Merge pull request #14 from imbi-heidelberg/basic_development

lemmatize corpus objects
imbi-heidelberg · Jul 3, 2024 · e442990 · e442990
2 parents bd4f110 + 5ccc2ba
commit e442990
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 5 deletions.
diff --git a/R/MetaNLP.R b/R/MetaNLP.R
@@ -113,15 +113,15 @@ MetaNLP <- function(file,
     (`[[`)(c("x")) |>
     # lower case
     tolower() |>
-    # lemmatization of the words
-    textstem::lemmatize_strings(dictionary = lexicon) |>
     tm::VectorSource() |>
     # create corpus object
     tm::Corpus() |>
     # remove special characters
     tm::tm_map(tm::content_transformer(replaceSpecialChars), language = language) |>
     # strip white space
     tm::tm_map(tm::stripWhitespace) |>
+    # lemmatization of the words
+    tm::tm_map(textstem::lemmatize_strings, dictionary = lexicon) |>
     # only use word stems
     tm::tm_map(tm::stemDocument, language = language) |>
     # create matrix
@@ -133,7 +133,7 @@ MetaNLP <- function(file,
 
   # only choose word stems that appear at least a pre-specified number of times
   temp <- temp[, colSums(temp) >= bounds[1] & colSums(temp) <= bounds[2]]
-
+#
   # order by column name
   index_vec <- order(names(temp))
   temp |>

diff --git a/tests/testthat/test_constructor.R b/tests/testthat/test_constructor.R
@@ -110,6 +110,7 @@ test_that("constructor works", {
     MetaNLP(source_path_ru, bounds = c(1, Inf), language = "russian",
             encoding = "UTF-8")
   )
+
 })
 
 test_that("print methods work", {

diff --git a/tests/testthat/test_deletion.R b/tests/testthat/test_deletion.R
@@ -45,8 +45,7 @@ test_that("Special characters can be replaces", {
 
   # load french data set
   source_path_fr <- test_path("data", "french_data.csv")
-  obj_fr <- MetaNLP(source_path_fr, bounds = c(1, Inf), language = "french",
-                    stringsAsFactors=FALSE, fileEncoding = "latin1")
+  obj_fr <- MetaNLP(source_path_fr, bounds = c(1, Inf), language = "french")
 
   # add a column name that contains all possible special characters
   obj_fr@data_frame <- data.frame(obj_fr@data_frame,