Adding caching and other performance improvements

bmschmidt · Aug 30, 2016 · 67b55a5 · 67b55a5
1 parent 2f843ae
commit 67b55a5
Show file tree

Hide file tree

Showing 26 changed files with 91 additions and 40 deletions.
diff --git a/.gitignore b/.gitignore
@@ -6,3 +6,6 @@ inst/extdata/
 hum2vec.Rproj
 src/*.o
 src/*.so
+cookbooks cookbooks.txt cookbooks.vectors cookbooks.zip
+cookbooks*
+etc
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,18 +1,23 @@
 Package: wordVectors
 Type: Package
 Title: Tools for creating and analyzing vector-space models of texts
-Version: 1.0
+Version: 1.1
 Date: 2015-09-10
 Author: Ben Schmidt, Jian Li
 Maintainer: Ben Schmidt <bmschmidt@gmail.com>
-Description: wordVectors wraps the word2vec code for creating vector-space models of texts, and defines a new class "VectorSpaceModel" extending matrix with a number of functions that make it easier to perform useful operations in a word-vector space.
+Description: wordVectors wraps Google's word2vec code for creating vector-space
+    models of texts, and defines a new class "VectorSpaceModel" (extending the native matrix class)
+    with a number of functions that make it easier to perform useful operations in a
+    word-vector space.
 License: Apache License (== 2.0)
-Depends: R (>= 2.14.0)
+Depends:
+    R (>= 2.14.0)
 LazyData: TRUE
 Imports:
-  graphics,
-  methods,
-  utils
+    graphics,
+    methods,
+    utils
 Suggests:
-  stringi,
-  tsne
+    stringi,
+    tsne
+RoxygenNote: 5.0.1
diff --git a/NAMESPACE b/NAMESPACE
@@ -1,4 +1,4 @@
-# Generated by roxygen2 (4.1.1): do not edit by hand
+# Generated by roxygen2: do not edit by hand
 
 export(as.VectorSpaceModel)
 export(cosineDist)

diff --git a/R/matrixFunctions.R b/R/matrixFunctions.R
@@ -18,14 +18,13 @@ setMethod("initialize", "VectorSpaceModel",
             callNextMethod(.Object, .cache=.cache, ...)
           })
 
-#' Cached Square Magnitudes
+#' Square Magnitudes with caching
 #'
-#' @param VectorSpaceModel
+#' @param VectorSpaceModel A matrix or VectorSpaceModel object
 #' @description square_magnitudes Returns the square magnitudes and
 #' caches them if necessary
 #' @return A vector of the square magnitudes for each row
 #' @keywords internal
-#' @examples
 square_magnitudes = function(object) {
   if (class(object)=="VectorSpaceModel") {
       if (.hasSlot(object, ".cache")) {
@@ -47,10 +46,11 @@ square_magnitudes = function(object) {
 
 #' VectorSpaceModel indexing
 #'
-#  @description Reduce a VectorSpaceModel to a smaller one
+#' @description Reduce a VectorSpaceModel to a smaller one
 #' @param x The vectorspace model to subset
 #' @param i The row numbers to extract
 #' @param j The column numbers to extract
+#' @param j Other arguments to extract (unlikely to be useful).
 #' @param drop Whether to drop columns. This parameter is ignored.
 #' @return A VectorSpaceModel
 #'
@@ -451,7 +451,7 @@ cosineDist <- function(x,y) {
 #' of the same length as the VectorSpaceModel.
 #'
 #' @return A new matrix or VectorSpaceModel of the same dimensions as `matrix`,
-#' each row of which is parallel to vector
+#' each row of which is parallel to vector.
 #'
 #' If the input is a matrix, the output will be a matrix: if a VectorSpaceModel,
 #' it will be a VectorSpaceModel.

diff --git a/data/demo_vectors.rda b/data/demo_vectors.rda
diff --git a/man/VectorSpaceModel-VectorSpaceModel-method.Rd b/man/VectorSpaceModel-VectorSpaceModel-method.Rd
diff --git a/man/VectorSpaceModel-class.Rd b/man/VectorSpaceModel-class.Rd
diff --git a/man/as.VectorSpaceModel.Rd b/man/as.VectorSpaceModel.Rd
diff --git a/man/cosineDist.Rd b/man/cosineDist.Rd
diff --git a/man/cosineSimilarity.Rd b/man/cosineSimilarity.Rd
diff --git a/man/demo_vectors.Rd b/man/demo_vectors.Rd
diff --git a/man/filter_to_rownames.Rd b/man/filter_to_rownames.Rd
diff --git a/man/magnitudes.Rd b/man/magnitudes.Rd
diff --git a/man/nearest_to.Rd b/man/nearest_to.Rd
diff --git a/man/normalize_lengths.Rd b/man/normalize_lengths.Rd
diff --git a/man/plot-VectorSpaceModel-method.Rd b/man/plot-VectorSpaceModel-method.Rd
diff --git a/man/prep_word2vec.Rd b/man/prep_word2vec.Rd
diff --git a/man/project.Rd b/man/project.Rd
diff --git a/man/read.binary.vectors.Rd b/man/read.binary.vectors.Rd
diff --git a/man/read.vectors.Rd b/man/read.vectors.Rd
diff --git a/man/reject.Rd b/man/reject.Rd
diff --git a/man/square_magnitudes.Rd b/man/square_magnitudes.Rd
diff --git a/man/sub-VectorSpaceModel-method.Rd b/man/sub-VectorSpaceModel-method.Rd
diff --git a/man/sub-sub-VectorSpaceModel-method.Rd b/man/sub-sub-VectorSpaceModel-method.Rd
diff --git a/man/train_word2vec.Rd b/man/train_word2vec.Rd
diff --git a/man/write.binary.word2vec.Rd b/man/write.binary.word2vec.Rd