Loading deepchem/feat/material_featurizers/lcnn_featurizer.py +46 −88 Original line number Diff line number Diff line Loading @@ -27,7 +27,6 @@ class LCNNFeaturizer(Featurizer): Examples ---------- The input format for primitive cell Template is stored in a file named [comment] Loading Loading @@ -218,7 +217,6 @@ class SiteEnvironment(object): from scipy.spatial.distance import pdist, squareform except: raise ImportError("This class requires scipy to be installed.") self.pos = pos self.sitetypes = sitetypes self.activesiteidx = [i for i, s in enumerate(self.sitetypes) if 'A' in s] Loading Loading @@ -305,29 +303,6 @@ class SiteEnvironment(object): n += 1 return G def __repr__(self): s = '<' + self.sitetypes[0] + \ '|%i active neighbors' % (len([s for s in self.sitetypes if 'A' in s]) - 1) + \ '|%i spectator neighbors' % len([s for s in self.sitetypes if 'S' in s]) + \ '|%4.2f Ang Cutoff' % self.cutoff + '| %i permutations>' % len(self.permutations) return s def __eq__(self, o): """ Local environment comparison is done by comparing represented site """ if not isinstance(o, SiteEnvironment): raise ValueError return self.sitetypes[0] == o.sitetypes[0] def __ne__(self, o): """ Local environment comparison is done by comparing represented site """ if isinstance(o, SiteEnvironment): raise ValueError return not self.__eq__(o) def GetMapping(self, env, path=None): """ Returns mapping of sites from input to this object Loading @@ -339,7 +314,8 @@ class SiteEnvironment(object): performed to make sure it is a match. NetworkX is used for portability. Parameters ---------- ----------any discussion during Thursday 8 Oct. Lect . ok env : dictionary that contains information of local environment of a site in datum. See _GetSiteEnvironments defintion in the class SiteEnvironments for what this variable should be. Loading Loading @@ -442,16 +418,6 @@ class SiteEnvironments(object): self.pbc = pbc self.cutoff = cutoff def __repr__(self): s = '<%i active sites' % (self.na) + '|%i spectator sites' % (self.ns) + '>' return s def __getitem__(self, el): """ Returns a site environment """ return self.site_envs[el] def ReadDatum(self, text, cutoff_factor=1.1): """ Load structure data and return neighbor information Loading Loading @@ -682,11 +648,3 @@ class SiteEnvironments(object): } site_envs.append(site_env) return site_envs def _chunks(length, number): """ Yield successive n-sized chunks from length. """ for i in range(0, len(length), number): yield length[i:i + number] deepchem/feat/tests/test_lcnn_featurizer.py +38 −1 Original line number Diff line number Diff line Loading @@ -46,11 +46,48 @@ structure = """-4.22779200e+00 -2.44091700e+00 0.00000000e+00 0.166670000000 0.750000000000 0.546547663253 A1 2 0.166670000000 0.250000000000 0.546547663253 A1 1 """ check1 = np.array([[0., 1., 0.], [0., 1., 0.], [0., 0., 1.], [1., 0., 0.]]) check2 = np.array([[[[0, 2, 3, 1, 1, 2, 3, 1, 0, 2, 3, 1, 0, 1, 2, 0, 0, 3, 1], [0, 3, 2, 1, 1, 3, 2, 1, 0, 3, 2, 1, 0, 1, 3, 0, 0, 2, 1], [0, 1, 2, 0, 1, 2, 0, 3, 1, 0, 3, 1, 2, 0, 3, 1, 3, 1, 2], [0, 1, 3, 0, 1, 3, 0, 2, 1, 0, 2, 1, 3, 0, 2, 1, 2, 1, 3], [0, 3, 0, 1, 0, 1, 3, 2, 1, 2, 1, 0, 2, 1, 0, 1, 3, 2, 3], [0, 2, 0, 1, 0, 1, 2, 3, 1, 3, 1, 0, 3, 1, 0, 1, 2, 3, 2]], [[1, 3, 2, 0, 0, 3, 2, 0, 1, 3, 2, 0, 1, 0, 3, 1, 1, 2, 0], [1, 2, 3, 0, 0, 2, 3, 0, 1, 2, 3, 0, 1, 0, 2, 1, 1, 3, 0], [1, 0, 3, 1, 0, 3, 1, 2, 0, 1, 2, 0, 3, 1, 2, 0, 2, 0, 3], [1, 0, 2, 1, 0, 2, 1, 3, 0, 1, 3, 0, 2, 1, 3, 0, 3, 0, 2], [1, 2, 1, 0, 1, 0, 2, 3, 0, 3, 0, 1, 3, 0, 1, 0, 2, 3, 2], [1, 3, 1, 0, 1, 0, 3, 2, 0, 2, 0, 1, 2, 0, 1, 0, 3, 2, 3]], [[2, 1, 0, 3, 3, 1, 0, 3, 2, 1, 0, 3, 2, 3, 1, 2, 2, 0, 3], [2, 0, 1, 3, 3, 0, 1, 3, 2, 0, 1, 3, 2, 3, 0, 2, 2, 1, 3], [2, 3, 1, 2, 3, 1, 2, 0, 3, 2, 0, 3, 1, 2, 0, 3, 0, 3, 1], [2, 3, 0, 2, 3, 0, 2, 1, 3, 2, 1, 3, 0, 2, 1, 3, 1, 3, 0], [2, 0, 2, 3, 2, 3, 0, 1, 3, 1, 3, 2, 1, 3, 2, 3, 0, 1, 0], [2, 1, 2, 3, 2, 3, 1, 0, 3, 0, 3, 2, 0, 3, 2, 3, 1, 0, 1]], [[3, 0, 1, 2, 2, 0, 1, 2, 3, 0, 1, 2, 3, 2, 0, 3, 3, 1, 2], [3, 1, 0, 2, 2, 1, 0, 2, 3, 1, 0, 2, 3, 2, 1, 3, 3, 0, 2], [3, 2, 0, 3, 2, 0, 3, 1, 2, 3, 1, 2, 0, 3, 1, 2, 1, 2, 0], [3, 2, 1, 3, 2, 1, 3, 0, 2, 3, 0, 2, 1, 3, 0, 2, 0, 2, 1], [3, 1, 3, 2, 3, 2, 1, 0, 2, 0, 2, 3, 0, 2, 3, 2, 1, 0, 1], [3, 0, 3, 2, 3, 2, 0, 1, 2, 1, 2, 3, 1, 2, 3, 2, 0, 1, 0]]]]) def test_LCNNFeaturizer(): featuriser = LCNNFeaturizer(np.around(6.00), template) data = featuriser._featurize(structure) assert np.all(data['X_Sites'] == check1) assert np.all(data['X_NSs'] == check2) assert data['X_Sites'].shape == (4, 3) assert data['X_NSs'].shape == (1, 4, 6, 19) if __name__ == "__main__": test_LCNNFeaturizer() Loading
deepchem/feat/material_featurizers/lcnn_featurizer.py +46 −88 Original line number Diff line number Diff line Loading @@ -27,7 +27,6 @@ class LCNNFeaturizer(Featurizer): Examples ---------- The input format for primitive cell Template is stored in a file named [comment] Loading Loading @@ -218,7 +217,6 @@ class SiteEnvironment(object): from scipy.spatial.distance import pdist, squareform except: raise ImportError("This class requires scipy to be installed.") self.pos = pos self.sitetypes = sitetypes self.activesiteidx = [i for i, s in enumerate(self.sitetypes) if 'A' in s] Loading Loading @@ -305,29 +303,6 @@ class SiteEnvironment(object): n += 1 return G def __repr__(self): s = '<' + self.sitetypes[0] + \ '|%i active neighbors' % (len([s for s in self.sitetypes if 'A' in s]) - 1) + \ '|%i spectator neighbors' % len([s for s in self.sitetypes if 'S' in s]) + \ '|%4.2f Ang Cutoff' % self.cutoff + '| %i permutations>' % len(self.permutations) return s def __eq__(self, o): """ Local environment comparison is done by comparing represented site """ if not isinstance(o, SiteEnvironment): raise ValueError return self.sitetypes[0] == o.sitetypes[0] def __ne__(self, o): """ Local environment comparison is done by comparing represented site """ if isinstance(o, SiteEnvironment): raise ValueError return not self.__eq__(o) def GetMapping(self, env, path=None): """ Returns mapping of sites from input to this object Loading @@ -339,7 +314,8 @@ class SiteEnvironment(object): performed to make sure it is a match. NetworkX is used for portability. Parameters ---------- ----------any discussion during Thursday 8 Oct. Lect . ok env : dictionary that contains information of local environment of a site in datum. See _GetSiteEnvironments defintion in the class SiteEnvironments for what this variable should be. Loading Loading @@ -442,16 +418,6 @@ class SiteEnvironments(object): self.pbc = pbc self.cutoff = cutoff def __repr__(self): s = '<%i active sites' % (self.na) + '|%i spectator sites' % (self.ns) + '>' return s def __getitem__(self, el): """ Returns a site environment """ return self.site_envs[el] def ReadDatum(self, text, cutoff_factor=1.1): """ Load structure data and return neighbor information Loading Loading @@ -682,11 +648,3 @@ class SiteEnvironments(object): } site_envs.append(site_env) return site_envs def _chunks(length, number): """ Yield successive n-sized chunks from length. """ for i in range(0, len(length), number): yield length[i:i + number]
deepchem/feat/tests/test_lcnn_featurizer.py +38 −1 Original line number Diff line number Diff line Loading @@ -46,11 +46,48 @@ structure = """-4.22779200e+00 -2.44091700e+00 0.00000000e+00 0.166670000000 0.750000000000 0.546547663253 A1 2 0.166670000000 0.250000000000 0.546547663253 A1 1 """ check1 = np.array([[0., 1., 0.], [0., 1., 0.], [0., 0., 1.], [1., 0., 0.]]) check2 = np.array([[[[0, 2, 3, 1, 1, 2, 3, 1, 0, 2, 3, 1, 0, 1, 2, 0, 0, 3, 1], [0, 3, 2, 1, 1, 3, 2, 1, 0, 3, 2, 1, 0, 1, 3, 0, 0, 2, 1], [0, 1, 2, 0, 1, 2, 0, 3, 1, 0, 3, 1, 2, 0, 3, 1, 3, 1, 2], [0, 1, 3, 0, 1, 3, 0, 2, 1, 0, 2, 1, 3, 0, 2, 1, 2, 1, 3], [0, 3, 0, 1, 0, 1, 3, 2, 1, 2, 1, 0, 2, 1, 0, 1, 3, 2, 3], [0, 2, 0, 1, 0, 1, 2, 3, 1, 3, 1, 0, 3, 1, 0, 1, 2, 3, 2]], [[1, 3, 2, 0, 0, 3, 2, 0, 1, 3, 2, 0, 1, 0, 3, 1, 1, 2, 0], [1, 2, 3, 0, 0, 2, 3, 0, 1, 2, 3, 0, 1, 0, 2, 1, 1, 3, 0], [1, 0, 3, 1, 0, 3, 1, 2, 0, 1, 2, 0, 3, 1, 2, 0, 2, 0, 3], [1, 0, 2, 1, 0, 2, 1, 3, 0, 1, 3, 0, 2, 1, 3, 0, 3, 0, 2], [1, 2, 1, 0, 1, 0, 2, 3, 0, 3, 0, 1, 3, 0, 1, 0, 2, 3, 2], [1, 3, 1, 0, 1, 0, 3, 2, 0, 2, 0, 1, 2, 0, 1, 0, 3, 2, 3]], [[2, 1, 0, 3, 3, 1, 0, 3, 2, 1, 0, 3, 2, 3, 1, 2, 2, 0, 3], [2, 0, 1, 3, 3, 0, 1, 3, 2, 0, 1, 3, 2, 3, 0, 2, 2, 1, 3], [2, 3, 1, 2, 3, 1, 2, 0, 3, 2, 0, 3, 1, 2, 0, 3, 0, 3, 1], [2, 3, 0, 2, 3, 0, 2, 1, 3, 2, 1, 3, 0, 2, 1, 3, 1, 3, 0], [2, 0, 2, 3, 2, 3, 0, 1, 3, 1, 3, 2, 1, 3, 2, 3, 0, 1, 0], [2, 1, 2, 3, 2, 3, 1, 0, 3, 0, 3, 2, 0, 3, 2, 3, 1, 0, 1]], [[3, 0, 1, 2, 2, 0, 1, 2, 3, 0, 1, 2, 3, 2, 0, 3, 3, 1, 2], [3, 1, 0, 2, 2, 1, 0, 2, 3, 1, 0, 2, 3, 2, 1, 3, 3, 0, 2], [3, 2, 0, 3, 2, 0, 3, 1, 2, 3, 1, 2, 0, 3, 1, 2, 1, 2, 0], [3, 2, 1, 3, 2, 1, 3, 0, 2, 3, 0, 2, 1, 3, 0, 2, 0, 2, 1], [3, 1, 3, 2, 3, 2, 1, 0, 2, 0, 2, 3, 0, 2, 3, 2, 1, 0, 1], [3, 0, 3, 2, 3, 2, 0, 1, 2, 1, 2, 3, 1, 2, 3, 2, 0, 1, 0]]]]) def test_LCNNFeaturizer(): featuriser = LCNNFeaturizer(np.around(6.00), template) data = featuriser._featurize(structure) assert np.all(data['X_Sites'] == check1) assert np.all(data['X_NSs'] == check2) assert data['X_Sites'].shape == (4, 3) assert data['X_NSs'].shape == (1, 4, 6, 19) if __name__ == "__main__": test_LCNNFeaturizer()
