Package Based Project Structure

bert_pytorch/__init__.py

@@ -0,0 +1,3 @@
+from .model import BERT
+
+__version__ = "0.0.1a0"

build_dataset.py

@@ -1,4 +1,4 @@
-from dataset import WordVocab, BERTDatasetCreator
+from bert_pytorch.dataset import WordVocab, BERTDatasetCreator
 
 import argparse
 import tqdm

build_vocab.py

@@ -1,6 +1,6 @@
 import argparse
 
-from dataset import WordVocab
+from bert_pytorch.dataset import WordVocab
 
 parser = argparse.ArgumentParser()
 parser.add_argument("-c", "--corpus_path", required=True, type=str)

setup.py

@@ -0,0 +1,47 @@
+from setuptools import setup, find_packages
+from setuptools.command.install import install
+from bert_pytorch import __version__
+import os
+import sys
+
+with open("requirements.txt") as f:
+    require_packages = [line[:-1] for line in f]
+
+with open("README.md", "r", encoding="utf-8") as f:
+    long_description = f.read()
+
+
+class VerifyVersionCommand(install):
+    """Custom command to verify that the git tag matches our version"""
+    description = 'verify that the git tag matches our version'
+
+    def run(self):
+        tag = os.getenv('CIRCLE_TAG')
+
+        if tag != __version__:
+            info = "Git tag: {0} does not match the version of this app: {1}".format(
+                tag, __version__
+            )
+            sys.exit(info)
+
+
+setup(
+    name="bert_pytorch",
+    version=__version__,
+    author='Junseong Kim',
+    author_email='codertimo@gmail.com',
+    packages=find_packages(),
+    install_requires=require_packages,
+    url="https://github.com/codertimo/BERT-pytorch",
+    description="Google AI 2018 BERT pytorch implementation",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: Apache Software License",
+        "Operating System :: OS Independent",
+    ],
+    cmdclass={
+        'verify': VerifyVersionCommand,
+    }
+)

train.py

@@ -2,9 +2,9 @@
 
 from torch.utils.data import DataLoader
 
-from model import BERT
-from trainer import BERTTrainer
-from dataset import BERTDataset, WordVocab
+from bert_pytorch import BERT
+from bert_pytorch.trainer import BERTTrainer
+from bert_pytorch.dataset import BERTDataset, WordVocab
 
 parser = argparse.ArgumentParser()