 0.7946581
## 0.1 5 10 15 0.8012008
## 0.1 5 10 20 0.8044515
## 0.1 5 10 25 0.8059307
## 0.1 5 10 30 0.8032662
## 0.1 5 10 35 0.8038786
## 0.1 5 10 40 0.8071248
## 0.1 5 10 45 0.8092033
## 0.1 5 10 50 0.8080049
## 0.1 5 20 5 0.7816406
## 0.1 5 20 10 0.7792768
## 0.1 5 20 15 0.7848955
## 0.1 5 20 20 0.7899151
## 0.1 5 20 25 0.7955340
## 0.1 5 20 30 0.7982204
## 0.1 5 20 35 0.7988174
## 0.1 5 20 40 0.8020636
## 0.1 5 20 45 0.8062206
## 0.1 5 20 50 0.8053207
## 0.1 5 30 5 0.7825295
## 0.1 5 30 10 0.7819369
## 0.1 5 30 15 0.7786644
## 0.1 5 30 20 0.7840219
## 0.1 5 30 25 0.7857954
## 0.1 5 30 30 0.7902137
## 0.1 5 30 35 0.7943508
## 0.1 5 30 40 0.7958390
## 0.1 5 30 45 0.7958390
## 0.1 5 30 50 0.7970308
## 0.2 1 10 5 0.7689259
## 0.2 1 10 10 0.7680370
## 0.2 1 10 15 0.7724707
## 0.2 1 10 20 0.7774990
## 0.2 1 10 25 0.7840023
## 0.2 1 10 30 0.7890284
## 0.2 1 10 35 0.7928715
## 0.2 1 10 40 0.7896188
## 0.2 1 10 45 0.7914054
## 0.2 1 10 50 0.7878476
## 0.2 1 20 5 0.7692200
## 0.2 1 20 10 0.7689237
## 0.2 1 20 15 0.7721917
## 0.2 1 20 20 0.7739607
## 0.2 1 20 25 0.7798760
## 0.2 1 20 30 0.7837147
## 0.2 1 20 35 0.7842984
## 0.2 1 20 40 0.7905186
## 0.2 1 20 45 0.7917082
## 0.2 1 20 50 0.7896364
## 0.2 1 30 5 0.7692200
## 0.2 1 30 10 0.7689259
## 0.2 1 30 15 0.7674225
## 0.2 1 30 20 0.7677363
## 0.2 1 30 25 0.7706753
## 0.2 1 30 30 0.7792703
## 0.2 1 30 35 0.7825252
## 0.2 1 30 40 0.7807560
## 0.2 1 30 45 0.7846037
## 0.2 1 30 50 0.7840132
## 0.2 2 10 5 0.7748410
## 0.2 2 10 10 0.7932160
## 0.2 2 10 15 0.8003097
## 0.2 2 10 20 0.8008892
## 0.2 2 10 25 0.7994076
## 0.2 2 10 30 0.7997258
## 0.2 2 10 35 0.8023905
## 0.2 2 10 40 0.8009047
## 0.2 2 10 45 0.7997281
## 0.2 2 10 50 0.7988458
## 0.2 2 20 5 0.7742417
## 0.2 2 20 10 0.7810325
## 0.2 2 20 15 0.7946603
## 0.2 2 20 20 0.7996799
## 0.2 2 20 25 0.8005688
## 0.2 2 20 30 0.7996844
## 0.2 2 20 35 0.7988020
## 0.2 2 20 40 0.8017803
## 0.2 2 20 45 0.8020701
## 0.2 2 20 50 0.8065299
## 0.2 2 30 5 0.7760043
## 0.2 2 30 10 0.7721699
## 0.2 2 30 15 0.7801503
## 0.2 2 30 20 0.7807429
## 0.2 2 30 25 0.7816318
## 0.2 2 30 30 0.7851919
## 0.2 2 30 35 0.7881506
## 0.2 2 30 40 0.7905165
## 0.2 2 30 45 0.7934730
## 0.2 2 30 50 0.7964360
## 0.2 3 10 5 0.7763180
## 0.2 3 10 10 0.7955580
## 0.2 3 10 15 0.8017782
## 0.2 3 10 20 0.8003165
## 0.2 3 10 25 0.8059462
## 0.2 3 10 30 0.8062512
## 0.2 3 10 35 0.8097696
## 0.2 3 10 40 0.8118678
## 0.2 3 10 45 0.8080246
## 0.2 3 10 50 0.8080113
## 0.2 3 20 5 0.7795665
## 0.2 3 20 10 0.7893313
## 0.2 3 20 15 0.7996866
## 0.2 3 20 20 0.7970154
## 0.2 3 20 25 0.7990808
## 0.2 3 20 30 0.8052988
## 0.2 3 20 35 0.8029306
## 0.2 3 20 40 0.8103381
## 0.2 3 20 45 0.8068087
## 0.2 3 20 50 0.8076801
## 0.2 3 30 5 0.7792658
## 0.2 3 30 10 0.7748060
## 0.2 3 30 15 0.7828214
## 0.2 3 30 20 0.7837169
## 0.2 3 30 25 0.7913944
## 0.2 3 30 30 0.7925995
## 0.2 3 30 35 0.7996933
## 0.2 3 30 40 0.7997019
## 0.2 3 30 45 0.8044494
## 0.2 3 30 50 0.8050310
## 0.2 4 10 5 0.7908192
## 0.2 4 10 10 0.8017716
## 0.2 4 10 15 0.8044579
## 0.2 4 10 20 0.8056322
## 0.2 4 10 25 0.8106780
## 0.2 4 10 30 0.8118502
## 0.2 4 10 35 0.8068175
## 0.2 4 10 40 0.8088872
## 0.2 4 10 45 0.8103644
## 0.2 4 10 50 0.8050376
## 0.2 4 20 5 0.7831286
## 0.2 4 20 10 0.7896561
## 0.2 4 20 15 0.7943838
## 0.2 4 20 20 0.8005908
## 0.2 4 20 25 0.8009111
## 0.2 4 20 30 0.8017782
## 0.2 4 20 35 0.8059352
## 0.2 4 20 40 0.8062075
## 0.2 4 20 45 0.8068001
## 0.2 4 20 50 0.8062097
## 0.2 4 30 5 0.7822332
## 0.2 4 30 10 0.7745448
## 0.2 4 30 15 0.7858064
## 0.2 4 30 20 0.7878696
## 0.2 4 30 25 0.7952508
## 0.2 4 30 30 0.8005646
## 0.2 4 30 35 0.7967280
## 0.2 4 30 40 0.7988043
## 0.2 4 30 45 0.8044122
## 0.2 4 30 50 0.7996844
## 0.2 5 10 5 0.7952419
## 0.2 5 10 10 0.7964493
## 0.2 5 10 15 0.7976344
## 0.2 5 10 20 0.7985101
## 0.2 5 10 25 0.8038567
## 0.2 5 10 30 0.8065278
## 0.2 5 10 35 0.8071096
## 0.2 5 10 40 0.8062161
## 0.2 5 10 45 0.8026781
## 0.2 5 10 50 0.7988219
## 0.2 5 20 5 0.7789585
## 0.2 5 20 10 0.7878563
## 0.2 5 20 15 0.7955602
## 0.2 5 20 20 0.8026452
## 0.2 5 20 25 0.8091770
## 0.2 5 20 30 0.8068021
## 0.2 5 20 35 0.8038479
## 0.2 5 20 40 0.8047390
## 0.2 5 20 45 0.7997238
## 0.2 5 20 50 0.8012032
## 0.2 5 30 5 0.7775077
## 0.2 5 30 10 0.7760349
## 0.2 5 30 15 0.7863968
## 0.2 5 30 20 0.7908106
## 0.2 5 30 25 0.7967478
## 0.2 5 30 30 0.8032314
## 0.2 5 30 35 0.8017629
## 0.2 5 30 40 0.8035385
## 0.2 5 30 45 0.8044319
## 0.2 5 30 50 0.8079656
## 0.3 1 10 5 0.7695163
## 0.3 1 10 10 0.7736666
## 0.3 1 10 15 0.7751416
## 0.3 1 10 20 0.7854707
## 0.3 1 10 25 0.7908084
## 0.3 1 10 30 0.7914011
## 0.3 1 10 35 0.7890328
## 0.3 1 10 40 0.7902202
## 0.3 1 10 45 0.7896167
## 0.3 1 10 50 0.7878432
## 0.3 1 20 5 0.7692090
## 0.3 1 20 10 0.7650652
## 0.3 1 20 15 0.7727472
## 0.3 1 20 20 0.7795644
## 0.3 1 20 25 0.7878521
## 0.3 1 20 30 0.7884425
## 0.3 1 20 35 0.7869675
## 0.3 1 20 40 0.7851831
## 0.3 1 20 45 0.7857846
## 0.3 1 20 50 0.7881680
## 0.3 1 30 5 0.7692200
## 0.3 1 30 10 0.7656535
## 0.3 1 30 15 0.7742330
## 0.3 1 30 20 0.7780894
## 0.3 1 30 25 0.7795577
## 0.3 1 30 30 0.7769018
## 0.3 1 30 35 0.7828148
## 0.3 1 30 40 0.7825032
## 0.3 1 30 45 0.7845991
## 0.3 1 30 50 0.7834074
## 0.3 2 10 5 0.7816580
## 0.3 2 10 10 0.7991005
## 0.3 2 10 15 0.8044229
## 0.3 2 10 20 0.8005843
## 0.3 2 10 25 0.7988195
## 0.3 2 10 30 0.7952791
## 0.3 2 10 35 0.7973424
## 0.3 2 10 40 0.7999914
## 0.3 2 10 45 0.8026911
## 0.3 2 10 50 0.8023731
## 0.3 2 20 5 0.7780937
## 0.3 2 20 10 0.7905384
## 0.3 2 20 15 0.7952530
## 0.3 2 20 20 0.7973336
## 0.3 2 20 25 0.7976342
## 0.3 2 20 30 0.7979306
## 0.3 2 20 35 0.7982467
## 0.3 2 20 40 0.8012031
## 0.3 2 20 45 0.8050594
## 0.3 2 20 50 0.8038654
## 0.3 2 30 5 0.7748541
## 0.3 2 30 10 0.7795599
## 0.3 2 30 15 0.7828257
## 0.3 2 30 20 0.7831309
## 0.3 2 30 25 0.7825208
## 0.3 2 30 30 0.7801746
## 0.3 2 30 35 0.7884556
## 0.3 2 30 40 0.7937956
## 0.3 2 30 45 0.7961464
## 0.3 2 30 50 0.7928826
## 0.3 3 10 5 0.7849019
## 0.3 3 10 10 0.7958740
## 0.3 3 10 15 0.8000047
## 0.3 3 10 20 0.7985342
## 0.3 3 10 25 0.8020897
## 0.3 3 10 30 0.8014949
## 0.3 3 10 35 0.7964666
## 0.3 3 10 40 0.7976585
## 0.3 3 10 45 0.7967499
## 0.3 3 10 50 0.8009069
## 0.3 3 20 5 0.7763357
## 0.3 3 20 10 0.7929307
## 0.3 3 20 15 0.7967650
## 0.3 3 20 20 0.7988327
## 0.3 3 20 25 0.8044471
## 0.3 3 20 30 0.8047653
## 0.3 3 20 35 0.8053470
## 0.3 3 20 40 0.8032905
## 0.3 3 20 45 0.8050551
## 0.3 3 20 50 0.8106761
## 0.3 3 30 5 0.7807297
## 0.3 3 30 10 0.7822068
## 0.3 3 30 15 0.7925644
## 0.3 3 30 20 0.7916886
## 0.3 3 30 25 0.7991071
## 0.3 3 30 30 0.7943685
## 0.3 3 30 35 0.7979327
## 0.3 3 30 40 0.8023707
## 0.3 3 30 45 0.8014929
## 0.3 3 30 50 0.8097673
## 0.3 4 10 5 0.7893665
## 0.3 4 10 10 0.7976364
## 0.3 4 10 15 0.8014905
## 0.3 4 10 20 0.8000308
## 0.3 4 10 25 0.8020721
## 0.3 4 10 30 0.8082728
## 0.3 4 10 35 0.8017737
## 0.3 4 10 40 0.8011746
## 0.3 4 10 45 0.8008828
## 0.3 4 10 50 0.7952618
## 0.3 4 20 5 0.7766188
## 0.3 4 20 10 0.7988065
## 0.3 4 20 15 0.8020615
## 0.3 4 20 20 0.8032511
## 0.3 4 20 25 0.8059155
## 0.3 4 20 30 0.8020899
## 0.3 4 20 35 0.8044559
## 0.3 4 20 40 0.8050464
## 0.3 4 20 45 0.8023709
## 0.3 4 20 50 0.8047238
## 0.3 4 30 5 0.7807692
## 0.3 4 30 10 0.7807429
## 0.3 4 30 15 0.7908083
## 0.3 4 30 20 0.8002791
## 0.3 4 30 25 0.8023686
## 0.3 4 30 30 0.7958411
## 0.3 4 30 35 0.8058979
## 0.3 4 30 40 0.8064971
## 0.3 4 30 45 0.8076889
## 0.3 4 30 50 0.8064886
## 0.3 5 10 5 0.7949631
## 0.3 5 10 10 0.7976430
## 0.3 5 10 15 0.8032662
## 0.3 5 10 20 0.8029721
## 0.3 5 10 25 0.8029807
## 0.3 5 10 30 0.8009067
## 0.3 5 10 35 0.8002967
## 0.3 5 10 40 0.8014687
## 0.3 5 10 45 0.8047368
## 0.3 5 10 50 0.7979131
## 0.3 5 20 5 0.7858084
## 0.3 5 20 10 0.8000134
## 0.3 5 20 15 0.7987889
## 0.3 5 20 20 0.8032772
## 0.3 5 20 25 0.8041531
## 0.3 5 20 30 0.8047390
## 0.3 5 20 35 0.8011878
## 0.3 5 20 40 0.8044580
## 0.3 5 20 45 0.8068241
## 0.3 5 20 50 0.8029437
## 0.3 5 30 5 0.7813617
## 0.3 5 30 10 0.7795929
## 0.3 5 30 15 0.7929002
## 0.3 5 30 20 0.7955537
## 0.3 5 30 25 0.7976235
## 0.3 5 30 30 0.8032576
## 0.3 5 30 35 0.8062118
## 0.3 5 30 40 0.8065016
## 0.3 5 30 45 0.8005908
## 0.3 5 30 50 0.7996977
## Kappa Accuracy SD Kappa SD
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5191203 0.03234106 0.06854046
## 0.5197694 0.03238810 0.06812746
## 0.5292037 0.03001320 0.06363436
## 0.5266549 0.03229885 0.06775505
## 0.5357588 0.03152644 0.06658660
## 0.5479427 0.03267741 0.06863636
## 0.5129120 0.03308138 0.07087347
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5125371 0.03207206 0.06827715
## 0.5217805 0.03423990 0.07265939
## 0.5227742 0.03461667 0.07339528
## 0.5187636 0.03172253 0.06657126
## 0.5219998 0.03306395 0.06978850
## 0.5388186 0.03601169 0.07497780
## 0.5129120 0.03308138 0.07087347
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5187623 0.03328308 0.07037158
## 0.5167253 0.03265732 0.06875086
## 0.5073610 0.03348434 0.07141457
## 0.5043920 0.03297063 0.07052438
## 0.5098637 0.03893390 0.08331708
## 0.5193747 0.03390441 0.07247806
## 0.5210296 0.03281182 0.07589674
## 0.5196404 0.03272431 0.07331539
## 0.5295893 0.03507608 0.07675815
## 0.5550468 0.03064376 0.06981859
## 0.5635714 0.03321750 0.07440048
## 0.5688584 0.03679681 0.08065808
## 0.5697985 0.03534985 0.07761932
## 0.5737398 0.03632389 0.07937564
## 0.5730305 0.03613155 0.07896953
## 0.5764080 0.04051097 0.08724491
## 0.5210296 0.03281182 0.07589674
## 0.5121614 0.03047265 0.07121906
## 0.5212090 0.03068615 0.07152340
## 0.5319495 0.03068007 0.06994657
## 0.5346366 0.03246633 0.07218970
## 0.5489193 0.03396812 0.07489160
## 0.5511353 0.03399065 0.07388498
## 0.5594119 0.03750440 0.08189125
## 0.5680006 0.03801944 0.08377953
## 0.5694889 0.03890836 0.08560819
## 0.5210296 0.03281182 0.07589674
## 0.5143389 0.03198798 0.07338106
## 0.5044280 0.03512856 0.07966227
## 0.5105136 0.03012137 0.06749083
## 0.5232800 0.03980970 0.08676608
## 0.5238435 0.03922048 0.08605167
## 0.5272517 0.03680009 0.08102951
## 0.5307358 0.03935275 0.08728833
## 0.5313922 0.04128408 0.09117526
## 0.5368732 0.04133045 0.09132017
## 0.5236322 0.03238332 0.07452237
## 0.5276644 0.03490517 0.07812823
## 0.5509909 0.03218069 0.07247623
## 0.5795665 0.03329984 0.07493349
## 0.5795425 0.03319484 0.07378773
## 0.5797838 0.03769627 0.08314820
## 0.5788753 0.03905971 0.08568866
## 0.5825189 0.03668385 0.08062980
## 0.5778401 0.04044120 0.08778295
## 0.5799190 0.04021630 0.08779683
## 0.5210296 0.03281182 0.07589674
## 0.5217859 0.03379657 0.07864503
## 0.5264079 0.03404875 0.07724029
## 0.5446845 0.03824793 0.08301641
## 0.5680657 0.03954969 0.08666314
## 0.5746614 0.03586512 0.07915909
## 0.5754097 0.03432135 0.07664862
## 0.5791768 0.03658954 0.08028893
## 0.5802257 0.03853887 0.08369594
## 0.5842352 0.03969796 0.08619462
## 0.5210296 0.03281182 0.07589674
## 0.5211282 0.03281182 0.07590869
## 0.5143273 0.03586893 0.08118366
## 0.5237615 0.03355769 0.07519913
## 0.5276281 0.03688102 0.08153954
## 0.5263837 0.03831999 0.08439204
## 0.5317599 0.03688078 0.08101987
## 0.5389632 0.03608005 0.07966941
## 0.5425207 0.03653517 0.08058609
## 0.5514920 0.03306540 0.07272810
## 0.5204990 0.03442250 0.07799758
## 0.5482350 0.03152948 0.07239077
## 0.5661017 0.03355598 0.07590924
## 0.5871777 0.03965501 0.08756962
## 0.5829752 0.04061988 0.08861809
## 0.5874944 0.03543665 0.07770856
## 0.5899804 0.04210912 0.09211458
## 0.5903280 0.04254705 0.09274102
## 0.5855795 0.04364052 0.09388850
## 0.5896841 0.04181467 0.09022895
## 0.5210296 0.03281182 0.07589674
## 0.5228649 0.03344102 0.07686302
## 0.5356187 0.03448879 0.07813136
## 0.5423391 0.04277478 0.09388909
## 0.5654346 0.04031012 0.08767534
## 0.5771612 0.04193320 0.09217213
## 0.5822795 0.04398321 0.09571264
## 0.5804765 0.04081500 0.08854718
## 0.5937126 0.04037305 0.08676155
## 0.5999357 0.04228673 0.09031525
## 0.5210296 0.03281182 0.07589674
## 0.5205376 0.03190186 0.07440786
## 0.5228057 0.03284034 0.07551231
## 0.5242798 0.03508364 0.07893724
## 0.5332382 0.03613066 0.08126921
## 0.5424308 0.03676733 0.08159230
## 0.5454652 0.03534139 0.07856561
## 0.5573948 0.03927584 0.08663164
## 0.5633977 0.03932614 0.08591894
## 0.5687352 0.04151075 0.09032322
## 0.5366426 0.03717174 0.08339964
## 0.5591298 0.03359876 0.07410411
## 0.5750715 0.03517323 0.07747841
## 0.5837964 0.03636965 0.07896338
## 0.5880846 0.03627035 0.07910978
## 0.5827740 0.03840365 0.08362873
## 0.5852619 0.03807153 0.08344146
## 0.5931229 0.03613146 0.07719163
## 0.5983229 0.03586319 0.07633857
## 0.5960238 0.03814359 0.08171305
## 0.5195215 0.03365416 0.07764080
## 0.5177603 0.03033465 0.07016951
## 0.5349548 0.03418802 0.07697207
## 0.5495220 0.03651616 0.08086185
## 0.5639333 0.04100075 0.09030176
## 0.5710154 0.03734297 0.08234066
## 0.5737560 0.03723285 0.08191723
## 0.5814023 0.04163711 0.09149771
## 0.5914669 0.03826183 0.08343730
## 0.5896858 0.03915350 0.08469542
## 0.5210296 0.03281182 0.07589674
## 0.5201440 0.03261634 0.07587571
## 0.5166205 0.03404089 0.07970591
## 0.5329872 0.03647345 0.08310136
## 0.5389088 0.03407723 0.07744444
## 0.5515756 0.03661211 0.08031136
## 0.5621379 0.04050150 0.08820487
## 0.5662897 0.03834789 0.08338702
## 0.5675135 0.04088093 0.08815303
## 0.5708063 0.04090293 0.08772237
## 0.5169710 0.03374533 0.07158638
## 0.5162331 0.03269375 0.06943390
## 0.5245889 0.03070576 0.06715717
## 0.5355876 0.03486774 0.07256399
## 0.5492955 0.03216373 0.06772441
## 0.5608190 0.03440854 0.07130463
## 0.5691649 0.03315484 0.06908724
## 0.5625317 0.03483139 0.07193866
## 0.5660156 0.03527126 0.07450274
## 0.5586791 0.03683458 0.07672224
## 0.5172302 0.03393878 0.07222091
## 0.5169430 0.03409502 0.07211000
## 0.5240244 0.03557313 0.07488809
## 0.5280154 0.03471953 0.07364855
## 0.5404931 0.03558414 0.07557249
## 0.5481914 0.03740993 0.08046742
## 0.5509045 0.03610213 0.07657604
## 0.5635013 0.03199403 0.06629718
## 0.5661979 0.03208350 0.06716770
## 0.5619031 0.02674801 0.05608425
## 0.5183773 0.03393878 0.07226845
## 0.5169710 0.03374533 0.07158638
## 0.5125321 0.03600090 0.07978609
## 0.5147364 0.03493376 0.07436015
## 0.5207422 0.03795410 0.07978023
## 0.5389725 0.03502212 0.07350799
## 0.5466634 0.03728317 0.07734130
## 0.5424862 0.03634710 0.07594400
## 0.5499888 0.03600662 0.07591392
## 0.5487772 0.03527150 0.07420066
## 0.5151364 0.03460563 0.07336020
## 0.5538143 0.03712949 0.08119513
## 0.5724385 0.03689205 0.08133921
## 0.5773178 0.03612364 0.07962547
## 0.5740210 0.03918786 0.08629756
## 0.5759474 0.03987098 0.08617559
## 0.5822817 0.03960086 0.08590261
## 0.5804765 0.03985016 0.08644292
## 0.5782216 0.04412113 0.09537168
## 0.5765517 0.04134973 0.08918746
## 0.5098323 0.03443781 0.07665337
## 0.5288048 0.03996181 0.08776722
## 0.5594083 0.03570276 0.07947883
## 0.5724996 0.03780955 0.08337814
## 0.5752432 0.03558608 0.07731139
## 0.5751618 0.03482490 0.07598149
## 0.5731883 0.03248281 0.07174552
## 0.5807215 0.03461498 0.07485997
## 0.5818974 0.03608299 0.07755620
## 0.5916328 0.03971055 0.08536831
## 0.5120512 0.03311360 0.07302380
## 0.5114586 0.03571320 0.07688703
## 0.5284180 0.03577555 0.07747355
## 0.5319119 0.03714831 0.08035902
## 0.5360551 0.03769851 0.08012579
## 0.5449478 0.03594037 0.07748335
## 0.5513411 0.03999050 0.08638223
## 0.5563151 0.03910416 0.08460597
## 0.5624419 0.04117473 0.08954341
## 0.5694958 0.03881296 0.08388195
## 0.5177990 0.03421471 0.07375515
## 0.5640656 0.03798410 0.08092939
## 0.5798566 0.03466880 0.07506243
## 0.5782000 0.04111478 0.08872517
## 0.5901665 0.04483206 0.09609667
## 0.5916416 0.03778544 0.08048460
## 0.5993856 0.03511544 0.07528379
## 0.6043174 0.03860621 0.08277416
## 0.5961063 0.04054591 0.08697952
## 0.5963522 0.03387993 0.07235589
## 0.5176038 0.03325828 0.07688195
## 0.5465009 0.03936737 0.08729711
## 0.5715992 0.04143881 0.09038113
## 0.5687730 0.03515260 0.07676421
## 0.5754229 0.03956888 0.08532286
## 0.5890040 0.03771307 0.08116247
## 0.5846145 0.03944418 0.08384134
## 0.6002162 0.04087528 0.08719130
## 0.5934902 0.04227046 0.09028416
## 0.5948964 0.04315231 0.09226684
## 0.5152369 0.03341526 0.07674052
## 0.5134326 0.03320953 0.07510068
## 0.5335568 0.02926585 0.06764545
## 0.5382668 0.03257208 0.07217027
## 0.5566589 0.03333004 0.07278096
## 0.5602561 0.03725714 0.08064917
## 0.5761592 0.03810637 0.08299231
## 0.5772956 0.04030138 0.08668568
## 0.5876205 0.03888818 0.08439298
## 0.5890094 0.03961574 0.08577761
## 0.5509863 0.03992643 0.08878486
## 0.5780249 0.03826006 0.08197373
## 0.5858111 0.03967289 0.08394771
## 0.5901439 0.03660329 0.07725096
## 0.6021863 0.03712531 0.07782299
## 0.6036144 0.03781755 0.08098577
## 0.5937869 0.03519088 0.07487157
## 0.5982164 0.04154017 0.08860018
## 0.6019594 0.04097429 0.08774003
## 0.5911334 0.03944279 0.08385222
## 0.5254849 0.03347740 0.07709293
## 0.5468191 0.03478796 0.07894762
## 0.5635063 0.03358091 0.07253656
## 0.5781834 0.03480269 0.07536725
## 0.5802188 0.03902883 0.08371333
## 0.5824465 0.03997173 0.08605627
## 0.5911436 0.03767634 0.08094850
## 0.5918902 0.03724839 0.07964735
## 0.5937591 0.03639199 0.07726405
## 0.5931066 0.03680520 0.07810488
## 0.5220965 0.03391652 0.07865779
## 0.5144430 0.03136557 0.07135533
## 0.5430473 0.03650011 0.08003451
## 0.5497814 0.03965942 0.08609346
## 0.5663920 0.04107202 0.08783240
## 0.5794407 0.03665504 0.07848265
## 0.5716394 0.03972462 0.08530502
## 0.5758561 0.03762483 0.08120198
## 0.5883612 0.03199938 0.06844049
## 0.5784763 0.03602444 0.07732959
## 0.5576538 0.03473094 0.08018002
## 0.5679164 0.03516879 0.07750935
## 0.5721984 0.04283439 0.09362600
## 0.5764187 0.04339775 0.09237538
## 0.5866252 0.04216237 0.09185605
## 0.5931450 0.04302776 0.09235933
## 0.5954580 0.03768359 0.08123017
## 0.5939111 0.03249291 0.07100813
## 0.5866180 0.03705052 0.07874142
## 0.5792904 0.03433515 0.07412373
## 0.5193730 0.03584080 0.08152691
## 0.5450906 0.04064278 0.08958551
## 0.5672573 0.03953345 0.08561184
## 0.5823305 0.03916616 0.08467624
## 0.5976332 0.03794928 0.08048823
## 0.5934562 0.03748358 0.07956714
## 0.5879086 0.03700696 0.07830587
## 0.5895409 0.03621346 0.07695299
## 0.5791640 0.03237916 0.06950094
## 0.5826546 0.03544921 0.07528752
## 0.5126078 0.03327680 0.07654340
## 0.5188632 0.03681436 0.08227781
## 0.5447337 0.04201053 0.09206103
## 0.5553937 0.03926278 0.08654355
## 0.5701376 0.04494570 0.09631607
## 0.5844844 0.04114056 0.08873242
## 0.5819877 0.04512505 0.09740622
## 0.5857281 0.04002385 0.08673185
## 0.5879042 0.04219032 0.09091708
## 0.5955157 0.03835778 0.08319063
## 0.5173230 0.03510666 0.07406089
## 0.5263093 0.03661521 0.07845586
## 0.5302914 0.03918775 0.08245652
## 0.5533769 0.04193622 0.08725709
## 0.5637770 0.04206413 0.08659977
## 0.5652285 0.04068528 0.08564903
## 0.5611792 0.04267703 0.08903293
## 0.5624020 0.04427843 0.09367776
## 0.5616826 0.04202142 0.09026935
## 0.5578672 0.03872668 0.08099412
## 0.5163474 0.03874189 0.08142296
## 0.5083774 0.03806797 0.07969086
## 0.5250499 0.03440642 0.07345228
## 0.5411946 0.03322540 0.06947629
## 0.5582229 0.03128788 0.06635300
## 0.5590008 0.03705383 0.07747178
## 0.5561777 0.03354009 0.06951671
## 0.5528666 0.03321974 0.06868763
## 0.5527689 0.03429193 0.07161825
## 0.5588035 0.03654684 0.07654890
## 0.5183773 0.03393878 0.07226845
## 0.5066314 0.03303584 0.07170006
## 0.5280664 0.04124586 0.08485467
## 0.5362309 0.03694530 0.07928800
## 0.5393689 0.03855971 0.08176881
## 0.5327965 0.03929538 0.08327213
## 0.5458970 0.03722415 0.07779203
## 0.5461336 0.03982100 0.08489335
## 0.5497313 0.03813788 0.08033136
## 0.5468864 0.03766296 0.07937718
## 0.5325504 0.04017198 0.08873467
## 0.5698391 0.03441056 0.07765143
## 0.5841508 0.03645767 0.07969209
## 0.5783758 0.03929615 0.08568416
## 0.5753212 0.03704756 0.08080705
## 0.5687679 0.04008192 0.08537032
## 0.5733113 0.04185164 0.09130995
## 0.5791768 0.03558646 0.07655883
## 0.5857847 0.03439634 0.07326127
## 0.5854023 0.03541230 0.07490209
## 0.5197226 0.03122924 0.07071840
## 0.5506291 0.03480891 0.07801667
## 0.5654541 0.03719945 0.08181575
## 0.5706060 0.03744835 0.08234192
## 0.5714652 0.04449873 0.09559615
## 0.5728319 0.04073704 0.08825683
## 0.5740299 0.04263504 0.09236888
## 0.5810442 0.03913269 0.08428265
## 0.5896073 0.03992316 0.08592560
## 0.5873714 0.04108527 0.08779392
## 0.5137135 0.03146380 0.07129480
## 0.5277143 0.03833634 0.08308231
## 0.5365923 0.03917834 0.08486242
## 0.5384600 0.04131852 0.08942134
## 0.5384556 0.03503511 0.07625280
## 0.5347983 0.04224760 0.09165276
## 0.5520973 0.04081726 0.08841518
## 0.5643723 0.03757131 0.08082400
## 0.5697999 0.04217028 0.09021698
## 0.5637296 0.04227767 0.09004172
## 0.5375323 0.03410659 0.07570885
## 0.5667587 0.04158580 0.08918644
## 0.5782773 0.03389681 0.07285345
## 0.5757450 0.03953227 0.08546941
## 0.5841031 0.03632392 0.07881900
## 0.5831806 0.03550018 0.07566367
## 0.5731353 0.03546272 0.07551706
## 0.5765515 0.03365441 0.07061175
## 0.5748990 0.03368857 0.07063089
## 0.5836300 0.03780360 0.07907016
## 0.5176877 0.03303860 0.07474052
## 0.5594043 0.03374972 0.07443424
## 0.5700692 0.04089944 0.08831211
## 0.5751357 0.03777140 0.08125848
## 0.5872933 0.03807141 0.08222702
## 0.5889305 0.04001726 0.08603474
## 0.5903879 0.03964014 0.08422658
## 0.5868624 0.04026519 0.08596284
## 0.5900932 0.04228541 0.09058700
## 0.6014563 0.04352503 0.09410263
## 0.5238863 0.03568051 0.08196458
## 0.5352401 0.03989012 0.08855209
## 0.5584502 0.04350113 0.09614454
## 0.5597404 0.04374462 0.09481454
## 0.5756727 0.03775187 0.08119077
## 0.5666469 0.04125414 0.08845772
## 0.5743438 0.04110343 0.08856086
## 0.5847041 0.03663583 0.07786538
## 0.5827792 0.03563940 0.07715386
## 0.6003405 0.03701778 0.07932249
## 0.5504019 0.03053928 0.06766362
## 0.5718700 0.04151282 0.08999472
## 0.5822923 0.04045436 0.08661237
## 0.5800868 0.04193850 0.08931330
## 0.5850621 0.03625584 0.07751109
## 0.5980514 0.03152014 0.06747862
## 0.5844063 0.03626072 0.07741476
## 0.5843031 0.03365481 0.07117046
## 0.5841121 0.03763028 0.08003716
## 0.5721526 0.03905111 0.08237885
## 0.5200005 0.03691389 0.08206691
## 0.5741727 0.03541807 0.07702171
## 0.5832893 0.03726587 0.08043449
## 0.5864972 0.03627496 0.07876949
## 0.5915313 0.03397767 0.07338427
## 0.5853462 0.03308261 0.07077401
## 0.5905677 0.03408001 0.07216388
## 0.5918596 0.03413789 0.07254356
## 0.5860294 0.03682606 0.07881973
## 0.5910720 0.03555247 0.07517700
## 0.5269860 0.03579981 0.07883735
## 0.5330094 0.03061641 0.06687986
## 0.5569869 0.03024174 0.06575329
## 0.5787363 0.03433392 0.07473972
## 0.5845707 0.03280745 0.07011649
## 0.5711026 0.02985536 0.06347885
## 0.5926910 0.03196354 0.06819938
## 0.5946017 0.03117025 0.06646160
## 0.5969273 0.03327437 0.07167926
## 0.5944426 0.03764294 0.08125867
## 0.5642591 0.03509784 0.07621106
## 0.5726951 0.03874634 0.08313882
## 0.5867072 0.04308909 0.08995230
## 0.5873029 0.04068917 0.08586542
## 0.5867448 0.04116462 0.08711239
## 0.5834792 0.03637273 0.07761817
## 0.5817994 0.03480958 0.07324626
## 0.5850144 0.03450280 0.07208284
## 0.5926059 0.03896494 0.08162206
## 0.5786861 0.03940778 0.08163989
## 0.5385558 0.03535088 0.08200617
## 0.5769759 0.03544124 0.07719127
## 0.5771997 0.03541039 0.07539439
## 0.5869317 0.04212114 0.09025827
## 0.5905111 0.03548789 0.07552194
## 0.5917737 0.03609223 0.07706930
## 0.5841522 0.04008411 0.08544700
## 0.5910386 0.03791604 0.08045472
## 0.5962463 0.03756961 0.08026425
## 0.5883126 0.03541171 0.07591678
## 0.5272089 0.03199805 0.07369057
## 0.5314608 0.03926174 0.08501290
## 0.5629267 0.03993214 0.08546334
## 0.5695637 0.03926128 0.08264877
## 0.5733012 0.03699451 0.07883112
## 0.5853242 0.03761768 0.08007517
## 0.5917886 0.03665754 0.07782738
## 0.5937817 0.03653243 0.07764409
## 0.5815142 0.04189606 0.08997057
## 0.5805268 0.03831341 0.08099892
##
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were n.trees = 40, interaction.depth
## = 3, shrinkage = 0.2 and n.minobsinnode = 10.trellis.par.set(caretTheme())
plot(gbmFit)
ggplot(gbmFit)
##Accuracy 0.8118678 (Stand.Dev. 0.03860621)Model selection procedure.
logisticReg #Accuracy 0.7887516 (Stand.Dev. 0.03060581)## Generalized Linear Model
##
## 676 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 540, 541, 541, 541, 541, 541, ...
## Resampling results
##
## Accuracy Kappa Accuracy SD Kappa SD
## 0.7887516 0.5613619 0.03060581 0.0632509
##
## BayesianLogReg #Accuracy 0.7896339 (Stand.Dev. 0.03101783) ## Bayesian Generalized Linear Model
##
## 676 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 540, 541, 541, 541, 541, 541, ...
## Resampling results
##
## Accuracy Kappa Accuracy SD Kappa SD
## 0.7896339 0.5629991 0.03101783 0.06455036
##
## rpartTune1 #Accuracy 0.7872922 (Stand.Dev. 0.03179111)## CART
##
## 676 samples
## 7 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 540, 541, 541, 541, 541, 541, ...
## Resampling results across tuning parameters:
##
## cp Accuracy Kappa Accuracy SD Kappa SD
## 0.00000000 0.7831285 0.5484498 0.03036959 0.06272175
## 0.04964539 0.7635967 0.5025345 0.02416022 0.05098645
## 0.09929078 0.7692133 0.5186312 0.02783123 0.05781905
## 0.14893617 0.7692133 0.5186312 0.02783123 0.05781905
## 0.19858156 0.7692133 0.5186312 0.02783123 0.05781905
## 0.24822695 0.7692133 0.5186312 0.02783123 0.05781905
## 0.29787234 0.7692133 0.5186312 0.02783123 0.05781905
## 0.34751773 0.7692133 0.5186312 0.02783123 0.05781905
## 0.39716312 0.7692133 0.5186312 0.02783123 0.05781905
## 0.44680851 0.6766599 0.2684261 0.08554935 0.24454961
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was cp = 0.rpartTune2 #Accuracy 0.7884292 (Stand.Dev. 0.03934454)## CART
##
## 676 samples
## 7 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 540, 541, 541, 541, 540, ...
## Resampling results across tuning parameters:
##
## maxdepth Accuracy Kappa Accuracy SD Kappa SD
## 1 0.7692321 0.5183231 0.03458839 0.07405691
## 2 0.7733913 0.5182442 0.03141861 0.06554766
## 4 0.7825918 0.5401786 0.03562312 0.07510554
## 5 0.7831889 0.5416102 0.03793152 0.08119068
## 9 0.7873044 0.5509052 0.03261511 0.06941881
## 10 0.7873044 0.5509052 0.03261511 0.06941881
## 16 0.7873044 0.5509052 0.03261511 0.06941881
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was maxdepth = 9.randomForestFit #Accuracy 0.8011962 (Stand.Dev. 0.03848834)## Random Forest
##
## 676 samples
## 7 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 540, 541, 541, 541, 541, 541, ...
## Resampling results across tuning parameters:
##
## mtry Accuracy Kappa Accuracy SD Kappa SD
## 1 0.7914380 0.5574521 0.03347622 0.06811380
## 2 0.8006145 0.5827785 0.03956907 0.08074349
## 3 0.8011962 0.5855667 0.03848834 0.07869026
## 4 0.7872856 0.5600704 0.02946737 0.06110196
## 5 0.7837233 0.5532518 0.03291143 0.06590668
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 3.gbmFit #Accuracy 0.8118678 (Stand.Dev. 0.03860621)## Stochastic Gradient Boosting
##
## 676 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 541, 540, 540, 542, 540, ...
## Resampling results across tuning parameters:
##
## shrinkage interaction.depth n.minobsinnode n.trees Accuracy
## 0.1 1 10 5 0.7692200
## 0.1 1 10 10 0.7692200
## 0.1 1 10 15 0.7692200
## 0.1 1 10 20 0.7692200
## 0.1 1 10 25 0.7695163
## 0.1 1 10 30 0.7704052
## 0.1 1 10 35 0.7742549
## 0.1 1 10 40 0.7730763
## 0.1 1 10 45 0.7771961
## 0.1 1 10 50 0.7825339
## 0.1 1 20 5 0.7671459
## 0.1 1 20 10 0.7692200
## 0.1 1 20 15 0.7692200
## 0.1 1 20 20 0.7692200
## 0.1 1 20 25 0.7668562
## 0.1 1 20 30 0.7709956
## 0.1 1 20 35 0.7712897
## 0.1 1 20 40 0.7689325
## 0.1 1 20 45 0.7703964
## 0.1 1 20 50 0.7786775
## 0.1 1 30 5 0.7671459
## 0.1 1 30 10 0.7692200
## 0.1 1 30 15 0.7692200
## 0.1 1 30 20 0.7692200
## 0.1 1 30 25 0.7695207
## 0.1 1 30 30 0.7686318
## 0.1 1 30 35 0.7638932
## 0.1 1 30 40 0.7627080
## 0.1 1 30 45 0.7653616
## 0.1 1 30 50 0.7700827
## 0.1 2 10 5 0.7825295
## 0.1 2 10 10 0.7804619
## 0.1 2 10 15 0.7834294
## 0.1 2 10 20 0.7946757
## 0.1 2 10 25 0.7976300
## 0.1 2 10 30 0.7988194
## 0.1 2 10 35 0.7991202
## 0.1 2 10 40 0.8005864
## 0.1 2 10 45 0.7996996
## 0.1 2 10 50 0.8005907
## 0.1 2 20 5 0.7825295
## 0.1 2 20 10 0.7774924
## 0.1 2 20 15 0.7810458
## 0.1 2 20 20 0.7840088
## 0.1 2 20 25 0.7840022
## 0.1 2 20 30 0.7899195
## 0.1 2 20 35 0.7902224
## 0.1 2 20 40 0.7940655
## 0.1 2 20 45 0.7976234
## 0.1 2 20 50 0.7979153
## 0.1 2 30 5 0.7825295
## 0.1 2 30 10 0.7783725
## 0.1 2 30 15 0.7715707
## 0.1 2 30 20 0.7736645
## 0.1 2 30 25 0.7792722
## 0.1 2 30 30 0.7789956
## 0.1 2 30 35 0.7795838
## 0.1 2 30 40 0.7810588
## 0.1 2 30 45 0.7810566
## 0.1 2 30 50 0.7831285
## 0.1 3 10 5 0.7831199
## 0.1 3 10 10 0.7825185
## 0.1 3 10 15 0.7914010
## 0.1 3 10 20 0.8044230
## 0.1 3 10 25 0.8035559
## 0.1 3 10 30 0.8032486
## 0.1 3 10 35 0.8020743
## 0.1 3 10 40 0.8035428
## 0.1 3 10 45 0.8008849
## 0.1 3 10 50 0.8020810
## 0.1 3 20 5 0.7825295
## 0.1 3 20 10 0.7822419
## 0.1 3 20 15 0.7819413
## 0.1 3 20 20 0.7878607
## 0.1 3 20 25 0.7979393
## 0.1 3 20 30 0.8005974
## 0.1 3 20 35 0.8011944
## 0.1 3 20 40 0.8020920
## 0.1 3 20 45 0.8020833
## 0.1 3 20 50 0.8038589
## 0.1 3 30 5 0.7825295
## 0.1 3 30 10 0.7825295
## 0.1 3 30 15 0.7774990
## 0.1 3 30 20 0.7801504
## 0.1 3 30 25 0.7810546
## 0.1 3 30 30 0.7795731
## 0.1 3 30 35 0.7807539
## 0.1 3 30 40 0.7837169
## 0.1 3 30 45 0.7852071
## 0.1 3 30 50 0.7890372
## 0.1 4 10 5 0.7813486
## 0.1 4 10 10 0.7917169
## 0.1 4 10 15 0.7985209
## 0.1 4 10 20 0.8071422
## 0.1 4 10 25 0.8044734
## 0.1 4 10 30 0.8062316
## 0.1 4 10 35 0.8065345
## 0.1 4 10 40 0.8065212
## 0.1 4 10 45 0.8038655
## 0.1 4 10 50 0.8059221
## 0.1 4 20 5 0.7825295
## 0.1 4 20 10 0.7816428
## 0.1 4 20 15 0.7858085
## 0.1 4 20 20 0.7869740
## 0.1 4 20 25 0.7970285
## 0.1 4 20 30 0.8017868
## 0.1 4 20 35 0.8035449
## 0.1 4 20 40 0.8020744
## 0.1 4 20 45 0.8079918
## 0.1 4 20 50 0.8103557
## 0.1 4 30 5 0.7825295
## 0.1 4 30 10 0.7822332
## 0.1 4 30 15 0.7816514
## 0.1 4 30 20 0.7801612
## 0.1 4 30 25 0.7825273
## 0.1 4 30 30 0.7860895
## 0.1 4 30 35 0.7869653
## 0.1 4 30 40 0.7922943
## 0.1 4 30 45 0.7943553
## 0.1 4 30 50 0.7964272
## 0.1 5 10 5 0.7875577
## 0.1 5 10 10 0.7946581
## 0.1 5 10 15 0.8012008
## 0.1 5 10 20 0.8044515
## 0.1 5 10 25 0.8059307
## 0.1 5 10 30 0.8032662
## 0.1 5 10 35 0.8038786
## 0.1 5 10 40 0.8071248
## 0.1 5 10 45 0.8092033
## 0.1 5 10 50 0.8080049
## 0.1 5 20 5 0.7816406
## 0.1 5 20 10 0.7792768
## 0.1 5 20 15 0.7848955
## 0.1 5 20 20 0.7899151
## 0.1 5 20 25 0.7955340
## 0.1 5 20 30 0.7982204
## 0.1 5 20 35 0.7988174
## 0.1 5 20 40 0.8020636
## 0.1 5 20 45 0.8062206
## 0.1 5 20 50 0.8053207
## 0.1 5 30 5 0.7825295
## 0.1 5 30 10 0.7819369
## 0.1 5 30 15 0.7786644
## 0.1 5 30 20 0.7840219
## 0.1 5 30 25 0.7857954
## 0.1 5 30 30 0.7902137
## 0.1 5 30 35 0.7943508
## 0.1 5 30 40 0.7958390
## 0.1 5 30 45 0.7958390
## 0.1 5 30 50 0.7970308
## 0.2 1 10 5 0.7689259
## 0.2 1 10 10 0.7680370
## 0.2 1 10 15 0.7724707
## 0.2 1 10 20 0.7774990
## 0.2 1 10 25 0.7840023
## 0.2 1 10 30 0.7890284
## 0.2 1 10 35 0.7928715
## 0.2 1 10 40 0.7896188
## 0.2 1 10 45 0.7914054
## 0.2 1 10 50 0.7878476
## 0.2 1 20 5 0.7692200
## 0.2 1 20 10 0.7689237
## 0.2 1 20 15 0.7721917
## 0.2 1 20 20 0.7739607
## 0.2 1 20 25 0.7798760
## 0.2 1 20 30 0.7837147
## 0.2 1 20 35 0.7842984
## 0.2 1 20 40 0.7905186
## 0.2 1 20 45 0.7917082
## 0.2 1 20 50 0.7896364
## 0.2 1 30 5 0.7692200
## 0.2 1 30 10 0.7689259
## 0.2 1 30 15 0.7674225
## 0.2 1 30 20 0.7677363
## 0.2 1 30 25 0.7706753
## 0.2 1 30 30 0.7792703
## 0.2 1 30 35 0.7825252
## 0.2 1 30 40 0.7807560
## 0.2 1 30 45 0.7846037
## 0.2 1 30 50 0.7840132
## 0.2 2 10 5 0.7748410
## 0.2 2 10 10 0.7932160
## 0.2 2 10 15 0.8003097
## 0.2 2 10 20 0.8008892
## 0.2 2 10 25 0.7994076
## 0.2 2 10 30 0.7997258
## 0.2 2 10 35 0.8023905
## 0.2 2 10 40 0.8009047
## 0.2 2 10 45 0.7997281
## 0.2 2 10 50 0.7988458
## 0.2 2 20 5 0.7742417
## 0.2 2 20 10 0.7810325
## 0.2 2 20 15 0.7946603
## 0.2 2 20 20 0.7996799
## 0.2 2 20 25 0.8005688
## 0.2 2 20 30 0.7996844
## 0.2 2 20 35 0.7988020
## 0.2 2 20 40 0.8017803
## 0.2 2 20 45 0.8020701
## 0.2 2 20 50 0.8065299
## 0.2 2 30 5 0.7760043
## 0.2 2 30 10 0.7721699
## 0.2 2 30 15 0.7801503
## 0.2 2 30 20 0.7807429
## 0.2 2 30 25 0.7816318
## 0.2 2 30 30 0.7851919
## 0.2 2 30 35 0.7881506
## 0.2 2 30 40 0.7905165
## 0.2 2 30 45 0.7934730
## 0.2 2 30 50 0.7964360
## 0.2 3 10 5 0.7763180
## 0.2 3 10 10 0.7955580
## 0.2 3 10 15 0.8017782
## 0.2 3 10 20 0.8003165
## 0.2 3 10 25 0.8059462
## 0.2 3 10 30 0.8062512
## 0.2 3 10 35 0.8097696
## 0.2 3 10 40 0.8118678
## 0.2 3 10 45 0.8080246
## 0.2 3 10 50 0.8080113
## 0.2 3 20 5 0.7795665
## 0.2 3 20 10 0.7893313
## 0.2 3 20 15 0.7996866
## 0.2 3 20 20 0.7970154
## 0.2 3 20 25 0.7990808
## 0.2 3 20 30 0.8052988
## 0.2 3 20 35 0.8029306
## 0.2 3 20 40 0.8103381
## 0.2 3 20 45 0.8068087
## 0.2 3 20 50 0.8076801
## 0.2 3 30 5 0.7792658
## 0.2 3 30 10 0.7748060
## 0.2 3 30 15 0.7828214
## 0.2 3 30 20 0.7837169
## 0.2 3 30 25 0.7913944
## 0.2 3 30 30 0.7925995
## 0.2 3 30 35 0.7996933
## 0.2 3 30 40 0.7997019
## 0.2 3 30 45 0.8044494
## 0.2 3 30 50 0.8050310
## 0.2 4 10 5 0.7908192
## 0.2 4 10 10 0.8017716
## 0.2 4 10 15 0.8044579
## 0.2 4 10 20 0.8056322
## 0.2 4 10 25 0.8106780
## 0.2 4 10 30 0.8118502
## 0.2 4 10 35 0.8068175
## 0.2 4 10 40 0.8088872
## 0.2 4 10 45 0.8103644
## 0.2 4 10 50 0.8050376
## 0.2 4 20 5 0.7831286
## 0.2 4 20 10 0.7896561
## 0.2 4 20 15 0.7943838
## 0.2 4 20 20 0.8005908
## 0.2 4 20 25 0.8009111
## 0.2 4 20 30 0.8017782
## 0.2 4 20 35 0.8059352
## 0.2 4 20 40 0.8062075
## 0.2 4 20 45 0.8068001
## 0.2 4 20 50 0.8062097
## 0.2 4 30 5 0.7822332
## 0.2 4 30 10 0.7745448
## 0.2 4 30 15 0.7858064
## 0.2 4 30 20 0.7878696
## 0.2 4 30 25 0.7952508
## 0.2 4 30 30 0.8005646
## 0.2 4 30 35 0.7967280
## 0.2 4 30 40 0.7988043
## 0.2 4 30 45 0.8044122
## 0.2 4 30 50 0.7996844
## 0.2 5 10 5 0.7952419
## 0.2 5 10 10 0.7964493
## 0.2 5 10 15 0.7976344
## 0.2 5 10 20 0.7985101
## 0.2 5 10 25 0.8038567
## 0.2 5 10 30 0.8065278
## 0.2 5 10 35 0.8071096
## 0.2 5 10 40 0.8062161
## 0.2 5 10 45 0.8026781
## 0.2 5 10 50 0.7988219
## 0.2 5 20 5 0.7789585
## 0.2 5 20 10 0.7878563
## 0.2 5 20 15 0.7955602
## 0.2 5 20 20 0.8026452
## 0.2 5 20 25 0.8091770
## 0.2 5 20 30 0.8068021
## 0.2 5 20 35 0.8038479
## 0.2 5 20 40 0.8047390
## 0.2 5 20 45 0.7997238
## 0.2 5 20 50 0.8012032
## 0.2 5 30 5 0.7775077
## 0.2 5 30 10 0.7760349
## 0.2 5 30 15 0.7863968
## 0.2 5 30 20 0.7908106
## 0.2 5 30 25 0.7967478
## 0.2 5 30 30 0.8032314
## 0.2 5 30 35 0.8017629
## 0.2 5 30 40 0.8035385
## 0.2 5 30 45 0.8044319
## 0.2 5 30 50 0.8079656
## 0.3 1 10 5 0.7695163
## 0.3 1 10 10 0.7736666
## 0.3 1 10 15 0.7751416
## 0.3 1 10 20 0.7854707
## 0.3 1 10 25 0.7908084
## 0.3 1 10 30 0.7914011
## 0.3 1 10 35 0.7890328
## 0.3 1 10 40 0.7902202
## 0.3 1 10 45 0.7896167
## 0.3 1 10 50 0.7878432
## 0.3 1 20 5 0.7692090
## 0.3 1 20 10 0.7650652
## 0.3 1 20 15 0.7727472
## 0.3 1 20 20 0.7795644
## 0.3 1 20 25 0.7878521
## 0.3 1 20 30 0.7884425
## 0.3 1 20 35 0.7869675
## 0.3 1 20 40 0.7851831
## 0.3 1 20 45 0.7857846
## 0.3 1 20 50 0.7881680
## 0.3 1 30 5 0.7692200
## 0.3 1 30 10 0.7656535
## 0.3 1 30 15 0.7742330
## 0.3 1 30 20 0.7780894
## 0.3 1 30 25 0.7795577
## 0.3 1 30 30 0.7769018
## 0.3 1 30 35 0.7828148
## 0.3 1 30 40 0.7825032
## 0.3 1 30 45 0.7845991
## 0.3 1 30 50 0.7834074
## 0.3 2 10 5 0.7816580
## 0.3 2 10 10 0.7991005
## 0.3 2 10 15 0.8044229
## 0.3 2 10 20 0.8005843
## 0.3 2 10 25 0.7988195
## 0.3 2 10 30 0.7952791
## 0.3 2 10 35 0.7973424
## 0.3 2 10 40 0.7999914
## 0.3 2 10 45 0.8026911
## 0.3 2 10 50 0.8023731
## 0.3 2 20 5 0.7780937
## 0.3 2 20 10 0.7905384
## 0.3 2 20 15 0.7952530
## 0.3 2 20 20 0.7973336
## 0.3 2 20 25 0.7976342
## 0.3 2 20 30 0.7979306
## 0.3 2 20 35 0.7982467
## 0.3 2 20 40 0.8012031
## 0.3 2 20 45 0.8050594
## 0.3 2 20 50 0.8038654
## 0.3 2 30 5 0.7748541
## 0.3 2 30 10 0.7795599
## 0.3 2 30 15 0.7828257
## 0.3 2 30 20 0.7831309
## 0.3 2 30 25 0.7825208
## 0.3 2 30 30 0.7801746
## 0.3 2 30 35 0.7884556
## 0.3 2 30 40 0.7937956
## 0.3 2 30 45 0.7961464
## 0.3 2 30 50 0.7928826
## 0.3 3 10 5 0.7849019
## 0.3 3 10 10 0.7958740
## 0.3 3 10 15 0.8000047
## 0.3 3 10 20 0.7985342
## 0.3 3 10 25 0.8020897
## 0.3 3 10 30 0.8014949
## 0.3 3 10 35 0.7964666
## 0.3 3 10 40 0.7976585
## 0.3 3 10 45 0.7967499
## 0.3 3 10 50 0.8009069
## 0.3 3 20 5 0.7763357
## 0.3 3 20 10 0.7929307
## 0.3 3 20 15 0.7967650
## 0.3 3 20 20 0.7988327
## 0.3 3 20 25 0.8044471
## 0.3 3 20 30 0.8047653
## 0.3 3 20 35 0.8053470
## 0.3 3 20 40 0.8032905
## 0.3 3 20 45 0.8050551
## 0.3 3 20 50 0.8106761
## 0.3 3 30 5 0.7807297
## 0.3 3 30 10 0.7822068
## 0.3 3 30 15 0.7925644
## 0.3 3 30 20 0.7916886
## 0.3 3 30 25 0.7991071
## 0.3 3 30 30 0.7943685
## 0.3 3 30 35 0.7979327
## 0.3 3 30 40 0.8023707
## 0.3 3 30 45 0.8014929
## 0.3 3 30 50 0.8097673
## 0.3 4 10 5 0.7893665
## 0.3 4 10 10 0.7976364
## 0.3 4 10 15 0.8014905
## 0.3 4 10 20 0.8000308
## 0.3 4 10 25 0.8020721
## 0.3 4 10 30 0.8082728
## 0.3 4 10 35 0.8017737
## 0.3 4 10 40 0.8011746
## 0.3 4 10 45 0.8008828
## 0.3 4 10 50 0.7952618
## 0.3 4 20 5 0.7766188
## 0.3 4 20 10 0.7988065
## 0.3 4 20 15 0.8020615
## 0.3 4 20 20 0.8032511
## 0.3 4 20 25 0.8059155
## 0.3 4 20 30 0.8020899
## 0.3 4 20 35 0.8044559
## 0.3 4 20 40 0.8050464
## 0.3 4 20 45 0.8023709
## 0.3 4 20 50 0.8047238
## 0.3 4 30 5 0.7807692
## 0.3 4 30 10 0.7807429
## 0.3 4 30 15 0.7908083
## 0.3 4 30 20 0.8002791
## 0.3 4 30 25 0.8023686
## 0.3 4 30 30 0.7958411
## 0.3 4 30 35 0.8058979
## 0.3 4 30 40 0.8064971
## 0.3 4 30 45 0.8076889
## 0.3 4 30 50 0.8064886
## 0.3 5 10 5 0.7949631
## 0.3 5 10 10 0.7976430
## 0.3 5 10 15 0.8032662
## 0.3 5 10 20 0.8029721
## 0.3 5 10 25 0.8029807
## 0.3 5 10 30 0.8009067
## 0.3 5 10 35 0.8002967
## 0.3 5 10 40 0.8014687
## 0.3 5 10 45 0.8047368
## 0.3 5 10 50 0.7979131
## 0.3 5 20 5 0.7858084
## 0.3 5 20 10 0.8000134
## 0.3 5 20 15 0.7987889
## 0.3 5 20 20 0.8032772
## 0.3 5 20 25 0.8041531
## 0.3 5 20 30 0.8047390
## 0.3 5 20 35 0.8011878
## 0.3 5 20 40 0.8044580
## 0.3 5 20 45 0.8068241
## 0.3 5 20 50 0.8029437
## 0.3 5 30 5 0.7813617
## 0.3 5 30 10 0.7795929
## 0.3 5 30 15 0.7929002
## 0.3 5 30 20 0.7955537
## 0.3 5 30 25 0.7976235
## 0.3 5 30 30 0.8032576
## 0.3 5 30 35 0.8062118
## 0.3 5 30 40 0.8065016
## 0.3 5 30 45 0.8005908
## 0.3 5 30 50 0.7996977
## Kappa Accuracy SD Kappa SD
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5191203 0.03234106 0.06854046
## 0.5197694 0.03238810 0.06812746
## 0.5292037 0.03001320 0.06363436
## 0.5266549 0.03229885 0.06775505
## 0.5357588 0.03152644 0.06658660
## 0.5479427 0.03267741 0.06863636
## 0.5129120 0.03308138 0.07087347
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5125371 0.03207206 0.06827715
## 0.5217805 0.03423990 0.07265939
## 0.5227742 0.03461667 0.07339528
## 0.5187636 0.03172253 0.06657126
## 0.5219998 0.03306395 0.06978850
## 0.5388186 0.03601169 0.07497780
## 0.5129120 0.03308138 0.07087347
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5183773 0.03393878 0.07226845
## 0.5187623 0.03328308 0.07037158
## 0.5167253 0.03265732 0.06875086
## 0.5073610 0.03348434 0.07141457
## 0.5043920 0.03297063 0.07052438
## 0.5098637 0.03893390 0.08331708
## 0.5193747 0.03390441 0.07247806
## 0.5210296 0.03281182 0.07589674
## 0.5196404 0.03272431 0.07331539
## 0.5295893 0.03507608 0.07675815
## 0.5550468 0.03064376 0.06981859
## 0.5635714 0.03321750 0.07440048
## 0.5688584 0.03679681 0.08065808
## 0.5697985 0.03534985 0.07761932
## 0.5737398 0.03632389 0.07937564
## 0.5730305 0.03613155 0.07896953
## 0.5764080 0.04051097 0.08724491
## 0.5210296 0.03281182 0.07589674
## 0.5121614 0.03047265 0.07121906
## 0.5212090 0.03068615 0.07152340
## 0.5319495 0.03068007 0.06994657
## 0.5346366 0.03246633 0.07218970
## 0.5489193 0.03396812 0.07489160
## 0.5511353 0.03399065 0.07388498
## 0.5594119 0.03750440 0.08189125
## 0.5680006 0.03801944 0.08377953
## 0.5694889 0.03890836 0.08560819
## 0.5210296 0.03281182 0.07589674
## 0.5143389 0.03198798 0.07338106
## 0.5044280 0.03512856 0.07966227
## 0.5105136 0.03012137 0.06749083
## 0.5232800 0.03980970 0.08676608
## 0.5238435 0.03922048 0.08605167
## 0.5272517 0.03680009 0.08102951
## 0.5307358 0.03935275 0.08728833
## 0.5313922 0.04128408 0.09117526
## 0.5368732 0.04133045 0.09132017
## 0.5236322 0.03238332 0.07452237
## 0.5276644 0.03490517 0.07812823
## 0.5509909 0.03218069 0.07247623
## 0.5795665 0.03329984 0.07493349
## 0.5795425 0.03319484 0.07378773
## 0.5797838 0.03769627 0.08314820
## 0.5788753 0.03905971 0.08568866
## 0.5825189 0.03668385 0.08062980
## 0.5778401 0.04044120 0.08778295
## 0.5799190 0.04021630 0.08779683
## 0.5210296 0.03281182 0.07589674
## 0.5217859 0.03379657 0.07864503
## 0.5264079 0.03404875 0.07724029
## 0.5446845 0.03824793 0.08301641
## 0.5680657 0.03954969 0.08666314
## 0.5746614 0.03586512 0.07915909
## 0.5754097 0.03432135 0.07664862
## 0.5791768 0.03658954 0.08028893
## 0.5802257 0.03853887 0.08369594
## 0.5842352 0.03969796 0.08619462
## 0.5210296 0.03281182 0.07589674
## 0.5211282 0.03281182 0.07590869
## 0.5143273 0.03586893 0.08118366
## 0.5237615 0.03355769 0.07519913
## 0.5276281 0.03688102 0.08153954
## 0.5263837 0.03831999 0.08439204
## 0.5317599 0.03688078 0.08101987
## 0.5389632 0.03608005 0.07966941
## 0.5425207 0.03653517 0.08058609
## 0.5514920 0.03306540 0.07272810
## 0.5204990 0.03442250 0.07799758
## 0.5482350 0.03152948 0.07239077
## 0.5661017 0.03355598 0.07590924
## 0.5871777 0.03965501 0.08756962
## 0.5829752 0.04061988 0.08861809
## 0.5874944 0.03543665 0.07770856
## 0.5899804 0.04210912 0.09211458
## 0.5903280 0.04254705 0.09274102
## 0.5855795 0.04364052 0.09388850
## 0.5896841 0.04181467 0.09022895
## 0.5210296 0.03281182 0.07589674
## 0.5228649 0.03344102 0.07686302
## 0.5356187 0.03448879 0.07813136
## 0.5423391 0.04277478 0.09388909
## 0.5654346 0.04031012 0.08767534
## 0.5771612 0.04193320 0.09217213
## 0.5822795 0.04398321 0.09571264
## 0.5804765 0.04081500 0.08854718
## 0.5937126 0.04037305 0.08676155
## 0.5999357 0.04228673 0.09031525
## 0.5210296 0.03281182 0.07589674
## 0.5205376 0.03190186 0.07440786
## 0.5228057 0.03284034 0.07551231
## 0.5242798 0.03508364 0.07893724
## 0.5332382 0.03613066 0.08126921
## 0.5424308 0.03676733 0.08159230
## 0.5454652 0.03534139 0.07856561
## 0.5573948 0.03927584 0.08663164
## 0.5633977 0.03932614 0.08591894
## 0.5687352 0.04151075 0.09032322
## 0.5366426 0.03717174 0.08339964
## 0.5591298 0.03359876 0.07410411
## 0.5750715 0.03517323 0.07747841
## 0.5837964 0.03636965 0.07896338
## 0.5880846 0.03627035 0.07910978
## 0.5827740 0.03840365 0.08362873
## 0.5852619 0.03807153 0.08344146
## 0.5931229 0.03613146 0.07719163
## 0.5983229 0.03586319 0.07633857
## 0.5960238 0.03814359 0.08171305
## 0.5195215 0.03365416 0.07764080
## 0.5177603 0.03033465 0.07016951
## 0.5349548 0.03418802 0.07697207
## 0.5495220 0.03651616 0.08086185
## 0.5639333 0.04100075 0.09030176
## 0.5710154 0.03734297 0.08234066
## 0.5737560 0.03723285 0.08191723
## 0.5814023 0.04163711 0.09149771
## 0.5914669 0.03826183 0.08343730
## 0.5896858 0.03915350 0.08469542
## 0.5210296 0.03281182 0.07589674
## 0.5201440 0.03261634 0.07587571
## 0.5166205 0.03404089 0.07970591
## 0.5329872 0.03647345 0.08310136
## 0.5389088 0.03407723 0.07744444
## 0.5515756 0.03661211 0.08031136
## 0.5621379 0.04050150 0.08820487
## 0.5662897 0.03834789 0.08338702
## 0.5675135 0.04088093 0.08815303
## 0.5708063 0.04090293 0.08772237
## 0.5169710 0.03374533 0.07158638
## 0.5162331 0.03269375 0.06943390
## 0.5245889 0.03070576 0.06715717
## 0.5355876 0.03486774 0.07256399
## 0.5492955 0.03216373 0.06772441
## 0.5608190 0.03440854 0.07130463
## 0.5691649 0.03315484 0.06908724
## 0.5625317 0.03483139 0.07193866
## 0.5660156 0.03527126 0.07450274
## 0.5586791 0.03683458 0.07672224
## 0.5172302 0.03393878 0.07222091
## 0.5169430 0.03409502 0.07211000
## 0.5240244 0.03557313 0.07488809
## 0.5280154 0.03471953 0.07364855
## 0.5404931 0.03558414 0.07557249
## 0.5481914 0.03740993 0.08046742
## 0.5509045 0.03610213 0.07657604
## 0.5635013 0.03199403 0.06629718
## 0.5661979 0.03208350 0.06716770
## 0.5619031 0.02674801 0.05608425
## 0.5183773 0.03393878 0.07226845
## 0.5169710 0.03374533 0.07158638
## 0.5125321 0.03600090 0.07978609
## 0.5147364 0.03493376 0.07436015
## 0.5207422 0.03795410 0.07978023
## 0.5389725 0.03502212 0.07350799
## 0.5466634 0.03728317 0.07734130
## 0.5424862 0.03634710 0.07594400
## 0.5499888 0.03600662 0.07591392
## 0.5487772 0.03527150 0.07420066
## 0.5151364 0.03460563 0.07336020
## 0.5538143 0.03712949 0.08119513
## 0.5724385 0.03689205 0.08133921
## 0.5773178 0.03612364 0.07962547
## 0.5740210 0.03918786 0.08629756
## 0.5759474 0.03987098 0.08617559
## 0.5822817 0.03960086 0.08590261
## 0.5804765 0.03985016 0.08644292
## 0.5782216 0.04412113 0.09537168
## 0.5765517 0.04134973 0.08918746
## 0.5098323 0.03443781 0.07665337
## 0.5288048 0.03996181 0.08776722
## 0.5594083 0.03570276 0.07947883
## 0.5724996 0.03780955 0.08337814
## 0.5752432 0.03558608 0.07731139
## 0.5751618 0.03482490 0.07598149
## 0.5731883 0.03248281 0.07174552
## 0.5807215 0.03461498 0.07485997
## 0.5818974 0.03608299 0.07755620
## 0.5916328 0.03971055 0.08536831
## 0.5120512 0.03311360 0.07302380
## 0.5114586 0.03571320 0.07688703
## 0.5284180 0.03577555 0.07747355
## 0.5319119 0.03714831 0.08035902
## 0.5360551 0.03769851 0.08012579
## 0.5449478 0.03594037 0.07748335
## 0.5513411 0.03999050 0.08638223
## 0.5563151 0.03910416 0.08460597
## 0.5624419 0.04117473 0.08954341
## 0.5694958 0.03881296 0.08388195
## 0.5177990 0.03421471 0.07375515
## 0.5640656 0.03798410 0.08092939
## 0.5798566 0.03466880 0.07506243
## 0.5782000 0.04111478 0.08872517
## 0.5901665 0.04483206 0.09609667
## 0.5916416 0.03778544 0.08048460
## 0.5993856 0.03511544 0.07528379
## 0.6043174 0.03860621 0.08277416
## 0.5961063 0.04054591 0.08697952
## 0.5963522 0.03387993 0.07235589
## 0.5176038 0.03325828 0.07688195
## 0.5465009 0.03936737 0.08729711
## 0.5715992 0.04143881 0.09038113
## 0.5687730 0.03515260 0.07676421
## 0.5754229 0.03956888 0.08532286
## 0.5890040 0.03771307 0.08116247
## 0.5846145 0.03944418 0.08384134
## 0.6002162 0.04087528 0.08719130
## 0.5934902 0.04227046 0.09028416
## 0.5948964 0.04315231 0.09226684
## 0.5152369 0.03341526 0.07674052
## 0.5134326 0.03320953 0.07510068
## 0.5335568 0.02926585 0.06764545
## 0.5382668 0.03257208 0.07217027
## 0.5566589 0.03333004 0.07278096
## 0.5602561 0.03725714 0.08064917
## 0.5761592 0.03810637 0.08299231
## 0.5772956 0.04030138 0.08668568
## 0.5876205 0.03888818 0.08439298
## 0.5890094 0.03961574 0.08577761
## 0.5509863 0.03992643 0.08878486
## 0.5780249 0.03826006 0.08197373
## 0.5858111 0.03967289 0.08394771
## 0.5901439 0.03660329 0.07725096
## 0.6021863 0.03712531 0.07782299
## 0.6036144 0.03781755 0.08098577
## 0.5937869 0.03519088 0.07487157
## 0.5982164 0.04154017 0.08860018
## 0.6019594 0.04097429 0.08774003
## 0.5911334 0.03944279 0.08385222
## 0.5254849 0.03347740 0.07709293
## 0.5468191 0.03478796 0.07894762
## 0.5635063 0.03358091 0.07253656
## 0.5781834 0.03480269 0.07536725
## 0.5802188 0.03902883 0.08371333
## 0.5824465 0.03997173 0.08605627
## 0.5911436 0.03767634 0.08094850
## 0.5918902 0.03724839 0.07964735
## 0.5937591 0.03639199 0.07726405
## 0.5931066 0.03680520 0.07810488
## 0.5220965 0.03391652 0.07865779
## 0.5144430 0.03136557 0.07135533
## 0.5430473 0.03650011 0.08003451
## 0.5497814 0.03965942 0.08609346
## 0.5663920 0.04107202 0.08783240
## 0.5794407 0.03665504 0.07848265
## 0.5716394 0.03972462 0.08530502
## 0.5758561 0.03762483 0.08120198
## 0.5883612 0.03199938 0.06844049
## 0.5784763 0.03602444 0.07732959
## 0.5576538 0.03473094 0.08018002
## 0.5679164 0.03516879 0.07750935
## 0.5721984 0.04283439 0.09362600
## 0.5764187 0.04339775 0.09237538
## 0.5866252 0.04216237 0.09185605
## 0.5931450 0.04302776 0.09235933
## 0.5954580 0.03768359 0.08123017
## 0.5939111 0.03249291 0.07100813
## 0.5866180 0.03705052 0.07874142
## 0.5792904 0.03433515 0.07412373
## 0.5193730 0.03584080 0.08152691
## 0.5450906 0.04064278 0.08958551
## 0.5672573 0.03953345 0.08561184
## 0.5823305 0.03916616 0.08467624
## 0.5976332 0.03794928 0.08048823
## 0.5934562 0.03748358 0.07956714
## 0.5879086 0.03700696 0.07830587
## 0.5895409 0.03621346 0.07695299
## 0.5791640 0.03237916 0.06950094
## 0.5826546 0.03544921 0.07528752
## 0.5126078 0.03327680 0.07654340
## 0.5188632 0.03681436 0.08227781
## 0.5447337 0.04201053 0.09206103
## 0.5553937 0.03926278 0.08654355
## 0.5701376 0.04494570 0.09631607
## 0.5844844 0.04114056 0.08873242
## 0.5819877 0.04512505 0.09740622
## 0.5857281 0.04002385 0.08673185
## 0.5879042 0.04219032 0.09091708
## 0.5955157 0.03835778 0.08319063
## 0.5173230 0.03510666 0.07406089
## 0.5263093 0.03661521 0.07845586
## 0.5302914 0.03918775 0.08245652
## 0.5533769 0.04193622 0.08725709
## 0.5637770 0.04206413 0.08659977
## 0.5652285 0.04068528 0.08564903
## 0.5611792 0.04267703 0.08903293
## 0.5624020 0.04427843 0.09367776
## 0.5616826 0.04202142 0.09026935
## 0.5578672 0.03872668 0.08099412
## 0.5163474 0.03874189 0.08142296
## 0.5083774 0.03806797 0.07969086
## 0.5250499 0.03440642 0.07345228
## 0.5411946 0.03322540 0.06947629
## 0.5582229 0.03128788 0.06635300
## 0.5590008 0.03705383 0.07747178
## 0.5561777 0.03354009 0.06951671
## 0.5528666 0.03321974 0.06868763
## 0.5527689 0.03429193 0.07161825
## 0.5588035 0.03654684 0.07654890
## 0.5183773 0.03393878 0.07226845
## 0.5066314 0.03303584 0.07170006
## 0.5280664 0.04124586 0.08485467
## 0.5362309 0.03694530 0.07928800
## 0.5393689 0.03855971 0.08176881
## 0.5327965 0.03929538 0.08327213
## 0.5458970 0.03722415 0.07779203
## 0.5461336 0.03982100 0.08489335
## 0.5497313 0.03813788 0.08033136
## 0.5468864 0.03766296 0.07937718
## 0.5325504 0.04017198 0.08873467
## 0.5698391 0.03441056 0.07765143
## 0.5841508 0.03645767 0.07969209
## 0.5783758 0.03929615 0.08568416
## 0.5753212 0.03704756 0.08080705
## 0.5687679 0.04008192 0.08537032
## 0.5733113 0.04185164 0.09130995
## 0.5791768 0.03558646 0.07655883
## 0.5857847 0.03439634 0.07326127
## 0.5854023 0.03541230 0.07490209
## 0.5197226 0.03122924 0.07071840
## 0.5506291 0.03480891 0.07801667
## 0.5654541 0.03719945 0.08181575
## 0.5706060 0.03744835 0.08234192
## 0.5714652 0.04449873 0.09559615
## 0.5728319 0.04073704 0.08825683
## 0.5740299 0.04263504 0.09236888
## 0.5810442 0.03913269 0.08428265
## 0.5896073 0.03992316 0.08592560
## 0.5873714 0.04108527 0.08779392
## 0.5137135 0.03146380 0.07129480
## 0.5277143 0.03833634 0.08308231
## 0.5365923 0.03917834 0.08486242
## 0.5384600 0.04131852 0.08942134
## 0.5384556 0.03503511 0.07625280
## 0.5347983 0.04224760 0.09165276
## 0.5520973 0.04081726 0.08841518
## 0.5643723 0.03757131 0.08082400
## 0.5697999 0.04217028 0.09021698
## 0.5637296 0.04227767 0.09004172
## 0.5375323 0.03410659 0.07570885
## 0.5667587 0.04158580 0.08918644
## 0.5782773 0.03389681 0.07285345
## 0.5757450 0.03953227 0.08546941
## 0.5841031 0.03632392 0.07881900
## 0.5831806 0.03550018 0.07566367
## 0.5731353 0.03546272 0.07551706
## 0.5765515 0.03365441 0.07061175
## 0.5748990 0.03368857 0.07063089
## 0.5836300 0.03780360 0.07907016
## 0.5176877 0.03303860 0.07474052
## 0.5594043 0.03374972 0.07443424
## 0.5700692 0.04089944 0.08831211
## 0.5751357 0.03777140 0.08125848
## 0.5872933 0.03807141 0.08222702
## 0.5889305 0.04001726 0.08603474
## 0.5903879 0.03964014 0.08422658
## 0.5868624 0.04026519 0.08596284
## 0.5900932 0.04228541 0.09058700
## 0.6014563 0.04352503 0.09410263
## 0.5238863 0.03568051 0.08196458
## 0.5352401 0.03989012 0.08855209
## 0.5584502 0.04350113 0.09614454
## 0.5597404 0.04374462 0.09481454
## 0.5756727 0.03775187 0.08119077
## 0.5666469 0.04125414 0.08845772
## 0.5743438 0.04110343 0.08856086
## 0.5847041 0.03663583 0.07786538
## 0.5827792 0.03563940 0.07715386
## 0.6003405 0.03701778 0.07932249
## 0.5504019 0.03053928 0.06766362
## 0.5718700 0.04151282 0.08999472
## 0.5822923 0.04045436 0.08661237
## 0.5800868 0.04193850 0.08931330
## 0.5850621 0.03625584 0.07751109
## 0.5980514 0.03152014 0.06747862
## 0.5844063 0.03626072 0.07741476
## 0.5843031 0.03365481 0.07117046
## 0.5841121 0.03763028 0.08003716
## 0.5721526 0.03905111 0.08237885
## 0.5200005 0.03691389 0.08206691
## 0.5741727 0.03541807 0.07702171
## 0.5832893 0.03726587 0.08043449
## 0.5864972 0.03627496 0.07876949
## 0.5915313 0.03397767 0.07338427
## 0.5853462 0.03308261 0.07077401
## 0.5905677 0.03408001 0.07216388
## 0.5918596 0.03413789 0.07254356
## 0.5860294 0.03682606 0.07881973
## 0.5910720 0.03555247 0.07517700
## 0.5269860 0.03579981 0.07883735
## 0.5330094 0.03061641 0.06687986
## 0.5569869 0.03024174 0.06575329
## 0.5787363 0.03433392 0.07473972
## 0.5845707 0.03280745 0.07011649
## 0.5711026 0.02985536 0.06347885
## 0.5926910 0.03196354 0.06819938
## 0.5946017 0.03117025 0.06646160
## 0.5969273 0.03327437 0.07167926
## 0.5944426 0.03764294 0.08125867
## 0.5642591 0.03509784 0.07621106
## 0.5726951 0.03874634 0.08313882
## 0.5867072 0.04308909 0.08995230
## 0.5873029 0.04068917 0.08586542
## 0.5867448 0.04116462 0.08711239
## 0.5834792 0.03637273 0.07761817
## 0.5817994 0.03480958 0.07324626
## 0.5850144 0.03450280 0.07208284
## 0.5926059 0.03896494 0.08162206
## 0.5786861 0.03940778 0.08163989
## 0.5385558 0.03535088 0.08200617
## 0.5769759 0.03544124 0.07719127
## 0.5771997 0.03541039 0.07539439
## 0.5869317 0.04212114 0.09025827
## 0.5905111 0.03548789 0.07552194
## 0.5917737 0.03609223 0.07706930
## 0.5841522 0.04008411 0.08544700
## 0.5910386 0.03791604 0.08045472
## 0.5962463 0.03756961 0.08026425
## 0.5883126 0.03541171 0.07591678
## 0.5272089 0.03199805 0.07369057
## 0.5314608 0.03926174 0.08501290
## 0.5629267 0.03993214 0.08546334
## 0.5695637 0.03926128 0.08264877
## 0.5733012 0.03699451 0.07883112
## 0.5853242 0.03761768 0.08007517
## 0.5917886 0.03665754 0.07782738
## 0.5937817 0.03653243 0.07764409
## 0.5815142 0.04189606 0.08997057
## 0.5805268 0.03831341 0.08099892
##
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were n.trees = 40, interaction.depth
## = 3, shrinkage = 0.2 and n.minobsinnode = 10.##gfbfit fits bestFurther solutions
We compute the importance of the variables to check for further potential to improve predictive accuaracy.
varImp(gbmFit)## gbm variable importance
##
## Overall
## Sexmale 100.00000
## Age 60.93041
## Fare 39.87357
## Pclass3 38.51935
## SibSp 10.70351
## EmbarkedC 1.72800
## Pclass2 1.62879
## Parch 0.48448
## EmbarkedQ 0.05637
## EmbarkedS 0.00000Based on these results, there exist evidence to remove variables Embarked and Parch
formula = Survived ~ Pclass + Sex + Age + SibSp + Fare
gbmFit <- train(formula, data = training_na,
method = "gbm",
trControl = fitControl,
## This last option is actually one
## for gbm() that passes through
verbose = FALSE,
tuneGrid = gbmGrid)
gbmFit## Stochastic Gradient Boosting
##
## 676 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 540, 542, 541, 540, 541, 541, ...
## Resampling results across tuning parameters:
##
## shrinkage interaction.depth n.minobsinnode n.trees Accuracy
## 0.1 1 10 5 0.7650465
## 0.1 1 10 10 0.7647480
## 0.1 1 10 15 0.7653406
## 0.1 1 10 20 0.7665171
## 0.1 1 10 25 0.7676979
## 0.1 1 10 30 0.7694801
## 0.1 1 10 35 0.7733232
## 0.1 1 10 40 0.7712513
## 0.1 1 10 45 0.7783254
## 0.1 1 10 50 0.7848593
## 0.1 1 20 5 0.7679877
## 0.1 1 20 10 0.7676827
## 0.1 1 20 15 0.7667938
## 0.1 1 20 20 0.7688635
## 0.1 1 20 25 0.7706413
## 0.1 1 20 30 0.7700487
## 0.1 1 20 35 0.7721162
## 0.1 1 20 40 0.7706565
## 0.1 1 20 45 0.7727328
## 0.1 1 20 50 0.7736238
## 0.1 1 30 5 0.7653406
## 0.1 1 30 10 0.7691641
## 0.1 1 30 15 0.7653406
## 0.1 1 30 20 0.7674038
## 0.1 1 30 25 0.7679920
## 0.1 1 30 30 0.7670966
## 0.1 1 30 35 0.7656195
## 0.1 1 30 40 0.7653384
## 0.1 1 30 45 0.7665280
## 0.1 1 30 50 0.7694866
## 0.1 2 10 5 0.7798879
## 0.1 2 10 10 0.7698026
## 0.1 2 10 15 0.7739267
## 0.1 2 10 20 0.7818919
## 0.1 2 10 25 0.7904889
## 0.1 2 10 30 0.7990795
## 0.1 2 10 35 0.8005697
## 0.1 2 10 40 0.7999945
## 0.1 2 10 45 0.7985109
## 0.1 2 10 50 0.7993998
## 0.1 2 20 5 0.7825546
## 0.1 2 20 10 0.7739310
## 0.1 2 20 15 0.7686043
## 0.1 2 20 20 0.7774626
## 0.1 2 20 25 0.7848613
## 0.1 2 20 30 0.7890161
## 0.1 2 20 35 0.7940752
## 0.1 2 20 40 0.7991057
## 0.1 2 20 45 0.7970315
## 0.1 2 20 50 0.8005807
## 0.1 2 30 5 0.7825546
## 0.1 2 30 10 0.7781101
## 0.1 2 30 15 0.7721554
## 0.1 2 30 20 0.7709746
## 0.1 2 30 25 0.7742274
## 0.1 2 30 30 0.7810226
## 0.1 2 30 35 0.7804431
## 0.1 2 30 40 0.7842863
## 0.1 2 30 45 0.7807373
## 0.1 2 30 50 0.7831164
## 0.1 3 10 5 0.7804563
## 0.1 3 10 10 0.7774824
## 0.1 3 10 15 0.7901948
## 0.1 3 10 20 0.8011536
## 0.1 3 10 25 0.8035305
## 0.1 3 10 30 0.8044304
## 0.1 3 10 35 0.8029576
## 0.1 3 10 40 0.8064913
## 0.1 3 10 45 0.8064957
## 0.1 3 10 50 0.8044391
## 0.1 3 20 5 0.7825546
## 0.1 3 20 10 0.7748177
## 0.1 3 20 15 0.7756958
## 0.1 3 20 20 0.7896000
## 0.1 3 20 25 0.7919573
## 0.1 3 20 30 0.7970162
## 0.1 3 20 35 0.8005784
## 0.1 3 20 40 0.8017657
## 0.1 3 20 45 0.8011579
## 0.1 3 20 50 0.7999793
## 0.1 3 30 5 0.7825546
## 0.1 3 30 10 0.7745236
## 0.1 3 30 15 0.7751295
## 0.1 3 30 20 0.7813343
## 0.1 3 30 25 0.7798549
## 0.1 3 30 30 0.7834061
## 0.1 3 30 35 0.7837024
## 0.1 3 30 40 0.7857722
## 0.1 3 30 45 0.7860684
## 0.1 3 30 50 0.7866567
## 0.1 4 10 5 0.7822473
## 0.1 4 10 10 0.7887439
## 0.1 4 10 15 0.8032517
## 0.1 4 10 20 0.8100360
## 0.1 4 10 25 0.8106395
## 0.1 4 10 30 0.8112343
## 0.1 4 10 35 0.8085850
## 0.1 4 10 40 0.8100513
## 0.1 4 10 45 0.8142082
## 0.1 4 10 50 0.8127224
## 0.1 4 20 5 0.7813694
## 0.1 4 20 10 0.7822297
## 0.1 4 20 15 0.7842753
## 0.1 4 20 20 0.7893168
## 0.1 4 20 25 0.7916916
## 0.1 4 20 30 0.7952407
## 0.1 4 20 35 0.7990948
## 0.1 4 20 40 0.8008813
## 0.1 4 20 45 0.8029511
## 0.1 4 20 50 0.8082626
## 0.1 4 30 5 0.7825546
## 0.1 4 30 10 0.7775065
## 0.1 4 30 15 0.7754105
## 0.1 4 30 20 0.7768875
## 0.1 4 30 25 0.7777743
## 0.1 4 30 30 0.7851796
## 0.1 4 30 35 0.7866698
## 0.1 4 30 40 0.7919812
## 0.1 4 30 45 0.7940619
## 0.1 4 30 50 0.7982013
## 0.1 5 10 5 0.7845980
## 0.1 5 10 10 0.7943409
## 0.1 5 10 15 0.8029337
## 0.1 5 10 20 0.8061995
## 0.1 5 10 25 0.8064979
## 0.1 5 10 30 0.8091603
## 0.1 5 10 35 0.8100536
## 0.1 5 10 40 0.8127115
## 0.1 5 10 45 0.8162649
## 0.1 5 10 50 0.8144849
## 0.1 5 20 5 0.7822583
## 0.1 5 20 10 0.7801797
## 0.1 5 20 15 0.7887351
## 0.1 5 20 20 0.7890226
## 0.1 5 20 25 0.7967178
## 0.1 5 20 30 0.8005741
## 0.1 5 20 35 0.8070927
## 0.1 5 20 40 0.8094499
## 0.1 5 20 45 0.8044260
## 0.1 5 20 50 0.8106352
## 0.1 5 30 5 0.7825546
## 0.1 5 30 10 0.7789769
## 0.1 5 30 15 0.7789682
## 0.1 5 30 20 0.7786588
## 0.1 5 30 25 0.7830945
## 0.1 5 30 30 0.7831055
## 0.1 5 30 35 0.7860751
## 0.1 5 30 40 0.7905020
## 0.1 5 30 45 0.7931687
## 0.1 5 30 50 0.7970227
## 0.2 1 10 5 0.7653406
## 0.2 1 10 10 0.7656326
## 0.2 1 10 15 0.7670988
## 0.2 1 10 20 0.7739027
## 0.2 1 10 25 0.7804190
## 0.2 1 10 30 0.7780531
## 0.2 1 10 35 0.7863495
## 0.2 1 10 40 0.7842907
## 0.2 1 10 45 0.7878420
## 0.2 1 10 50 0.7860685
## 0.2 1 20 5 0.7644517
## 0.2 1 20 10 0.7656304
## 0.2 1 20 15 0.7709463
## 0.2 1 20 20 0.7744931
## 0.2 1 20 25 0.7792362
## 0.2 1 20 30 0.7771752
## 0.2 1 20 35 0.7831099
## 0.2 1 20 40 0.7816262
## 0.2 1 20 45 0.7825151
## 0.2 1 20 50 0.7866524
## 0.2 1 30 5 0.7673885
## 0.2 1 30 10 0.7668112
## 0.2 1 30 15 0.7671162
## 0.2 1 30 20 0.7694844
## 0.2 1 30 25 0.7715498
## 0.2 1 30 30 0.7727415
## 0.2 1 30 35 0.7762927
## 0.2 1 30 40 0.7745171
## 0.2 1 30 45 0.7745171
## 0.2 1 30 50 0.7754060
## 0.2 2 10 5 0.7727371
## 0.2 2 10 10 0.7834039
## 0.2 2 10 15 0.8008639
## 0.2 2 10 20 0.7996851
## 0.2 2 10 25 0.7996743
## 0.2 2 10 30 0.8011580
## 0.2 2 10 35 0.8023606
## 0.2 2 10 40 0.7999967
## 0.2 2 10 45 0.7996917
## 0.2 2 10 50 0.8014652
## 0.2 2 20 5 0.7739267
## 0.2 2 20 10 0.7774671
## 0.2 2 20 15 0.7851512
## 0.2 2 20 20 0.7896196
## 0.2 2 20 25 0.7973082
## 0.2 2 20 30 0.7979008
## 0.2 2 20 35 0.8011798
## 0.2 2 20 40 0.8023606
## 0.2 2 20 45 0.7997005
## 0.2 2 20 50 0.7988094
## 0.2 2 30 5 0.7724474
## 0.2 2 30 10 0.7689225
## 0.2 2 30 15 0.7724519
## 0.2 2 30 20 0.7792930
## 0.2 2 30 25 0.7846045
## 0.2 2 30 30 0.7843016
## 0.2 2 30 35 0.7834367
## 0.2 2 30 40 0.7887657
## 0.2 2 30 45 0.7943823
## 0.2 2 30 50 0.7946743
## 0.2 3 10 5 0.7854912
## 0.2 3 10 10 0.7973169
## 0.2 3 10 15 0.8020643
## 0.2 3 10 20 0.8017658
## 0.2 3 10 25 0.8053170
## 0.2 3 10 30 0.8050119
## 0.2 3 10 35 0.8061883
## 0.2 3 10 40 0.8050163
## 0.2 3 10 45 0.8088594
## 0.2 3 10 50 0.8070970
## 0.2 3 20 5 0.7783733
## 0.2 3 20 10 0.7848788
## 0.2 3 20 15 0.7893257
## 0.2 3 20 20 0.7982124
## 0.2 3 20 25 0.8002996
## 0.2 3 20 30 0.8035327
## 0.2 3 20 35 0.8094871
## 0.2 3 20 40 0.8112431
## 0.2 3 20 45 0.8109489
## 0.2 3 20 50 0.8100491
## 0.2 3 30 5 0.7792821
## 0.2 3 30 10 0.7703929
## 0.2 3 30 15 0.7863712
## 0.2 3 30 20 0.7807592
## 0.2 3 30 25 0.7907961
## 0.2 3 30 30 0.7958288
## 0.2 3 30 35 0.7928900
## 0.2 3 30 40 0.7988006
## 0.2 3 30 45 0.7958377
## 0.2 3 30 50 0.8032298
## 0.2 4 10 5 0.7887199
## 0.2 4 10 10 0.8047092
## 0.2 4 10 15 0.7990927
## 0.2 4 10 20 0.8017724
## 0.2 4 10 25 0.8097550
## 0.2 4 10 30 0.8097507
## 0.2 4 10 35 0.8130209
## 0.2 4 10 40 0.8085677
## 0.2 4 10 45 0.8094872
## 0.2 4 10 50 0.8115481
## 0.2 4 20 5 0.7789814
## 0.2 4 20 10 0.7843104
## 0.2 4 20 15 0.7946524
## 0.2 4 20 20 0.8008616
## 0.2 4 20 25 0.8064825
## 0.2 4 20 30 0.8088486
## 0.2 4 20 35 0.8112146
## 0.2 4 20 40 0.8180076
## 0.2 4 20 45 0.8162495
## 0.2 4 20 50 0.8159532
## 0.2 4 30 5 0.7766088
## 0.2 4 30 10 0.7768985
## 0.2 4 30 15 0.7872515
## 0.2 4 30 20 0.7916718
## 0.2 4 30 25 0.7984845
## 0.2 4 30 30 0.8035150
## 0.2 4 30 35 0.8064760
## 0.2 4 30 40 0.8088441
## 0.2 4 30 45 0.8053083
## 0.2 4 30 50 0.8082561
## 0.2 5 10 5 0.7893323
## 0.2 5 10 10 0.8005654
## 0.2 5 10 15 0.8088772
## 0.2 5 10 20 0.8126940
## 0.2 5 10 25 0.8127049
## 0.2 5 10 30 0.8115416
## 0.2 5 10 35 0.8044370
## 0.2 5 10 40 0.8059075
## 0.2 5 10 45 0.8038400
## 0.2 5 10 50 0.8068030
## 0.2 5 20 5 0.7807591
## 0.2 5 20 10 0.7911013
## 0.2 5 20 15 0.7952517
## 0.2 5 20 20 0.8064847
## 0.2 5 20 25 0.8103322
## 0.2 5 20 30 0.8147877
## 0.2 5 20 35 0.8165677
## 0.2 5 20 40 0.8204000
## 0.2 5 20 45 0.8144870
## 0.2 5 20 50 0.8136069
## 0.2 5 30 5 0.7798703
## 0.2 5 30 10 0.7739333
## 0.2 5 30 15 0.7795609
## 0.2 5 30 20 0.7872471
## 0.2 5 30 25 0.7943583
## 0.2 5 30 30 0.7979073
## 0.2 5 30 35 0.8020489
## 0.2 5 30 40 0.8097550
## 0.2 5 30 45 0.8067986
## 0.2 5 30 50 0.8044238
## 0.3 1 10 5 0.7629877
## 0.3 1 10 10 0.7665432
## 0.3 1 10 15 0.7759878
## 0.3 1 10 20 0.7795500
## 0.3 1 10 25 0.7807374
## 0.3 1 10 30 0.7836916
## 0.3 1 10 35 0.7860729
## 0.3 1 10 40 0.7872494
## 0.3 1 10 45 0.7869531
## 0.3 1 10 50 0.7810315
## 0.3 1 20 5 0.7709289
## 0.3 1 20 10 0.7709463
## 0.3 1 20 15 0.7751251
## 0.3 1 20 20 0.7798418
## 0.3 1 20 25 0.7783538
## 0.3 1 20 30 0.7792667
## 0.3 1 20 35 0.7842755
## 0.3 1 20 40 0.7813300
## 0.3 1 20 45 0.7786697
## 0.3 1 20 50 0.7810292
## 0.3 1 30 5 0.7694604
## 0.3 1 30 10 0.7670770
## 0.3 1 30 15 0.7727393
## 0.3 1 30 20 0.7706565
## 0.3 1 30 25 0.7712688
## 0.3 1 30 30 0.7736501
## 0.3 1 30 35 0.7754192
## 0.3 1 30 40 0.7777764
## 0.3 1 30 45 0.7807635
## 0.3 1 30 50 0.7766022
## 0.3 2 10 5 0.7688984
## 0.3 2 10 10 0.7952495
## 0.3 2 10 15 0.8044216
## 0.3 2 10 20 0.7999771
## 0.3 2 10 25 0.8002756
## 0.3 2 10 30 0.8002691
## 0.3 2 10 35 0.8038465
## 0.3 2 10 40 0.8059009
## 0.3 2 10 45 0.8047331
## 0.3 2 10 50 0.8064978
## 0.3 2 20 5 0.7706652
## 0.3 2 20 10 0.7893124
## 0.3 2 20 15 0.7934674
## 0.3 2 20 20 0.7997028
## 0.3 2 20 25 0.8020688
## 0.3 2 20 30 0.8005982
## 0.3 2 20 35 0.8056242
## 0.3 2 20 40 0.8094696
## 0.3 2 20 45 0.8094630
## 0.3 2 20 50 0.8097441
## 0.3 2 30 5 0.7668286
## 0.3 2 30 10 0.7759986
## 0.3 2 30 15 0.7845825
## 0.3 2 30 20 0.7869814
## 0.3 2 30 25 0.7854759
## 0.3 2 30 30 0.7902036
## 0.3 2 30 35 0.7887287
## 0.3 2 30 40 0.8014521
## 0.3 2 30 45 0.7976024
## 0.3 2 30 50 0.8014476
## 0.3 3 10 5 0.7872383
## 0.3 3 10 10 0.8032321
## 0.3 3 10 15 0.8020578
## 0.3 3 10 20 0.8035415
## 0.3 3 10 25 0.8044347
## 0.3 3 10 30 0.8056111
## 0.3 3 10 35 0.8118247
## 0.3 3 10 40 0.8053193
## 0.3 3 10 45 0.8082626
## 0.3 3 10 50 0.8070818
## 0.3 3 20 5 0.7789771
## 0.3 3 20 10 0.7943605
## 0.3 3 20 15 0.7993868
## 0.3 3 20 20 0.8100491
## 0.3 3 20 25 0.8085589
## 0.3 3 20 30 0.8103476
## 0.3 3 20 35 0.8130209
## 0.3 3 20 40 0.8118291
## 0.3 3 20 45 0.8100688
## 0.3 3 20 50 0.8121321
## 0.3 3 30 5 0.7760032
## 0.3 3 30 10 0.7837135
## 0.3 3 30 15 0.7881273
## 0.3 3 30 20 0.7955347
## 0.3 3 30 25 0.7973170
## 0.3 3 30 30 0.8020577
## 0.3 3 30 35 0.8065023
## 0.3 3 30 40 0.8056025
## 0.3 3 30 45 0.8124085
## 0.3 3 30 50 0.8094522
## 0.3 4 10 5 0.7914216
## 0.3 4 10 10 0.8044435
## 0.3 4 10 15 0.8029532
## 0.3 4 10 20 0.8014718
## 0.3 4 10 25 0.8091667
## 0.3 4 10 30 0.8085698
## 0.3 4 10 35 0.8064805
## 0.3 4 10 40 0.8088597
## 0.3 4 10 45 0.8032060
## 0.3 4 10 50 0.8002779
## 0.3 4 20 5 0.7766132
## 0.3 4 20 10 0.7943364
## 0.3 4 20 15 0.7999903
## 0.3 4 20 20 0.8044326
## 0.3 4 20 25 0.8088727
## 0.3 4 20 30 0.8112496
## 0.3 4 20 35 0.8100426
## 0.3 4 20 40 0.8088617
## 0.3 4 20 45 0.8097463
## 0.3 4 20 50 0.8088705
## 0.3 4 30 5 0.7733495
## 0.3 4 30 10 0.7795389
## 0.3 4 30 15 0.7904824
## 0.3 4 30 20 0.8011491
## 0.3 4 30 25 0.8020489
## 0.3 4 30 30 0.8038574
## 0.3 4 30 35 0.8097637
## 0.3 4 30 40 0.8139054
## 0.3 4 30 45 0.8112301
## 0.3 4 30 50 0.8121298
## 0.3 5 10 5 0.7896197
## 0.3 5 10 10 0.8011842
## 0.3 5 10 15 0.7982321
## 0.3 5 10 20 0.8014827
## 0.3 5 10 25 0.8008968
## 0.3 5 10 30 0.8094764
## 0.3 5 10 35 0.8038379
## 0.3 5 10 40 0.8032452
## 0.3 5 10 45 0.8035328
## 0.3 5 10 50 0.8044172
## 0.3 5 20 5 0.7828288
## 0.3 5 20 10 0.7979292
## 0.3 5 20 15 0.8070925
## 0.3 5 20 20 0.8109445
## 0.3 5 20 25 0.8141798
## 0.3 5 20 30 0.8130077
## 0.3 5 20 35 0.8159532
## 0.3 5 20 40 0.8124065
## 0.3 5 20 45 0.8115242
## 0.3 5 20 50 0.8088553
## 0.3 5 30 5 0.7733320
## 0.3 5 30 10 0.7792449
## 0.3 5 30 15 0.7922952
## 0.3 5 30 20 0.8005741
## 0.3 5 30 25 0.8064891
## 0.3 5 30 30 0.8076743
## 0.3 5 30 35 0.8088639
## 0.3 5 30 40 0.8082627
## 0.3 5 30 45 0.8115242
## 0.3 5 30 50 0.8100426
## Kappa Accuracy SD Kappa SD
## 0.5076039 0.04109361 0.08625388
## 0.5075779 0.04036660 0.08278741
## 0.5096842 0.04089764 0.08441598
## 0.5125854 0.04194913 0.08649251
## 0.5151579 0.04249631 0.08761360
## 0.5189609 0.04085342 0.08474285
## 0.5268325 0.04268683 0.08845805
## 0.5226071 0.04398196 0.09038121
## 0.5377509 0.04815179 0.09983048
## 0.5522024 0.04537137 0.09274322
## 0.5148522 0.04690653 0.09776215
## 0.5143781 0.04557419 0.09404177
## 0.5124787 0.04643057 0.09657169
## 0.5176696 0.04816493 0.10003366
## 0.5211326 0.05030914 0.10434950
## 0.5194282 0.04762548 0.09840924
## 0.5239292 0.04869914 0.10054480
## 0.5218169 0.04553362 0.09342422
## 0.5261565 0.04281365 0.08773389
## 0.5284063 0.04429297 0.09036232
## 0.5096842 0.04089764 0.08441598
## 0.5184834 0.04699744 0.09746740
## 0.5096842 0.04089764 0.08441598
## 0.5138082 0.04238335 0.08715462
## 0.5152669 0.04277144 0.08795833
## 0.5129152 0.04233791 0.08675609
## 0.5086150 0.04202676 0.08582201
## 0.5094311 0.04434393 0.09012278
## 0.5111905 0.04318451 0.08829421
## 0.5189913 0.04327424 0.08807619
## 0.5175588 0.02955306 0.06099920
## 0.5013281 0.03731496 0.07342117
## 0.5121850 0.03797362 0.07542406
## 0.5327311 0.03862864 0.07848536
## 0.5531304 0.03573868 0.07272478
## 0.5728126 0.03283221 0.06661084
## 0.5755592 0.03461442 0.07131651
## 0.5748925 0.03836310 0.08139844
## 0.5733039 0.03454678 0.07166469
## 0.5756245 0.03245140 0.06730315
## 0.5213100 0.02152455 0.05095544
## 0.5078162 0.03784780 0.07526784
## 0.5011413 0.03772270 0.07459307
## 0.5222073 0.04018724 0.07902225
## 0.5377672 0.03852563 0.07825214
## 0.5487356 0.03902357 0.07981537
## 0.5594051 0.03405851 0.07093463
## 0.5708445 0.03416711 0.06997745
## 0.5675487 0.03747646 0.07736933
## 0.5760492 0.03485519 0.07229500
## 0.5213100 0.02152455 0.05095544
## 0.5141004 0.03128100 0.06776064
## 0.5062801 0.03251339 0.06590047
## 0.5054374 0.03108089 0.06284462
## 0.5165689 0.03513114 0.07021495
## 0.5310920 0.03712679 0.07574970
## 0.5302199 0.03325284 0.06819921
## 0.5389278 0.03808922 0.07891001
## 0.5322533 0.03797813 0.07925735
## 0.5384944 0.03187188 0.06692075
## 0.5183923 0.02297541 0.05138336
## 0.5176027 0.03201758 0.06379236
## 0.5489239 0.03039948 0.06503384
## 0.5761347 0.03134652 0.06335007
## 0.5826072 0.03154359 0.06439724
## 0.5851293 0.03120455 0.06523071
## 0.5818726 0.03251205 0.06837112
## 0.5907046 0.03192052 0.06552983
## 0.5916830 0.02959812 0.06073760
## 0.5875177 0.03077353 0.06402562
## 0.5213100 0.02152455 0.05095544
## 0.5092355 0.03742428 0.07470615
## 0.5159406 0.04203777 0.08433922
## 0.5478035 0.03694859 0.07551868
## 0.5557258 0.04015328 0.08266016
## 0.5676968 0.03434081 0.07128932
## 0.5759916 0.03629467 0.07558158
## 0.5791580 0.03584918 0.07508882
## 0.5791266 0.03251351 0.06710495
## 0.5764155 0.03254344 0.06915580
## 0.5213100 0.02152455 0.05095544
## 0.5080019 0.03698989 0.07280167
## 0.5113073 0.02953740 0.06184614
## 0.5273182 0.03267575 0.06922616
## 0.5271039 0.03249820 0.06699687
## 0.5366589 0.03786335 0.07765569
## 0.5387421 0.03903135 0.08054338
## 0.5429512 0.03777564 0.07852863
## 0.5441142 0.03770652 0.07877465
## 0.5470530 0.03685731 0.07717848
## 0.5232440 0.02454842 0.05699751
## 0.5454102 0.02764014 0.05840005
## 0.5793553 0.03210739 0.07044302
## 0.5959995 0.02856420 0.06010641
## 0.5981550 0.02658368 0.05474358
## 0.6002488 0.02663878 0.05598578
## 0.5950835 0.02749477 0.05832082
## 0.5991693 0.03020445 0.06441936
## 0.6085242 0.03199389 0.06838405
## 0.6060848 0.03256386 0.06952893
## 0.5190530 0.02298929 0.05365006
## 0.5241182 0.02828445 0.06279925
## 0.5343323 0.03650077 0.07897491
## 0.5482101 0.03329880 0.07189492
## 0.5551829 0.03419294 0.07319042
## 0.5646453 0.03651268 0.07755369
## 0.5741573 0.03327655 0.07076414
## 0.5789351 0.03132005 0.06616363
## 0.5838577 0.02930055 0.06211104
## 0.5950659 0.02822253 0.05985576
## 0.5213100 0.02152455 0.05095544
## 0.5129001 0.02551997 0.05532715
## 0.5143028 0.03680123 0.07461167
## 0.5210360 0.03972924 0.08163682
## 0.5253807 0.03840247 0.07947669
## 0.5417008 0.03802720 0.07989643
## 0.5464618 0.03973444 0.08429474
## 0.5591978 0.04384399 0.09134254
## 0.5644824 0.03952669 0.08309843
## 0.5732771 0.03611418 0.07591907
## 0.5284078 0.02380003 0.05473521
## 0.5566749 0.03418736 0.07660423
## 0.5795601 0.03295329 0.07133374
## 0.5880549 0.03116554 0.06688114
## 0.5894423 0.02819350 0.06100916
## 0.5958218 0.02912897 0.06300663
## 0.5984637 0.03081703 0.06632380
## 0.6051336 0.03164944 0.06772540
## 0.6130816 0.03372100 0.07173444
## 0.6103864 0.03614719 0.07651870
## 0.5211476 0.02174908 0.05131352
## 0.5198622 0.02529036 0.05730606
## 0.5447671 0.03361916 0.07361804
## 0.5494535 0.03217431 0.06704887
## 0.5678168 0.03011052 0.06290892
## 0.5772009 0.02945917 0.06179046
## 0.5924384 0.03436586 0.07326183
## 0.5976637 0.03319264 0.06984863
## 0.5878723 0.03450372 0.07338230
## 0.6015569 0.03102212 0.06512620
## 0.5213100 0.02152455 0.05095544
## 0.5158157 0.02797872 0.05910639
## 0.5211805 0.03293776 0.06891332
## 0.5241776 0.03544275 0.07358851
## 0.5364619 0.04158817 0.08542879
## 0.5379413 0.03705418 0.07788416
## 0.5459351 0.03166404 0.06666944
## 0.5570653 0.03668386 0.07642142
## 0.5634764 0.03602403 0.07542007
## 0.5720147 0.03589099 0.07582715
## 0.5096842 0.04089764 0.08441598
## 0.5097745 0.04042629 0.08382582
## 0.5113034 0.04028399 0.08190335
## 0.5280877 0.04328993 0.08949897
## 0.5427489 0.04542295 0.09173215
## 0.5388583 0.04392948 0.08916430
## 0.5559891 0.04237092 0.08631715
## 0.5514131 0.03770301 0.07735375
## 0.5594434 0.03954732 0.08125163
## 0.5555267 0.04101671 0.08454199
## 0.5065067 0.04000939 0.08188262
## 0.5099226 0.04110228 0.08426382
## 0.5202525 0.04402044 0.08958087
## 0.5290694 0.04691860 0.09668624
## 0.5404020 0.04625627 0.09508709
## 0.5367168 0.04154235 0.08470142
## 0.5492057 0.04051175 0.08295952
## 0.5465520 0.03830180 0.07826517
## 0.5484461 0.03701835 0.07596669
## 0.5575396 0.04079483 0.08395236
## 0.5125757 0.04551904 0.09405954
## 0.5132541 0.04233581 0.08730651
## 0.5141972 0.04737213 0.09703677
## 0.5172625 0.04406786 0.09041093
## 0.5218390 0.04582741 0.09341824
## 0.5257537 0.04423183 0.09154254
## 0.5338981 0.04639196 0.09574870
## 0.5298938 0.04709359 0.09658647
## 0.5297235 0.04427554 0.09167856
## 0.5315917 0.04560200 0.09470374
## 0.5079217 0.03853810 0.07627750
## 0.5360035 0.03524754 0.06972443
## 0.5739809 0.02615674 0.05398488
## 0.5747495 0.02801653 0.05824022
## 0.5762993 0.02613900 0.05267640
## 0.5801644 0.02994956 0.06217244
## 0.5837482 0.03072015 0.06434400
## 0.5786283 0.03082365 0.06446365
## 0.5782029 0.03342865 0.06948328
## 0.5820599 0.03249122 0.06758447
## 0.5075192 0.03639621 0.07580686
## 0.5206488 0.03481448 0.07139675
## 0.5409527 0.03389840 0.06868138
## 0.5519179 0.03932030 0.08155925
## 0.5703539 0.03685034 0.07738060
## 0.5721592 0.03821345 0.07983189
## 0.5793062 0.03274957 0.06818837
## 0.5821861 0.03734070 0.07817908
## 0.5772583 0.03350335 0.06955575
## 0.5752508 0.03111882 0.06356680
## 0.5054414 0.03721578 0.07392187
## 0.5014728 0.03258299 0.06757576
## 0.5136569 0.03671668 0.07512743
## 0.5288001 0.03911664 0.08216517
## 0.5425643 0.03773109 0.07919908
## 0.5428113 0.04025326 0.08417897
## 0.5421458 0.04164559 0.08755444
## 0.5531057 0.03870218 0.08179105
## 0.5653479 0.03702377 0.07863791
## 0.5659117 0.02997941 0.06337842
## 0.5355387 0.02755000 0.05764481
## 0.5682288 0.03150435 0.06734523
## 0.5806250 0.03024239 0.06471188
## 0.5818961 0.02982371 0.06318456
## 0.5898285 0.02852691 0.05891095
## 0.5897497 0.03179742 0.06652565
## 0.5928928 0.03423097 0.07040280
## 0.5907854 0.03443952 0.07040868
## 0.5989032 0.03445367 0.07087042
## 0.5956191 0.03389762 0.06959290
## 0.5162144 0.03101454 0.06443504
## 0.5382354 0.03966719 0.08405207
## 0.5530446 0.03535511 0.07440991
## 0.5727021 0.03274281 0.06810121
## 0.5779696 0.03160342 0.06779031
## 0.5851008 0.03484363 0.07418638
## 0.5987294 0.03265857 0.06847261
## 0.6033878 0.03330392 0.06936604
## 0.6015052 0.03618210 0.07661692
## 0.6006915 0.03505363 0.07414880
## 0.5157394 0.02363133 0.05414740
## 0.5063243 0.03909304 0.08285609
## 0.5429770 0.03145474 0.06685636
## 0.5330626 0.03763184 0.08145356
## 0.5570273 0.03948657 0.08265040
## 0.5683632 0.03730431 0.07849854
## 0.5631842 0.03663926 0.07678405
## 0.5758562 0.03483930 0.07315695
## 0.5712759 0.03045508 0.06327053
## 0.5869201 0.03721804 0.07814438
## 0.5471224 0.03383751 0.07245848
## 0.5851025 0.02875253 0.06083880
## 0.5754297 0.03077736 0.06437173
## 0.5818841 0.03110770 0.06679376
## 0.6002900 0.02942571 0.06159563
## 0.6011870 0.03030955 0.06426296
## 0.6079054 0.02847538 0.06059109
## 0.5990938 0.02417482 0.05233494
## 0.6013742 0.02210729 0.04810795
## 0.6061870 0.02791413 0.05881502
## 0.5171456 0.02503762 0.05743251
## 0.5387677 0.03297126 0.06992072
## 0.5639126 0.03331173 0.07277313
## 0.5808149 0.03127880 0.06619241
## 0.5927774 0.02720043 0.05811248
## 0.5991408 0.03406167 0.07042201
## 0.6047117 0.03330791 0.06925659
## 0.6189718 0.02876857 0.05908081
## 0.6154176 0.02933371 0.06084238
## 0.6145587 0.02983024 0.06136669
## 0.5108602 0.02753795 0.05908533
## 0.5200771 0.02963807 0.06317179
## 0.5448621 0.03163938 0.06643466
## 0.5572472 0.03715770 0.07711604
## 0.5729225 0.03819616 0.07986788
## 0.5849380 0.04387361 0.09126109
## 0.5915193 0.03492118 0.07253683
## 0.5982519 0.03531545 0.07359388
## 0.5905825 0.03301882 0.06948311
## 0.5968970 0.02975709 0.06225711
## 0.5481971 0.03105093 0.06775289
## 0.5772178 0.02378279 0.04990814
## 0.5971521 0.02734852 0.05777045
## 0.6066114 0.02748552 0.05777791
## 0.6075743 0.02789555 0.05801328
## 0.6053878 0.02752251 0.05761901
## 0.5907568 0.02862461 0.06049590
## 0.5940568 0.02869773 0.05988225
## 0.5901794 0.02382209 0.04986138
## 0.5968362 0.02389333 0.04969293
## 0.5223668 0.02616293 0.05792231
## 0.5523792 0.02878512 0.06159664
## 0.5660404 0.02952033 0.06356401
## 0.5915798 0.02519588 0.05303270
## 0.6020469 0.02752672 0.05668169
## 0.6119612 0.02517679 0.05263668
## 0.6149341 0.02421316 0.05030188
## 0.6228926 0.02930726 0.06109909
## 0.6112014 0.02558445 0.05293903
## 0.6096875 0.02772749 0.05825149
## 0.5170963 0.02476453 0.05553599
## 0.5151831 0.03428780 0.07097545
## 0.5307831 0.03262224 0.06886704
## 0.5506689 0.03772972 0.07864446
## 0.5670876 0.03468113 0.07156817
## 0.5751079 0.03111586 0.06496373
## 0.5839473 0.03177174 0.06729742
## 0.6006997 0.02424229 0.05127555
## 0.5945101 0.02645968 0.05671359
## 0.5897804 0.02693891 0.05647164
## 0.5042317 0.04384368 0.09169462
## 0.5116983 0.04635709 0.09471758
## 0.5313406 0.04366831 0.09057961
## 0.5417169 0.03600518 0.07295383
## 0.5442813 0.03760072 0.07806973
## 0.5506486 0.03492069 0.07075305
## 0.5546959 0.03571396 0.07309115
## 0.5568940 0.04199370 0.08714508
## 0.5564235 0.04430977 0.09116239
## 0.5444169 0.04369730 0.09047547
## 0.5212752 0.04707608 0.09720894
## 0.5214658 0.04499715 0.09306589
## 0.5309629 0.04174981 0.08537250
## 0.5422248 0.04156958 0.08675282
## 0.5400004 0.04451907 0.09187509
## 0.5411602 0.03883559 0.08014758
## 0.5513452 0.04385616 0.09079675
## 0.5450848 0.03872794 0.08008243
## 0.5402264 0.03435820 0.07034475
## 0.5449724 0.03538585 0.07296943
## 0.5188928 0.04727114 0.09785920
## 0.5137496 0.04858935 0.10136736
## 0.5259463 0.04446813 0.09003924
## 0.5206879 0.04832771 0.09887403
## 0.5227818 0.04496342 0.09210506
## 0.5283646 0.03762565 0.07612483
## 0.5311199 0.04211432 0.08647997
## 0.5358893 0.04620546 0.09478386
## 0.5415556 0.03892112 0.08122184
## 0.5337292 0.04504885 0.09346850
## 0.5044123 0.03775535 0.07447129
## 0.5642861 0.03142521 0.06605216
## 0.5863658 0.02643911 0.05574419
## 0.5788642 0.03157367 0.06709909
## 0.5805628 0.03552186 0.07430208
## 0.5802454 0.03754532 0.07901513
## 0.5887020 0.03661169 0.07723999
## 0.5935198 0.03418836 0.07300737
## 0.5912376 0.03279460 0.06912068
## 0.5954065 0.03463777 0.07258563
## 0.5089089 0.03655702 0.07330838
## 0.5502465 0.03551789 0.07336626
## 0.5628419 0.03490337 0.07189782
## 0.5760193 0.02298250 0.04879009
## 0.5821927 0.02977339 0.06225723
## 0.5800978 0.03052812 0.06414805
## 0.5906182 0.02667596 0.05631229
## 0.5991200 0.02777143 0.05892695
## 0.5988207 0.03564606 0.07645734
## 0.6001534 0.03607723 0.07664771
## 0.4989912 0.03302064 0.06698692
## 0.5208135 0.03716078 0.07714448
## 0.5422144 0.03392747 0.06919272
## 0.5477268 0.03304372 0.07001594
## 0.5454116 0.03798427 0.08016327
## 0.5562474 0.03870330 0.08041220
## 0.5550359 0.03518586 0.07339118
## 0.5817618 0.03630595 0.07601738
## 0.5744521 0.02986221 0.06199226
## 0.5821185 0.03600664 0.07428438
## 0.5441500 0.04197669 0.09029240
## 0.5841730 0.03171718 0.06397713
## 0.5834974 0.03399715 0.07024507
## 0.5867952 0.03128235 0.06673191
## 0.5890839 0.03428360 0.07308671
## 0.5916379 0.03414146 0.07275355
## 0.6053033 0.03153638 0.06636247
## 0.5925895 0.03097384 0.06430859
## 0.5986427 0.03381693 0.07090420
## 0.5961111 0.02935593 0.06152150
## 0.5226873 0.02758189 0.06096110
## 0.5632308 0.03816074 0.08161615
## 0.5749646 0.03041004 0.06504771
## 0.5997318 0.03525065 0.07495393
## 0.5973271 0.02959861 0.06275124
## 0.6016746 0.03006988 0.06406117
## 0.6073858 0.03462254 0.07299245
## 0.6058377 0.03301105 0.06848608
## 0.6020970 0.03125907 0.06454750
## 0.6057274 0.03241306 0.06752622
## 0.5148866 0.02905466 0.06433447
## 0.5390347 0.03444367 0.07208687
## 0.5498964 0.04034992 0.08495636
## 0.5691522 0.03893100 0.08172473
## 0.5729750 0.03301208 0.07051275
## 0.5841490 0.02770665 0.05794515
## 0.5936804 0.02405845 0.05203295
## 0.5919237 0.02549919 0.05342341
## 0.6058790 0.02843001 0.05988551
## 0.5999448 0.02753489 0.05859149
## 0.5552277 0.03164579 0.06690612
## 0.5869941 0.02537365 0.05411274
## 0.5867479 0.02977445 0.06139830
## 0.5846483 0.03051675 0.06451691
## 0.6007183 0.02836043 0.05951653
## 0.5995462 0.02510463 0.05209373
## 0.5967910 0.02685240 0.05463060
## 0.6008504 0.02893028 0.06099129
## 0.5897348 0.03273025 0.06770714
## 0.5838191 0.02802303 0.05836531
## 0.5209105 0.03655691 0.07452222
## 0.5635245 0.03541104 0.07421372
## 0.5779275 0.03093168 0.06593276
## 0.5889012 0.02866678 0.06051698
## 0.5986066 0.02909130 0.06081404
## 0.6041638 0.03004180 0.06282546
## 0.6016781 0.03020032 0.06330321
## 0.5992187 0.03053641 0.06493718
## 0.6017382 0.02806929 0.05880999
## 0.6001568 0.03377323 0.07066079
## 0.5120004 0.03332007 0.07139964
## 0.5301313 0.03469333 0.07131935
## 0.5566584 0.03874601 0.08242654
## 0.5804191 0.03394473 0.07152096
## 0.5836423 0.03216495 0.06764591
## 0.5887043 0.02847678 0.06055578
## 0.6018528 0.02752930 0.05873195
## 0.6104733 0.02355763 0.04976941
## 0.6046108 0.03010337 0.06286530
## 0.6067995 0.02414104 0.05078873
## 0.5520928 0.03020684 0.06206806
## 0.5799999 0.02759902 0.05974073
## 0.5758925 0.03759393 0.08009871
## 0.5846172 0.03451766 0.07274120
## 0.5839624 0.03765868 0.07840593
## 0.6020309 0.03161781 0.06545618
## 0.5897636 0.03581917 0.07437561
## 0.5891368 0.03432899 0.07127742
## 0.5899718 0.03482340 0.07264926
## 0.5920343 0.03432148 0.07072547
## 0.5336794 0.04045648 0.08430304
## 0.5736655 0.04120289 0.08451669
## 0.5948249 0.03199455 0.06570885
## 0.6026876 0.02995352 0.06227179
## 0.6108138 0.03077921 0.06367999
## 0.6082740 0.02804759 0.05863661
## 0.6142975 0.02844371 0.06003546
## 0.6074679 0.02931430 0.06172579
## 0.6056868 0.02681293 0.05639974
## 0.6002665 0.03161779 0.06557887
## 0.5104267 0.03222468 0.06566327
## 0.5332100 0.04378971 0.09090689
## 0.5617907 0.03623420 0.07596338
## 0.5806184 0.03298525 0.06823559
## 0.5943340 0.02943948 0.06157529
## 0.5970835 0.03087593 0.06494774
## 0.5999543 0.02633078 0.05563549
## 0.5988983 0.02944703 0.06202289
## 0.6051584 0.02715112 0.05723168
## 0.6021276 0.02462742 0.05376976
##
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were n.trees = 40, interaction.depth
## = 5, shrinkage = 0.2 and n.minobsinnode = 20.trellis.par.set(caretTheme())
plot(gbmFit)
ggplot(gbmFit)
##Accuracy 0.8118678 (Stand.Dev. 0.03860621)