python 2 compatibility

examples/run_classifier.py

@@ -15,26 +15,27 @@
 # limitations under the License.
 """BERT finetuning runner."""
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
+from __future__ import absolute_import, division, print_function
 
-import csv
-import os
-import logging
 import argparse
+import csv
+import logging
+import os
 import random
-from tqdm import tqdm, trange
+import sys
+from io import open
 
 import numpy as np
 import torch
-from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
+from torch.utils.data import (DataLoader, RandomSampler, SequentialSampler,
+                              TensorDataset)
 from torch.utils.data.distributed import DistributedSampler
+from tqdm import tqdm, trange
 
-from pytorch_pretrained_bert.tokenization import BertTokenizer
+from pytorch_pretrained_bert.file_utils import PYTORCH_PRETRAINED_BERT_CACHE
 from pytorch_pretrained_bert.modeling import BertForSequenceClassification
 from pytorch_pretrained_bert.optimization import BertAdam
-from pytorch_pretrained_bert.file_utils import PYTORCH_PRETRAINED_BERT_CACHE
+from pytorch_pretrained_bert.tokenization import BertTokenizer
 
 logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
                     datefmt = '%m/%d/%Y %H:%M:%S',
@@ -91,10 +92,12 @@ class DataProcessor(object):
     @classmethod
     def _read_tsv(cls, input_file, quotechar=None):
         """Reads a tab separated value file."""
-        with open(input_file, "r", encoding='utf-8') as f:
+        with open(input_file, "rb") as f:
             reader = csv.reader(f, delimiter="\t", quotechar=quotechar)
             lines = []
             for line in reader:
+                if sys.version_info[0] == 2:
+                    line = list(unicode(cell, 'utf-8') for cell in line)
                 lines.append(line)
             return lines
 
@@ -429,7 +432,8 @@ def main():
 
     if os.path.exists(args.output_dir) and os.listdir(args.output_dir) and args.do_train:
         raise ValueError("Output directory ({}) already exists and is not empty.".format(args.output_dir))
-    os.makedirs(args.output_dir, exist_ok=True)
+    if not os.path.exists(args.output_dir):
+        os.makedirs(args.output_dir)
 
     task_name = args.task_name.lower()
 
@@ -451,7 +455,7 @@ def main():
 
     # Prepare model
     model = BertForSequenceClassification.from_pretrained(args.bert_model,
-              cache_dir=PYTORCH_PRETRAINED_BERT_CACHE / 'distributed_{}'.format(args.local_rank),
+              cache_dir=os.path.join(PYTORCH_PRETRAINED_BERT_CACHE, 'distributed_{}'.format(args.local_rank)),
               num_labels = num_labels)
     if args.fp16:
         model.half()