Document all datasets

DESCRIPTION

@@ -1,10 +1,16 @@
 Package: fastknn
 Version: 0.1.0
 Title: Build Fast k-Nearest Neighbor Classifiers
-Description: A fast KNN learner for binary and multinomial classification problems, build upon the ANN library. It has been developed to deal with very large datasets (> 100k rows). The 'fastknn' makes it easy to find the best 'k' and to plot beautiful decision boundaries for the classifiers. Moreover, it provides estimators for the class membership probabilities based on voting and weighted voting. The last one gives more calibrated probabilities in general, and reduces log-loss.  
+Description: A fast KNN learner for binary and multinomial classification
+    problems, build upon the ANN library. It has been developed to deal with very
+    large datasets (> 100k rows). The 'fastknn' makes it easy to find the best 'k'
+    and to plot beautiful decision boundaries for the classifiers. Moreover, it
+    provides estimators for the class membership probabilities based on voting and
+    weighted voting. The last one gives more calibrated probabilities in general,
+    and reduces log-loss.
 Authors@R: person("David", "Pinto", , "[email protected]", c("aut", "cre"))
 Depends:
-    R (>= 3.3.1), 
+    R (>= 3.3.1),
     ggplot2 (>= 2.1.0)
 Imports:
     RANN (>= 2.5),
@@ -20,3 +26,4 @@ License: GPL-2
 URL: https://github.com/davpinto/fastknn
 BugReports: https://github.com/davpinto/fastknn/issues
 LazyData: true
+RoxygenNote: 5.0.1

NAMESPACE

@@ -4,4 +4,5 @@ export("%>%")
 export(fastknn)
 export(fastknnCV)
 export(knnDecision)
+import(ggplot2)
 importFrom(magrittr,"%>%")

R/data.R

@@ -2,9 +2,45 @@
 #'
 #' Bidimensional binary dataset to be used in toy examples.
 #'
-#' @format A data frame with 2000 rows and 2 variables:
+#' @format A data.frame with 2000 rows and 3 variables:
 #' \describe{
 #'   \item{x1}{random generated}
 #'   \item{x2}{random generated}
+#'   \item{target}{class labels}
 #' }
-"chess"
+"chess"
+
+#' Spirals Dataset
+#'
+#' Bidimensional binary dataset to be used in toy examples.
+#'
+#' @format A data.frame with 2000 rows and 3 variables:
+#' \describe{
+#'   \item{x1}{random generated}
+#'   \item{x2}{random generated}
+#'   \item{target}{class labels}
+#' }
+"spirals"
+
+#' Multi Spirals Dataset
+#'
+#' Bidimensional multiclass dataset to be used in toy examples.
+#'
+#' @format A data.frame with 2000 rows and 3 variables:
+#' \describe{
+#'   \item{x1}{random generated}
+#'   \item{x2}{random generated}
+#'   \item{target}{class labels}
+#' }
+"multi_spirals"
+
+#' Covertype Data
+#'
+#' Sample of size 50k from the multiclass dataset Covertype from the UCI repository.
+#'
+#' @format A data.frame with 50000 rows and 55 variables:
+#' \describe{
+#'   \item{V1...V54}{binary features}
+#'   \item{Target}{class labels}
+#' }
+"covertype"

R/knn.R

@@ -85,7 +85,7 @@ fastknn <- function(xtr, ytr, xte, k, method = "dist") {
 #' @param folds number of folds (default is 5) or an array with fold ids between 
 #' 1 and \code{n} identifying what fold each observation is in. The fold 
 #' assigment given by \code{fastknnCV} does stratified sampling.
-#' @param eval loss to use for cross-validation. Currently five options are available:
+#' @param eval.metric loss to use for cross-validation. Currently five options are available:
 #' \itemize{
 #'  \item \code{eval.metric="overal_error"}: default option. It gives the overall 
 #'  misclassification rate.

R/utils.R

@@ -1,3 +1,5 @@
+#' @import ggplot2
+
 #' @importFrom magrittr %>%
 #' @export
-magrittr::`%>%`
+magrittr::`%>%`