Sort imports with isort.

This is the result of:

    $ isort --recursive examples templates transformers utils hubconf.py setup.py

examples/run_generation.py

@@ -21,15 +21,23 @@ from __future__ import absolute_import, division, print_function, unicode_litera
 import argparse
 import logging
 
-import torch
 import numpy as np
+import torch
 
-from transformers import GPT2LMHeadModel, GPT2Tokenizer
-from transformers import OpenAIGPTLMHeadModel, OpenAIGPTTokenizer
-from transformers import XLNetLMHeadModel, XLNetTokenizer
-from transformers import TransfoXLLMHeadModel, TransfoXLTokenizer
-from transformers import CTRLLMHeadModel, CTRLTokenizer
-from transformers import XLMWithLMHeadModel, XLMTokenizer
+from transformers import (
+    CTRLLMHeadModel,
+    CTRLTokenizer,
+    GPT2LMHeadModel,
+    GPT2Tokenizer,
+    OpenAIGPTLMHeadModel,
+    OpenAIGPTTokenizer,
+    TransfoXLLMHeadModel,
+    TransfoXLTokenizer,
+    XLMTokenizer,
+    XLMWithLMHeadModel,
+    XLNetLMHeadModel,
+    XLNetTokenizer,
+)
 
 
 logging.basicConfig(

examples/run_glue.py

@@ -19,54 +19,54 @@ from __future__ import absolute_import, division, print_function
 
 import argparse
 import glob
+import json
 import logging
 import os
 import random
-import json
 
 import numpy as np
 import torch
 from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset
 from torch.utils.data.distributed import DistributedSampler
-
-try:
-    from torch.utils.tensorboard import SummaryWriter
-except:
-    from tensorboardX import SummaryWriter
-
 from tqdm import tqdm, trange
 
 from transformers import (
     WEIGHTS_NAME,
+    AdamW,
+    AlbertConfig,
+    AlbertForSequenceClassification,
+    AlbertTokenizer,
     BertConfig,
     BertForSequenceClassification,
     BertTokenizer,
+    DistilBertConfig,
+    DistilBertForSequenceClassification,
+    DistilBertTokenizer,
     RobertaConfig,
     RobertaForSequenceClassification,
     RobertaTokenizer,
     XLMConfig,
     XLMForSequenceClassification,
+    XLMRobertaConfig,
+    XLMRobertaForSequenceClassification,
+    XLMRobertaTokenizer,
     XLMTokenizer,
     XLNetConfig,
     XLNetForSequenceClassification,
     XLNetTokenizer,
-    DistilBertConfig,
-    DistilBertForSequenceClassification,
-    DistilBertTokenizer,
-    AlbertConfig,
-    AlbertForSequenceClassification,
-    AlbertTokenizer,
-    XLMRobertaConfig,
-    XLMRobertaForSequenceClassification,
-    XLMRobertaTokenizer,
+    get_linear_schedule_with_warmup,
 )
-
-from transformers import AdamW, get_linear_schedule_with_warmup
-
 from transformers import glue_compute_metrics as compute_metrics
+from transformers import glue_convert_examples_to_features as convert_examples_to_features
 from transformers import glue_output_modes as output_modes
 from transformers import glue_processors as processors
-from transformers import glue_convert_examples_to_features as convert_examples_to_features
+
+
+try:
+    from torch.utils.tensorboard import SummaryWriter
+except:
+    from tensorboardX import SummaryWriter
+
 
 logger = logging.getLogger(__name__)
 

examples/run_lm_finetuning.py

@@ -32,23 +32,22 @@ import shutil
 
 import numpy as np
 import torch
-from torch.utils.data import DataLoader, Dataset, SequentialSampler, RandomSampler
+from torch.utils.data import DataLoader, Dataset, RandomSampler, SequentialSampler
 from torch.utils.data.distributed import DistributedSampler
-
-try:
-    from torch.utils.tensorboard import SummaryWriter
-except:
-    from tensorboardX import SummaryWriter
-
 from tqdm import tqdm, trange
 
 from transformers import (
     WEIGHTS_NAME,
     AdamW,
-    get_linear_schedule_with_warmup,
     BertConfig,
     BertForMaskedLM,
     BertTokenizer,
+    CamembertConfig,
+    CamembertForMaskedLM,
+    CamembertTokenizer,
+    DistilBertConfig,
+    DistilBertForMaskedLM,
+    DistilBertTokenizer,
     GPT2Config,
     GPT2LMHeadModel,
     GPT2Tokenizer,
@@ -58,15 +57,16 @@ from transformers import (
     RobertaConfig,
     RobertaForMaskedLM,
     RobertaTokenizer,
-    DistilBertConfig,
-    DistilBertForMaskedLM,
-    DistilBertTokenizer,
-    CamembertConfig,
-    CamembertForMaskedLM,
-    CamembertTokenizer,
+    get_linear_schedule_with_warmup,
 )
 
 
+try:
+    from torch.utils.tensorboard import SummaryWriter
+except:
+    from tensorboardX import SummaryWriter
+
+
 logger = logging.getLogger(__name__)
 
 

examples/run_multiple_choice.py

@@ -23,35 +23,34 @@ import logging
 import os
 import random
 
-
 import numpy as np
 import torch
 from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset
 from torch.utils.data.distributed import DistributedSampler
-
-try:
-    from torch.utils.tensorboard import SummaryWriter
-except:
-    from tensorboardX import SummaryWriter
-
 from tqdm import tqdm, trange
 
 from transformers import (
     WEIGHTS_NAME,
+    AdamW,
     BertConfig,
     BertForMultipleChoice,
     BertTokenizer,
-    XLNetConfig,
-    XLNetForMultipleChoice,
-    XLNetTokenizer,
     RobertaConfig,
     RobertaForMultipleChoice,
     RobertaTokenizer,
+    XLNetConfig,
+    XLNetForMultipleChoice,
+    XLNetTokenizer,
+    get_linear_schedule_with_warmup,
 )
+from utils_multiple_choice import convert_examples_to_features, processors
 
-from transformers import AdamW, get_linear_schedule_with_warmup
 
-from utils_multiple_choice import convert_examples_to_features, processors
+try:
+    from torch.utils.tensorboard import SummaryWriter
+except:
+    from tensorboardX import SummaryWriter
+
 
 logger = logging.getLogger(__name__)
 

examples/run_ner.py

@@ -25,20 +25,35 @@ import random
 
 import numpy as np
 import torch
-from seqeval.metrics import precision_score, recall_score, f1_score
 from tensorboardX import SummaryWriter
 from torch.nn import CrossEntropyLoss
 from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset
 from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
+
+from seqeval.metrics import f1_score, precision_score, recall_score
+from transformers import (
+    WEIGHTS_NAME,
+    AdamW,
+    BertConfig,
+    BertForTokenClassification,
+    BertTokenizer,
+    CamembertConfig,
+    CamembertForTokenClassification,
+    CamembertTokenizer,
+    DistilBertConfig,
+    DistilBertForTokenClassification,
+    DistilBertTokenizer,
+    RobertaConfig,
+    RobertaForTokenClassification,
+    RobertaTokenizer,
+    XLMRobertaConfig,
+    XLMRobertaForTokenClassification,
+    XLMRobertaTokenizer,
+    get_linear_schedule_with_warmup,
+)
 from utils_ner import convert_examples_to_features, get_labels, read_examples_from_file
 
-from transformers import AdamW, get_linear_schedule_with_warmup
-from transformers import WEIGHTS_NAME, BertConfig, BertForTokenClassification, BertTokenizer
-from transformers import RobertaConfig, RobertaForTokenClassification, RobertaTokenizer
-from transformers import DistilBertConfig, DistilBertForTokenClassification, DistilBertTokenizer
-from transformers import CamembertConfig, CamembertForTokenClassification, CamembertTokenizer
-from transformers import XLMRobertaConfig, XLMRobertaForTokenClassification, XLMRobertaTokenizer
 
 logger = logging.getLogger(__name__)
 

examples/run_squad.py

@@ -16,57 +16,57 @@
 """ Finetuning the library models for question-answering on SQuAD (DistilBERT, Bert, XLM, XLNet)."""
 
 from __future__ import absolute_import, division, print_function
-from transformers.data.processors.squad import SquadV1Processor, SquadV2Processor, SquadResult
-from transformers.data.metrics.squad_metrics import (
-    compute_predictions_logits,
-    compute_predictions_log_probs,
-    squad_evaluate,
-)
 
 import argparse
+import glob
 import logging
 import os
 import random
-import glob
 import timeit
+
 import numpy as np
 import torch
 from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset
 from torch.utils.data.distributed import DistributedSampler
-
-try:
-    from torch.utils.tensorboard import SummaryWriter
-except:
-    from tensorboardX import SummaryWriter
-
 from tqdm import tqdm, trange
 
 from transformers import (
     WEIGHTS_NAME,
+    AdamW,
+    AlbertConfig,
+    AlbertForQuestionAnswering,
+    AlbertTokenizer,
     BertConfig,
     BertForQuestionAnswering,
     BertTokenizer,
+    DistilBertConfig,
+    DistilBertForQuestionAnswering,
+    DistilBertTokenizer,
+    RobertaConfig,
     RobertaForQuestionAnswering,
     RobertaTokenizer,
-    RobertaConfig,
     XLMConfig,
     XLMForQuestionAnswering,
     XLMTokenizer,
     XLNetConfig,
     XLNetForQuestionAnswering,
     XLNetTokenizer,
-    DistilBertConfig,
-    DistilBertForQuestionAnswering,
-    DistilBertTokenizer,
-    AlbertConfig,
-    AlbertForQuestionAnswering,
-    AlbertTokenizer,
-    XLMConfig,
-    XLMForQuestionAnswering,
-    XLMTokenizer,
+    get_linear_schedule_with_warmup,
+    squad_convert_examples_to_features,
 )
+from transformers.data.metrics.squad_metrics import (
+    compute_predictions_log_probs,
+    compute_predictions_logits,
+    squad_evaluate,
+)
+from transformers.data.processors.squad import SquadResult, SquadV1Processor, SquadV2Processor
+
+
+try:
+    from torch.utils.tensorboard import SummaryWriter
+except:
+    from tensorboardX import SummaryWriter
 
-from transformers import AdamW, get_linear_schedule_with_warmup, squad_convert_examples_to_features
 
 logger = logging.getLogger(__name__)
 

examples/run_tf_glue.py

 import os
+
 import tensorflow as tf
+
 import tensorflow_datasets
 from transformers import (
+    BertConfig,
+    BertForSequenceClassification,
     BertTokenizer,
     TFBertForSequenceClassification,
-    BertConfig,
     glue_convert_examples_to_features,
-    BertForSequenceClassification,
     glue_processors,
 )
 
+
 # script parameters
 BATCH_SIZE = 32
 EVAL_BATCH_SIZE = BATCH_SIZE * 2

examples/run_tf_ner.py

 # coding=utf-8
+import _pickle as pickle
+import collections
 import datetime
-import os
-import math
 import glob
+import math
+import os
 import re
-import tensorflow as tf
-import collections
+
 import numpy as np
+import tensorflow as tf
+from absl import app, flags, logging
+
+from fastprogress import master_bar, progress_bar
 from seqeval import metrics
-import _pickle as pickle
-from absl import logging
-from transformers import TF2_WEIGHTS_NAME, BertConfig, BertTokenizer, TFBertForTokenClassification
-from transformers import RobertaConfig, RobertaTokenizer, TFRobertaForTokenClassification
-from transformers import DistilBertConfig, DistilBertTokenizer, TFDistilBertForTokenClassification
-from transformers import create_optimizer, GradientAccumulator
+from transformers import (
+    TF2_WEIGHTS_NAME,
+    BertConfig,
+    BertTokenizer,
+    DistilBertConfig,
+    DistilBertTokenizer,
+    GradientAccumulator,
+    RobertaConfig,
+    RobertaTokenizer,
+    TFBertForTokenClassification,
+    TFDistilBertForTokenClassification,
+    TFRobertaForTokenClassification,
+    create_optimizer,
+)
 from utils_ner import convert_examples_to_features, get_labels, read_examples_from_file
-from fastprogress import master_bar, progress_bar
-from absl import flags
-from absl import app
 
 
 ALL_MODELS = sum(

examples/run_xnli.py

@@ -28,34 +28,33 @@ import numpy as np
 import torch
 from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset
 from torch.utils.data.distributed import DistributedSampler
-
-try:
-    from torch.utils.tensorboard import SummaryWriter
-except:
-    from tensorboardX import SummaryWriter
-
 from tqdm import tqdm, trange
 
 from transformers import (
     WEIGHTS_NAME,
+    AdamW,
     BertConfig,
     BertForSequenceClassification,
     BertTokenizer,
-    XLMConfig,
-    XLMForSequenceClassification,
-    XLMTokenizer,
     DistilBertConfig,
     DistilBertForSequenceClassification,
     DistilBertTokenizer,
+    XLMConfig,
+    XLMForSequenceClassification,
+    XLMTokenizer,
+    get_linear_schedule_with_warmup,
 )
-
-from transformers import AdamW, get_linear_schedule_with_warmup
-
+from transformers import glue_convert_examples_to_features as convert_examples_to_features
 from transformers import xnli_compute_metrics as compute_metrics
 from transformers import xnli_output_modes as output_modes
 from transformers import xnli_processors as processors
 
-from transformers import glue_convert_examples_to_features as convert_examples_to_features
+
+try:
+    from torch.utils.tensorboard import SummaryWriter
+except:
+    from tensorboardX import SummaryWriter
+
 
 logger = logging.getLogger(__name__)
 

examples/summarization/convert_bertabs_original_pytorch_checkpoint.py

@@ -20,13 +20,13 @@ the model within the original codebase to be able to only save its `state_dict`.
 """
 
 import argparse
-from collections import namedtuple
 import logging
+from collections import namedtuple
+
 import torch
 
-from models.model_builder import AbsSummarizer  # The authors' implementation
 from model_bertabs import BertAbsSummarizer
-
+from models.model_builder import AbsSummarizer  # The authors' implementation
 from transformers import BertTokenizer
 
 

examples/summarization/modeling_bertabs.py

@@ -27,9 +27,8 @@ import torch
 from torch import nn
 from torch.nn.init import xavier_uniform_
 
-from transformers import BertModel, BertConfig, PreTrainedModel
-
 from configuration_bertabs import BertAbsConfig
+from transformers import BertConfig, BertModel, PreTrainedModel
 
 
 MAX_SIZE = 5000

examples/summarization/run_summarization.py

 #! /usr/bin/python3
 import argparse
-from collections import namedtuple
 import logging
 import os
 import sys
+from collections import namedtuple
 
 import torch
 from torch.utils.data import DataLoader, SequentialSampler
 from tqdm import tqdm
 
-from transformers import BertTokenizer
-
 from modeling_bertabs import BertAbs, build_predictor
-
+from transformers import BertTokenizer
 from utils_summarization import (
     SummarizationDataset,
-    encode_for_summarization,
     build_mask,
-    fit_to_block_size,
     compute_token_type_ids,
+    encode_for_summarization,
+    fit_to_block_size,
 )
 
+
 logger = logging.getLogger(__name__)
 logging.basicConfig(stream=sys.stdout, level=logging.INFO)
 

examples/summarization/utils_summarization.py

-from collections import deque
 import os
+from collections import deque
 
 import torch
 from torch.utils.data import Dataset

examples/summarization/utils_summarization_test.py

@@ -17,12 +17,7 @@ import unittest
 import numpy as np
 import torch
 
-from utils_summarization import (
-    compute_token_type_ids,
-    fit_to_block_size,
-    build_mask,
-    process_story,
-)
+from utils_summarization import build_mask, compute_token_type_ids, fit_to_block_size, process_story
 
 
 class SummarizationDataProcessingTest(unittest.TestCase):

examples/test_examples.py

@@ -12,14 +12,17 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
+from __future__ import absolute_import, division, print_function
 
-import sys
-import unittest
 import argparse
 import logging
+import sys
+import unittest
+
+import run_generation
+import run_glue
+import run_squad
+
 
 try:
     # python 3.4+ can use builtin unittest.mock instead of mock package
@@ -27,9 +30,6 @@ try:
 except ImportError:
     from mock import patch
 
-import run_glue
-import run_squad
-import run_generation
 
 logging.basicConfig(level=logging.DEBUG)
 

examples/utils_multiple_choice.py

@@ -17,16 +17,17 @@
 
 from __future__ import absolute_import, division, print_function
 
-
+import csv
+import glob
+import json
 import logging
 import os
 import sys
 from io import open
-import json
-import csv
-import glob
-import tqdm
 from typing import List
+
+import tqdm
+
 from transformers import PreTrainedTokenizer
 
 

examples/utils_ner.py

@@ -21,6 +21,7 @@ import logging
 import os
 from io import open
 
+
 logger = logging.getLogger(__name__)
 
 

hubconf.py

 from transformers import (
-    AutoTokenizer,
     AutoConfig,
     AutoModel,
-    AutoModelWithLMHead,
-    AutoModelForSequenceClassification,
     AutoModelForQuestionAnswering,
+    AutoModelForSequenceClassification,
+    AutoModelWithLMHead,
+    AutoTokenizer,
 )
 from transformers.file_utils import add_start_docstrings
 
+
 dependencies = ["torch", "tqdm", "boto3", "requests", "regex", "sentencepiece", "sacremoses"]
 
 

setup.py

@@ -34,6 +34,7 @@ To create the package for pypi.
 
 """
 from io import open
+
 from setuptools import find_packages, setup
 
 

templates/adding_a_new_example_script/run_xxx.py

@@ -17,54 +17,55 @@
 from __future__ import absolute_import, division, print_function
 
 import argparse
+import glob
 import logging
 import os
 import random
-import glob
 
 import numpy as np
 import torch
 from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset
 from torch.utils.data.distributed import DistributedSampler
-
-try:
-    from torch.utils.tensorboard import SummaryWriter
-except:
-    from tensorboardX import SummaryWriter
-
 from tqdm import tqdm, trange
 
 from transformers import (
     WEIGHTS_NAME,
+    AdamW,
     BertConfig,
     BertForQuestionAnswering,
     BertTokenizer,
+    DistilBertConfig,
+    DistilBertForQuestionAnswering,
+    DistilBertTokenizer,
     XLMConfig,
     XLMForQuestionAnswering,
     XLMTokenizer,
     XLNetConfig,
     XLNetForQuestionAnswering,
     XLNetTokenizer,
-    DistilBertConfig,
-    DistilBertForQuestionAnswering,
-    DistilBertTokenizer,
+    get_linear_schedule_with_warmup,
 )
-
-from transformers import AdamW, get_linear_schedule_with_warmup
-
 from utils_squad import (
-    read_squad_examples,
-    convert_examples_to_features,
     RawResult,
-    write_predictions,
     RawResultExtended,
+    convert_examples_to_features,
+    read_squad_examples,
+    write_predictions,
     write_predictions_extended,
 )
 
 # The follwing import is the official SQuAD evaluation script (2.0).
 # You can remove it from the dependencies if you are using this script outside of the library
 # We've added it here for automated tests (see examples/test_examples.py file)
-from utils_squad_evaluate import EVAL_OPTS, main as evaluate_on_squad
+from utils_squad_evaluate import EVAL_OPTS
+from utils_squad_evaluate import main as evaluate_on_squad
+
+
+try:
+    from torch.utils.tensorboard import SummaryWriter
+except:
+    from tensorboardX import SummaryWriter
+
 
 logger = logging.getLogger(__name__)