Added first version for 10 UCI datasets

.gitignore

@@ -16,3 +16,7 @@ vignettes/*.pdf
 # OAuth2 token, see https://github.com/hadley/httr/releases/tag/v0.3
 .httr-oauth
 
+# data collection
+
+data-collection/*/original/*
+data-collection/*/preprocessed/*

config.R

@@ -0,0 +1,28 @@
+# ---- checkpoint ----
+
+CHECKPOINT.MRAN.URL      = "http://mran.microsoft.com/snapshot/"
+CHECKPOINT.SNAPSHOT.DATE = "2016-04-10"
+
+library(checkpoint)
+options(checkpoint.mranUrl=CHECKPOINT.MRAN.URL)
+checkpoint(CHECKPOINT.SNAPSHOT.DATE)
+
+# ---- logger ----
+
+LOGGER_LEVEL = futile.logger::INFO
+
+library(futile.logger)
+flog.threshold(LOGGER_LEVEL)
+
+# ---- other ----
+
+PATH_DATASETS             = "data-collection/"
+PATH_DATASET_ORIGINAL     = paste0(PATH_DATASETS, "*/original/")
+PATH_DATASET_PREPROCESSED = paste0(PATH_DATASETS, "*/preprocessed/")
+
+FILE_CONFIG_YAML          = "config.yaml"
+FILE_PREPROCESSING_SCRIPT = "preprocess.R"
+FILE_PREPROCESSED_OUTPUT  = "dataset.rds"
+
+if (file.exists("config.R.user"))
+    source("config.R.user")

data-collection/bank-marketing/config.yaml

@@ -0,0 +1,10 @@
+--- 
+name: Bank Marketing
+
+info: https://archive.ics.uci.edu/ml/datasets/Bank+Marketing
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank-additional.zip
+
+cite: > 
+    [Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014

data-collection/bank-marketing/preprocess.R

@@ -0,0 +1,50 @@
+preprocessDataset = function()
+{
+    #set.seed(SEED)
+    
+    temp.dir = tempdir()
+    
+    zip.file = "bank-additional.zip"
+    zip.dataset.path = "bank-additional/bank-additional-full.csv"
+    
+    flog.debug(paste("Unzipping", zip.file))
+    
+    unzip(zipfile=paste0(orig.dir, zip.file),
+          files=zip.dataset.path,
+          exdir=temp.dir)
+    
+    flog.debug(paste("Loading", zip.dataset.path))
+    
+    dataset = read.csv(paste0(temp.dir, "/", zip.dataset.path), sep=";")
+    
+    flog.debug("Preprocessing loaded dataset")
+    
+    dataset = dataset %>% 
+        select(-c(duration, pdays, default)) %>%
+        filter(job != "unknown" & marital != "unknown" & education != "unknown" & 
+               education != "illiterate" & housing != "unknown" & loan != "unknown") %>%
+        droplevels()
+    
+    #dataset.yes = dataset %>% filter(y == "yes")
+    #dataset.no = dataset %>% filter(y == "no") %>% sample_n(nrow(dataset.yes))
+    #
+    #dataset = rbind(dataset.yes, dataset.no)
+    
+    dataset = dataset %>% mutate(
+                        education=factor(education, levels=c("basic.4y", "basic.6y", 
+                                                             "basic.9y", "high.school",
+                                                             "professional.course",
+                                                             "university.degree"),
+                                         ordered=TRUE),
+                        month=factor(month, levels=c("jan", "feb", "mar", 
+                                                     "apr", "may", "jun", 
+                                                     "jul", "aug", "sep", 
+                                                     "oct", "nov", "dec"), 
+                                     ordered=TRUE),
+                        day_of_week=factor(day_of_week, levels=c("mon", "tue", "wed",
+                                                                 "thu", "fri"),
+                                           ordered=TRUE)
+    )
+    
+    return(dataset)
+}

data-collection/breast-cancer-wisconsin-diagnostic/config.yaml

@@ -0,0 +1,18 @@
+--- 
+name: Breast Cancer Wisconsin (Diagnostic)
+
+info: https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Diagnostic%29
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data
+- https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.names
+
+cite: > 
+    https://archive.ics.uci.edu/ml/citation_policy.html
+
+    @misc{Lichman:2013 ,
+    author = "M. Lichman",
+    year = "2013",
+    title = "{UCI} Machine Learning Repository",
+    url = "http://archive.ics.uci.edu/ml",
+    institution = "University of California, Irvine, School of Information and Computer Sciences" } 

data-collection/breast-cancer-wisconsin-diagnostic/preprocess.R

@@ -0,0 +1,18 @@
+preprocessDataset = function()
+{   
+    csv.file = "wdbc.data"
+    
+    dataset = read.csv(paste0(orig.dir, "/", csv.file), header=FALSE)
+    
+    colnames(dataset) = c("id", "diagnosis", 
+                          apply(expand.grid(c("radius", "texture", "perimeter", 
+                                              "area", "smoothness", "compactness", 
+                                              "concavity", "concave points", 
+                                              "symmetry", "fractal dimension"),
+                                            c("mean", "se", "worst")), 
+                                1, function(x){paste(x[2], x[1])}))
+    
+    dataset = dataset %>% select(`mean radius`:`worst fractal dimension`, diagnosis)
+
+    return(dataset)
+}

data-collection/breast-cancer-wisconsin-original/config.yaml

@@ -0,0 +1,11 @@
+--- 
+name: Breast Cancer Wisconsin (Original)
+
+info: https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Original%29
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data
+- https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.names
+
+cite: > 
+    O. L. Mangasarian and W. H. Wolberg: "Cancer diagnosis via linear programming", SIAM News, Volume 23, Number 5, September 1990, pp 1 & 18.

data-collection/breast-cancer-wisconsin-original/preprocess.R

@@ -0,0 +1,20 @@
+preprocessDataset = function()
+{   
+    csv.file = "breast-cancer-wisconsin.data"
+    
+    dataset = read.csv(paste0(orig.dir, "/", csv.file), header=FALSE)
+    
+    colnames(dataset) = c("Sample code number", "Clump Thickness", 
+                          "Uniformity of Cell Size", "Uniformity of Cell Shape", 
+                          "Marginal Adhesion", "Single Epithelial Cell Size", 
+                          "Bare Nuclei", "Bland Chromatin", "Normal Nucleoli", 
+                          "Mitoses", "Class")
+    
+    dataset = dataset %>% select(-`Sample code number`) %>%
+              filter(`Bare Nuclei` != "?") %>%
+              mutate(Class=factor(Class), 
+                     `Bare Nuclei`=as.integer(`Bare Nuclei`)) %>%
+              droplevels()
+    
+    return(dataset)
+}

data-collection/cardiotocography/config.yaml

@@ -0,0 +1,10 @@
+--- 
+name: Cardiotocography
+
+info: https://archive.ics.uci.edu/ml/datasets/Cardiotocography
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/00193/CTG.xls
+
+cite: > 
+    Ayres de Campos et al. (2000) SisPorto 2.0 A Program for Automated Analysis of Cardiotocograms. J Matern Fetal Med 5:311-318 

data-collection/cardiotocography/preprocess.R

@@ -0,0 +1,40 @@
+preprocessDataset = function()
+{   
+    xls.file = "CTG.xls"
+    
+    wk = loadWorkbook(paste0(orig.dir, "/", xls.file))
+    dataset = readWorksheet(wk, sheet="Raw Data")
+    
+    dataset = dataset %>% select(LB:FS, NSP, -c(DS, DR)) %>% 
+              filter(complete.cases(.)) %>%
+              mutate(LB=as.integer(LB),
+                     AC=as.integer(AC),
+                     FM=as.integer(FM),
+                     UC=as.integer(UC),
+                     ASTV=as.integer(ASTV),
+                     ALTV=as.integer(ALTV),
+                     DL=as.integer(DL),
+                     DP=as.integer(DP),
+                     Width=as.integer(Width),
+                     Min=as.integer(Min),
+                     Max=as.integer(Max),
+                     Nmax=as.integer(Nmax),
+                     Nzeros=as.integer(Nzeros),
+                     Mode=as.integer(Mode),
+                     Mean=as.integer(Mean),
+                     Median=as.integer(Median),
+                     Variance=as.integer(Variance),
+                     Tendency=factor(Tendency, levels=c(-1,0,1), ordered=TRUE),
+                     A=factor(A),
+                     B=factor(B),
+                     C=factor(C),
+                     D=factor(D),
+                     E=factor(E),
+                     AD=factor(AD),
+                     DE=factor(DE),
+                     LD=factor(LD),
+                     FS=factor(FS),
+                     NSP=factor(replace(NSP, NSP==2, 3)))
+
+    return(dataset)
+}

data-collection/credit-card/config.yaml

@@ -0,0 +1,10 @@
+--- 
+name: Default of credit card clients
+
+info: https://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/00350/default%20of%20credit%20card%20clients.xls
+
+cite: > 
+    Yeh, I. C., & Lien, C. H. (2009). The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert Systems with Applications, 36(2), 2473-2480.

data-collection/credit-card/preprocess.R

@@ -0,0 +1,48 @@
+preprocessDataset = function()
+{   
+    #set.seed(SEED)
+    
+    xls.file = "default of credit card clients.xls"
+    
+    wk = loadWorkbook(paste0(orig.dir, "/", xls.file))
+    dataset = readWorksheet(wk, sheet="Data", startRow=2, startCol=2,
+                            check.names=FALSE)
+    
+    dataset = dataset %>% 
+              mutate(LIMIT_BAL=as.integer(LIMIT_BAL),
+                     SEX=factor(SEX),
+                     EDUCATION=factor(EDUCATION), # can't order due to
+                                                  # inconsistency with
+                                                 # UCI description
+                     MARRIAGE=factor(MARRIAGE),
+                     AGE=as.integer(AGE),
+                     PAY_0=as.integer(replace(PAY_0, PAY_0<0, 0)),
+                     PAY_2=as.integer(replace(PAY_2, PAY_2<0, 0)),
+                     PAY_3=as.integer(replace(PAY_3, PAY_3<0, 0)),
+                     PAY_4=as.integer(replace(PAY_4, PAY_4<0, 0)),
+                     PAY_5=as.integer(replace(PAY_5, PAY_5<0, 0)),
+                     PAY_6=as.integer(replace(PAY_6, PAY_6<0, 0)),
+                     BILL_AMT1=as.integer(BILL_AMT1),
+                     BILL_AMT2=as.integer(BILL_AMT2),
+                     BILL_AMT3=as.integer(BILL_AMT3),
+                     BILL_AMT4=as.integer(BILL_AMT4),
+                     BILL_AMT5=as.integer(BILL_AMT5),
+                     BILL_AMT6=as.integer(BILL_AMT6),
+                     PAY_AMT1=as.integer(PAY_AMT1),
+                     PAY_AMT2=as.integer(PAY_AMT2),
+                     PAY_AMT3=as.integer(PAY_AMT3),
+                     PAY_AMT4=as.integer(PAY_AMT4),
+                     PAY_AMT5=as.integer(PAY_AMT5),
+                     PAY_AMT6=as.integer(PAY_AMT6),
+                     `default payment next month`=factor(
+                        `default payment next month`)
+              )
+    
+    #dataset.1 = dataset %>% filter(`default payment next month` == 1)
+    #dataset.0 = dataset %>% filter(`default payment next month` == 0) %>% 
+    #            sample_n(nrow(dataset.1))
+    #
+    #dataset = rbind(dataset.0, dataset.1)
+
+    return(dataset)
+}

data-collection/indian-liver/config.yaml

@@ -0,0 +1,17 @@
+--- 
+name: ILPD (Indian Liver Patient Dataset)
+
+info: https://archive.ics.uci.edu/ml/datasets/ILPD+(Indian+Liver+Patient+Dataset)
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/00225/Indian%20Liver%20Patient%20Dataset%20(ILPD).csv
+
+cite: > 
+    https://archive.ics.uci.edu/ml/citation_policy.html
+
+    @misc{Lichman:2013 ,
+    author = "M. Lichman",
+    year = "2013",
+    title = "{UCI} Machine Learning Repository",
+    url = "http://archive.ics.uci.edu/ml",
+    institution = "University of California, Irvine, School of Information and Computer Sciences" } 

data-collection/indian-liver/preprocess.R

@@ -0,0 +1,14 @@
+preprocessDataset = function()
+{   
+    csv.file = "Indian Liver Patient Dataset (ILPD).csv"
+    
+    dataset = read.csv(paste0(orig.dir, "/", csv.file),
+                       header=FALSE)
+    
+    colnames(dataset) = c("Age", "Gender", "TB", "DB", "Alkphos", "Sgpt", 
+                          "Sgot", "TP", "ALB", "A/G Ratio", "Selector")
+    
+    dataset = dataset %>% mutate(Selector=factor(Selector))
+
+    return(dataset)
+}

data-collection/magic/config.yaml

@@ -0,0 +1,18 @@
+--- 
+name: MAGIC Gamma Telescope
+
+info: https://archive.ics.uci.edu/ml/datasets/MAGIC+Gamma+Telescope
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/magic/magic04.data
+- https://archive.ics.uci.edu/ml/machine-learning-databases/magic/magic04.names
+
+cite: > 
+    https://archive.ics.uci.edu/ml/citation_policy.html
+
+    @misc{Lichman:2013 ,
+    author = "M. Lichman",
+    year = "2013",
+    title = "{UCI} Machine Learning Repository",
+    url = "http://archive.ics.uci.edu/ml",
+    institution = "University of California, Irvine, School of Information and Computer Sciences" } 

data-collection/magic/preprocess.R

@@ -0,0 +1,13 @@
+preprocessDataset = function()
+{   
+    csv.file = "magic04.data"
+    
+    dataset = read.csv(paste0(orig.dir, "/", csv.file),
+                       header=FALSE)
+    
+    colnames(dataset) = c("fLength", "fWidth", "fSize", "fConc", "fConc1", 
+                          "fAsym", "fM3Long", "fM3Trans", "fAlpha", "fDist", 
+                          "class")
+
+    return(dataset)
+}

data-collection/seismic-bumps/config.yaml

@@ -0,0 +1,10 @@
+--- 
+name: Seismic bumps
+
+info: https://archive.ics.uci.edu/ml/datasets/seismic-bumps
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/00266/seismic-bumps.arff
+
+cite: > 
+    Sikora M., Wrobel L.: Application of rule induction algorithms for analysis of data collected by seismic hazard monitoring systems in coal mines. Archives of Mining Sciences, 55(1), 2010, 91-114.

data-collection/seismic-bumps/preprocess.R

@@ -0,0 +1,30 @@
+preprocessDataset = function()
+{   
+    #set.seed(SEED)
+    
+    arff.file = "seismic-bumps.arff"
+    
+    dataset = read.arff(paste0(orig.dir, "/", arff.file))
+    
+    dataset = dataset %>% select(-c(nbumps6:nbumps89)) %>%
+              mutate(genergy=as.integer(genergy),
+                     gpuls=as.integer(gpuls),
+                     gdenergy=as.integer(gdenergy),
+                     gdpuls=as.integer(gdpuls),
+                     nbumps=as.integer(nbumps),
+                     nbumps2=as.integer(nbumps2),
+                     nbumps3=as.integer(nbumps3),
+                     nbumps4=as.integer(nbumps4),
+                     nbumps5=as.integer(nbumps5),
+                     energy=as.integer(energy),
+                     maxenergy=as.integer(maxenergy)
+              )
+    
+    #dataset.1 = dataset %>% filter(class == "1")
+    #dataset.0 = dataset %>% filter(class == "0") %>% 
+    #            sample_n(nrow(dataset.1)*4)
+    #
+    #dataset = rbind(dataset.0, dataset.1)
+
+    return(dataset)
+}

data-collection/spambase/config.yaml

@@ -0,0 +1,19 @@
+--- 
+name: Spambase
+
+info: https://archive.ics.uci.edu/ml/datasets/Spambase
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/spambase/spambase.DOCUMENTATION
+- https://archive.ics.uci.edu/ml/machine-learning-databases/spambase/spambase.data
+- https://archive.ics.uci.edu/ml/machine-learning-databases/spambase/spambase.names
+
+cite: > 
+    https://archive.ics.uci.edu/ml/citation_policy.html
+
+    @misc{Lichman:2013 ,
+    author = "M. Lichman",
+    year = "2013",
+    title = "{UCI} Machine Learning Repository",
+    url = "http://archive.ics.uci.edu/ml",
+    institution = "University of California, Irvine, School of Information and Computer Sciences" }

data-collection/spambase/preprocess.R

@@ -0,0 +1,33 @@
+preprocessDataset = function()
+{   
+    csv.file = "spambase.data"
+    
+    dataset = read.csv(paste0(orig.dir, "/", csv.file),
+                      header=FALSE)
+    
+    colnames(dataset) = c("word_freq_make", "word_freq_address", "word_freq_all",
+                          "word_freq_3d", "word_freq_our", "word_freq_over", 
+                          "word_freq_remove", "word_freq_internet", 
+                          "word_freq_order", "word_freq_mail", "word_freq_receive",
+                          "word_freq_will", "word_freq_people", "word_freq_report",
+                          "word_freq_addresses", "word_freq_free", 
+                          "word_freq_business", "word_freq_email", "word_freq_you",
+                          "word_freq_credit", "word_freq_your", "word_freq_font",
+                          "word_freq_000", "word_freq_money", "word_freq_hp",
+                          "word_freq_hpl", "word_freq_george", "word_freq_650",
+                          "word_freq_lab", "word_freq_labs", "word_freq_telnet",
+                          "word_freq_857", "word_freq_data", "word_freq_415", 
+                          "word_freq_85", "word_freq_technology", "word_freq_1999",
+                          "word_freq_parts", "word_freq_pm", "word_freq_direct",
+                          "word_freq_cs", "word_freq_meeting", "word_freq_original",
+                          "word_freq_project", "word_freq_re", "word_freq_edu",
+                          "word_freq_table", "word_freq_conference", "char_freq_;",
+                          "char_freq_(", "char_freq_[", "char_freq_!", "char_freq_$",
+                          "char_freq_#", "capital_run_length_average", 
+                          "capital_run_length_longest", "capital_run_length_total",
+                          "class")
+    
+    dataset = dataset %>% mutate(class=factor(class))
+
+    return(dataset)
+}

data-collection/wine-quality/config.yaml

@@ -0,0 +1,13 @@
+--- 
+name: Wine Quality
+
+info: https://archive.ics.uci.edu/ml/datasets/Wine+Quality
+
+urls:
+- https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv
+- https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv
+- https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality.names
+
+cite: > 
+    P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis.
+    Modeling wine preferences by data mining from physicochemical properties. In Decision Support Systems, Elsevier, 47(4):547-553, 2009.

data-collection/wine-quality/preprocess.R

@@ -0,0 +1,21 @@
+preprocessDataset = function()
+{   
+    csv.file.w = "winequality-white.csv"
+    csv.file.r = "winequality-red.csv"
+    
+    dataset.w = read.csv(paste0(orig.dir, "/", csv.file.w), sep=";",
+                         check.names=FALSE)
+    dataset.w = dataset.w %>% mutate(color="white")
+    
+    dataset.r = read.csv(paste0(orig.dir, "/", csv.file.r), sep=";",
+                         check.names=FALSE)
+    dataset.r = dataset.r %>% mutate(color="red")
+    
+    dataset = rbind(dataset.w, dataset.r) %>%
+              mutate(color=factor(color),
+                     quality=ifelse(quality>5, 1, 0)) %>%
+              select(`fixed acidity`:alcohol, color, quality) %>%
+              mutate(quality=factor(quality))
+
+    return(dataset)
+}

data-download.R

@@ -0,0 +1,49 @@
+rm(list=ls())
+
+source("config.R")
+source("utils.R")
+
+library(RCurl)
+library(tools)
+library(yaml)
+
+flog.info("Started downloading dataset collection")
+
+for (dir.name in dir(PATH_DATASETS))
+{
+    flog.info(paste("Dataset:", dir.name))
+    
+    dest.dir  = gsub("\\*", dir.name, PATH_DATASET_ORIGINAL)
+    config.yaml.file = paste0(PATH_DATASETS, dir.name, "/", FILE_CONFIG_YAML)
+    
+    urls.list = yaml.load_file(config.yaml.file)$urls
+
+    mkdir(dest.dir)
+    
+    for (url in urls.list)
+    {
+        flog.info(paste("URL:", url))
+        
+        dest.file = URLdecode(basename(url))
+        dest.file.path = paste0(dest.dir, dest.file)
+        
+        if (file.exists(dest.file.path))
+        {
+            flog.warn(paste("Target file", basename(dest.file.path), 
+                            "already exists; skipping..."))
+            next
+        }
+        
+        tryCatch(
+            raw.content <- getBinaryURL(url, .opts=curlOptions(ssl.verifypeer=FALSE)),
+            error = function(e){flog.error(e); stop(e)}
+        )
+        
+        writeBin(raw.content, dest.file.path)
+        
+    }
+    
+    flog.info("*****")
+}
+
+flog.info("Finished downloading dataset collection")

data-preprocess.R

@@ -0,0 +1,43 @@
+rm(list=ls())
+
+source("config.R")
+source("utils.R")
+
+library(dplyr)
+library(foreign)
+library(XLConnect)
+
+flog.info("Started preprocessing dataset collection")
+
+for (dir.name in dir(PATH_DATASETS))
+{
+    flog.info(paste("Dataset:", dir.name))
+    
+    orig.dir = gsub("\\*", dir.name, PATH_DATASET_ORIGINAL)
+    dest.dir = gsub("\\*", dir.name, PATH_DATASET_PREPROCESSED)
+    dest.file.path = paste0(dest.dir, FILE_PREPROCESSED_OUTPUT)
+    
+    if (file.exists(dest.file.path))
+    {
+        flog.warn(paste("Target file", basename(dest.file.path), 
+                        "already exists; skipping..."))
+        flog.info("*****")
+        next
+    }
+    
+    r.src.file = paste0(PATH_DATASETS, dir.name, "/", FILE_PREPROCESSING_SCRIPT)
+    
+    source(r.src.file)
+    dataset = preprocessDataset()
+    
+    printDatasetStatistics(dataset)
+    
+    mkdir(dest.dir)
+    saveRDS(dataset, dest.file.path)
+    
+    flog.info(paste("Created preprocessed file", FILE_PREPROCESSED_OUTPUT))
+    
+    flog.info("*****")
+}
+
+flog.info("Finished preprocessing dataset collection")

uci-ml-to-r.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 4
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX

utils.R

@@ -0,0 +1,28 @@
+library(futile.logger)
+
+mkdir = function(dest.dir)
+{
+    if (!dir.exists(dest.dir))
+    {
+        flog.debug(paste("Creating directory", dest.dir))
+        dir.create(dest.dir)
+    } else {
+        flog.debug(paste("Target directory", dest.dir, "already exists"))
+    }
+}
+
+printDatasetStatistics = function(dataset)
+{
+    if (ncol(dataset)==0) # for mockups
+    {
+        flog.warn("Empty dataset")
+        return()
+    }
+    
+    no.cases = nrow(dataset)
+    no.attributes = ncol(dataset) - 1
+    perc.classes = round(100*as.numeric(table(dataset[, ncol(dataset)]))/nrow(dataset), 0)
+    
+    flog.info(paste0("Cases: ", no.cases, ", attributes: ", no.attributes,
+                     ", classes: ", perc.classes[1], "%/", perc.classes[2], "%"))
+}