code health

README.md

@@ -35,10 +35,10 @@ So, why don't we take pandas to the structural biology world? Working with molec
 ![3eiy](./docs/sources/img/index/3eiy.png)
 
 ```python
-# Initialize a new PandasPDB object
+# Initialize a new PandasPdb object
 # and fetch the PDB file from rcsb.org
->>> from biopandas.pdb import PandasPDB
->>> ppdb = PandasPDB().fetch_pdb('3eiy')
+>>> from biopandas.pdb import PandasPdb
+>>> ppdb = PandasPdb().fetch_pdb('3eiy')
 >>> ppdb.df['ATOM'].head()
 ```
 
@@ -53,10 +53,10 @@ So, why don't we take pandas to the structural biology world? Working with molec
 ```python
 # Load structures from your drive and compute the
 # Root Mean Square Deviation
->>> from biopandas.pdb import PandasPDB
->>> pl1 = PandasPDB().read_pdb('./docking_pose_1.pdb')
->>> pl2 = PandasPDB().read_pdb('./docking_pose_2.pdb')
->>> r = PandasPDB.rmsd(pl1.df['HETATM'], pl2.df['HETATM'],
+>>> from biopandas.pdb import PandasPdb
+>>> pl1 = PandasPdb().read_pdb('./docking_pose_1.pdb')
+>>> pl2 = PandasPdb().read_pdb('./docking_pose_2.pdb')
+>>> r = PandasPdb.rmsd(pl1.df['HETATM'], pl2.df['HETATM'],
                        s='hydrogen', invert=True)
 >>> print('RMSD: %.4f Angstrom' % r)
 

biopandas/mol2/__init__.py

@@ -9,7 +9,7 @@
 files in pandas DataFrames.
 """
 
-from .pandas_mol2 import PandasMOL2
+from .pandas_mol2 import PandasMol2
 from .mol2_io import split_multimol2
 
-__all__ = ["PandasMOL2", "split_multimol2"]
+__all__ = ["PandasMol2", "split_multimol2"]

biopandas/mol2/pandas_mol2.py

@@ -24,7 +24,7 @@
 COLUMN_TYPES = (int, str, float, float, float, str, int, str, float)
 
 
-class PandasMOL2(object):
+class PandasMol2(object):
     """ Object for working with Tripos Mol2 structure files.
 
    Attributes

biopandas/mol2/tests/test_pandas_mol2.py

@@ -5,7 +5,7 @@
 # Code Repository: https://github.com/rasbt/biopandas
 
 import os
-from biopandas.mol2 import PandasMOL2
+from biopandas.mol2 import PandasMol2
 from biopandas.mol2.mol2_io import split_multimol2
 
 this_dir = os.path.dirname(os.path.realpath(__file__))
@@ -17,7 +17,7 @@ def test_read_mol2():
     data_path_2 = os.path.join(this_dir, 'data', '40_mol2_files.mol2.gz')
 
     for data_path in (data_path_1, data_path_2):
-        pdmol = PandasMOL2().read_mol2(data_path)
+        pdmol = PandasMol2().read_mol2(data_path)
         assert pdmol.df.shape == (65, 9)
         assert pdmol.code == 'ZINC38611810'
 
@@ -32,7 +32,7 @@ def test_read_mol2_from_list():
     data_path = os.path.join(this_dir, 'data', '40_mol2_files.mol2')
     mol2 = next(split_multimol2(data_path))
 
-    pdmol = PandasMOL2().read_mol2_from_list(mol2_lines=mol2[1],
+    pdmol = PandasMol2().read_mol2_from_list(mol2_lines=mol2[1],
                                              mol2_code=mol2[0])
     assert pdmol.df.shape == (65, 9)
     assert pdmol.code == 'ZINC38611810'
@@ -42,8 +42,8 @@ def test_rmsd():
     data_path_1 = os.path.join(this_dir, 'data', '1b5e_1.mol2')
     data_path_2 = os.path.join(this_dir, 'data', '1b5e_2.mol2')
 
-    pdmol_1 = PandasMOL2().read_mol2(data_path_1)
-    pdmol_2 = PandasMOL2().read_mol2(data_path_2)
+    pdmol_1 = PandasMol2().read_mol2(data_path_1)
+    pdmol_2 = PandasMol2().read_mol2(data_path_2)
 
     assert pdmol_1.rmsd(pdmol_1.df, pdmol_2.df, heavy_only=False) == 1.5523
     assert pdmol_1.rmsd(pdmol_1.df, pdmol_2.df) == 1.1609
@@ -52,5 +52,5 @@ def test_rmsd():
 def test_distance():
     data_path = os.path.join(this_dir, 'data', '1b5e_1.mol2')
 
-    pdmol = PandasMOL2().read_mol2(data_path)
+    pdmol = PandasMol2().read_mol2(data_path)
     assert round(pdmol.distance().values[0], 3) == 31.185

biopandas/pdb/__init__.py

@@ -9,6 +9,6 @@
 files in pandas DataFrames.
 """
 
-from .pandas_pdb import PandasPDB
+from .pandas_pdb import PandasPdb
 
-__all__ = ["PandasPDB"]
+__all__ = ["PandasPdb"]

biopandas/pdb/pandas_pdb.py

@@ -19,7 +19,7 @@
 from .engines import amino3to1dict
 
 
-class PandasPDB(object):
+class PandasPdb(object):
     """ Object for working with Protein Databank structure files.
 
     Attributes
@@ -117,12 +117,12 @@ def get(self, s, df=None, invert=False):
             df = self._df['ATOM']
         return self._get_dict[s](df, invert=invert)
 
-    def impute_element(self, sections=['ATOM', 'HETATM'], inplace=False):
+    def impute_element(self, sections=('ATOM', 'HETATM'), inplace=False):
         """Impute element_symbol from atom_name section.
 
         Parameters
         ----------
-        sections : iterable (default: ['ATOM', 'HETATM'])
+        sections : iterable (default: ('ATOM', 'HETATM'))
             Coordinate sections for which the element symbols should be
             imputed.
 
@@ -181,7 +181,7 @@ def rmsd(df1, df2, s=None, invert=False):
         """
         if df1.shape[0] != df2.shape[0]:
             raise AttributeError('DataFrames have unequal lengths')
-        get_dict = PandasPDB._init_get_dict()
+        get_dict = PandasPdb._init_get_dict()
         if s:
             if s not in get_dict.keys():
                 raise AttributeError('s must be in '
@@ -198,11 +198,11 @@ def rmsd(df1, df2, s=None, invert=False):
     @staticmethod
     def _init_get_dict():
         """Initialize dictionary for filter operations."""
-        get_dict = {'main chain': PandasPDB._get_mainchain,
-                    'hydrogen': PandasPDB._get_hydrogen,
-                    'c-alpha': PandasPDB._get_calpha,
-                    'carbon': PandasPDB._get_carbon,
-                    'heavy': PandasPDB._get_heavy}
+        get_dict = {'main chain': PandasPdb._get_mainchain,
+                    'hydrogen': PandasPdb._get_hydrogen,
+                    'c-alpha': PandasPdb._get_calpha,
+                    'carbon': PandasPdb._get_carbon,
+                    'heavy': PandasPdb._get_heavy}
         return get_dict
 
     @staticmethod

biopandas/pdb/tests/test_amino3to1.py

@@ -4,14 +4,14 @@
 # Project Website: http://rasbt.github.io/biopandas/
 # Code Repository: https://github.com/rasbt/biopandas
 
-from biopandas.pdb import PandasPDB
+from biopandas.pdb import PandasPdb
 import os
 
 
 def test_defaults():
     TESTDATA_1t48 = os.path.join(os.path.dirname(__file__), 'data',
                                                             '1t48_995.pdb')
-    p1t48 = PandasPDB()
+    p1t48 = PandasPdb()
     p1t48.read_pdb(TESTDATA_1t48)
     expect = ['M', 'E', 'M', 'E', 'K', 'E', 'F', 'E', 'Q',
               'I', 'D', 'K', 'S', 'G', 'S', 'W', 'A', 'A',

biopandas/pdb/tests/test_distance.py

@@ -5,7 +5,7 @@
 # Code Repository: https://github.com/rasbt/biopandas
 
 import pandas as pd
-from biopandas.pdb import PandasPDB
+from biopandas.pdb import PandasPdb
 import os
 from nose.tools import raises
 
@@ -14,7 +14,7 @@ def test_equal():
     TESTDATA_1t48 = os.path.join(os.path.dirname(__file__), 'data',
                                                             '1t48_995.pdb')
 
-    p1t48 = PandasPDB()
+    p1t48 = PandasPdb()
     p1t48.read_pdb(TESTDATA_1t48)
     dist = p1t48.distance(xyz=(70.785, 15.477, 23.359), record='ATOM')
 

biopandas/pdb/tests/test_impute.py

@@ -5,7 +5,7 @@
 # Code Repository: https://github.com/rasbt/biopandas
 
 
-from biopandas.pdb import PandasPDB
+from biopandas.pdb import PandasPdb
 import os
 import numpy as np
 import pandas as pd
@@ -14,7 +14,7 @@
 TESTDATA_FILENAME = os.path.join(os.path.dirname(__file__), 'data',
                                  '3eiy_stripped_no_ele.pdb')
 
-ppdb = PandasPDB()
+ppdb = PandasPdb()
 ppdb.read_pdb(TESTDATA_FILENAME)
 
 

biopandas/pdb/tests/test_read_pdb.py

@@ -5,7 +5,7 @@
 # Code Repository: https://github.com/rasbt/biopandas
 
 
-from biopandas.pdb import PandasPDB
+from biopandas.pdb import PandasPdb
 import os
 import numpy as np
 import pandas as pd
@@ -50,7 +50,7 @@
 
 def test__read_pdb():
     """Test private _read_pdb"""
-    ppdb = PandasPDB()
+    ppdb = PandasPdb()
     txt = ppdb._read_pdb(TESTDATA_FILENAME)
     print(txt)
     assert txt == three_eiy
@@ -60,7 +60,7 @@ def test_fetch_pdb():
     """Test fetch_pdb"""
 
     try:
-        ppdb = PandasPDB()
+        ppdb = PandasPdb()
         txt = ppdb._fetch_pdb('3eiy')
     except HTTPError:
         pass
@@ -73,14 +73,14 @@ def test_fetch_pdb():
 
 def test__read_pdb_gz():
     """Test public _read_pdb with gzip files"""
-    ppdb = PandasPDB()
+    ppdb = PandasPdb()
     txt = ppdb._read_pdb(TESTDATA_FILENAME_GZ)
     assert txt == three_eiy
 
 
 def test__construct_df():
     """Test pandas dataframe construction"""
-    ppdb = PandasPDB()
+    ppdb = PandasPdb()
     dfs = ppdb._construct_df(three_eiy.splitlines())
     assert set(dfs.keys()) == {'OTHERS', 'ATOM', 'ANISOU', 'HETATM'}
     assert set(dfs['ATOM'].columns) == set(ATOM_DF_COLUMNS)
@@ -102,36 +102,36 @@ def test__construct_df():
 
 def test_read_pdb():
     """Test public read_pdb"""
-    ppdb = PandasPDB()
+    ppdb = PandasPdb()
     ppdb.read_pdb(TESTDATA_FILENAME)
     assert ppdb.pdb_text == three_eiy
     assert ppdb.code == '3eiy', ppdb.code
 
 
 def test_anisou_input_handling():
     """Test public read_pdb"""
-    ppdb = PandasPDB()
+    ppdb = PandasPdb()
     ppdb.read_pdb(TESTDATA_FILENAME2)
     assert ppdb.pdb_text == four_eiy
     assert ppdb.code == '4eiy', ppdb.code
 
 
 @raises(AttributeError)
 def test_get_exceptions():
-    ppdb = PandasPDB()
+    ppdb = PandasPdb()
     ppdb.read_pdb(TESTDATA_FILENAME)
     ppdb.get('main-chai')
 
 
 def test_get_all():
-    ppdb = PandasPDB()
+    ppdb = PandasPdb()
     ppdb.read_pdb(TESTDATA_FILENAME)
     for i in ['c-alpha', 'hydrogen', 'main chain']:
         ppdb.get(i)
 
 
 def test_get_df():
-    ppdb = PandasPDB()
+    ppdb = PandasPdb()
     ppdb.read_pdb(TESTDATA_FILENAME)
 
     shape = ppdb.get('c-alpha').shape

biopandas/pdb/tests/test_rmsd.py

@@ -4,7 +4,7 @@
 # Project Website: http://rasbt.github.io/biopandas/
 # Code Repository: https://github.com/rasbt/biopandas
 
-from biopandas.pdb import PandasPDB
+from biopandas.pdb import PandasPdb
 import os
 from nose.tools import raises
 
@@ -18,50 +18,50 @@
 TESTDATA_lig2 = os.path.join(os.path.dirname(__file__), 'data',
                                                         'lig_conf_2.pdb')
 
-p1t48 = PandasPDB()
+p1t48 = PandasPdb()
 p1t48.read_pdb(TESTDATA_1t48)
-p1t49 = PandasPDB()
+p1t49 = PandasPdb()
 p1t49.read_pdb(TESTDATA_1t49)
 
-pl1 = PandasPDB()
+pl1 = PandasPdb()
 pl1.read_pdb(TESTDATA_lig1)
-pl2 = PandasPDB()
+pl2 = PandasPdb()
 pl2.read_pdb(TESTDATA_lig2)
 
 
 def test_equal():
-    r = PandasPDB.rmsd(p1t48.df['ATOM'], p1t48.df['ATOM'], s=None)
+    r = PandasPdb.rmsd(p1t48.df['ATOM'], p1t48.df['ATOM'], s=None)
     assert r == 0.000, r
 
 
 @raises(AttributeError)
 def test_wrong_arg():
-    PandasPDB.rmsd(p1t48.df['ATOM'].loc[1:, :], p1t48.df['ATOM'], s='bla')
+    PandasPdb.rmsd(p1t48.df['ATOM'].loc[1:, :], p1t48.df['ATOM'], s='bla')
 
 
 @raises(AttributeError)
 def test_incompatible():
-    PandasPDB.rmsd(p1t48.df['ATOM'].loc[1:, :], p1t48.df['ATOM'], s=None)
+    PandasPdb.rmsd(p1t48.df['ATOM'].loc[1:, :], p1t48.df['ATOM'], s=None)
 
 
 @raises(AttributeError)
 def test_invalid_query():
-    PandasPDB.rmsd(p1t48.df['ATOM'].loc[1:, :], p1t48.df['ATOM'], s='bla')
+    PandasPdb.rmsd(p1t48.df['ATOM'].loc[1:, :], p1t48.df['ATOM'], s='bla')
 
 
 def test_protein():
-    r = PandasPDB.rmsd(p1t48.df['ATOM'], p1t49.df['ATOM'],
+    r = PandasPdb.rmsd(p1t48.df['ATOM'], p1t49.df['ATOM'],
                        s='c-alpha', invert=False)
     assert r == 0.4785, r
 
 
 def test_ligand():
-    r = PandasPDB.rmsd(pl1.df['HETATM'], pl2.df['HETATM'],
+    r = PandasPdb.rmsd(pl1.df['HETATM'], pl2.df['HETATM'],
                        s='hydrogen', invert=True)
     assert r == 1.9959, r
 
 
 def test_ligand_default():
-    r = PandasPDB.rmsd(pl1.df['HETATM'], pl2.df['HETATM'],
+    r = PandasPdb.rmsd(pl1.df['HETATM'], pl2.df['HETATM'],
                        s=None)
     assert r == 2.6444, r