Config flake8 and fix may linter errors (#198)

docs/conf.py

@@ -28,9 +28,9 @@ html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
 htmlhelp_basename = 'TorchANIdoc'
 
 sphinx_gallery_conf = {
-     'examples_dirs': '../examples',
-     'gallery_dirs': 'examples',
-     'filename_pattern': r'.*\.py'
+    'examples_dirs': '../examples',
+    'gallery_dirs': 'examples',
+    'filename_pattern': r'.*\.py'
 }
 
 intersphinx_mapping = {

examples/cache_aev.py

@@ -52,8 +52,8 @@ log = 'runs'
 ###############################################################################
 # Here, there is no need to manually construct aev computer and energy shifter,
 # but we do need to generate a disk cache for datasets
-const_file = os.path.join(path, '../torchani/resources/ani-1x_8x/rHCNO-5.2R_16-3.5A_a4-8.params')  # noqa: E501
-sae_file = os.path.join(path, '../torchani/resources/ani-1x_8x/sae_linfit.dat')  # noqa: E501
+const_file = os.path.join(path, '../torchani/resources/ani-1x_8x/rHCNO-5.2R_16-3.5A_a4-8.params')
+sae_file = os.path.join(path, '../torchani/resources/ani-1x_8x/sae_linfit.dat')
 training_cache = './training_cache'
 validation_cache = './validation_cache'
 
@@ -113,7 +113,9 @@ container = torchani.ignite.Container({'energies': model})
 optimizer = torch.optim.Adam(model.parameters())
 trainer = ignite.engine.create_supervised_trainer(
     container, optimizer, torchani.ignite.MSELoss('energies'))
-evaluator = ignite.engine.create_supervised_evaluator(container, metrics={
+evaluator = ignite.engine.create_supervised_evaluator(
+    container,
+    metrics={
         'RMSE': torchani.ignite.RMSEMetric('energies')
     })
 

examples/energy_force.py

@@ -33,11 +33,11 @@ model = torchani.models.ANI1ccx()
 # preceding ``1`` in the shape is here to support batch processing like in
 # training. If you have ``N`` different structures to compute, then make it
 # ``N``.
-coordinates = torch.tensor([[[0.03192167,  0.00638559,  0.01301679],
-                             [-0.83140486,  0.39370209, -0.26395324],
-                             [-0.66518241, -0.84461308,  0.20759389],
-                             [0.45554739,   0.54289633,  0.81170881],
-                             [0.66091919,  -0.16799635, -0.91037834]]],
+coordinates = torch.tensor([[[0.03192167, 0.00638559, 0.01301679],
+                             [-0.83140486, 0.39370209, -0.26395324],
+                             [-0.66518241, -0.84461308, 0.20759389],
+                             [0.45554739, 0.54289633, 0.81170881],
+                             [0.66091919, -0.16799635, -0.91037834]]],
                            requires_grad=True, device=device)
 species = model.species_to_tensor('CHHHH').to(device).unsqueeze(0)
 

examples/load_from_neurochem.py

@@ -64,11 +64,11 @@ print(calculator1)
 
 ###############################################################################
 # Now let's define a methane molecule
-coordinates = torch.tensor([[[0.03192167,  0.00638559,  0.01301679],
-                             [-0.83140486,  0.39370209, -0.26395324],
-                             [-0.66518241, -0.84461308,  0.20759389],
-                             [0.45554739,   0.54289633,  0.81170881],
-                             [0.66091919,  -0.16799635, -0.91037834]]],
+coordinates = torch.tensor([[[0.03192167, 0.00638559, 0.01301679],
+                             [-0.83140486, 0.39370209, -0.26395324],
+                             [-0.66518241, -0.84461308, 0.20759389],
+                             [0.45554739, 0.54289633, 0.81170881],
+                             [0.66091919, -0.16799635, -0.91037834]]],
                            requires_grad=True)
 species = consts.species_to_tensor('CHHHH').unsqueeze(0)
 methane = ase.Atoms('CHHHH', positions=coordinates.squeeze().detach().numpy())

examples/nnp_training.py

@@ -148,7 +148,9 @@ container = torchani.ignite.Container({'energies': model})
 optimizer = torch.optim.Adam(model.parameters())
 trainer = ignite.engine.create_supervised_trainer(
     container, optimizer, torchani.ignite.MSELoss('energies'))
-evaluator = ignite.engine.create_supervised_evaluator(container, metrics={
+evaluator = ignite.engine.create_supervised_evaluator(
+    container,
+    metrics={
         'RMSE': torchani.ignite.RMSEMetric('energies')
     })
 

setup.cfg

@@ -2,4 +2,13 @@
 verbosity=3
 detailed-errors=1
 with-coverage=1
-cover-package=torchani
+cover-package=torchani
\ No newline at end of file
+
+[flake8]
+ignore = E501
+exclude =
+    .git,
+    __pycache__,
+    build,
+    .eggs,
+    docs/examples

tests/test_aev.py

@@ -74,7 +74,7 @@ class TestAEV(unittest.TestCase):
         for expected_radial, expected_angular in radial_angular:
             conformations = expected_radial.shape[0]
             atoms = expected_radial.shape[1]
-            aev_ = aev[start:start+conformations, 0:atoms]
+            aev_ = aev[start:(start + conformations), 0:atoms]
             start += conformations
             self._assertAEVEqual(expected_radial, expected_angular, aev_)
 

tests/test_data.py

@@ -21,7 +21,7 @@ class TestData(unittest.TestCase):
                                                   batch_size)
 
     def _assertTensorEqual(self, t1, t2):
-        self.assertEqual((t1-t2).abs().max().item(), 0)
+        self.assertEqual((t1 - t2).abs().max().item(), 0)
 
     def testSplitBatch(self):
         species1 = torch.randint(4, (5, 4), dtype=torch.long)
@@ -45,8 +45,8 @@ class TestData(unittest.TestCase):
                 self.assertNotEqual(last[-1], n[0])
             conformations = s.shape[0]
             self.assertGreater(conformations, 0)
-            s_ = species[start:start+conformations, ...]
-            c_ = coordinates[start:start+conformations, ...]
+            s_ = species[start:(start + conformations), ...]
+            c_ = coordinates[start:(start + conformations), ...]
             s_, c_ = torchani.utils.strip_redundant_padding(s_, c_)
             self._assertTensorEqual(s, s_)
             self._assertTensorEqual(c, c_)

torchani/aev.py

@@ -77,8 +77,7 @@ def _angular_subaev_terms(Rca, ShfZ, EtaA, Zeta, ShfA, vectors1, vectors2):
     fcj1 = _cutoff_cosine(distances1, Rca)
     fcj2 = _cutoff_cosine(distances2, Rca)
     factor1 = ((1 + torch.cos(angles - ShfZ)) / 2) ** Zeta
-    factor2 = torch.exp(-EtaA *
-                        ((distances1 + distances2) / 2 - ShfA) ** 2)
+    factor2 = torch.exp(-EtaA * ((distances1 + distances2) / 2 - ShfA) ** 2)
     ret = 2 * factor1 * factor2 * fcj1 * fcj2
     # At this point, ret now have shape
     # (conformations, atoms, N, ?, ?, ?, ?) where ? depend on constants.
@@ -157,9 +156,7 @@ def default_neighborlist(species, coordinates, cutoff):
 def _compute_mask_r(species_r, num_species):
     # type: (Tensor, int) -> Tensor
     """Get mask of radial terms for each supported species from indices"""
-    mask_r = (species_r.unsqueeze(-1) ==
-              torch.arange(num_species, dtype=torch.long,
-                           device=species_r.device))
+    mask_r = (species_r.unsqueeze(-1) == torch.arange(num_species, dtype=torch.long, device=species_r.device))
     return mask_r
 
 
@@ -199,10 +196,7 @@ def _assemble(radial_terms, angular_terms, present_species,
     atoms = radial_terms.shape[1]
 
     # assemble radial subaev
-    present_radial_aevs = (
-        radial_terms.unsqueeze(-2) *
-        mask_r.unsqueeze(-1).to(radial_terms.dtype)
-    ).sum(-3)
+    present_radial_aevs = (radial_terms.unsqueeze(-2) * mask_r.unsqueeze(-1).to(radial_terms.dtype)).sum(-3)
     # present_radial_aevs has shape
     # (conformations, atoms, present species, radial_length)
     radial_aevs = present_radial_aevs.flatten(start_dim=2)

torchani/data/__init__.py

@@ -53,7 +53,7 @@ def split_batch(natoms, species, coordinates):
         improved = False
         cycle_split = split
         cycle_cost = cost
-        for i in range(len(counts)-1):
+        for i in range(len(counts) - 1):
             if i not in split:
                 s = sorted(split + [i])
                 c = split_cost(counts, s)

torchani/data/_pyanitools.py

@@ -42,7 +42,7 @@ class anidataloader:
 
     def __init__(self, store_file):
         if not os.path.exists(store_file):
-            exit('Error: file not found - '+store_file)
+            exit('Error: file not found - ' + store_file)
         self.store = h5py.File(store_file, 'r')
 
     ''' Group recursive iterator (iterate through all groups

torchani/nn.py

@@ -61,4 +61,4 @@ class Ensemble(torch.nn.ModuleList):
 class Gaussian(torch.nn.Module):
     """Gaussian activation"""
     def forward(self, x):
-        return torch.exp(-x*x)
+        return torch.exp(- x * x)