Fix warnings related to forhcoming v3

Author: kbenoit

.Rbuildignore

@@ -6,3 +6,4 @@
 ^LICENSE$
 ^\.github$
 ^CRAN-RELEASE$
+^revdep$

.gitignore

@@ -6,3 +6,4 @@ src/*.o
 src/*.so
 src/*.dll
 quanteda.textstats.Rproj
+revdep

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: quanteda.textstats
-Version: 0.92.9000
+Version: 0.93
 Title: Textual Statistics for the Quantitative Analysis of Textual Data
 Description: Textual statistics functions formerly in the 'quanteda' package.
     Textual statistics for characterizing and comparing textual data. Includes 
@@ -17,7 +17,7 @@ Authors@R: c(
     )
 License: GPL-3
 Depends:
-    R (>= 3.2.0)
+    R (>= 3.5.0)
 Imports:
     quanteda,
     Matrix,

NAMESPACE

@@ -67,6 +67,7 @@ importFrom(quanteda,dfm_remove)
 importFrom(quanteda,dfm_weight)
 importFrom(quanteda,docnames)
 importFrom(quanteda,featnames)
+importFrom(quanteda,is.corpus)
 importFrom(quanteda,is.dfm)
 importFrom(quanteda,ndoc)
 importFrom(quanteda,nsentence)

NEWS.md

@@ -1,6 +1,7 @@
 # quanteda.textstats 0.93
 
 * Minor changes to ensure compatibility with **quanteda** v3.
+* Changes to avoid breaking tests on older releases, caused by changes to the default for `stringsAsFactors` in `data.frame()`.
 
 # quanteda.textstats 0.92
 

R/textstat-methods.R

@@ -30,7 +30,9 @@
 #' library("quanteda")
 #'
 #' period <- ifelse(docvars(data_corpus_inaugural, "Year") < 1945, "pre-war", "post-war")
-#' dfmat <- dfm(data_corpus_inaugural, groups = period)
+#' dfmat <- tokens(data_corpus_inaugural) %>%
+#'     dfm() %>%
+#'     dfm_group(groups = period)
 #' tstat <- textstat_keyness(dfmat)
 #' textstat_select(tstat, 'america*')
 #'

R/textstat_frequency.R

@@ -30,14 +30,16 @@
 #' @examples
 #' library("quanteda")
 #' set.seed(20)
-#' dfmat1 <- dfm(c("a a b b c d", "a d d d", "a a a"))
+#' dfmat1 <- dfm(tokens(c("a a b b c d", "a d d d", "a a a")))
 #'
 #' textstat_frequency(dfmat1)
 #' textstat_frequency(dfmat1, groups = c("one", "two", "one"), ties_method = "first")
 #' textstat_frequency(dfmat1, groups = c("one", "two", "one"), ties_method = "average")
 #'
 #' dfmat2 <- corpus_subset(data_corpus_inaugural, President == "Obama") %>%
-#'    dfm(remove_punct = TRUE, remove = stopwords("english"))
+#'    tokens(remove_punct = TRUE) %>%
+#'    tokens_remove(stopwords("english")) %>%
+#'    dfm()
 #' tstat1 <- textstat_frequency(dfmat2)
 #' head(tstat1, 10)
 #'

R/textstat_keyness.R

@@ -54,17 +54,19 @@
 #'
 #' # compare pre- v. post-war terms using grouping
 #' period <- ifelse(docvars(data_corpus_inaugural, "Year") < 1945, "pre-war", "post-war")
-#' dfmat1 <- dfm(data_corpus_inaugural, groups = period)
+#' dfmat1 <- tokens(data_corpus_inaugural) %>%
+#'     dfm() %>%
+#'     dfm_group(groups = period)
 #' head(dfmat1) # make sure 'post-war' is in the first row
 #' head(tstat1 <- textstat_keyness(dfmat1), 10)
 #' tail(tstat1, 10)
 #'
 #' # compare pre- v. post-war terms using logical vector
-#' dfmat2 <- dfm(data_corpus_inaugural)
+#' dfmat2 <- dfm(tokens(data_corpus_inaugural))
 #' head(textstat_keyness(dfmat2, docvars(data_corpus_inaugural, "Year") >= 1945), 10)
 #'
 #' # compare Trump 2017 to other post-war preseidents
-#' dfmat3 <- dfm(corpus_subset(data_corpus_inaugural, period == "post-war"))
+#' dfmat3 <- dfm(tokens(corpus_subset(data_corpus_inaugural, period == "post-war")))
 #' head(textstat_keyness(dfmat3, target = "2017-Trump"), 10)
 #'
 #' # using the likelihood ratio method

R/textstat_lexdiv.R

@@ -148,7 +148,7 @@
 #'           sandwich.")
 #' tokens(txt) %>%
 #'     textstat_lexdiv(measure = c("TTR", "CTTR", "K"))
-#' dfm(txt) %>%
+#' dfm(tokens(txt)) %>%
 #'     textstat_lexdiv(measure = c("TTR", "CTTR", "K"))
 #'
 #' toks <- tokens(corpus_subset(data_corpus_inaugural, Year > 2000))
@@ -382,7 +382,7 @@ compute_lexdiv_dfm_stats <- function(x, measure = NULL, log.base = 10) {
 #' @param MSTTR_segment a numeric value defining the size of the each segment
 #'   for the computation of the the Mean Segmental Type-Token Ratio (Johnson, 1944)
 compute_lexdiv_tokens_stats <- function(x, measure = c("MATTR", "MSTTR"),
-                                     MATTR_window, MSTTR_segment) {
+                                        MATTR_window, MSTTR_segment) {
     measure <- match.arg(measure, several.ok = TRUE)
     result <- data.frame(document = docnames(x), stringsAsFactors = FALSE)
 
@@ -426,7 +426,7 @@ compute_mattr <- function(x, MATTR_window = 100L) {
     x <- tokens_ngrams(x, n = MATTR_window, concatenator = " ")
 
     # get a list of TTRs by document
-    temp <- lapply(as.list(x), function(y) textstat_lexdiv(dfm(y), "TTR")[["TTR"]])
+    temp <- lapply(as.list(x), function(y) textstat_lexdiv(dfm(tokens(y)), "TTR")[["TTR"]])
     result <- unlist(lapply(temp, mean))
     return(result)
 }

R/textstat_readability.R

@@ -646,7 +646,7 @@ textstat_readability.corpus <- function(x,
     }
 
     if ("Dickes.Steiwer" %in% measure) {
-        TTR <- textstat_lexdiv(dfm(x, verbose = FALSE), measure = "TTR")$TTR
+        TTR <- textstat_lexdiv(dfm(tokens(x), verbose = FALSE), measure = "TTR")$TTR
         result[["Dickes.Steiwer"]] <- 235.95993 - (73.021 * C / W) - (12.56438 * W / St) - (50.03293 * TTR)
     }