Changed the directory structure

setup.py

@@ -0,0 +1,25 @@
+import setuptools
+
+with open("README.md", "r") as fh:
+    long_description = fh.read()
+
+setuptools.setup(
+    name="simple_elmo",
+    version="0.1.0",
+    author="Andrey Kutuzov",
+    author_email="[email protected]",
+    description="Useful library to work with pre-trained ELMo embeddings in TensorFlow ",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/ltgoslo/simple_elmo",
+    packages=setuptools.find_packages(),
+    python_requires='>=3.6',
+    install_requires=["tensorflow>1.15", "h5py", "numpy", "smart_open>1.8.1", "pandas", "scikit-learn"],
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+        "Topic :: Scientific/Engineering :: Artifical Intelligence ",
+        "Topic :: Utilities"
+    ],
+)

simple_elmo/__init__.py

@@ -0,0 +1,2 @@
+name = "simple_elmo"
+from simple_elmo.elmo_helpers import ElmoModel

data.py → simple_elmo/data.py

@@ -5,6 +5,7 @@
 from smart_open import open
 import numpy as np
 from typing import List
+import logging
 
 
 class Vocabulary(object):
@@ -338,7 +339,7 @@ def __init__(self, filepattern, vocab, reverse=False, test=False,
         """
         self._vocab = vocab
         self._all_shards = glob.glob(filepattern + '*.gz')
-        print(f'Found {len(self._all_shards)} shards at {filepattern}', file=sys.stderr)
+        logging.info(f'Found {len(self._all_shards)} shards at {filepattern}')
         self._shards_to_choose = []
 
         self._reverse = reverse
@@ -383,7 +384,7 @@ def _load_shard(self, shard_name):
         Returns:
             list of (id, char_id) tuples.
         """
-        print(f'Loading data from: {shard_name}', file=sys.stderr)
+        logging.info(f'Loading data from: {shard_name}')
         with open(shard_name, 'r') as f:
             sentences_raw = f.readlines()
 
@@ -407,8 +408,8 @@ def _load_shard(self, shard_name):
         else:
             chars_ids = [None] * len(ids)
 
-        print(f'Loaded {len(ids)} sentences', file=sys.stderr)
-        print('Finished loading', file=sys.stderr)
+        logging.info(f'Loaded {len(ids)} sentences')
+        logging.info('Finished loading')
         return list(zip(ids, chars_ids))
 
     def get_sentence(self):