From 14f3f3659bc727ef1ac46e4ec4dcaba58e5922c4 Mon Sep 17 00:00:00 2001 From: vilmar-hillow Date: Thu, 7 Sep 2017 15:19:48 +0300 Subject: [PATCH] Fix for Python 3 in conll dataset loading --- keras_contrib/datasets/conll2000.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) mode change 100644 => 100755 keras_contrib/datasets/conll2000.py diff --git a/keras_contrib/datasets/conll2000.py b/keras_contrib/datasets/conll2000.py old mode 100644 new mode 100755 index 22a97e1..5561f17 --- a/keras_contrib/datasets/conll2000.py +++ b/keras_contrib/datasets/conll2000.py @@ -16,7 +16,7 @@ def load_data(path='conll2000.zip', min_freq=2): archive.close() word_counts = Counter(row[0].lower() for sample in train for row in sample) - vocab = ['', ''] + [w for w, f in word_counts.iteritems() if f >= min_freq] + vocab = ['', ''] + [w for w, f in iter(word_counts.items()) if f >= min_freq] pos_tags = sorted(list(set(row[1] for sample in train + test for row in sample))) # in alphabetic order chunk_tags = sorted(list(set(row[2] for sample in train + test for row in sample))) # in alphabetic order @@ -27,7 +27,7 @@ def load_data(path='conll2000.zip', min_freq=2): def _parse_data(fh): string = fh.read() - data = [[row.split() for row in sample.split('\n')] for sample in string.strip().split('\n\n')] + data = [[row.split() for row in sample.split('\n')] for sample in string.decode().strip().split('\n\n')] fh.close() return data