summaryrefslogtreecommitdiff
path: root/brown.py
diff options
context:
space:
mode:
Diffstat (limited to 'brown.py')
-rw-r--r--brown.py9
1 files changed, 9 insertions, 0 deletions
diff --git a/brown.py b/brown.py
new file mode 100644
index 0000000..c5d3974
--- /dev/null
+++ b/brown.py
@@ -0,0 +1,9 @@
+from nltk.corpus import brown
+from nltk.text import TextCollection
+
+# the default initialization for a corpus fails
+# since files() was changed to fileids()
+# anyway, brown_collection = TextCollection(brown) doesn't work
+# so we use this workaround
+words = [brown.words(f) for f in brown.fileids()]
+brown_collection = TextCollection(words)