Add isort to pre-commit hooks

.github/workflows/python-package-macos.yml

@@ -39,11 +39,14 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install flake8 pytest black
+        python -m pip install flake8 pytest black isort
         pip install -e .
     - name: Check formatting with black
       run: |
         black --check .
+    - name: Check imports with isort
+      run: |
+        isort -c .
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names

.github/workflows/python-package-ubuntu.yml

@@ -42,11 +42,14 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install flake8 pytest black
+        python -m pip install flake8 pytest black isort
         pip install -e .
     - name: Check formatting with black
       run: |
         black --check .
+    - name: Check imports with isort
+      run: |
+        isort -c .
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names

.github/workflows/python-package-windows.yml

@@ -39,11 +39,14 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install flake8 pytest black
+        python -m pip install flake8 pytest black isort
         pip install -e .
     - name: Check formatting with black
       run: |
         black --check .
+    - name: Check imports with isort
+      run: |
+        isort -c .
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names

.pre-commit-config.yaml

@@ -8,3 +8,8 @@ repos:
     hooks:
     -   id: flake8
         args: [--count, "--select=E9,F63,F7,F82", --show-source, --statistics, --]
+-   repo: https://github.com/pycqa/isort
+    rev: 5.12.0
+    hooks:
+    -   id: isort
+        name: isort (python)

docker/model_download.py

@@ -1,10 +1,8 @@
 import os
-from transformers import (
-    AutoConfig,
-    AutoModel,
-    AutoTokenizer,
-)
-from cnlpt.CnlpModelForClassification import CnlpModelForClassification, CnlpConfig
+
+from transformers import AutoConfig, AutoModel, AutoTokenizer
+
+from cnlpt.CnlpModelForClassification import CnlpConfig, CnlpModelForClassification
 from cnlpt.HierarchicalTransformer import HierarchicalModel
 from cnlpt.train_system import is_hub_model
 

pyproject.toml

@@ -1,3 +1,6 @@
 [build-system]
 requires = ["setuptools", "wheel"]
 build-backend = "setuptools.build_meta"
+
+[tool.isort]
+profile = "black"

src/cnlpt/BaselineModels.py

@@ -1,8 +1,8 @@
 from typing import Dict, List
 
 import torch
-from torch import nn
 import torch.nn.functional as F
+from torch import nn
 
 
 class CnnSentenceClassifier(nn.Module):

src/cnlpt/CnlpModelForClassification.py

@@ -4,21 +4,21 @@
 # from transformers.models.auto import  AutoModel, AutoConfig
 import copy
 import inspect
+import logging
+import math
+import random
 from os import PathLike
-from typing import Optional, List, Any, Dict, Union
-
-from transformers import AutoModel, AutoConfig
-from transformers.modeling_utils import PreTrainedModel
-from transformers.configuration_utils import PretrainedConfig
+from typing import Any, Dict, List, Optional, Union
 
 import torch
 from torch import nn
-import logging
 from torch.nn import CrossEntropyLoss, MSELoss
+from torch.nn.functional import relu, softmax
+from transformers import AutoConfig, AutoModel
+from transformers.configuration_utils import PretrainedConfig
 from transformers.modeling_outputs import SequenceClassifierOutput
-from torch.nn.functional import softmax, relu
-import math
-import random
+from transformers.modeling_utils import PreTrainedModel
+
 from . import __version__ as cnlpt_version
 
 logger = logging.getLogger(__name__)

src/cnlpt/HierarchicalTransformer.py

@@ -1,26 +1,26 @@
 """
 Module containing the Hierarchical Transformer module, adapted from Xin Su.
 """
-import logging
 import copy
+import logging
 import random
-from typing import Optional, List, cast, Dict, Tuple
+from dataclasses import dataclass
+from typing import Dict, List, Optional, Tuple, cast
 
 import numpy as np
-from torch import nn
-import torch.nn.functional as F
 import torch
+import torch.nn.functional as F
+from torch import nn
 from torch.nn import CrossEntropyLoss
-from dataclasses import dataclass
+from transformers import AutoConfig, AutoModel
 from transformers.modeling_outputs import SequenceClassifierOutput
 from transformers.modeling_utils import PreTrainedModel
-from transformers import AutoModel, AutoConfig
 
 from .CnlpModelForClassification import (
-    CnlpConfig,
     ClassificationHead,
-    generalize_encoder_forward_kwargs,
+    CnlpConfig,
     freeze_encoder_weights,
+    generalize_encoder_forward_kwargs,
 )
 
 logger = logging.getLogger(__name__)

src/cnlpt/api/cnlp_rest.py

@@ -1,3 +1,6 @@
+"""
+isort:skip_file
+"""
 # Core python imports
 import os
 

src/cnlpt/api/cnn_rest.py

@@ -14,20 +14,19 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
-from fastapi import FastAPI
-
+import json
 import logging
 import os
-from os.path import join
 import sys
-import json
+from os.path import join
 
-from transformers import AutoTokenizer, Trainer
-import torch
 import numpy as np
+import torch
+from fastapi import FastAPI
+from transformers import AutoTokenizer, Trainer
 
-from .cnlp_rest import UnannotatedDocument, get_dataset
 from ..BaselineModels import CnnSentenceClassifier
+from .cnlp_rest import UnannotatedDocument, get_dataset
 
 app = FastAPI()
 model_name = os.getenv("MODEL_PATH")

src/cnlpt/api/current_rest.py

@@ -14,21 +14,20 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
+import logging
+from time import time
+from typing import List
+
+import numpy as np
 from fastapi import FastAPI
 from pydantic import BaseModel
 
-from typing import List
-
 from .cnlp_rest import (
     EntityDocument,
     create_instance_string,
-    initialize_cnlpt_model,
     get_dataset,
+    initialize_cnlpt_model,
 )
-import numpy as np
-
-import logging
-from time import time
 
 app = FastAPI()
 model_name = "mlml-chip/current-thyme"

src/cnlpt/api/dtr_rest.py

@@ -14,21 +14,14 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
-from fastapi import FastAPI
-from pydantic import BaseModel
 import logging
-from typing import List
 from time import time
+from typing import List
 
-from ..CnlpModelForClassification import CnlpModelForClassification, CnlpConfig
-from .cnlp_rest import (
-    EntityDocument,
-    initialize_cnlpt_model,
-    create_instance_string,
-    get_dataset,
-)
-from .temporal_rest import dtr_label_list, old_dtr_label_list
-
+import numpy as np
+from fastapi import FastAPI
+from pydantic import BaseModel
+from torch.utils.data.dataset import Dataset
 from transformers import (
     AutoConfig,
     AutoModel,
@@ -37,9 +30,16 @@
     Trainer,
     TrainingArguments,
 )
-from transformers.data.processors.utils import InputFeatures, InputExample
-from torch.utils.data.dataset import Dataset
-import numpy as np
+from transformers.data.processors.utils import InputExample, InputFeatures
+
+from ..CnlpModelForClassification import CnlpConfig, CnlpModelForClassification
+from .cnlp_rest import (
+    EntityDocument,
+    create_instance_string,
+    get_dataset,
+    initialize_cnlpt_model,
+)
+from .temporal_rest import dtr_label_list, old_dtr_label_list
 
 app = FastAPI()
 model_name = "tmills/tiny-dtr"

src/cnlpt/api/event_rest.py

@@ -15,27 +15,28 @@
 # specific language governing permissions and limitations
 # under the License.
 
+import logging
 import os
+from time import time
+from typing import Dict, List, Tuple
+
+import numpy as np
 from fastapi import FastAPI
+from nltk.tokenize import wordpunct_tokenize as tokenize
 from pydantic import BaseModel
-from typing import List, Tuple, Dict
-from transformers.data.processors.utils import InputFeatures, InputExample
-from torch.utils.data.dataset import Dataset
-import numpy as np
-from .cnlp_rest import initialize_cnlpt_model, get_dataset
-from ..CnlpModelForClassification import CnlpModelForClassification, CnlpConfig
 from seqeval.metrics.sequence_labeling import get_entities
-import logging
-from time import time
-from nltk.tokenize import wordpunct_tokenize as tokenize
+from torch.utils.data.dataset import Dataset
+from transformers.data.processors.utils import InputExample, InputFeatures
 
+from ..CnlpModelForClassification import CnlpConfig, CnlpModelForClassification
+from .cnlp_rest import get_dataset, initialize_cnlpt_model
 from .temporal_rest import (
-    event_label_list,
-    TokenizedSentenceDocument,
-    SentenceDocument,
     Event,
+    SentenceDocument,
     TemporalResults,
+    TokenizedSentenceDocument,
     create_instance_string,
+    event_label_list,
 )
 
 app = FastAPI()

src/cnlpt/api/hier_rest.py

@@ -14,25 +14,24 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
+import logging
+import os
+from time import time
+from typing import Dict, List, Tuple
+
+import numpy as np
+import torch
 from fastapi import FastAPI
 from pydantic import BaseModel
 
-from typing import List, Tuple, Dict
-
+from ..CnlpModelForClassification import CnlpConfig, CnlpModelForClassification
 from .cnlp_rest import (
     UnannotatedDocument,
     create_instance_string,
+    get_dataset,
     initialize_cnlpt_model,
     initialize_hier_model,
-    get_dataset,
 )
-from ..CnlpModelForClassification import CnlpModelForClassification, CnlpConfig
-import torch
-import numpy as np
-
-import logging
-from time import time
-import os
 
 app = FastAPI()
 model_name = os.getenv("MODEL_PATH")

src/cnlpt/api/negation_rest.py

@@ -14,22 +14,21 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
+import logging
+from time import time
+from typing import Dict, List, Tuple
+
+import numpy as np
 from fastapi import FastAPI
 from pydantic import BaseModel
 
-from typing import List, Tuple, Dict
-
+from ..CnlpModelForClassification import CnlpConfig, CnlpModelForClassification
 from .cnlp_rest import (
     EntityDocument,
     create_instance_string,
-    initialize_cnlpt_model,
     get_dataset,
+    initialize_cnlpt_model,
 )
-from ..CnlpModelForClassification import CnlpModelForClassification, CnlpConfig
-import numpy as np
-
-import logging
-from time import time
 
 app = FastAPI()
 model_name = "mlml-chip/negation_pubmedbert_sharpseed"

src/cnlpt/api/temporal_rest.py

@@ -15,17 +15,19 @@
 # specific language governing permissions and limitations
 # under the License.
 
+import logging
 import os
+from time import time
+from typing import Dict, List, Tuple, Union
+
+import numpy as np
 from fastapi import FastAPI
+from nltk.tokenize import wordpunct_tokenize as tokenize
 from pydantic import BaseModel
-from typing import List, Tuple, Dict, Union
-import numpy as np
-from .cnlp_rest import create_instance_string, initialize_cnlpt_model, get_dataset
-from ..CnlpModelForClassification import CnlpModelForClassification, CnlpConfig
 from seqeval.metrics.sequence_labeling import get_entities
-import logging
-from time import time
-from nltk.tokenize import wordpunct_tokenize as tokenize
+
+from ..CnlpModelForClassification import CnlpConfig, CnlpModelForClassification
+from .cnlp_rest import create_instance_string, get_dataset, initialize_cnlpt_model
 
 app = FastAPI()
 model_name = "mlml-chip/thyme2_colon_e2e"