Internship Presentation

Dorcas Oluwadare

2024-06-20

Introduction to R

Summary on Data Import.

R is is a free open source programming language that serves as a powerful tool for statistical computations, data analysis and data visualization.
The first step in using R for analysis is Importation of data using the tidyverse library, readr package for csv file with code: Object <- read_csv(“Data.csv”) , while using the readxl package with code: object <- read_excel(“Data.xslx”).

Summary on Data Wrangling

The next step is Data Wrangling using the five main functions which are: filter(), arrange(), mutate, summarize() and select().

Function	Task
filter()	is used to pick observations by their values through the use of logical commands or %in%.
arrange()	is used to reorder a data set.
mutate()	is used to create new variables with functions of existing variables.
summarize()	is used to collapse many values down to a summary.
select()	is used to pick variables by their names.

These functions are found in dplyr package of tidyverse,
The pipe ( %>% ) is also very important in data wrangling, it allows you to chain together a sequence of operations.

Graphics In R package

Graphics are visual images used to illustrate, inform or entertain.

Graphics can be done in R with different packages :

Graphics package

Lattice package 

 Ggplot2 package

Graphics using ggplot2 in R

Graphics in ggplot2 is based on the “grammar of graphics”. The ggplot2 package is loaded into the tidyverse library. The base form of the ggplot2 code line is :

A <- ggplot(data) +
  aes(x= var_x , y= var_y) +
  geom_x()

Function	Task
ggplot()	is used to call the data
aes()	is used to specify the variables of the data that will be used to plot the graph on the axes of the graph.
geom_x()	where x is used to specify the type of graph to be created and example being geom_boxplot().
labs()	is used to add extras to the graph such as title, subtitle, captions
themes_x()	where x is used to specify the theme displayed.

Practical Example

Import the barrero.maize data set and save it as maize
Visualize the relationship between earheight in the x-axis and yield in they-axis by location (choose any four locations of your choice).
change the shape of the points (choose one as you see fit).
Add a title sub-tile caption change the x-axis and y-axis labels.
Visualize this relationship in a plot with different panels (the number of panels is the number of selected locations).

Results

maize <- read_csv("data/barrero.maize.csv")

## Rows: 14568 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (4): loc, env, rep, gen
## dbl (10): year, yor, daystoflower, plantheight, earheight, population, lodge...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

maize

## # A tibble: 14,568 × 14
##     year   yor loc   env    rep   gen   daystoflower plantheight earheight
##    <dbl> <dbl> <chr> <chr>  <chr> <chr>        <dbl>       <dbl>     <dbl>
##  1  2000  2000 BA    2000BA R1    9211            78        234.      83.8
##  2  2000  2000 BA    2000BA R2    9211            77        236.      76.2
##  3  2000  2000 BA    2000BA R3    9211            77        229.      78.7
##  4  2000  2000 BA    2000BA R4    9211            78        241.      88.9
##  5  2000  2000 BA    2000BA R1    9114            77        244.      88.9
##  6  2000  2000 BA    2000BA R2    9114            78        236.      78.7
##  7  2000  2000 BA    2000BA R3    9114            77        239.      94.0
##  8  2000  2000 BA    2000BA R4    9114            78        231.      91.4
##  9  2000  2000 BA    2000BA R1    8216            80        246.      88.9
## 10  2000  2000 BA    2000BA R2    8216            81        236.      88.9
## # ℹ 14,558 more rows
## # ℹ 5 more variables: population <dbl>, lodged <dbl>, moisture <dbl>,
## #   testweight <dbl>, yield <dbl>

unique(maize$loc)

##  [1] "BA" "CA" "CC" "CS" "DU" "GR" "PR" "SL" "WE" "WH" "HW" "DA" "HO" "TY" "LE"
## [16] "TH"

maize %>% 
  filter(loc %in% c("DU", "GR", "PR", "CS")) %>%
  ggplot() +
  aes(x = earheight, y = yield, fill=loc) +
  geom_point(shape=21, colour="black", size=3, fill="blue") +
  labs(title = "Multi-environment Trial of Maize In Texas",
       subtitle = "Period::2000-2010",
       caption = "Data::agridat:barrero.maize",
       x = "Earheight (cm)",
       y = "Yield (Mt/ha)"
  ) +
  facet_grid(.~ loc) +
  scale_color_discrete("Location") +
  theme_classic()

Regression Line

Regression is used to predict the value of “y” for a given value of “x”.
The regression line is added to a plot using the geom_smooth(method = lm).
The geom_smooth function is used to create a regression line fitted to the data, which expresses the relationship in a scatter plot of different points, showing the trend or correlation between the independent and dependent variables.

Practical Example

Import the australia.soybean data set and save it in an object (choose an appropriate object name).
Visualize the relationship between oil in the x-axis and protein in the y-axis by location.
change the shape of the points (choose one as you see fit).
Add a title, sub-tile, caption, change the x-axis and y-axis labels.
Visualize this relationship in a plot with different panels.

Results

soyBean.aus <- read_csv("data/australia.soybean.csv")

## Rows: 464 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): env, loc, gen
## dbl (7): year, yield, height, lodging, size, protein, oil
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

p <- ggplot(soyBean.aus) +
  aes(x= oil, y = protein) +
  geom_point(shape= 20, color = "pink", fill= "red", size= 4)
p <- p + geom_smooth(method = lm)
p <- p +
  labs(title = "Soybeans, Protein and Oil in Austrlia",
       subtitle = "Period 1970-1971",
       caption = "Data::agridat::Australia.soybean",
       x= "Oil (%)",
       y= "Protein(%)"
       )
p <- p+ scale_size_continuous("Protein")
p <- p + theme_classic()
p + facet_grid(.~ env)

## `geom_smooth()` using formula = 'y ~ x'

Density Plot and Histogram

Density plot is used to represent the distribution of data, it can also be used in the same context as a histogram.
Histogram and density plot only has input values for the x axis while the y displays the count or density. A density curve may be preferred to a histogram as it shows better skewness and number of peaks in the data
It is important to note that:

A left skew shows that the mean of the data is less than the median.

A right skew shows the mean is greater than the median.

No skew shows the mean is equal to the median.

Skewness In Density Curve

Practical Example

a <- ggplot(soyBean.aus) +
  aes(x = yield, color= env, fill= env)+
  geom_density(alpha= 0.25)
a <- a + scale_fill_discrete(name = "Environment")
a <- a +guides(color = FALSE)
a <- a+ facet_grid(.~env)

a <- a + theme_classic()
a <-  a + guides(fill= FALSE)
a

Boxplot

Boxplots are used to show distributions of numeric data values which will be compared.
It gives information on the data’s skewness, variability, outliers and symmetry.

Skewness in Boxplot

A negative skew shows that the mean of the data is less than the median.
A Positive skew shows that the mean of the data is greater than the median.
A No skew shows that the mean and median are equal.

Practical Example

Import the barrero.maize into R.
Make a summary of the table: calculate and display the mean,standard deviation, variance, number of observations by year.
Display the boxplot of earheight by year using colors.
Add a title Change the x-axis label Change the y-axis label remove the legend.

Results

maize <- read_csv("data/barrero.maize.csv")

## Rows: 14568 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (4): loc, env, rep, gen
## dbl (10): year, yor, daystoflower, plantheight, earheight, population, lodge...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

maize

## # A tibble: 14,568 × 14
##     year   yor loc   env    rep   gen   daystoflower plantheight earheight
##    <dbl> <dbl> <chr> <chr>  <chr> <chr>        <dbl>       <dbl>     <dbl>
##  1  2000  2000 BA    2000BA R1    9211            78        234.      83.8
##  2  2000  2000 BA    2000BA R2    9211            77        236.      76.2
##  3  2000  2000 BA    2000BA R3    9211            77        229.      78.7
##  4  2000  2000 BA    2000BA R4    9211            78        241.      88.9
##  5  2000  2000 BA    2000BA R1    9114            77        244.      88.9
##  6  2000  2000 BA    2000BA R2    9114            78        236.      78.7
##  7  2000  2000 BA    2000BA R3    9114            77        239.      94.0
##  8  2000  2000 BA    2000BA R4    9114            78        231.      91.4
##  9  2000  2000 BA    2000BA R1    8216            80        246.      88.9
## 10  2000  2000 BA    2000BA R2    8216            81        236.      88.9
## # ℹ 14,558 more rows
## # ℹ 5 more variables: population <dbl>, lodged <dbl>, moisture <dbl>,
## #   testweight <dbl>, yield <dbl>

maize %>% 
  group_by(year) %>% 
  summarise(
    Mean_PL = mean(plantheight, na.rm = TRUE),
    SD_PL = sd(plantheight, na.rm = TRUE),
    Variance_PL = var(plantheight, na.rm = TRUE),
    N_PL = n(),
    Mean_TW = mean(testweight, na.rm = TRUE),
    SD_TW = sd(testweight, na.rm = TRUE),
    Variance_TW = var(testweight, na.rm = TRUE),
    N_TW = n()
  )

## # A tibble: 11 × 9
##     year Mean_PL SD_PL Variance_PL  N_PL Mean_TW SD_TW Variance_TW  N_TW
##    <dbl>   <dbl> <dbl>       <dbl> <int>   <dbl> <dbl>       <dbl> <int>
##  1  2000    238.  30.4        925.  1288    76.4  2.42        5.84  1288
##  2  2001    251.  21.7        469.  1136    74.5  4.03       16.3   1136
##  3  2002    234.  39.4       1549.   912    75.4  2.15        4.63   912
##  4  2003    234.  26.6        709.   948    74.3  2.45        6.02   948
##  5  2004    243.  14.1        198.  1136    74.9  2.30        5.28  1136
##  6  2005    262.  21.7        473.  1476    73.0  2.99        8.96  1476
##  7  2006    239.  32.0       1027.  1668    73.4  2.13        4.54  1668
##  8  2007    258.  29.2        851.  1596    74.6  2.02        4.09  1596
##  9  2008    234.  27.6        761.  1380    72.7  3.24       10.5   1380
## 10  2009    223.  32.5       1058.  1188    72.9  3.82       14.6   1188
## 11  2010    234.  31.0        960.  1840    74.5  2.01        4.04  1840

Results cont’d

maize$year <- as.factor(maize$year)
maize %>% 
  ggplot() +
  aes(y = earheight, x = year, fill = year) +
  geom_boxplot() +
  guides(fill=FALSE) +
  theme_classic()

Correlation

Correlation is used to check the strength and direction(positive or negative) of the relationship between two variables. Correlation values ranges from 0 to 1.

	Values
Correlation Value Indicator
Perfect Correlation	1
Very strong positive	0.7-0.9
Strong positive	0.5- 0.69
Moderate positive	0.3-0.49
Weak positve	0.1-0.29
None	0

Pearson correlation test is used for linear, normally distributed variables while Spearman rank correlation is used for measuring rank correlation. cor.test() function is used for single correlation (method=“” to choose the correlation type).

Correlation

Multiple Correlation

It is possible to carry out multiple correlation test on a data frame using the rcorr() function from the library Hmisc .

mult.corr <- maize %>% 
  select(-c(1:6)) %>% 
  as.matrix() %>% 
rcorr(type = "pearson")
mult.corr

##              daystoflower plantheight earheight population lodged moisture
## daystoflower         1.00        0.13      0.14       0.24   0.11     0.05
## plantheight          0.13        1.00      0.79       0.44   0.04     0.38
## earheight            0.14        0.79      1.00       0.49   0.09     0.43
## population           0.24        0.44      0.49       1.00   0.07     0.42
## lodged               0.11        0.04      0.09       0.07   1.00    -0.03
## moisture             0.05        0.38      0.43       0.42  -0.03     1.00
## testweight           0.07        0.05      0.17       0.22  -0.11     0.13
## yield                0.14        0.61      0.57       0.66  -0.16     0.55
##              testweight yield
## daystoflower       0.07  0.14
## plantheight        0.05  0.61
## earheight          0.17  0.57
## population         0.22  0.66
## lodged            -0.11 -0.16
## moisture           0.13  0.55
## testweight         1.00  0.33
## yield              0.33  1.00
## 
## n
##              daystoflower plantheight earheight population lodged moisture
## daystoflower        13020       12484     12372      12519  12175    12830
## plantheight         12484       13923     13785      13824  13437    13710
## earheight           12372       13785     13915      13815  13427    13701
## population          12519       13824     13815      14057  13536    13896
## lodged              12175       13437     13427      13536  13714    13542
## moisture            12830       13710     13701      13896  13542    14346
## testweight          12736       13566     13557      13753  13396    14173
## yield               12746       13614     13606      13816  13453    14230
##              testweight yield
## daystoflower      12736 12746
## plantheight       13566 13614
## earheight         13557 13606
## population        13753 13816
## lodged            13396 13453
## moisture          14173 14230
## testweight        14199 14090
## yield             14090 14247
## 
## P
##              daystoflower plantheight earheight population lodged moisture
## daystoflower              0e+00       0e+00     0e+00      0e+00  0e+00   
## plantheight  0e+00                    0e+00     0e+00      0e+00  0e+00   
## earheight    0e+00        0e+00                 0e+00      0e+00  0e+00   
## population   0e+00        0e+00       0e+00                0e+00  0e+00   
## lodged       0e+00        0e+00       0e+00     0e+00             1e-04   
## moisture     0e+00        0e+00       0e+00     0e+00      1e-04          
## testweight   0e+00        0e+00       0e+00     0e+00      0e+00  0e+00   
## yield        0e+00        0e+00       0e+00     0e+00      0e+00  0e+00   
##              testweight yield
## daystoflower 0e+00      0e+00
## plantheight  0e+00      0e+00
## earheight    0e+00      0e+00
## population   0e+00      0e+00
## lodged       0e+00      0e+00
## moisture     0e+00      0e+00
## testweight              0e+00
## yield        0e+00

Machine Learning

Introduction

Machine learning is a part of artificial intelligence that focuses on the study of how computer algorithm can improve automatically through the use of historical data sets.
Machine learning prioritizes prediction and accuracy using large data sets while classical statistical method prioritizes explanations using smaller data sets.

Machine Learning Branches

Supervised Learning: is a form of machine learning in which the algorithm is trained on labeled data to make predictions or decisions based on the data inputs.In supervised learning, the algorithm learns a mapping between the input and output data. A labelled data set is one that has both input and output parameters. In this type of learning both training and test data sets are used.
Unsupervised Learning: algorithms are tasked with finding patterns and relationships within the data without any prior knowledge of the data’s meaning. Unsupervised learning models are given unlabeled data and allow discover patterns and insights on their own—without explicit direction or instruction.
Reinforcement Learning: uses algorithms that learn from outcomes and decide which action to take next. After each action, the algorithm receives feedback that helps it determine whether the choice it made was correct, neutral or incorrect.

Branches

Branches of Machine Learning

Machine Learning Workflow

Four major steps are involved in the creation of a machine learning model, they include:

Data pre-processing: this involves using steps of data wrangling to prepare the data for analysis, it involves splitting the data into training and testing data sets usually in the 80:20 ratio respectively, scaling and normalizing the data.
Training the Model: the training data set is used to train the model by running it through a cross validation process for a set repeated number of folds.
Evaluate the model: the model’s results are assessed and the final model is ran.
Test the Model: this involves using the test data set to evaluate the model and decided which model performed best.

Machine Learning (Supervised Learning)

Regression

Regression aspect of machine learning focuses on the prediction of numerical variables (quantitative variables).
The three main method for carrying out a regression analysis are: Random forest, linear/ multi-linear regression, Gradient boosting machine.
The library caret (Classification and Regression Training) is used to run machine learning analysis in R.
It is quite difficult to know which method is best to carry out the prediction of the particular data set so it is necessary to test all before concluding.

Models

Linear Regression Method

This method models a relationship between a target variable( dependent) and predictor variables(independent), it uses the \(y= b_0+b_iX+e\) formula to fit a regression line (line of best fit) in the data.

Random Forest

Fits multiple trees to a model to achieve high accuracy to capture non linear relationship.

Gradient Boosting machine

it combines weak learners of decision trees to create a strong predictive model.

Picking The best Model (Regression Analysis)

The R squared (coefficient of determination) Value signifies the level in which the model was able to correctly predict the test values. The value should be closer to one to signify a good model.
The Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE) values signifies the errors the model made in predicting the results. The values should be closer to zero to signify a good model.

Practical Example

Import the Honey.Avocado.csv data set and save it in an object.
Visualize the relationship between Purity and Viscosity attribute.
Summarize the following attributes-Density, WC, and pH and display the Mean, SD, Variance, Minimum and Maximum.
Select all the attributes except Price into another object named Honey.Avocado.updated
Build an ML using the ML model (lm) to predict the Purity of the honey sample-Honey.Avocado.updated.

Results

library(tidyverse)
library(caret)

honey.avocado <- read_csv("data/Honey.Avocado.csv")

## Rows: 13191 Columns: 11
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (1): Pollen_analysis
## dbl (10): CS, Density, WC, pH, EC, F, G, Viscosity, Purity, Price
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

honey.avocado

## # A tibble: 13,191 × 11
##       CS Density    WC    pH    EC     F     G Pollen_analysis Viscosity Purity
##    <dbl>   <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>               <dbl>  <dbl>
##  1  5.09    1.5   22.9  2.81  0.74  40.6  21.3 Avocado             9215.   0.95
##  2  7.59    1.66  17.3  2.75  0.72  48.3  44.6 Avocado             4715.   0.85
##  3  7.57    1.71  21.1  6.63  0.79  32.6  39.5 Avocado             3284.   0.68
##  4  6.63    1.24  21.0  3.88  0.77  23.0  25.4 Avocado             7229.   1   
##  5  9.29    1.71  22    3.67  0.88  48.0  29.3 Avocado             5712.   0.82
##  6  2.5     1.33  17.6  4.22  0.78  45.9  40.7 Avocado             5124.   1   
##  7  6.33    1.47  14.2  5.64  0.74  39.8  31.3 Avocado             3348.   0.99
##  8  9.65    1.59  21.2  6.04  0.89  27.3  35.4 Avocado             3638.   0.66
##  9  3.11    1.28  17.6  5.03  0.71  45.8  31.6 Avocado             5608.   0.87
## 10  2.47    1.35  15.1  3.81  0.81  42.3  42.1 Avocado             5567.   0.8 
## # ℹ 13,181 more rows
## # ℹ 1 more variable: Price <dbl>

honey.avocado %>% 
ggplot() +
  aes(x = Viscosity, y = Purity) +
  geom_point()

Summary Of Data

honey.avocado %>% summarise(
     Mean_D = mean(Density, na.rm = TRUE),
    SD_D = mean(Density, na.rm = TRUE),
    Variance_D = var(Density, na.rm = TRUE),
    min_D= min(Density),
    max_D= max(Density),
   Mean_WC = mean(WC, na.rm = TRUE),
    SD_WC = mean(WC, na.rm = TRUE),
    Variance_WC = var(WC, na.rm = TRUE),
    min_WC= min(WC),
    max_WC= max(WC),
    Mean_P = mean(pH, na.rm = TRUE),
    SD_P = sd(pH, na.rm = TRUE),
    Variance_P= var(pH, na.rm = TRUE),
    min_p = min(pH),
   max_p = max(pH)
 
   )

## # A tibble: 1 × 15
##   Mean_D  SD_D Variance_D min_D max_D Mean_WC SD_WC Variance_WC min_WC max_WC
##    <dbl> <dbl>      <dbl> <dbl> <dbl>   <dbl> <dbl>       <dbl>  <dbl>  <dbl>
## 1   1.54  1.54     0.0355  1.21  1.86    18.5  18.5        14.0     12     25
## # ℹ 5 more variables: Mean_P <dbl>, SD_P <dbl>, Variance_P <dbl>, min_p <dbl>,
## #   max_p <dbl>

Building the lm model

Data Preprocessing

honey.avocado

## # A tibble: 13,191 × 11
##       CS Density    WC    pH    EC     F     G Pollen_analysis Viscosity Purity
##    <dbl>   <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>               <dbl>  <dbl>
##  1  5.09    1.5   22.9  2.81  0.74  40.6  21.3 Avocado             9215.   0.95
##  2  7.59    1.66  17.3  2.75  0.72  48.3  44.6 Avocado             4715.   0.85
##  3  7.57    1.71  21.1  6.63  0.79  32.6  39.5 Avocado             3284.   0.68
##  4  6.63    1.24  21.0  3.88  0.77  23.0  25.4 Avocado             7229.   1   
##  5  9.29    1.71  22    3.67  0.88  48.0  29.3 Avocado             5712.   0.82
##  6  2.5     1.33  17.6  4.22  0.78  45.9  40.7 Avocado             5124.   1   
##  7  6.33    1.47  14.2  5.64  0.74  39.8  31.3 Avocado             3348.   0.99
##  8  9.65    1.59  21.2  6.04  0.89  27.3  35.4 Avocado             3638.   0.66
##  9  3.11    1.28  17.6  5.03  0.71  45.8  31.6 Avocado             5608.   0.87
## 10  2.47    1.35  15.1  3.81  0.81  42.3  42.1 Avocado             5567.   0.8 
## # ℹ 13,181 more rows
## # ℹ 1 more variable: Price <dbl>

honey.avocado <- honey.avocado %>%
  select(-Pollen_analysis)

psych::pairs.panels(honey.avocado, gap= 0, pch = 21)

honey.avocado <-  honey.avocado %>% 
  select(-Price)

Data Partitioning

set.seed(123)
index.h <- createDataPartition(honey.avocado$Purity, p=.08, list = FALSE)
train.h <- honey.avocado[index.h,]
test.h <- honey.avocado[-index.h,]

dim(test.h)

## [1] 12133     9

dim(train.h)

## [1] 1058    9

Scaling and Normalizing

preProcvalues.h <- preProcess(train.h, method = c("center", "scale"))
traintransformed.h <- predict(preProcvalues.h, train.h)
summary(traintransformed.h)

##        CS              Density               WC                  pH          
##  Min.   :-1.75069   Min.   :-1.76047   Min.   :-1.761324   Min.   :-1.71302  
##  1st Qu.:-0.86891   1st Qu.:-0.90350   1st Qu.:-0.872763   1st Qu.:-0.80635  
##  Median : 0.04394   Median :-0.01974   Median : 0.007671   Median :-0.06009  
##  Mean   : 0.00000   Mean   : 0.00000   Mean   : 0.000000   Mean   : 0.00000  
##  3rd Qu.: 0.84415   3rd Qu.: 0.86401   3rd Qu.: 0.879301   3rd Qu.: 0.86575  
##  Max.   : 1.74146   Max.   : 1.72099   Max.   : 1.757703   Max.   : 1.77416  
##        EC                F                  G              Viscosity       
##  Min.   :-1.7238   Min.   :-1.68115   Min.   :-1.71005   Min.   :-1.74286  
##  1st Qu.:-0.8692   1st Qu.:-0.89242   1st Qu.:-0.88400   1st Qu.:-0.83867  
##  Median :-0.0147   Median :-0.03628   Median : 0.00156   Median :-0.01408  
##  Mean   : 0.0000   Mean   : 0.00000   Mean   : 0.00000   Mean   : 0.00000  
##  3rd Qu.: 0.8398   3rd Qu.: 0.84440   3rd Qu.: 0.85223   3rd Qu.: 0.86303  
##  Max.   : 1.6944   Max.   : 1.85693   Max.   : 1.70907   Max.   : 1.73536  
##      Purity        
##  Min.   :-1.54103  
##  1st Qu.:-1.18091  
##  Median :-0.02852  
##  Mean   : 0.00000  
##  3rd Qu.: 1.05184  
##  Max.   : 1.26791

testtransformed.h <- predict(preProcvalues.h, test.h)
summary(testtransformed.h)

##        CS               Density                WC           
##  Min.   :-1.750688   Min.   :-1.760473   Min.   :-1.761324  
##  1st Qu.:-0.861141   1st Qu.:-0.903498   1st Qu.:-0.880890  
##  Median : 0.008984   Median : 0.007037   Median :-0.003165  
##  Mean   : 0.001392   Mean   :-0.001691   Mean   :-0.006199  
##  3rd Qu.: 0.867456   3rd Qu.: 0.864011   3rd Qu.: 0.866433  
##  Max.   : 1.745349   Max.   : 1.720985   Max.   : 1.760412  
##        pH                  EC                F                  G            
##  Min.   :-1.713015   Min.   :-1.7238   Min.   :-1.68352   Min.   :-1.710052  
##  1st Qu.:-0.855170   1st Qu.:-0.8692   1st Qu.:-0.81910   1st Qu.:-0.857667  
##  Median : 0.009651   Median :-0.0147   Median : 0.07252   Median : 0.012505  
##  Mean   : 0.019581   Mean   :-0.0150   Mean   : 0.07427   Mean   : 0.004421  
##  3rd Qu.: 0.888420   3rd Qu.: 0.8398   3rd Qu.: 0.95704   3rd Qu.: 0.873100  
##  Max.   : 1.774163   Max.   : 1.6944   Max.   : 1.86402   Max.   : 1.710435  
##    Viscosity             Purity        
##  Min.   :-1.742870   Min.   :-1.54103  
##  1st Qu.:-0.855622   1st Qu.:-1.18091  
##  Median : 0.014647   Median :-0.02852  
##  Mean   : 0.009574   Mean   : 0.00333  
##  3rd Qu.: 0.880332   3rd Qu.: 1.05184  
##  Max.   : 1.735915   Max.   : 1.26791

Training The Model

set.seed(123)
modelPurity.h <- train(
  Purity ~.,
  traintransformed.h,
  method= "lm",
  trControl= trainControl(
    method = "repeatedcv",
    number = 10,
    repeats = 10,
    verboseIter = TRUE
  )
)

## + Fold01.Rep01: intercept=TRUE 
## - Fold01.Rep01: intercept=TRUE 
## + Fold02.Rep01: intercept=TRUE 
## - Fold02.Rep01: intercept=TRUE 
## + Fold03.Rep01: intercept=TRUE 
## - Fold03.Rep01: intercept=TRUE 
## + Fold04.Rep01: intercept=TRUE 
## - Fold04.Rep01: intercept=TRUE 
## + Fold05.Rep01: intercept=TRUE 
## - Fold05.Rep01: intercept=TRUE 
## + Fold06.Rep01: intercept=TRUE 
## - Fold06.Rep01: intercept=TRUE 
## + Fold07.Rep01: intercept=TRUE 
## - Fold07.Rep01: intercept=TRUE 
## + Fold08.Rep01: intercept=TRUE 
## - Fold08.Rep01: intercept=TRUE 
## + Fold09.Rep01: intercept=TRUE 
## - Fold09.Rep01: intercept=TRUE 
## + Fold10.Rep01: intercept=TRUE 
## - Fold10.Rep01: intercept=TRUE 
## + Fold01.Rep02: intercept=TRUE 
## - Fold01.Rep02: intercept=TRUE 
## + Fold02.Rep02: intercept=TRUE 
## - Fold02.Rep02: intercept=TRUE 
## + Fold03.Rep02: intercept=TRUE 
## - Fold03.Rep02: intercept=TRUE 
## + Fold04.Rep02: intercept=TRUE 
## - Fold04.Rep02: intercept=TRUE 
## + Fold05.Rep02: intercept=TRUE 
## - Fold05.Rep02: intercept=TRUE 
## + Fold06.Rep02: intercept=TRUE 
## - Fold06.Rep02: intercept=TRUE 
## + Fold07.Rep02: intercept=TRUE 
## - Fold07.Rep02: intercept=TRUE 
## + Fold08.Rep02: intercept=TRUE 
## - Fold08.Rep02: intercept=TRUE 
## + Fold09.Rep02: intercept=TRUE 
## - Fold09.Rep02: intercept=TRUE 
## + Fold10.Rep02: intercept=TRUE 
## - Fold10.Rep02: intercept=TRUE 
## + Fold01.Rep03: intercept=TRUE 
## - Fold01.Rep03: intercept=TRUE 
## + Fold02.Rep03: intercept=TRUE 
## - Fold02.Rep03: intercept=TRUE 
## + Fold03.Rep03: intercept=TRUE 
## - Fold03.Rep03: intercept=TRUE 
## + Fold04.Rep03: intercept=TRUE 
## - Fold04.Rep03: intercept=TRUE 
## + Fold05.Rep03: intercept=TRUE 
## - Fold05.Rep03: intercept=TRUE 
## + Fold06.Rep03: intercept=TRUE 
## - Fold06.Rep03: intercept=TRUE 
## + Fold07.Rep03: intercept=TRUE 
## - Fold07.Rep03: intercept=TRUE 
## + Fold08.Rep03: intercept=TRUE 
## - Fold08.Rep03: intercept=TRUE 
## + Fold09.Rep03: intercept=TRUE 
## - Fold09.Rep03: intercept=TRUE 
## + Fold10.Rep03: intercept=TRUE 
## - Fold10.Rep03: intercept=TRUE 
## + Fold01.Rep04: intercept=TRUE 
## - Fold01.Rep04: intercept=TRUE 
## + Fold02.Rep04: intercept=TRUE 
## - Fold02.Rep04: intercept=TRUE 
## + Fold03.Rep04: intercept=TRUE 
## - Fold03.Rep04: intercept=TRUE 
## + Fold04.Rep04: intercept=TRUE 
## - Fold04.Rep04: intercept=TRUE 
## + Fold05.Rep04: intercept=TRUE 
## - Fold05.Rep04: intercept=TRUE 
## + Fold06.Rep04: intercept=TRUE 
## - Fold06.Rep04: intercept=TRUE 
## + Fold07.Rep04: intercept=TRUE 
## - Fold07.Rep04: intercept=TRUE 
## + Fold08.Rep04: intercept=TRUE 
## - Fold08.Rep04: intercept=TRUE 
## + Fold09.Rep04: intercept=TRUE 
## - Fold09.Rep04: intercept=TRUE 
## + Fold10.Rep04: intercept=TRUE 
## - Fold10.Rep04: intercept=TRUE 
## + Fold01.Rep05: intercept=TRUE 
## - Fold01.Rep05: intercept=TRUE 
## + Fold02.Rep05: intercept=TRUE 
## - Fold02.Rep05: intercept=TRUE 
## + Fold03.Rep05: intercept=TRUE 
## - Fold03.Rep05: intercept=TRUE 
## + Fold04.Rep05: intercept=TRUE 
## - Fold04.Rep05: intercept=TRUE 
## + Fold05.Rep05: intercept=TRUE 
## - Fold05.Rep05: intercept=TRUE 
## + Fold06.Rep05: intercept=TRUE 
## - Fold06.Rep05: intercept=TRUE 
## + Fold07.Rep05: intercept=TRUE 
## - Fold07.Rep05: intercept=TRUE 
## + Fold08.Rep05: intercept=TRUE 
## - Fold08.Rep05: intercept=TRUE 
## + Fold09.Rep05: intercept=TRUE 
## - Fold09.Rep05: intercept=TRUE 
## + Fold10.Rep05: intercept=TRUE 
## - Fold10.Rep05: intercept=TRUE 
## + Fold01.Rep06: intercept=TRUE 
## - Fold01.Rep06: intercept=TRUE 
## + Fold02.Rep06: intercept=TRUE 
## - Fold02.Rep06: intercept=TRUE 
## + Fold03.Rep06: intercept=TRUE 
## - Fold03.Rep06: intercept=TRUE 
## + Fold04.Rep06: intercept=TRUE 
## - Fold04.Rep06: intercept=TRUE 
## + Fold05.Rep06: intercept=TRUE 
## - Fold05.Rep06: intercept=TRUE 
## + Fold06.Rep06: intercept=TRUE 
## - Fold06.Rep06: intercept=TRUE 
## + Fold07.Rep06: intercept=TRUE 
## - Fold07.Rep06: intercept=TRUE 
## + Fold08.Rep06: intercept=TRUE 
## - Fold08.Rep06: intercept=TRUE 
## + Fold09.Rep06: intercept=TRUE 
## - Fold09.Rep06: intercept=TRUE 
## + Fold10.Rep06: intercept=TRUE 
## - Fold10.Rep06: intercept=TRUE 
## + Fold01.Rep07: intercept=TRUE 
## - Fold01.Rep07: intercept=TRUE 
## + Fold02.Rep07: intercept=TRUE 
## - Fold02.Rep07: intercept=TRUE 
## + Fold03.Rep07: intercept=TRUE 
## - Fold03.Rep07: intercept=TRUE 
## + Fold04.Rep07: intercept=TRUE 
## - Fold04.Rep07: intercept=TRUE 
## + Fold05.Rep07: intercept=TRUE 
## - Fold05.Rep07: intercept=TRUE 
## + Fold06.Rep07: intercept=TRUE 
## - Fold06.Rep07: intercept=TRUE 
## + Fold07.Rep07: intercept=TRUE 
## - Fold07.Rep07: intercept=TRUE 
## + Fold08.Rep07: intercept=TRUE 
## - Fold08.Rep07: intercept=TRUE 
## + Fold09.Rep07: intercept=TRUE 
## - Fold09.Rep07: intercept=TRUE 
## + Fold10.Rep07: intercept=TRUE 
## - Fold10.Rep07: intercept=TRUE 
## + Fold01.Rep08: intercept=TRUE 
## - Fold01.Rep08: intercept=TRUE 
## + Fold02.Rep08: intercept=TRUE 
## - Fold02.Rep08: intercept=TRUE 
## + Fold03.Rep08: intercept=TRUE 
## - Fold03.Rep08: intercept=TRUE 
## + Fold04.Rep08: intercept=TRUE 
## - Fold04.Rep08: intercept=TRUE 
## + Fold05.Rep08: intercept=TRUE 
## - Fold05.Rep08: intercept=TRUE 
## + Fold06.Rep08: intercept=TRUE 
## - Fold06.Rep08: intercept=TRUE 
## + Fold07.Rep08: intercept=TRUE 
## - Fold07.Rep08: intercept=TRUE 
## + Fold08.Rep08: intercept=TRUE 
## - Fold08.Rep08: intercept=TRUE 
## + Fold09.Rep08: intercept=TRUE 
## - Fold09.Rep08: intercept=TRUE 
## + Fold10.Rep08: intercept=TRUE 
## - Fold10.Rep08: intercept=TRUE 
## + Fold01.Rep09: intercept=TRUE 
## - Fold01.Rep09: intercept=TRUE 
## + Fold02.Rep09: intercept=TRUE 
## - Fold02.Rep09: intercept=TRUE 
## + Fold03.Rep09: intercept=TRUE 
## - Fold03.Rep09: intercept=TRUE 
## + Fold04.Rep09: intercept=TRUE 
## - Fold04.Rep09: intercept=TRUE 
## + Fold05.Rep09: intercept=TRUE 
## - Fold05.Rep09: intercept=TRUE 
## + Fold06.Rep09: intercept=TRUE 
## - Fold06.Rep09: intercept=TRUE 
## + Fold07.Rep09: intercept=TRUE 
## - Fold07.Rep09: intercept=TRUE 
## + Fold08.Rep09: intercept=TRUE 
## - Fold08.Rep09: intercept=TRUE 
## + Fold09.Rep09: intercept=TRUE 
## - Fold09.Rep09: intercept=TRUE 
## + Fold10.Rep09: intercept=TRUE 
## - Fold10.Rep09: intercept=TRUE 
## + Fold01.Rep10: intercept=TRUE 
## - Fold01.Rep10: intercept=TRUE 
## + Fold02.Rep10: intercept=TRUE 
## - Fold02.Rep10: intercept=TRUE 
## + Fold03.Rep10: intercept=TRUE 
## - Fold03.Rep10: intercept=TRUE 
## + Fold04.Rep10: intercept=TRUE 
## - Fold04.Rep10: intercept=TRUE 
## + Fold05.Rep10: intercept=TRUE 
## - Fold05.Rep10: intercept=TRUE 
## + Fold06.Rep10: intercept=TRUE 
## - Fold06.Rep10: intercept=TRUE 
## + Fold07.Rep10: intercept=TRUE 
## - Fold07.Rep10: intercept=TRUE 
## + Fold08.Rep10: intercept=TRUE 
## - Fold08.Rep10: intercept=TRUE 
## + Fold09.Rep10: intercept=TRUE 
## - Fold09.Rep10: intercept=TRUE 
## + Fold10.Rep10: intercept=TRUE 
## - Fold10.Rep10: intercept=TRUE 
## Aggregating results
## Fitting final model on full training set

modelPurity.h

## Linear Regression 
## 
## 1058 samples
##    8 predictor
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 10 times) 
## Summary of sample sizes: 951, 951, 953, 953, 953, 952, ... 
## Resampling results:
## 
##   RMSE       Rsquared    MAE      
##   0.9651998  0.07672933  0.8520641
## 
## Tuning parameter 'intercept' was held constant at a value of TRUE

sd(honey.avocado$Purity)

## [1] 0.1394149

set.seed(123)
modelFinal.h <- train(
  Purity ~.,
  traintransformed.h,
  method = "lm",
  trControl = trainControl(
    method = "none",
    verboseIter = TRUE
  )
)

## Fitting intercept = TRUE on full training set

Evaluating The model

summary(modelFinal.h)

## 
## Call:
## lm(formula = .outcome ~ ., data = dat)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.0338 -0.8619 -0.1249  0.9623  1.8276 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept) -1.446e-15  2.958e-02   0.000 1.000000    
## CS           1.014e-01  2.972e-02   3.413 0.000668 ***
## Density     -1.318e-01  2.970e-02  -4.438 1.01e-05 ***
## WC          -9.685e-03  2.965e-02  -0.327 0.743959    
## pH          -2.314e-01  2.964e-02  -7.808 1.40e-14 ***
## EC          -4.806e-03  2.963e-02  -0.162 0.871195    
## F           -3.025e-03  2.965e-02  -0.102 0.918774    
## G            4.295e-02  2.971e-02   1.446 0.148530    
## Viscosity    8.138e-03  2.970e-02   0.274 0.784129    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.9622 on 1049 degrees of freedom
## Multiple R-squared:  0.08118,    Adjusted R-squared:  0.07417 
## F-statistic: 11.58 on 8 and 1049 DF,  p-value: 7.208e-16

predictions.h <- predict(modelFinal.h, testtransformed.h)
performance.h <- postResample(predictions.h,testtransformed.h$Purity)
print(performance.h)

##       RMSE   Rsquared        MAE 
## 0.97242290 0.06412193 0.85841030

Summary (Regression)

After running the other models with results:

LM

RMSE:0.97242290 Rsquared:0.06412193 MAE:0.8584103

GBM

RMSE:0.6972944 Rsquared:0.6503224 MAE:0.6010673

Random Forest

RMSE:0.5004887 Rsquared:0.8422298 MAE:0.4160595

We can conclude that the best model for this data set is the Random Forest model.

Machine learning

Classification

Classification focuses on the prediction of qualitative variables.
The classification methods (linear/multivariate regression, Random Forest and Gradient Boosting machine) are similar to the regression method with only slight differences.
The library caret is also used for classification.

Picking The Right model (Classification).

ROC (receiver operating characteristic) is important in classification analysis to pick the best ml model.The ROC value is used to identify how good or bad the model is. A high ROC, closer to 1 indicates a good model and vice versa.
Confusion matrix is also used in picking the right model. It shows the number of values the model was able to predict correctly, the sensitivity value (which shows how well the model predicted the target variable), the specificity value (which indicates how well the model predicted the non target variable).
AUC (Area Under The Curve): This represents the area under the ROC curve, it ranges from 0-1 . We want to maximize this area so that we can have the highest True Positive and the lowest False Positive. Values closer to one indicates a good model, while a value of 0.5 indicates no discriminating ability (random guessing), a value closer to 0 indicates the model is inversely predicting.

Practical Example

import the abalone.csv data set and save it in an object.
Make a boxplot of one quantitative variable of your choice by the age of the animal.
Make a bar chart using the age variable
Compute the mean, median, variance, minimum, and maximum of any three quantitative variables of your choice by age.
Build any of GLM, Random Forest, or GBM machine learning models to predict whether the abalone is old or not.

Results

library(tidyverse)
library(caret)
library(pROC)

abalone <- read_csv("data/abalone.csv")

## Rows: 4177 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): age
## dbl (7): length, diameter, height, whole.weight, shucked.weight, viscera.wei...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

summary(abalone)

##      length         diameter          height        whole.weight   
##  Min.   :0.075   Min.   :0.0550   Min.   :0.0000   Min.   :0.0020  
##  1st Qu.:0.450   1st Qu.:0.3500   1st Qu.:0.1150   1st Qu.:0.4415  
##  Median :0.545   Median :0.4250   Median :0.1400   Median :0.7995  
##  Mean   :0.524   Mean   :0.4079   Mean   :0.1395   Mean   :0.8287  
##  3rd Qu.:0.615   3rd Qu.:0.4800   3rd Qu.:0.1650   3rd Qu.:1.1530  
##  Max.   :0.815   Max.   :0.6500   Max.   :1.1300   Max.   :2.8255  
##  shucked.weight   viscera.weight    shell.weight        age           
##  Min.   :0.0010   Min.   :0.0005   Min.   :0.0015   Length:4177       
##  1st Qu.:0.1860   1st Qu.:0.0935   1st Qu.:0.1300   Class :character  
##  Median :0.3360   Median :0.1710   Median :0.2340   Mode  :character  
##  Mean   :0.3594   Mean   :0.1806   Mean   :0.2388                     
##  3rd Qu.:0.5020   3rd Qu.:0.2530   3rd Qu.:0.3290                     
##  Max.   :1.4880   Max.   :0.7600   Max.   :1.0050

abalone$age <- as.factor(abalone$age)
abalone

## # A tibble: 4,177 × 8
##    length diameter height whole.weight shucked.weight viscera.weight
##     <dbl>    <dbl>  <dbl>        <dbl>          <dbl>          <dbl>
##  1  0.455    0.365  0.095        0.514         0.224          0.101 
##  2  0.35     0.265  0.09         0.226         0.0995         0.0485
##  3  0.53     0.42   0.135        0.677         0.256          0.142 
##  4  0.44     0.365  0.125        0.516         0.216          0.114 
##  5  0.33     0.255  0.08         0.205         0.0895         0.0395
##  6  0.425    0.3    0.095        0.352         0.141          0.0775
##  7  0.53     0.415  0.15         0.778         0.237          0.142 
##  8  0.545    0.425  0.125        0.768         0.294          0.150 
##  9  0.475    0.37   0.125        0.509         0.216          0.112 
## 10  0.55     0.44   0.15         0.894         0.314          0.151 
## # ℹ 4,167 more rows
## # ℹ 2 more variables: shell.weight <dbl>, age <fct>

age_sh <- ggplot(abalone) + 
  aes(x = age, y = shell.weight, fill = age) + 
  geom_boxplot() +
  labs(title = "Boxplot of Age and Shell.Weight of Abalone") +
  theme_classic() +
  guides(fill= FALSE)
age_sh

A.BC <- ggplot(abalone)+
  aes(x= age, colour= age, fill= age) +
  geom_bar() +
  labs(title = "Barchart of Abalone Age") + guides(fill= FALSE)+
  theme_classic()  
 
A.BC

Summary of quantitative variable

length.Summary <- abalone %>% 
  group_by(age) %>% 
  summarise(mean.len = mean(length, na.rm = TRUE),
            median.len = median(length, na.rm = TRUE),
            var.len = var(length, na.rm = TRUE),
            max.len = max(length, na.rm = TRUE),
            min.len = min(length, na.rm = TRUE)
            )
length.Summary

## # A tibble: 2 × 6
##   age   mean.len median.len var.len max.len min.len
##   <fct>    <dbl>      <dbl>   <dbl>   <dbl>   <dbl>
## 1 old      0.591      0.6   0.00692   0.815   0.31 
## 2 young    0.488      0.505 0.0148    0.77    0.075

shell.weight <- abalone %>% 
  group_by(age) %>% 
  summarise(mean.SW = mean(shell.weight, na.rm = TRUE),
            median.SW = median(shell.weight, na.rm = TRUE),
            var.SW = var(shell.weight, na.rm = TRUE),
            max.SW = max(shell.weight, na.rm = TRUE),
            min.SW = min(shell.weight, na.rm = TRUE)
            )
shell.weight

## # A tibble: 2 × 6
##   age   mean.SW median.SW var.SW max.SW min.SW
##   <fct>   <dbl>     <dbl>  <dbl>  <dbl>  <dbl>
## 1 old     0.335     0.324 0.0171  1.00  0.04  
## 2 young   0.188     0.175 0.0131  0.655 0.0015

viscrea.weight <- abalone %>% 
  group_by(age) %>% 
  summarise(mean.VW = mean(viscera.weight, na.rm = TRUE),
            median.VW = median(viscera.weight, na.rm = TRUE),
            var.VW = var(viscera.weight, na.rm = TRUE),
            max.VW = max(viscera.weight, na.rm = TRUE),
            min.VW = min(viscera.weight, na.rm = TRUE)
            )
viscrea.weight

## # A tibble: 2 × 6
##   age   mean.VW median.VW  var.VW max.VW min.VW
##   <fct>   <dbl>     <dbl>   <dbl>  <dbl>  <dbl>
## 1 old     0.243     0.234 0.0107   0.76  0.024 
## 2 young   0.147     0.132 0.00952  0.541 0.0005

ML model

Random Forest Method

Data Preprocessing

abalone

## # A tibble: 4,177 × 8
##    length diameter height whole.weight shucked.weight viscera.weight
##     <dbl>    <dbl>  <dbl>        <dbl>          <dbl>          <dbl>
##  1  0.455    0.365  0.095        0.514         0.224          0.101 
##  2  0.35     0.265  0.09         0.226         0.0995         0.0485
##  3  0.53     0.42   0.135        0.677         0.256          0.142 
##  4  0.44     0.365  0.125        0.516         0.216          0.114 
##  5  0.33     0.255  0.08         0.205         0.0895         0.0395
##  6  0.425    0.3    0.095        0.352         0.141          0.0775
##  7  0.53     0.415  0.15         0.778         0.237          0.142 
##  8  0.545    0.425  0.125        0.768         0.294          0.150 
##  9  0.475    0.37   0.125        0.509         0.216          0.112 
## 10  0.55     0.44   0.15         0.894         0.314          0.151 
## # ℹ 4,167 more rows
## # ℹ 2 more variables: shell.weight <dbl>, age <fct>

skimr::skim(abalone)

Data summary
Name	abalone
Number of rows	4177
Number of columns	8
_______________________
Column type frequency:
factor	1
numeric	7
________________________
Group variables	None

Variable type: factor

skim_variable	n_missing	complete_rate	ordered	n_unique	top_counts
age	0	1	FALSE	2	you: 2730, old: 1447

Variable type: numeric

skim_variable	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
length	1	0.52	0.12	0.07	0.45	0.54	0.62	0.81	▁▂▅▇▂
diameter	1	0.41	0.10	0.06	0.35	0.42	0.48	0.65	▁▂▆▇▁
height	1	0.14	0.04	0.00	0.12	0.14	0.16	1.13	▇▁▁▁▁
whole.weight	1	0.83	0.49	0.00	0.44	0.80	1.15	2.83	▇▇▅▁▁
shucked.weight	1	0.36	0.22	0.00	0.19	0.34	0.50	1.49	▇▇▂▁▁
viscera.weight	1	0.18	0.11	0.00	0.09	0.17	0.25	0.76	▇▇▂▁▁
shell.weight	1	0.24	0.14	0.00	0.13	0.23	0.33	1.00	▇▇▂▁▁

unique(abalone$age)

## [1] old   young
## Levels: old young

abalone$age <- as.factor(abalone$age)
abalone

## # A tibble: 4,177 × 8
##    length diameter height whole.weight shucked.weight viscera.weight
##     <dbl>    <dbl>  <dbl>        <dbl>          <dbl>          <dbl>
##  1  0.455    0.365  0.095        0.514         0.224          0.101 
##  2  0.35     0.265  0.09         0.226         0.0995         0.0485
##  3  0.53     0.42   0.135        0.677         0.256          0.142 
##  4  0.44     0.365  0.125        0.516         0.216          0.114 
##  5  0.33     0.255  0.08         0.205         0.0895         0.0395
##  6  0.425    0.3    0.095        0.352         0.141          0.0775
##  7  0.53     0.415  0.15         0.778         0.237          0.142 
##  8  0.545    0.425  0.125        0.768         0.294          0.150 
##  9  0.475    0.37   0.125        0.509         0.216          0.112 
## 10  0.55     0.44   0.15         0.894         0.314          0.151 
## # ℹ 4,167 more rows
## # ℹ 2 more variables: shell.weight <dbl>, age <fct>

psych::pairs.panels(abalone, gap = 0, pch=21)

Splitting The data set

set.seed(123)
index.a <- createDataPartition(abalone$age, p = .80, list = FALSE)
train.a <- abalone[index.a, ]
test.a <- abalone[-index.a, ]

dim(train.a)

## [1] 3342    8

dim(test.a)

## [1] 835   8

Training the Model

set.seed(123)
modelCV.a <- train(
  age~.,
  train.a,
  method = "ranger",
  trControl = trainControl(
    method = "repeatedcv",
    number = 10,
    repeats = 10,
    summaryFunction = twoClassSummary,
    classProbs = TRUE,
    verboseIter = TRUE
  ),
  metric = "ROC"
)

## + Fold01.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep01: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep01: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep01: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep01: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep01: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep01: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep02: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep02: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep02: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep02: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep02: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep02: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep03: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep03: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep03: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep03: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep03: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep03: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep04: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep04: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep04: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep04: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep04: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep04: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep05: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep05: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep05: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep05: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep05: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep05: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep06: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep06: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep06: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep06: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep06: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep06: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep07: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep07: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep07: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep07: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep07: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep07: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep08: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep08: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep08: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep08: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep08: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep08: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep09: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep09: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep09: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep09: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep09: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep09: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold01.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold01.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold01.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold01.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold01.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold01.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold01.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold01.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold02.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold02.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold02.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold02.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold02.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold02.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold02.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold02.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold03.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold03.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold03.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold03.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold03.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold03.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold03.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold03.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold04.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold04.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold04.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold04.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold04.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold04.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold04.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold04.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold05.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold05.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold05.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold05.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold05.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold05.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold05.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold05.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold06.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold06.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold06.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold06.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold06.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold06.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold06.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold06.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold07.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold07.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold07.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold07.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold07.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold07.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold07.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold07.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold08.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold08.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold08.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold08.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold08.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold08.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold08.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold08.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold09.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold09.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold09.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold09.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold09.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold09.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold09.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold09.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## - Fold10.Rep10: mtry=2, min.node.size=1, splitrule=gini 
## + Fold10.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## - Fold10.Rep10: mtry=4, min.node.size=1, splitrule=gini 
## + Fold10.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## - Fold10.Rep10: mtry=7, min.node.size=1, splitrule=gini 
## + Fold10.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep10: mtry=2, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep10: mtry=4, min.node.size=1, splitrule=extratrees 
## + Fold10.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## - Fold10.Rep10: mtry=7, min.node.size=1, splitrule=extratrees 
## Aggregating results
## Selecting tuning parameters
## Fitting mtry = 2, splitrule = extratrees, min.node.size = 1 on full training set

modelCV.a

## Random Forest 
## 
## 3342 samples
##    7 predictor
##    2 classes: 'old', 'young' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 10 times) 
## Summary of sample sizes: 3008, 3008, 3007, 3007, 3007, 3009, ... 
## Resampling results across tuning parameters:
## 
##   mtry  splitrule   ROC        Sens       Spec     
##   2     gini        0.8466395  0.6189835  0.8497738
##   2     extratrees  0.8518589  0.6150945  0.8616744
##   4     gini        0.8430006  0.6168133  0.8437770
##   4     extratrees  0.8496125  0.6163051  0.8539416
##   7     gini        0.8389330  0.6170787  0.8378696
##   7     extratrees  0.8470111  0.6194955  0.8478535
## 
## Tuning parameter 'min.node.size' was held constant at a value of 1
## ROC was used to select the optimal model using the largest value.
## The final values used for the model were mtry = 2, splitrule = extratrees
##  and min.node.size = 1.

set.seed(123)
modelFinal.a <- train(
  age~.,
  train.a,
  method = "ranger",
  trControl = trainControl(
    method = "none",
    summaryFunction = twoClassSummary,
    classProbs = TRUE,
    verboseIter = TRUE
  ),
  metric = "ROC"
)

## Fitting mtry = 2, min.node.size = 1, splitrule = gini on full training set

Evaluating The model

predictions.a <- predict(modelFinal.a, test.a)
 

 
prediction_prob.a <- predict(modelFinal.a, test.a, type = "prob")
roc_results.a <- roc(test.a$age, prediction_prob.a[,"old"])

## Setting levels: control = old, case = young

## Setting direction: controls > cases

confusionMatrix(predictions.a, as.factor(test.a$age))

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction old young
##      old   195    71
##      young  94   475
##                                           
##                Accuracy : 0.8024          
##                  95% CI : (0.7737, 0.8289)
##     No Information Rate : 0.6539          
##     P-Value [Acc > NIR] : < 2e-16         
##                                           
##                   Kappa : 0.5551          
##                                           
##  Mcnemar's Test P-Value : 0.08677         
##                                           
##             Sensitivity : 0.6747          
##             Specificity : 0.8700          
##          Pos Pred Value : 0.7331          
##          Neg Pred Value : 0.8348          
##              Prevalence : 0.3461          
##          Detection Rate : 0.2335          
##    Detection Prevalence : 0.3186          
##       Balanced Accuracy : 0.7724          
##                                           
##        'Positive' Class : old             
##

auc(roc_results.a)

## Area under the curve: 0.8659

Summary (Classification)

After running the data through other models with results:

GLM

Accuracy:0.7904 Sensitivity:0.5986 Specificity:0.8919 AUC:0.8531

GBM

Accuracy:0.7581 Sensitivity:0.5121 Specificity:0.8883 AUC:0.8107

Random Forest

Accuracy:0.8024 Sensitivity:0.6747 Specificity:0.8608 AUC:0.8659 .

Following the analysis we can conclude that the best model is Random Forest Model.

R Markdown and Dashboard

R markdown is a plain text authoring framework with the extension .Rmd which allows you to save and execute code while simultaneously generating high quality reports.It uses the library rmarkdown and knitr which are installed automatically. It allows the author to embed links, pictures, videos and code chunks into the data analysis report which can be displayed as

html document
pdf documents
iosslides presentation
slidy presentation
powerpoint presentation etc.

Rmarkdown Interface

Dashboard makes use of the library flexdashboard and it is used to display and easily communicate a large number of graphs.

Conlusion

R provides excellent visualization features, which is essential to explore the data before building any machine learning model, as well as assessing the results of the model. Many R packages for machine learning are readily available for easier analysis.

THANK YOU