Roll the first version of UCI data with the wine dataset

Author: coatless

.Rbuildignore

@@ -0,0 +1,3 @@
+^.*\.Rproj$
+^\.Rproj\.user$
+^data-raw$

.gitignore

@@ -0,0 +1,4 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata

DESCRIPTION

@@ -0,0 +1,11 @@
+Package: ucidata
+Title: Collection of Datasets from the UCI Irving Machine Learning Repository
+Version: 0.0.1
+Authors@R: person("James", "Balamuta", email = "[email protected]", role = c("aut", "cre"))
+Description: Varying datasets from the UCI Irving Machine Learning Repository
+Depends: R (>= 3.4.1)
+License: GPL (>=2)
+Encoding: UTF-8
+LazyData: true
+Roxygen: list(markdown = TRUE)
+RoxygenNote: 6.0.1

NAMESPACE

@@ -0,0 +1,2 @@
+# Generated by roxygen2: do not edit by hand
+

R/pkg_datasets.R

@@ -0,0 +1,33 @@
+#' Wine Data Set
+#'
+#' This data set is the combination of two datasets that were created, using red and white wine samples.
+#' The inputs include objective tests (e.g. PH values) and the output is based on sensory data
+#' (median of at least 3 evaluations made by wine experts). Each expert graded the wine quality
+#' between 0 (very bad) and 10 (very excellent). Several data mining methods were applied to model
+#' these datasets under a regression approach. The support vector machine model achieved the
+#' best results. Several metrics were computed: MAD, confusion matrix for a fixed error tolerance (T),
+#' etc. Also, we plot the relative importances of the input variables (as measured by a sensitivity
+#'                                                                     analysis procedure).
+#' @format A data frame with 6497 observations (1599 Red and 4898 White) on the following 12 variables.
+#' - fixed acidity
+#' - volatile acidity
+#' - citric acid
+#' - residual sugar
+#' - chlorides
+#' - free sulfur dioxide
+#' - total sulfur dioxide
+#' - density
+#' - pH
+#' - sulphates
+#' - alcohol
+#' - quality
+#'     - Score between 0 and 10 based on sensor reading
+#' - color
+#'     - `"White"` or `"Red"`
+#' @source 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. ISSN: 0167-9236.
+#' @references
+#' <https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.names>
+#' <https://archive.ics.uci.edu/ml/datasets/wine>
+"wine"

R/ucidata.R

@@ -0,0 +1,2 @@
+#' @keywords internal
+"_PACKAGE"

data-raw/wine_build.R

@@ -0,0 +1,25 @@
+### UCI Irving
+## Wine Data https://archive.ics.uci.edu/ml/datasets/wine
+
+# Location of Data Sets
+red_wine_url   = "http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv"
+white_wine_url = "http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv"
+
+# Note the .csv uses a `;` as the separater. Not `,`
+red_wine_data   = read.csv(red_wine_url, sep = ";")
+white_wine_data = read.csv(white_wine_url, sep = ";")
+
+# Load in Red vs. White Data
+red_wine_data$color   = "Red"
+white_wine_data$color = "White"
+
+# Merge the two data sets together
+wine = rbind(red_wine_data, white_wine_data)
+
+# Convert color into a factor
+wine$color = as.factor(wine$color)
+
+# Remove periods
+colnames(wine) = gsub("\\.", "_", colnames(wine))
+
+devtools::use_data(wine)