first commit

.Rbuildignore

@@ -0,0 +1,21 @@
+^.*\.Rproj$
+^\.Rproj\.user$
+^\.gitignore
+NEWS.md
+FAQ.md
+NEWS.html
+FAQ.html
+^\.travis\.yml$
+travis-tool.sh
+inst/web
+contributors.geojson
+inst/build.R
+^.*\.Rprofile$
+README.Rmd
+README.R
+travis.yml
+inst/gofastr_logo
+inst/staticdocs
+inst/extra_statdoc
+inst/maintenance.R
+

.gitignore

@@ -0,0 +1,10 @@
+# History files
+.Rhistory
+
+# Example code in package build process
+*-Ex.R
+
+.Rprofile
+.Rproj.user
+gofastr.Rproj
+inst/maintenance.R

.travis.yml

@@ -0,0 +1,26 @@
+language:      c
+
+sudo: required
+before_install:
+  - curl -OL http://raw.github.com/craigcitro/r-travis/master/scripts/travis-tool.sh
+  - chmod 755 ./travis-tool.sh
+  - ./travis-tool.sh bootstrap
+install:
+  - sh -e /etc/init.d/xvfb start
+  - ./travis-tool.sh aptget_install r-cran-xml 
+  - ./travis-tool.sh install_github hadley/devtools
+  - ./travis-tool.sh install_deps
+  - ./travis-tool.sh github_package jimhester/covr
+script:      ./travis-tool.sh run_tests
+after_success:
+  - Rscript -e 'library(covr);coveralls()'
+notifications:
+  email:
+    on_success:      change
+    on_failure:      change
+env:
+   global:
+     - R_BUILD_ARGS="--resave-data=best" 
+     - R_CHECK_ARGS="--as-cran"
+     - DISPLAY=:99.0
+     - BOOTSTRAP_LATEX=1

DESCRIPTION

@@ -0,0 +1,13 @@
+Package: gofastr
+Title: Fast DocumentTermMatrix and TermDocumentMatric Creation
+Version: 0.0.1
+Authors@R: c(person("Tyler", "Rinker", email = "tyler.rinker@gmail.com", role = c("aut", "cre")))
+Maintainer: Tyler Rinker <tyler.rinker@gmail.com>
+Description: Harness the power of 'data.table' and 'stringi' to quickly generate 'tm' DocumentTermMatrix and TermDocumentMatrix data structures.
+Depends: R (>= 3.2.2)
+Suggests: testthat
+Imports: data.table (>= 1.9.5), slam, stringi, tm
+Date: 2015-09-08
+License: GPL-2
+LazyData: TRUE
+Roxygen: list(wrap = FALSE)

NAMESPACE

@@ -0,0 +1,8 @@
+# Generated by roxygen2 (4.1.1): do not edit by hand
+
+S3method(remove_stopwords,DocumentTermMatrix)
+S3method(remove_stopwords,TermDocumentMatrix)
+export(q_dtm)
+export(q_tdm)
+export(remove_stopwords)
+importFrom(data.table,":=")

NEWS

@@ -0,0 +1,23 @@
+NEWS 
+====
+
+Versioning
+----------
+
+Releases will be numbered with the following semantic versioning format:
+
+<major>.<minor>.<patch>
+
+And constructed with the following guidelines:
+
+* Breaking backward compatibility bumps the major (and resets the minor 
+  and patch)
+* New additions without breaking backward compatibility bumps the minor 
+  (and resets the patch)
+* Bug fixes and misc changes bumps the patch
+
+
+gofastr 0.0.1 
+----------------------------------------------------------------
+
+This package is...

R/gofastr-package.R

@@ -0,0 +1,30 @@
+#' Fast DocumentTermMatrix and TermDocumentMatric Creation
+#'
+#' This package does one thing...It harness the power of \pkg{data.table} and
+#' \pkg{stringi} to quickly generate \pkg{tm} \code{\link[tm]{TermDocumentMatrix}}
+#' and \code{\link[tm]{DocumentTermMatrix}} data structures without creating a
+#' \code{\link[tm]{Corpus}} first.
+#' @docType package
+#' @name gofastr
+#' @aliases gofastr package-gofastr
+NULL
+
+#' 2012 U.S. Presidential Debates
+#'
+#' A dataset containing a cleaned version of all three presidential debates for
+#' the 2012 election.
+#'
+#' @details
+#' \itemize{
+#'   \item person. The speaker
+#'   \item tot. Turn of talk
+#'   \item dialogue. The words spoken
+#'   \item time. Variable indicating which of the three debates the dialogue is from
+#' }
+#'
+#' @docType data
+#' @keywords datasets
+#' @name presidential_debates_2012
+#' @usage data(presidential_debates_2012)
+#' @format A data frame with 2912 rows and 4 variables
+NULL

R/q_dtm.R

@@ -0,0 +1,27 @@
+#' Quick DocumentTermMatrix
+#'
+#' Make a \code{\link[tm]{DocumentTermMatrix}} from a vector of text and and
+#' optional vector of documents.
+#'
+#' @param text A vector of strings.
+#' @param docs An optional vector of document names.
+#' @param weighting A \pkg{tm} weighting: \code{\link[tm]{weightTf}},
+#' \code{\link[tm]{weightTfIdf}}, \code{\link[tm]{weightBin}}, or
+#' \code{\link[tm]{weightSMART}}.
+#' @param \ldots Additional arguments passed to \code{\link[tm]{as.DocumentTermMatrix}}.
+#' @return Returns a \code{\link[tm]{DocumentTermMatrix}}.
+#' @keywords dtm DocumentTermMatrix
+#' @export
+#' @importFrom data.table :=
+#' @examples
+#' with(presidential_debates_2012, q_dtm(dialogue, paste(time, tot, sep = "_")))
+q_dtm <- function(text, docs = seq_along(text), weighting = tm::weightTf, ...){
+    . <- x <- y <- NULL
+    dat <- data.table::data.table(y = stringi::stri_trans_tolower(text), x = docs)[,
+        y := stringi::stri_extract_all_words(y)][, .(y = unlist(y)), by = x][!is.na(y),]
+    out <- suppressMessages(data.table::dcast(dat, x ~ y, fun=length, drop=FALSE, fill=0))
+    out2 <- as.matrix(out[, -1, with = FALSE])
+    row.names(out2) <- out[[1]]
+    tm::as.DocumentTermMatrix(slam::as.simple_triplet_matrix(out2), weighting = weighting, ...)
+}
+

R/q_tdm.R

@@ -0,0 +1,27 @@
+#' Quick TermDocumentMatrix
+#'
+#' Make a \code{\link[tm]{TermDocumentMatrix}} from a vector of text and and
+#' optional vector of documents.
+#'
+#' @param text A vector of strings.
+#' @param docs An optional vector of document names.
+#' @param weighting A \pkg{tm} weighting: \code{\link[tm]{weightTf}},
+#' \code{\link[tm]{weightTfIdf}}, \code{\link[tm]{weightBin}}, or
+#' \code{\link[tm]{weightSMART}}.
+#' @param \ldots Additional arguments passed to \code{\link[tm]{as.TermDocumentMatrix}}.
+#' @return Returns a \code{\link[tm]{TermDocumentMatrix}}.
+#' @keywords tdm TermDocumentMatrix
+#' @importFrom data.table :=
+#' @export
+#' @examples
+#' with(presidential_debates_2012, q_tdm(dialogue, paste(time, tot, sep = "_")))
+q_tdm <- function(text, docs = seq_along(text), weighting = tm::weightTf, ...){
+    . <- x <- y <- NULL
+    dat <- data.table::data.table(y = stringi::stri_trans_tolower(text), x = docs)[,
+        y := stringi::stri_extract_all_words(y)][, .(y = unlist(y)), by = x][!is.na(y),]
+    out <- suppressMessages(data.table::dcast(dat, y~x, fun=length, drop=FALSE, fill=0))
+    out2 <- as.matrix(out[, -1, with = FALSE])
+    row.names(out2) <- out[[1]]
+    tm::as.TermDocumentMatrix(slam::as.simple_triplet_matrix(out2), weighting = weighting, ...)
+}
+

R/remove_stopwords.R

@@ -0,0 +1,47 @@
+#' Remove Stopwords from a TermDocumentMatrix/DocumentTermMatrix
+#'
+#' Remove stopwords and < nchar words from a \code{\link[tm]{TermDocumentMatrix}}
+#' or \code{\link[tm]{DocumentTermMatrix}}.
+#'
+#' @param x A \code{\link[tm]{TermDocumentMatrix}} or \code{\link[tm]{DocumentTermMatrix}}.
+#' @param stopwords A vector of stopwords to remove.
+#' @param min.char The minial length character for retained words.
+#' @return Returns a \code{\link[tm]{TermDocumentMatrix}} or \code{\link[tm]{DocumentTermMatrix}}.
+#' @keywords stopwords
+#' @export
+#' @examples
+#' (x <-with(presidential_debates_2012, q_dtm(dialogue, paste(time, tot, sep = "_"))))
+#' remove_stopwords(x)
+#' (y <- with(presidential_debates_2012, q_tdm(dialogue, paste(time, tot, sep = "_"))))
+#' remove_stopwords(y)
+remove_stopwords  <- function(x, stopwords = tm::stopwords("english"), min.char = 3) {
+    UseMethod("remove_stopwords")
+}
+
+#' @export
+#' @method remove_stopwords TermDocumentMatrix
+remove_stopwords.TermDocumentMatrix  <- function(x, stopwords = tm::stopwords("english"), min.char = 3) {
+
+    if (!is.null(stopwords)){
+        x <- x[!rownames(x) %in% stopwords, ]
+    }
+    if (!is.null(min.char)){
+        x <- x[nchar(rownames(x)) > min.char - 1, ]
+    }
+    x
+}
+
+#' @export
+#' @method remove_stopwords DocumentTermMatrix
+remove_stopwords.DocumentTermMatrix  <- function(x, stopwords = tm::stopwords("english"), min.char = 3) {
+
+    if (!is.null(stopwords)){
+        x <- x[, !colnames(x) %in% stopwords]
+    }
+    if (!is.null(min.char)){
+        x <- x[, nchar(colnames(x)) > min.char - 1]
+    }
+    x
+}
+
+

README.Rmd

@@ -0,0 +1,64 @@
+---
+title: "gofastr"
+date: "`r format(Sys.time(), '%d %B, %Y')`"
+output:
+  md_document:
+    toc: true      
+---
+
+```{r, echo=FALSE}
+desc <- suppressWarnings(readLines("DESCRIPTION"))
+regex <- "(^Version:\\s+)(\\d+\\.\\d+\\.\\d+)"
+loc <- grep(regex, desc)
+ver <- gsub(regex, "\\2", desc[loc])
+verbadge <- sprintf('<a href="https://img.shields.io/badge/Version-%s-orange.svg"><img src="https://img.shields.io/badge/Version-%s-orange.svg" alt="Version"/></a></p>', ver, ver)
+````
+
+[![Build Status](https://travis-ci.org/trinker/gofastr.svg?branch=master)](https://travis-ci.org/trinker/gofastr)
+[![Coverage Status](https://coveralls.io/repos/trinker/gofastr/badge.svg?branch=master)](https://coveralls.io/r/trinker/gofastr?branch=master)
+`r verbadge`
+
+<img src="inst/gofastr_logo/r_gofastr.png" width="150" alt="readability Logo">  
+
+
+**gofastr** is designed to do one thing really well...It harnesses the power of **data.table** and **stringi** to quickly generate **tm** `DocumentTermMatrix` and `TermDocumentMatrix` data structures. 
+
+In my work I often get data in the form of large .csv files.  The `Corpus` structure is an unnecessary step that requires additional run time.  **gofastr** skips this step and uses **data.table** and **stringi** to quickly make the `DocumentTermMatrix` and `TermDocumentMatrix` data structures directly.  
+
+There are three functions:
+
+| Function           |  Description                                          |
+|--------------------|-------------------------------------------------------|
+| `q_tdm`            | `TermDocumentMatrix` from string vector |
+| `q_dtm`            | `DocumentTermMatrix` from string vector |
+| `remove_stopwords` | Remove stopwords and minimal character words from `TermDocumentMatrix`/`DocumentTermMatrix` |
+
+
+# Installation
+
+To download the development version of **gofastr**:
+
+Download the [zip ball](https://github.com/trinker/gofastr/zipball/master) or [tar ball](https://github.com/trinker/gofastr/tarball/master), decompress and run `R CMD INSTALL` on it, or use the **pacman** package to install the development version:
+
+```r
+if (!require("pacman")) install.packages("pacman")
+pacman::p_load_gh("trinker/gofastr")
+```
+
+# Contact
+
+You are welcome to:
+* submit suggestions and bug-reports at: <https://github.com/trinker/gofastr/issues>
+* send a pull request on: <https://github.com/trinker/gofastr/>
+* compose a friendly e-mail to: <tyler.rinker@gmail.com>
+
+
+# Examples
+
+```{r}
+library(gofastr)
+(x <-with(presidential_debates_2012, q_dtm(dialogue, paste(time, tot, sep = "_"))))
+remove_stopwords(x)
+(y <- with(presidential_debates_2012, q_tdm(dialogue, paste(time, tot, sep = "_"))))
+remove_stopwords(y)
+```