First attempt: panedr and panedrlite

.github/workflows/gh-ci.yaml

@@ -56,11 +56,12 @@ jobs:
 
     - name: install package
       run: |
-        python -m pip install -v .
+        python -m pip install -v ./panedrlite
+        # python -m pip install -v ./panedr
 
     - name: run unit tests
       run: |
-        pytest -n 2 -v --cov=panedr --cov-report=xml --color=yes ./tests
+        pytest -n 2 -v --cov=panedrlite --cov-report=xml --color=yes ./tests
 
     - name: codecov
       uses: codecov/codecov-action@v3

panedr/__init__.py → panedr/panedr/__init__.py

@@ -4,4 +4,4 @@
 __version__ = pbr.version.VersionInfo('panedr').release_string()
 del pbr
 
-from .panedr import *
+from panedrlite import *

panedr/requirements.txt

@@ -0,0 +1,3 @@
+panedrlite[pandas]
+numpy>=1.19.0
+pbr

setup.cfg → panedr/setup.cfg

@@ -5,7 +5,7 @@ author_email = [email protected]
 summary = Read and manipulate Gromacs energy files
 license = LGPL
 description_file =
-    README.rst
+    ../README.rst
 long_description_content_type = text/x-rst
 home_page = https://github.com/MDAnalysis/panedr
 python_requires = >=3.6

panedrlite/panedrlite/__init__.py

@@ -0,0 +1,7 @@
+# -*- coding: utf-8 -*-
+
+import pbr.version
+__version__ = pbr.version.VersionInfo('panedrlite').release_string()
+del pbr
+
+from .panedr import *

panedr/panedr.py → panedrlite/panedrlite/panedr.py

@@ -45,7 +45,8 @@
 import sys
 import itertools
 import time
-import pandas
+import numpy as np
+
 
 #Index for the IDs of additional blocks in the energy file.
 #Blocks can be added without sacrificing backward and forward
@@ -75,7 +76,7 @@
 Enxnm = collections.namedtuple('Enxnm', 'name unit')
 ENX_VERSION = 5
 
-__all__ = ['edr_to_df']
+__all__ = ['edr_to_df', 'edr_to_dict', 'read_edr']
 
 
 class EDRFile(object):
@@ -395,14 +396,14 @@ def edr_strings(data, file_version, n):
 
 def is_frame_magic(data):
     """Unpacks an int and checks whether it matches the EDR frame magic number
-    
+
     Does not roll the reading position back.
     """
     magic = data.unpack_int()
     return magic == -7777777
 
 
-def edr_to_df(path, verbose=False):
+def read_edr(path, verbose=False):
     begin = time.time()
     edr_file = EDRFile(str(path))
     all_energies = []
@@ -427,5 +428,27 @@ def edr_to_df(path, verbose=False):
               end='', file=sys.stderr)
         print('\n{} frame read in {:.2f} seconds'.format(ifr, end - begin),
               file=sys.stderr)
+
+    return all_energies, all_names, times
+
+
+def edr_to_df(path: str, verbose: bool = False):
+    try:
+        import pandas
+    except ImportError:
+        raise ImportError("""ERROR --- pandas was not found!
+                          pandas is required to use the `.edr_to_df()`
+                          functionality. Try installing it using pip, e.g.:
+                          python -m pip install pandas""")
+    all_energies, all_names, times = read_edr(path, verbose=verbose)
     df = pandas.DataFrame(all_energies, columns=all_names, index=times)
     return df
+
+
+def edr_to_dict(path: str, verbose: bool = False):
+    all_energies, all_names, times = read_edr(path, verbose=verbose)
+    energy_dict = {}
+    for idx, name in enumerate(all_names):
+        energy_dict[name] = np.array(
+            [all_energies[frame][idx] for frame in range(len(times))])
+    return energy_dict

panedrlite/requirements.txt

@@ -0,0 +1,2 @@
+numpy>=1.19.0
+pbr

panedrlite/setup.cfg

@@ -0,0 +1,31 @@
+[metadata]
+name = panedrlite
+author = Jonathan Barnoud
+author_email = [email protected]
+summary = Read and manipulate Gromacs energy files
+license = LGPL
+description_file =
+    ../README.rst
+long_description_content_type = text/x-rst
+home_page = https://github.com/MDAnalysis/panedr
+python_requires = >=3.6
+classifier =
+    Development Status :: 4 - Beta
+    Intended Audience :: Developers
+    Topic :: Scientific/Engineering :: Bio-Informatics
+    Topic :: Scientific/Engineering :: Chemistry
+    Topic :: Scientific/Engineering :: Physics
+    License :: OSI Approved :: GNU Lesser General Public License v2 or later (LGPLv2+)
+    Programming Language :: Python :: 3.6
+    Programming Language :: Python :: 3.7
+    Programming Language :: Python :: 3.8
+    Programming Language :: Python :: 3.9
+    Programming Language :: Python :: 3.10
+    Operating System :: OS Independent
+
+[extras]
+test =
+    six
+    pytest
+pandas =
+    pandas

panedrlite/setup.py

@@ -0,0 +1,6 @@
+from setuptools import setup
+
+setup(
+    setup_requires=['pbr'],
+    pbr=True,
+)

tests/test_edr.py

@@ -14,7 +14,7 @@
 import contextlib
 import numpy
 import pandas
-import panedr
+import panedrlite as panedr
 import re
 
 # On python 2, cStringIO is a faster version of StringIO. It may not be