[Rprotobuf-commits] r749 - papers/jss
noreply at r-forge.r-project.org
noreply at r-forge.r-project.org
Sat Jan 11 18:28:04 CET 2014
Author: edd
Date: 2014-01-11 18:28:04 +0100 (Sat, 11 Jan 2014)
New Revision: 749
Added:
papers/jss/article.bib
Removed:
papers/jss/eddelbuettel-stokely.bib
Modified:
papers/jss/article.Rnw
Log:
rename bib file
Modified: papers/jss/article.Rnw
===================================================================
--- papers/jss/article.Rnw 2014-01-11 17:17:46 UTC (rev 748)
+++ papers/jss/article.Rnw 2014-01-11 17:28:04 UTC (rev 749)
@@ -14,8 +14,9 @@
\DefineVerbatimEnvironment{example}{Verbatim}{}
%% almost as usual
-\author{Dirk Eddelbuettel\\Debian and R Projects \And
- Murray Stokely\\Google, Inc}
+\author{Dirk Eddelbuettel\\Debian Project \And
+ Murray Stokely\\Google, Inc \And
+ Jeroen Ooms\\UCLA}
\title{\pkg{RProtoBuf}: Efficient Cross-Language Data Serialization in R}
%% for pretty printing and a nice hypersummary also set:
@@ -50,7 +51,11 @@
%% The address of (at least) one author should be given
%% in the following format:
\Address{
- Dirk Eddelbuettel\\
+ Dirk Eddelbuettel \\
+ Debian Project \\
+ River Forest, IL, USA\\
+ E-mail: \email{edd at debian.org}\\
+ URL: \url{http://dirk.eddelbuettel.com}\\
\\
Murray Stokely\\
Google, Inc.\\
@@ -58,7 +63,13 @@
Mountain View, CA 94040\\
USA\\
E-mail: \email{mstokely at google.com}\\
- URL: \url{http://www.stokely.org/}
+ URL: \url{http://www.stokely.org/}\\
+ \\
+ Jeroen Ooms\\
+ UCLA Department of Statistics\\
+ University of California\\
+ E-mail: \email{jeroen.ooms at stat.ucla.edu}\\
+ URL: \url{http://jeroenooms.github.io}
}
%% It is also possible to add a telephone and fax number
%% before the e-mail in the following format:
@@ -636,24 +647,23 @@
% TODO(ms): Add column check box for doing dynamic dispatch based on type.
\begin{table}[h]
\centering
-\begin{tabular}{|l|c|c|l|}
-\hline
-\textbf{Class} & \textbf{Slots} & \textbf{Methods} & \textbf{Dynamic Dispatch}\\
-\hline
-\hline
-Message & 2 & 20 & yes (field names)\\
-\hline
-Descriptor & 2 & 16 & yes (field names, enum types, nested types)\\
-\hline
-FieldDescriptor & 4 & 18 & no\\
-\hline
-EnumDescriptor & 4 & 11 & yes (enum constant names)\\
-\hline
-FileDescriptor & 3 & 6 & yes (message/field definitions)\\
-\hline
-EnumValueDescriptor & 3 & 6 & no\\
-\hline
+\begin{tabular}{lccl}
+\toprule
+\textbf{Class} &
+ \textbf{Slots} &
+ \textbf{Methods} &
+ \textbf{Dynamic Dispatch}\\
+\cmidrule{1-4}
+Message & 2 & 20 & yes (field names)\\
+Descriptor & 2 & 16 & yes (field names, enum types, nested types)\\
+FieldDescriptor & 4 & 18 & no\\
+EnumDescriptor & 4 & 11 & yes (enum constant names)\\
+FileDescriptor & 3 & \phantom{1}6 & yes (message/field definitions)\\
+EnumValueDescriptor & 3 & \phantom{1}6 & no\\
+\bottomrule
\end{tabular}
+\caption{\label{Message-methods-table}Overview of Class, Slot, Method and
+ Dispatch Relationships}
\end{table}
\subsection{Messages}
@@ -669,34 +679,32 @@
\begin{table}[h]
\centering
\begin{small}
-\begin{tabular}{l|p{10cm}}
-\hline
+\begin{tabular}{lp{10cm}}
+\toprule
\textbf{Slot} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{pointer} & External pointer to the \texttt{Message} object of the C++ proto library. Documentation for the
\texttt{Message} class is available from the protocol buffer project page:
\url{http://code.google.com/apis/protocolbuffers/docs/reference/cpp/google.protobuf.message.html#Message} \\
-\hline
\texttt{type} & Fully qualified name of the message. For example a \texttt{Person} message
has its \texttt{type} slot set to \texttt{tutorial.Person} \\[.3cm]
-\hline
\textbf{Method} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{has} & Indicates if a message has a given field. \\
\texttt{clone} & Creates a clone of the message \\
\texttt{isInitialized} & Indicates if a message has all its required fields set\\
\texttt{serialize} & serialize a message to a file, binary connection, or raw vector\\
\texttt{clear} & Clear one or several fields of a message, or the entire message\\
\texttt{size} & The number of elements in a message field\\
-\texttt{bytesize} & The number of bytes the message would take once serialized\\
-\hline
+\texttt{bytesize} & The number of bytes the message would take once serialized\\[3mm]
+%
\texttt{swap} & swap elements of a repeated field of a message\\
\texttt{set} & set elements of a repeated field\\
\texttt{fetch} & fetch elements of a repeated field\\
\texttt{setExtension} & set an extension of a message\\
\texttt{getExtension} & get the value of an extension of a message\\
-\texttt{add} & add elements to a repeated field \\
-\hline
+\texttt{add} & add elements to a repeated field \\[3mm]
+%
\texttt{str} & the R structure of the message\\
\texttt{as.character} & character representation of a message\\
\texttt{toString} & character representation of a message (same as \texttt{as.character}) \\
@@ -745,23 +753,21 @@
\begin{table}[h]
\centering
\begin{small}
-\begin{tabular}{l|p{10cm}}
-\hline
+\begin{tabular}{lp{10cm}}
+\toprule
\textbf{Slot} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{pointer} & External pointer to the \texttt{Descriptor} object of the C++ proto library. Documentation for the
\texttt{Descriptor} class is available from the protocol buffer project page:
\url{http://code.google.com/apis/protocolbuffers/docs/reference/cpp/google.protobuf.descriptor.html#Descriptor} \\
-\hline
\texttt{type} & Fully qualified path of the message type. \\[.3cm]
-\hline
+%
\textbf{Method} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{new} & Creates a prototype of a message described by this descriptor.\\
\texttt{read} & Reads a message from a file or binary connection.\\
\texttt{readASCII} & Read a message in ASCII format from a file or
text connection.\\
-\hline
\texttt{name} & Retrieve the name of the message type associated with
this descriptor.\\
\texttt{as.character} & character representation of a descriptor\\
@@ -769,7 +775,6 @@
\texttt{as.list} & return a named
list of the field, enum, and nested descriptors included in this descriptor.\\
\texttt{asMessage} & return DescriptorProto message. \\
-\hline
\texttt{fileDescriptor} & Retrieve the file descriptor of this
descriptor.\\
\texttt{containing\_type} & Retrieve the descriptor describing the message type containing this descriptor.\\
@@ -781,7 +786,7 @@
\texttt{enum\_type\_count} & The number of enum types in this descriptor.\\
\texttt{enum\_type} & Return the descriptor for the specified enum
type in this descriptor.\\
-\hline
+\bottomrule
\end{tabular}
\end{small}
\caption{\label{Descriptor-methods-table}Description of slots and methods for the \texttt{Descriptor} S4 class}
@@ -799,23 +804,19 @@
\begin{table}[h]
\centering
\begin{small}
-\begin{tabular}{l|p{10cm}}
-\hline
+\begin{tabular}{lp{10cm}}
+\toprule
\textbf{Slot} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{pointer} & External pointer to the \texttt{FieldDescriptor} C++ variable \\
-\hline
\texttt{name} & Simple name of the field \\
-\hline
\texttt{full\_name} & Fully qualified name of the field \\
-\hline
\texttt{type} & Name of the message type where the field is declared \\[.3cm]
-\hline
+%
\textbf{Method} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{as.character} & Character representation of a descriptor\\
-\texttt{toString} & Character
-representation of a descriptor (same as \texttt{as.character}) \\
+\texttt{toString} & Character representation of a descriptor (same as \texttt{as.character}) \\
\texttt{asMessage} & Return FieldDescriptorProto message. \\
\texttt{name} & Return the name of the field descriptor.\\
\texttt{fileDescriptor} & Return the fileDescriptor where this field is defined.\\
@@ -832,7 +833,7 @@
\texttt{default\_value} & Return the default value.\\
\texttt{message\_type} & Return the message type if this is a message type field.\\
\texttt{enum\_type} & Return the enum type if this is an enum type field.\\
-\hline
+\bottomrule
\end{tabular}
\end{small}
\caption{\label{fielddescriptor-methods-table}Description of slots and
@@ -863,20 +864,17 @@
\begin{table}[h]
\centering
\begin{small}
-\begin{tabular}{l|p{10cm}}
-\hline
+\begin{tabular}{lp{10cm}}
+\toprule
\textbf{Slot} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{pointer} & External pointer to the \texttt{EnumDescriptor} C++ variable \\
-\hline
\texttt{name} & Simple name of the enum \\
-\hline
\texttt{full\_name} & Fully qualified name of the enum \\
-\hline
\texttt{type} & Name of the message type where the enum is declared \\[.3cm]
-\hline
+%
\textbf{Method} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{as.list} & return a named
integer vector with the values of the enum and their names.\\
\texttt{as.character} & character representation of a descriptor\\
@@ -890,7 +888,7 @@
\texttt{has} & Return TRUE if this enum contains the specified named constant string.\\
\texttt{value\_count} & Return the number of constants in this enum (same as \texttt{length}).\\
\texttt{value} & Return the EnumValueDescriptor of an enum value of specified index, name, or number.\\
-\hline
+\bottomrule
\end{tabular}
\end{small}
\caption{\label{enumdescriptor-methods-table}Description of slots and methods for the \texttt{EnumDescriptor} S4 class}
@@ -916,27 +914,24 @@
\begin{table}[h]
\centering
\begin{small}
-\begin{tabular}{l|p{10cm}}
-\hline
-\textbf{slot} & \textbf{description} \\
-\hline
+\begin{tabular}{lp{10cm}}
+\toprule
+\textbf{Slot} & \textbf{Description} \\
+\cmidrule(r){2-2}
\texttt{pointer} & external pointer to the \texttt{FileDescriptor} object of the C++ proto library. Documentation for the
\texttt{FileDescriptor} class is available from the protocol buffer project page:
\url{http://developers.google.com/protocol-buffers/docs/reference/cpp/google.protobuf.descriptor.html#FileDescriptor} \\
-\hline
\texttt{filename} & fully qualified pathname of the \texttt{.proto} file.\\
-\hline
\texttt{package} & package name defined in this \texttt{.proto} file.\\[.3cm]
-\hline
\textbf{Method} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{name} & Return the filename for this FileDescriptorProto.\\
\texttt{package} & Return the file-level package name specified in this FileDescriptorProto.\\
\texttt{as.character} & character representation of a descriptor. \\
\texttt{toString} & character representation of a descriptor (same as \texttt{as.character}). \\
\texttt{asMessage} & return FileDescriptorProto message. \\
\texttt{as.list} & return named list of descriptors defined in this file descriptor.\\
-\hline
+\bottomrule
\end{tabular}
\end{small}
\caption{\label{filedescriptor-methods-table}Description of slots and methods for the \texttt{FileDescriptor} S4 class}
@@ -961,25 +956,23 @@
\begin{table}[h]
\centering
\begin{small}
-\begin{tabular}{l|p{10cm}}
-\hline
-\textbf{slot} & \textbf{description} \\
-\hline
+\begin{tabular}{lp{10cm}}
+\toprule
+\textbf{Slot} & \textbf{Description} \\
+\cmidrule(r){2-2}
\texttt{pointer} & External pointer to the \texttt{EnumValueDescriptor} C++ variable \\
-\hline
\texttt{name} & simple name of the enum value \\
-\hline
\texttt{full\_name} & fully qualified name of the enum value \\[.3cm]
-\hline
+%
\textbf{Method} & \textbf{Description} \\
-\hline
+\cmidrule(r){2-2}
\texttt{number} & return the number of this EnumValueDescriptor. \\
\texttt{name} & Return the name of the enum value descriptor.\\
\texttt{enum\_type} & return the EnumDescriptor type of this EnumValueDescriptor. \\
\texttt{as.character} & character representation of a descriptor. \\
\texttt{toString} & character representation of a descriptor (same as \texttt{as.character}). \\
\texttt{asMessage} & return EnumValueDescriptorProto message. \\
-\hline
+\bottomrule
\end{tabular}
\end{small}
\caption{\label{EnumValueDescriptor-methods-table}Description of slots
@@ -1000,37 +993,29 @@
\begin{table}[h]
\centering
\begin{small}
-\begin{tabular}{|c|p{5cm}p{5cm}|}
-\hline
-field type & R type (non repeated) & R type (repeated) \\
-\hline
-\hline
+\begin{tabular}{lp{5cm}p{5cm}}
+\toprule
+Field type & R type (non repeated) & R type (repeated) \\
+\cmidrule(r){2-3}
double & \texttt{double} vector & \texttt{double} vector \\
-float & \texttt{double} vector & \texttt{double} vector \\
-\hline
+float & \texttt{double} vector & \texttt{double} vector \\[3mm]
uint32 & \texttt{double} vector & \texttt{double} vector \\
-fixed32 & \texttt{double} vector & \texttt{double} vector \\
-\hline
+fixed32 & \texttt{double} vector & \texttt{double} vector \\[3mm]
int32 & \texttt{integer} vector & \texttt{integer} vector \\
sint32 & \texttt{integer} vector & \texttt{integer} vector \\
-sfixed32 & \texttt{integer} vector & \texttt{integer} vector \\
-\hline
+sfixed32 & \texttt{integer} vector & \texttt{integer} vector \\[3mm]
int64 & \texttt{integer} or \texttt{character}
vector \footnotemark & \texttt{integer} or \texttt{character} vector \\
uint64 & \texttt{integer} or \texttt{character} vector & \texttt{integer} or \texttt{character} vector \\
sint64 & \texttt{integer} or \texttt{character} vector & \texttt{integer} or \texttt{character} vector \\
fixed64 & \texttt{integer} or \texttt{character} vector & \texttt{integer} or \texttt{character} vector \\
-sfixed64 & \texttt{integer} or \texttt{character} vector & \texttt{integer} or \texttt{character} vector \\
-\hline
-bool & \texttt{logical} vector & \texttt{logical} vector \\
-\hline
+sfixed64 & \texttt{integer} or \texttt{character} vector & \texttt{integer} or \texttt{character} vector \\\hline
+bool & \texttt{logical} vector & \texttt{logical} vector \\[3mm]
string & \texttt{character} vector & \texttt{character} vector \\
-bytes & \texttt{character} vector & \texttt{character} vector \\
-\hline
-enum & \texttt{integer} vector & \texttt{integer} vector \\
-\hline
+bytes & \texttt{character} vector & \texttt{character} vector \\[3mm]
+enum & \texttt{integer} vector & \texttt{integer} vector \\[3mm]
message & \texttt{S4} object of class \texttt{Message} & \texttt{list} of \texttt{S4} objects of class \texttt{Message} \\
-\hline
+\bottomrule
\end{tabular}
\end{small}
\caption{\label{table-get-types}Correspondence between field type and
@@ -1240,68 +1225,69 @@
% Fri Dec 27 17:00:03 2013
\begin{table}[h!]
\begin{center}
+ \small
\scalebox{0.9}{
-\begin{tabular}{l|r|r|r|r|r}
- \hline
-Data Set & object.size & \multicolumn{2}{c|}{R Serialization} &
-\multicolumn{2}{c}{RProtoBuf Serialization} \\
- & & Default & gzipped & Default & gzipped \\
- \hline
-uspop & 584.00 & 268 & 172 & 211 & 148 \\
- Titanic & 1960.00 & 633 & 257 & 481 & 249 \\
- volcano & 42656.00 & 42517 & 5226 & 42476 & 4232 \\
- euro.cross & 2728.00 & 1319 & 910 & 1207 & 891 \\
- attenu & 14568.00 & 8234 & 2165 & 7771 & 2336 \\
- ToothGrowth & 2568.00 & 1486 & 349 & 1239 & 391 \\
- lynx & 1344.00 & 1028 & 429 & 971 & 404 \\
- nottem & 2352.00 & 2036 & 627 & 1979 & 641 \\
- sleep & 2752.00 & 746 & 282 & 483 & 260 \\
- co2 & 4176.00 & 3860 & 1473 & 3803 & 1453 \\
- austres & 1144.00 & 828 & 439 & 771 & 410 \\
- ability.cov & 1944.00 & 716 & 357 & 589 & 341 \\
- EuStockMarkets & 60664.00 & 59785 & 21232 & 59674 & 19882 \\
- treering & 64272.00 & 63956 & 17647 & 63900 & 17758 \\
- freeny.x & 1944.00 & 1445 & 1311 & 1372 & 1289 \\
- Puromycin & 2088.00 & 813 & 306 & 620 & 320 \\
- warpbreaks & 2768.00 & 1231 & 310 & 811 & 343 \\
- BOD & 1088.00 & 334 & 182 & 226 & 168 \\
- sunspots & 22992.00 & 22676 & 6482 & 22620 & 6742 \\
- beaver2 & 4184.00 & 3423 & 751 & 3468 & 840 \\
- anscombe & 2424.00 & 991 & 375 & 884 & 352 \\
- esoph & 5624.00 & 3111 & 548 & 2240 & 665 \\
- PlantGrowth & 1680.00 & 646 & 303 & 459 & 314 \\
- infert & 15848.00 & 14328 & 1172 & 13197 & 1404 \\
- BJsales & 1632.00 & 1316 & 496 & 1259 & 465 \\
- stackloss & 1688.00 & 917 & 293 & 844 & 283 \\
- crimtab & 7936.00 & 4641 & 713 & 1655 & 576 \\
- LifeCycleSavings & 6048.00 & 3014 & 1420 & 2825 & 1407 \\
- Harman74.cor & 9144.00 & 6056 & 2045 & 5861 & 2070 \\
- nhtemp & 912.00 & 596 & 240 & 539 & 223 \\
- faithful & 5136.00 & 4543 & 1339 & 4936 & 1776 \\
- freeny & 5296.00 & 2465 & 1518 & 2271 & 1507 \\
- discoveries & 1232.00 & 916 & 199 & 859 & 180 \\
- state.x77 & 7168.00 & 4251 & 1754 & 4068 & 1756 \\
- pressure & 1096.00 & 498 & 277 & 427 & 273 \\
- fdeaths & 1008.00 & 692 & 291 & 635 & 272 \\
- euro & 976.00 & 264 & 186 & 202 & 161 \\
- LakeHuron & 1216.00 & 900 & 420 & 843 & 404 \\
- mtcars & 6736.00 & 3798 & 1204 & 3633 & 1206 \\
- precip & 4992.00 & 1793 & 813 & 1615 & 815 \\
- state.area & 440.00 & 422 & 246 & 405 & 235 \\
- attitude & 3024.00 & 1990 & 544 & 1920 & 561 \\
- randu & 10496.00 & 9794 & 8859 & 10441 & 9558 \\
- state.name & 3088.00 & 844 & 408 & 724 & 415 \\
- airquality & 5496.00 & 4551 & 1241 & 2874 & 1294 \\
- airmiles & 624.00 & 308 & 170 & 251 & 148 \\
- quakes & 33112.00 & 32246 & 9898 & 29063 & 11595 \\
- islands & 3496.00 & 1232 & 563 & 1098 & 561 \\
- OrchardSprays & 3600.00 & 2164 & 445 & 1897 & 483 \\
- WWWusage & 1232.00 & 916 & 274 & 859 & 251 \\
- \hline
+\begin{tabular}{lrrrrr}
+ \toprule
+ Data Set & object.size & \multicolumn{2}{c}{R Serialization} &
+ \multicolumn{2}{c}{RProtoBuf Serial.} \\
+ & & default & gzipped & default & gzipped \\
+ \cmidrule(r){2-6}
+ uspop & 584 & 268 & 172 & 211 & 148 \\
+ Titanic & 1960 & 633 & 257 & 481 & 249 \\
+ volcano & 42656 & 42517 & 5226 & 42476 & 4232 \\
+ euro.cross & 2728 & 1319 & 910 & 1207 & 891 \\
+ attenu & 14568 & 8234 & 2165 & 7771 & 2336 \\
+ ToothGrowth & 2568 & 1486 & 349 & 1239 & 391 \\
+ lynx & 1344 & 1028 & 429 & 971 & 404 \\
+ nottem & 2352 & 2036 & 627 & 1979 & 641 \\
+ sleep & 2752 & 746 & 282 & 483 & 260 \\
+ co2 & 4176 & 3860 & 1473 & 3803 & 1453 \\
+ austres & 1144 & 828 & 439 & 771 & 410 \\
+ ability.cov & 1944 & 716 & 357 & 589 & 341 \\
+ EuStockMarkets & 60664 & 59785 & 21232 & 59674 & 19882 \\
+ treering & 64272 & 63956 & 17647 & 63900 & 17758 \\
+ freeny.x & 1944 & 1445 & 1311 & 1372 & 1289 \\
+ Puromycin & 2088 & 813 & 306 & 620 & 320 \\
+ warpbreaks & 2768 & 1231 & 310 & 811 & 343 \\
+ BOD & 1088 & 334 & 182 & 226 & 168 \\
+ sunspots & 22992 & 22676 & 6482 & 22620 & 6742 \\
+ beaver2 & 4184 & 3423 & 751 & 3468 & 840 \\
+ anscombe & 2424 & 991 & 375 & 884 & 352 \\
+ esoph & 5624 & 3111 & 548 & 2240 & 665 \\
+ PlantGrowth & 1680 & 646 & 303 & 459 & 314 \\
+ infert & 15848 & 14328 & 1172 & 13197 & 1404 \\
+ BJsales & 1632 & 1316 & 496 & 1259 & 465 \\
+ stackloss & 1688 & 917 & 293 & 844 & 283 \\
+ crimtab & 7936 & 4641 & 713 & 1655 & 576 \\
+ LifeCycleSavings & 6048 & 3014 & 1420 & 2825 & 1407 \\
+ Harman74.cor & 9144 & 6056 & 2045 & 5861 & 2070 \\
+ nhtemp & 912 & 596 & 240 & 539 & 223 \\
+ faithful & 5136 & 4543 & 1339 & 4936 & 1776 \\
+ freeny & 5296 & 2465 & 1518 & 2271 & 1507 \\
+ discoveries & 1232 & 916 & 199 & 859 & 180 \\
+ state.x77 & 7168 & 4251 & 1754 & 4068 & 1756 \\
+ pressure & 1096 & 498 & 277 & 427 & 273 \\
+ fdeaths & 1008 & 692 & 291 & 635 & 272 \\
+ euro & 976 & 264 & 186 & 202 & 161 \\
+ LakeHuron & 1216 & 900 & 420 & 843 & 404 \\
+ mtcars & 6736 & 3798 & 1204 & 3633 & 1206 \\
+ precip & 4992 & 1793 & 813 & 1615 & 815 \\
+ state.area & 440 & 422 & 246 & 405 & 235 \\
+ attitude & 3024 & 1990 & 544 & 1920 & 561 \\
+ randu & 10496 & 9794 & 8859 & 10441 & 9558 \\
+ state.name & 3088 & 844 & 408 & 724 & 415 \\
+ airquality & 5496 & 4551 & 1241 & 2874 & 1294 \\
+ airmiles & 624 & 308 & 170 & 251 & 148 \\
+ quakes & 33112 & 32246 & 9898 & 29063 & 11595 \\
+ islands & 3496 & 1232 & 563 & 1098 & 561 \\
+ OrchardSprays & 3600 & 2164 & 445 & 1897 & 483 \\
+ WWWusage & 1232 & 916 & 274 & 859 & 251 \\
+ \bottomrule
\end{tabular}
}
-\caption{Serialization sizes with R's built-in serialization and
- RProtoBuf for 50 sample R datasets.}
+\caption{Serialization sizes for default serialization in R and
+ RProtoBuf for 50 R datasets.}
\label{tab:compression}
\end{center}
\end{table}
@@ -1637,7 +1623,7 @@
helpful in reviewing code or offering suggestions. The contemporaneous
work by Saptarshi Guha on \pkg{RHIPE} was a strong initial motivator.
-\bibliography{eddelbuettel-stokely}
+\bibliography{article}
%\section[About Java]{About \proglang{Java}}
%% Note: If there is markup in \(sub)section, then it has to be escape as above.
Copied: papers/jss/article.bib (from rev 747, papers/jss/eddelbuettel-stokely.bib)
===================================================================
--- papers/jss/article.bib (rev 0)
+++ papers/jss/article.bib 2014-01-11 17:28:04 UTC (rev 749)
@@ -0,0 +1,294 @@
+ at article{eddelbuettel2011rcpp,
+ title={Rcpp: Seamless R and C++ integration},
+ author={Dirk Eddelbuettel and Romain Fran{\c{c}}ois},
+ journal={Journal of Statistical Software},
+ volume={40},
+ number={8},
+ pages={1--18},
+ year={2011}
+}
+ at Manual{msgpackR,
+ title = {msgpackR: A library to serialize or unserialize data in MessagePack format},
+ author = {Mikiya Tanizawa},
+ year = {2013},
+ note = {R package version 1.1},
+ url = {http://CRAN.R-project.org/package=msgpackR},
+}
+ at Manual{rmongodb,
+ title={rmongodb: R-MongoDB driver},
+ author={Gerald Lindsly},
+ year = {2013},
+ note = {R package version 1.3.3},
+ url = {http://CRAN.R-project.org/package=rmongodb},
+}
+ at Manual{int64,
+ title = {int64: 64 bit integer types},
+ author = {Romain Fran{\c{c}}ois},
+ year = {2011},
+ note = {R package version 1.1.2},
+ url = {http://CRAN.R-project.org/package=int64},
+}
+ at Manual{bit64,
+ title = {bit64: A S3 class for vectors of 64bit integers},
+ author = {Jens Oehlschl\"{a}gel},
+ year = {2012},
+ note = {R package version 0.9-3},
+ url = {http://CRAN.R-project.org/package=bit64},
+}
+ at book{eddelbuettel2013seamless,
+ title={Seamless R and C++ Integration with Rcpp},
+ author={Dirk Eddelbuettel},
+ year={2013},
+ publisher={Springer}
+}
+ at Manual{rhipe,
+ title = {RHIPE: A Distributed Environment for the Analysis of Large and Complex Datasets},
+ author = {Saptarshi Guha},
+ year = {2010},
+ url = {http://www.stat.purdue.edu/~sguha/rhipe/},
+}
+ at misc{serialization,
+author= {Luke Tierney},
+title = {A New Serialization Mechanism for R},
+url = {http://www.cs.uiowa.edu/~luke/R/serialize/serialize.ps},
+year = {2003},
+}
+ at manual{eddelbuettel2013exposing,
+ title={Exposing C++ functions and classes with Rcpp modules},
+ author={Dirk Eddelbuettel and Romain Fran{\c{c}}ois},
+ year={2013},
+ note={Vignette included in R package Rcpp},
+ url = {http://CRAN.R-project.org/package=Rcpp},
+}
+ at inproceedings{cantrill2004dynamic,
+ title={Dynamic Instrumentation of Production Systems.},
+ author={Bryan Cantrill and Michael W Shapiro and Adam H Leventhal and others},
+ booktitle={USENIX Annual Technical Conference, General Track},
+ pages={15--28},
+ year={2004}
+}
+ at article{swain1991color,
+ title={Color indexing},
+ author={Michael J Swain and Dana H Ballard},
+ journal={International journal of computer vision},
+ volume={7},
+ number={1},
+ pages={11--32},
+ year={1991},
+ publisher={Springer}
+}
+ at article{rubner2000earth,
+ title={The earth mover's distance as a metric for image retrieval},
+ author={Yossi Rubner and Carlo Tomasi and Leonidas J Guibas},
+ journal={International Journal of Computer Vision},
+ volume={40},
+ number={2},
+ pages={99--121},
+ year={2000},
+ publisher={Springer}
+}
+ at book{kullback1997information,
+ title={Information theory and statistics},
+ author={Solomon Kullback},
+ year={1997},
+ publisher={Courier Dover Publications}
+}
+ at inproceedings{puzicha1997non,
+ title={Non-parametric similarity measures for unsupervised texture segmentation and image retrieval},
+ author={Jan Puzicha and Thomas Hofmann and Joachim M Buhmann},
+ booktitle={Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on},
+ pages={267--272},
+ year={1997},
+ organization={IEEE}
+}
+ at inproceedings{fang1999computing,
+ title={Computing Iceberg Queries Efficiently.},
+ author={Min Fang and Narayanan Shivakumar and Hector Garcia-Molina and Rajeev Motwani and Jeffrey D Ullman},
+ booktitle={Internaational Conference on Very Large Databases (VLDB'98), New York, August 1998},
+ year={1999},
+ organization={Stanford InfoLab}
+}
+ at Manual{emdist,
+ title = {emdist: Earth Mover's Distance},
+ author = {Simon Urbanek and Yossi Rubner},
+ year = {2012},
+ note = {R package version 0.3-1},
+ url = {http://cran.r-project.org/package=emdist},
+}
+ at article{Wegiel:2010:CTT:1932682.1869479,
+ author = {Michal Wegiel and Chandra Krintz},
+ title = {Cross-language, Type-safe, and Transparent Object Sharing for Co-located Managed Runtimes},
+ journal = {SIGPLAN Not.},
+ issue_date = {October 2010},
+ volume = {45},
+ number = {10},
+ month = oct,
+ year = {2010},
+ issn = {0362-1340},
+ pages = {223--240},
+ numpages = {18},
+ url = {http://doi.acm.org/10.1145/1932682.1869479},
+ doi = {10.1145/1932682.1869479},
+ acmid = {1869479},
+ publisher = {ACM},
+ address = {New York, NY, USA},
+ keywords = {collection, communication, cross-language, garbage, managed, memory, model, object, rpc, runtimes, shared, synchronization, transparent, type-safe},
+}
+ at article{wickham2011split,
+ title={The split-apply-combine strategy for data analysis},
+ author={Hadley Wickham},
+ journal={Journal of Statistical Software},
+ volume={40},
+ number={1},
+ pages={1--29},
+ year={2011},
+ publisher={Citeseer}
+}
+ at inproceedings{Sumaray:2012:CDS:2184751.2184810,
+ author = {Audie Sumaray and S. Kami Makki},
+ title = {A Comparison of Data Serialization Formats for Optimal Efficiency on a Mobile Platform},
+ booktitle = {Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication},
+ series = {ICUIMC '12},
+ year = {2012},
+ isbn = {978-1-4503-1172-4},
+ location = {Kuala Lumpur, Malaysia},
+ pages = {48:1--48:6},
+ articleno = {48},
+ numpages = {6},
+ url = {http://doi.acm.org/10.1145/2184751.2184810},
+ doi = {10.1145/2184751.2184810},
+ acmid = {2184810},
+ publisher = {ACM},
+ address = {New York, NY, USA},
+ keywords = {Android, Dalvik, JSON, ProtoBuf, XML, data serialization, thrift},
+}
+ at Manual{RObjectTables,
+ title = {User-Defined Tables in the R Search Path},
+ author = {Duncan {Temple Lang}},
+ year = {2012},
+ url = {http://www.omegahat.org/RObjectTables/RObjectTables.pdf},
+}
+ at Manual{rprotobuf,
+ title = {RProtoBuf: R Interface to the Protocol Buffers API},
+ author = {Romain Francois and Dirk Eddelbuettel and Murray Stokely},
+ note = {R package version 0.3.2},
+ year = {2013},
+ url = {http://cran.r-project.org/web/packages/RProtoBuf/index.html},
+}
+ at Manual{r,
+ title = {R: A Language and Environment for Statistical Computing},
+ author = {{R Core Team}},
+ organization = {R Foundation for Statistical Computing},
+ address = {Vienna, Austria},
+ year = {2013},
+ url = {http://www.R-project.org/},
+ }
+ at article{dean2008mapreduce,
+ title={MapReduce: simplified data processing on large clusters},
+ author={Jeffrey Dean and Sanjay Ghemawat},
+ journal={Communications of the ACM},
+ volume={51},
+ number={1},
+ pages={107--113},
+ year={2008},
+ publisher={ACM}
+}
+ at article{bostock2011d3,
+ title={D$^3$ Data-Driven Documents},
+ author={Michael Bostock and Vadim Ogievetsky and Jeffrey Heer},
+ journal={Visualization and Computer Graphics, IEEE Transactions on},
+ volume={17},
+ number={12},
+ pages={2301--2309},
+ year={2011},
+ publisher={IEEE}
+}
+% celebrated article in this field. Also see the parallel paragraph.
+ at article{Manku:1998:AMO:276305.276342,
+ author = {Gurmeet Singh Manku and Sridhar Rajagopalan and Bruce G. Lindsay},
+ title = {Approximate medians and other quantiles in one pass and with limited memory},
+ journal = {SIGMOD Rec.},
+ issue_date = {June 1998},
+ volume = {27},
+ number = {2},
+ month = jun,
+ year = {1998},
+ issn = {0163-5808},
+ pages = {426--435},
+ numpages = {10},
+ url = {http://doi.acm.org/10.1145/276305.276342},
+ doi = {10.1145/276305.276342},
+ acmid = {276342},
+ publisher = {ACM},
+ address = {New York, NY, USA},
+}
+% Has a section on protocol buffers
+ at article{Pike:2005:IDP:1239655.1239658,
+ author = {Rob Pike and Sean Dorward and Robert Griesemer and Sean Quinlan},
+ title = {Interpreting the data: Parallel analysis with Sawzall},
+ journal = {Sci. Program.},
+ issue_date = {October 2005},
+ volume = {13},
+ number = {4},
+ month = oct,
+ year = {2005},
+ issn = {1058-9244},
+ pages = {277--298},
+ numpages = {22},
+ acmid = {1239658},
+ publisher = {IOS Press},
+ address = {Amsterdam, The Netherlands, The Netherlands},
+}
+ at Manual{protobuf,
+ title = {Protocol Buffers: Developer Guide},
+ author = {Google},
+ year = {2012},
+ url = {http://code.google.com/apis/protocolbuffers/docs/overview.html}
+}
+ at article{sturges1926choice,
+ title={The choice of a class interval},
+ author={Herbert A Sturges},
+ journal={Journal of the American Statistical Association},
+ volume={21},
+ number={153},
+ pages={65--66},
+ year={1926}
+}
+ at Manual{histogramtools,
+ title = {HistogramTools: Utility Functions for R Histograms},
+ author = {Murray Stokely},
+ year = {2013},
+ note = {R package version 0.3},
+ url = {https://r-forge.r-project.org/projects/histogramtools/},
+}
+ at article{scott1979optimal,
+ title={On optimal and data-based histograms},
+ author={David W Scott},
+ journal={Biometrika},
+ volume={66},
+ number={3},
+ pages={605--610},
+ year={1979},
+ publisher={Biometrika Trust}
+}
+ at book{scott2009multivariate,
+ title={Multivariate density estimation: theory, practice, and visualization},
+ author={David W Scott},
+ volume={383},
+ year={2009},
+ publisher={Wiley. com}
+}
+ at Manual{httr,
+ title = {httr: Tools for working with URLs and HTTP},
+ author = {Hadley Wickham},
+ year = {2012},
+ note = {R package version 0.2},
+ url = {http://CRAN.R-project.org/package=httr},
+}
+ at Manual{opencpu,
+ title = {OpenCPU system for embedded statistical computation and reproducible research},
+ author = {Jeroen Ooms},
+ year = {2013},
+ note = {R package version 1.2.2},
+ url = {http://www.opencpu.org},
+}
Deleted: papers/jss/eddelbuettel-stokely.bib
===================================================================
--- papers/jss/eddelbuettel-stokely.bib 2014-01-11 17:17:46 UTC (rev 748)
+++ papers/jss/eddelbuettel-stokely.bib 2014-01-11 17:28:04 UTC (rev 749)
@@ -1,294 +0,0 @@
- at article{eddelbuettel2011rcpp,
- title={Rcpp: Seamless R and C++ integration},
- author={Dirk Eddelbuettel and Romain Fran{\c{c}}ois},
- journal={Journal of Statistical Software},
- volume={40},
- number={8},
- pages={1--18},
- year={2011}
-}
- at Manual{msgpackR,
- title = {msgpackR: A library to serialize or unserialize data in MessagePack format},
- author = {Mikiya Tanizawa},
- year = {2013},
- note = {R package version 1.1},
- url = {http://CRAN.R-project.org/package=msgpackR},
-}
- at Manual{rmongodb,
- title={rmongodb: R-MongoDB driver},
- author={Gerald Lindsly},
- year = {2013},
- note = {R package version 1.3.3},
- url = {http://CRAN.R-project.org/package=rmongodb},
-}
- at Manual{int64,
- title = {int64: 64 bit integer types},
- author = {Romain Fran{\c{c}}ois},
- year = {2011},
- note = {R package version 1.1.2},
- url = {http://CRAN.R-project.org/package=int64},
-}
- at Manual{bit64,
- title = {bit64: A S3 class for vectors of 64bit integers},
- author = {Jens Oehlschl\"{a}gel},
- year = {2012},
- note = {R package version 0.9-3},
- url = {http://CRAN.R-project.org/package=bit64},
-}
- at book{eddelbuettel2013seamless,
- title={Seamless R and C++ Integration with Rcpp},
- author={Dirk Eddelbuettel},
- year={2013},
- publisher={Springer}
-}
- at Manual{rhipe,
- title = {RHIPE: A Distributed Environment for the Analysis of Large and Complex Datasets},
- author = {Saptarshi Guha},
- year = {2010},
- url = {http://www.stat.purdue.edu/~sguha/rhipe/},
-}
- at misc{serialization,
-author= {Luke Tierney},
-title = {A New Serialization Mechanism for R},
-url = {http://www.cs.uiowa.edu/~luke/R/serialize/serialize.ps},
-year = {2003},
-}
- at manual{eddelbuettel2013exposing,
- title={Exposing C++ functions and classes with Rcpp modules},
- author={Dirk Eddelbuettel and Romain Fran{\c{c}}ois},
- year={2013},
- note={Vignette included in R package Rcpp},
- url = {http://CRAN.R-project.org/package=Rcpp},
-}
- at inproceedings{cantrill2004dynamic,
- title={Dynamic Instrumentation of Production Systems.},
- author={Bryan Cantrill and Michael W Shapiro and Adam H Leventhal and others},
- booktitle={USENIX Annual Technical Conference, General Track},
- pages={15--28},
- year={2004}
-}
- at article{swain1991color,
- title={Color indexing},
- author={Michael J Swain and Dana H Ballard},
- journal={International journal of computer vision},
- volume={7},
- number={1},
- pages={11--32},
- year={1991},
- publisher={Springer}
-}
- at article{rubner2000earth,
- title={The earth mover's distance as a metric for image retrieval},
- author={Yossi Rubner and Carlo Tomasi and Leonidas J Guibas},
- journal={International Journal of Computer Vision},
- volume={40},
- number={2},
- pages={99--121},
- year={2000},
- publisher={Springer}
-}
- at book{kullback1997information,
- title={Information theory and statistics},
- author={Solomon Kullback},
- year={1997},
- publisher={Courier Dover Publications}
-}
- at inproceedings{puzicha1997non,
[TRUNCATED]
To get the complete diff run:
svnlook diff /svnroot/rprotobuf -r 749
More information about the Rprotobuf-commits
mailing list