add winequality data set, fix windows support

.gitignore

@@ -1,4 +1,3 @@
-/data/
 *.DS_Store
 *.Rhistory
 *.Rdata

DESCRIPTION

@@ -1,15 +1,15 @@
 Package: sgd
 Type: Package
 Title: Stochastic Gradient Descent for Scalable Estimation
-Version: 1.0
+Version: 1.1
 Authors@R: c(
-    person("Dustin", "Tran", email = "[email protected].edu", role = c("aut", "cre")),
+    person("Dustin", "Tran", email = "[email protected].edu", role = c("aut", "cre")),
     person("Panos", "Toulis", role = "aut"),
     person("Tian", "Lian", role = "ctb"),
     person("Ye", "Kuang", role = "ctb"),
     person("Edoardo", "Airoldi", role = "ctb")
     )
-Maintainer: Dustin Tran <[email protected].edu>
+Maintainer: Dustin Tran <[email protected].edu>
 Description: A fast and flexible set of tools for large scale estimation. It
     features many stochastic gradient methods, built-in models, visualization
     tools, automated hyperparameter tuning, model checking, interval estimation,
@@ -27,6 +27,7 @@ Imports:
     MASS,
     methods,
     Rcpp (>= 0.11.3)
+LazyData: yes
 LinkingTo:
     BH,
     bigmemory,

R/data-winequality.R

@@ -0,0 +1,25 @@
+#' Wine quality data of white wine samples from Portugal
+#'
+#' This dataset is a collection of white "Vinho Verde" wine
+#' samples from the north of Portugal. Due to privacy and logistic
+#' issues, only physicochemical (inputs) and sensory (the output)
+#' variables are available (e.g. there is no data about grape types,
+#' wine brand, wine selling price, etc.).
+#'
+#' @format A data frame with 4898 rows and 12 variables
+#' \itemize{
+#'   \item fixed acidity.
+#'   \item volatile acidity.
+#'   \item citric acid.
+#'   \item residual sugar.
+#'   \item chlorides.
+#'   \item free sulfur dioxide.
+#'   \item total sulfur dioxide.
+#'   \item density.
+#'   \item pH.
+#'   \item sulphates.
+#'   \item alcohol.
+#'   \item quality (score between 0 and 10).
+#' }
+#' @source \url{https://archive.ics.uci.edu/ml/datasets/Wine+Quality}
+"winequality"

R/sgd.R

@@ -174,12 +174,13 @@
 #' data("winequality")
 #' dat <- winequality
 #' dat$quality <- as.numeric(dat$quality > 5) # transform to binary
-#' test.set <- sample(1:nrow(dat), size=nrow(dat)/8, replace=F)
+#' test.set <- sample(1:nrow(dat), size=nrow(dat)/8, replace=FALSE)
 #' dat.test <- dat[test.set, ]
 #' dat <- dat[-test.set, ]
 #' sgd.theta <- sgd(quality ~ ., data=dat,
 #'                model="glm", model.control=binomial(link="logit"),
-#'                sgd.control=list(reltol=1e-5, npasses=200), lr.control=c(scale=1, gamma=1, alpha=30, c=1))
+#'                sgd.control=list(reltol=1e-5, npasses=200),
+#'                  lr.control=c(scale=1, gamma=1, alpha=30, c=1))
 #' sgd.theta
 #'
 #' @useDynLib sgd

man/sgd.Rd

@@ -171,12 +171,13 @@ set.seed(42)
 data("winequality")
 dat <- winequality
 dat$quality <- as.numeric(dat$quality > 5) # transform to binary
-test.set <- sample(1:nrow(dat), size=nrow(dat)/8, replace=F)
+test.set <- sample(1:nrow(dat), size=nrow(dat)/8, replace=FALSE)
 dat.test <- dat[test.set, ]
 dat <- dat[-test.set, ]
 sgd.theta <- sgd(quality ~ ., data=dat,
                model="glm", model.control=binomial(link="logit"),
-               sgd.control=list(reltol=1e-5, npasses=200), lr.control=c(scale=1, gamma=1, alpha=30, c=1))
+               sgd.control=list(reltol=1e-5, npasses=200),
+                 lr.control=c(scale=1, gamma=1, alpha=30, c=1))
 sgd.theta
 }
 \author{

man/winequality.Rd

@@ -0,0 +1,36 @@
+% Generated by roxygen2 (4.1.1): do not edit by hand
+% Please edit documentation in R/data-winequality.R
+\docType{data}
+\name{winequality}
+\alias{winequality}
+\title{Wine quality data of white wine samples from Portugal}
+\format{A data frame with 4898 rows and 12 variables
+\itemize{
+  \item fixed acidity.
+  \item volatile acidity.
+  \item citric acid.
+  \item residual sugar.
+  \item chlorides.
+  \item free sulfur dioxide.
+  \item total sulfur dioxide.
+  \item density.
+  \item pH.
+  \item sulphates.
+  \item alcohol.
+  \item quality (score between 0 and 10).
+}}
+\source{
+\url{https://archive.ics.uci.edu/ml/datasets/Wine+Quality}
+}
+\usage{
+winequality
+}
+\description{
+This dataset is a collection of white "Vinho Verde" wine
+samples from the north of Portugal. Due to privacy and logistic
+issues, only physicochemical (inputs) and sensory (the output)
+variables are available (e.g. there is no data about grape types,
+wine brand, wine selling price, etc.).
+}
+\keyword{datasets}
+

src/Makevars.win

@@ -1,2 +1,2 @@
-
 PKG_LIBS = $(LAPACK_LIBS) $(BLAS_LIBS) $(FLIBS)
+PKG_CPPFLAGS = -I.

src/sgd/base_sgd.h

@@ -39,7 +39,8 @@ class base_sgd {
     // Set which iterations to store estimates
     unsigned n_iters = n_samples*n_passes_;
     for (unsigned i = 0; i < size_; ++i) {
-      pos_(0, i) = int(round(pow(10, i * log10(n_iters) / (size_-1))));
+      pos_(0, i) = int(round(pow(10.,
+                   i * log10(static_cast<double>(n_iters)) / (size_-1))));
     }
     if (pos_(0, pos_.n_cols-1) != n_iters) {
       pos_(0, pos_.n_cols-1) = n_iters;