summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYuval Adam <yuv.adm@gmail.com>2011-05-06 00:36:19 +0300
committerYuval Adam <yuv.adm@gmail.com>2011-05-06 00:36:19 +0300
commitc3574e45a3a18d8964f04316fc7305329afe1120 (patch)
treef071ed3f1ee0f0f57c908af4a45bc50fa96bbf65
parentf1a0f7b12f8817f6893641146b593a44cd6c7a0d (diff)
added brown TextCollection
-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)