Expanded docstrings and added graph unittest

- [BioPython](https://biopython.org/wiki/Documentation)

- [OpenAI Gym](https://gym.openai.com/)

- [matminer](https://hackingmaterials.lbl.gov/matminer/)

- [MDTraj](http://mdtraj.org/)

- [NetworkX](https://networkx.github.io/documentation/stable/index.html)

- [OpenMM](http://openmm.org/)

- [PDBFixer](https://github.com/pandegroup/pdbfixer)

- [Pillow](https://pypi.org/project/Pillow/)

- [pyGPGO](https://pygpgo.readthedocs.io/en/latest/)

- [Pymatgen](https://pymatgen.org/)

- [PyTorch](https://pytorch.org/)

- [RDKit](http://www.rdkit.org/docs/Install.html)

- [simdna](https://github.com/kundajelab/simdna)

## Getting Started

The DeepChem project maintains an extensive colelction of [tutorials](https://github.com/deepchem/deepchem/tree/master/examples/tutorials). All tutorials are designed to be run on Google colab (or locally if you prefer). Tutorials are arranged in a suggested learning sequence which will take you from beginner to proficient at molecular machine learning and computational biology more broadly.

The DeepChem project maintains an extensive collection of [tutorials](https://github.com/deepchem/deepchem/tree/master/examples/tutorials). All tutorials are designed to be run on Google colab (or locally if you prefer). Tutorials are arranged in a suggested learning sequence which will take you from beginner to proficient at molecular machine learning and computational biology more broadly.

After working through the tutorials, you can also go through other [examples](https://github.com/deepchem/deepchem/tree/master/examples). To apply `deepchem` to a new problem, try starting from one of the existing examples or tutorials and modifying it step by step to work with your new use-case. If you have questions or comments you can raise them on our [gitter](https://gitter.im/deepchem/Lobby).

  based on elemental stoichiometry. E.g., the average electronegativity

  of atoms in a crystal structure. The chemical fingerprint is a 

  vector of these statistics. For a full list of properties and statistics,

  see ElementProperty(data_source).feature_labels().

  see ``matminer.featurizers.composition.ElementProperty(data_source).feature_labels()``.

  This featurizer requires the optional dependencies pymatgen and

  matminer. It may be useful when only crystal compositions are available

    comp : str

      Reduced formula of crystal.

    Returns

    -------

    feats: np.ndarray

      Vector of properties and statistics derived from chemical

      stoichiometry.

    """

    from pymatgen import Composition

    Parameters

    ----------

    struct : dict

      pymatgen structure dictionary

      Json-serializable dictionary representation of pymatgen.core.structure

      https://pymatgen.org/pymatgen.core.structure.html

    Returns

    -------

    features: np.ndarray

      2D sine Coulomb matrix, or 1D matrix eigenvalues. 

    """

    Parameters

    ----------

    s : pymatgen structure

    s : pymatgen.core.structure

      A periodic crystal composed of a lattice and a sequence of atomic

      sites with 3D coordinates and elements.

    Returns

    -------

    eigs: np.ndarray

      1D matrix eigenvalues. 

    sine_mat: np.ndarray

      2D sine Coulomb matrix.

    """

      eigs, _ = np.linalg.eig(sine_mat)

      zeros = np.zeros((self.max_atoms,))

      zeros[:len(eigs)] = eigs

      return zeros

      eigs = zeros

      return eigs

    else:

      sine_mat = pad_array(sine_mat, self.max_atoms)

      return sine_mat

    Parameters

    ----------

    struct : dict

      pymatgen structure dictionary.

      Json-serializable dictionary representation of pymatgen.core.structure

      https://pymatgen.org/pymatgen.core.structure.html

    Returns

    -------

    feats: tuple

      atomic numbers, nodes, and edges in networkx.classes.multidigraph.MultiDiGraph format.

    """

    Parameters

    ----------

    struct : pymatgen structure

    struct : pymatgen.core.structure

      A periodic crystal composed of a lattice and a sequence of atomic

      sites with 3D coordinates and elements.

    Returns

    -------

    feats: tuple

      atomic numbers, nodes, and edges in networkx.classes.multidigraph.MultiDiGraph format.

    """

    atom_features = np.array([site.specie.Z for site in struct], dtype='int32')

    sg = StructureGraph.with_local_env_strategy(struct, self.strategy)

    nodes = np.asarray(sg.graph.nodes)

    edges = np.asarray(sg.graph.edges)

    nodes = np.array(list(sg.graph.nodes))

    edges = np.array(list(sg.graph.edges))

    return (atom_features, nodes, edges)

    assert len(features) == 1

    assert np.isclose(features[0], 1244, atol=.5)

  def testSGF(self):

    """

    Test StructureGraphFeaturizer.

    """

    featurizer = StructureGraphFeaturizer()

    features = featurizer.featurize([self.struct_dict])

    assert len(features[0]) == 3

    assert features[0][0] == 26

    assert len(features[0][2]) == 6

.. autoclass:: deepchem.feat.NeighborListComplexAtomicCoordinates

  :members:

MaterialsFeaturizers

-------------------

Materials Featurizers are those that work with datasets of inorganic crystals.

These featurizers operate on chemical compositions (e.g. "MoS2"), or on a

lattice and 3D coordinates that specify a periodic crystal structure. They

should be applied on systems that have periodic boundary conditions. Materials

featurizers are not designed to work with molecules. 

ChemicalFingerprint

^^^^^^^^^^^^^^^^^^^

    py-xgboost \

    rdkit \

    simdna \

    pymatgen \

    pytest \

    pytest-cov \

    flaky

yes | pip install -U tensorflow tensorflow-probability

yes | pip install -U matminer tensorflow tensorflow-probability