Merge branch 'master' into update-dependecies

[![Anaconda-Server Badge](https://anaconda.org/conda-forge/deepchem/badges/version.svg)](https://anaconda.org/conda-forge/deepchem)

[![PyPI version](https://badge.fury.io/py/deepchem.svg)](https://badge.fury.io/py/deepchem)

[Website](https://deepchem.io/) | [Documentation (master)](https://deepchem.readthedocs.io/en/latest/)) | [Colab Tutorial](https://github.com/deepchem/deepchem/tree/master/examples/tutorials) | [Discussion Forum](https://forum.deepchem.io/) | [Gitter](https://gitter.im/deepchem/Lobby)

[Website](https://deepchem.io/) | [Documentation (master)](https://deepchem.readthedocs.io/en/latest/) | [Colab Tutorial](https://github.com/deepchem/deepchem/tree/master/examples/tutorials) | [Discussion Forum](https://forum.deepchem.io/) | [Gitter](https://gitter.im/deepchem/Lobby)

DeepChem aims to provide a high quality open-source toolchain

that democratizes the use of deep-learning in drug discovery,

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

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

- [XGBoost](https://xgboost.readthedocs.io/en/latest/)

- [Weights & Biases](https://docs.wandb.com/)

- [Tensorflow Probability](https://www.tensorflow.org/probability)

## Installation

    Returns

    -------

    If `X_stats == True`, returns `(X_means, X_stds)`. If `y_stats ==

    True`, returns `(y_means, y_stds)`. If both are true, returns

    If `X_stats == True`, returns `(X_means, X_stds)`. If `y_stats == True`,

    returns `(y_means, y_stds)`. If both are true, returns

    `(X_means, X_stds, y_means, y_stds)`.

    """

    X_means = 0.0

    `math.ceil(len(dataset)/batch_size)`. Each minibatch is returned as

    a tuple of four numpy arrays: `(X, y, w, ids)`.

    Parameters:

    -----------

    Parameters

    ----------

    batch_size: int

      Number of elements in a batch. If None, then it yields batches

      with size equal to the size of each individual shard.

    return np.array(

        load_from_disk(os.path.join(self.data_dir, row['ids'])), dtype=object)

  def get_shard_y(self, i):

    """Retrieves the labels for the i-th shard from disk.

    Parameters

    ----------

    i: int

      Shard index for shard to retrieve labels from

    """

    if self._cached_shards is not None and self._cached_shards[i] is not None:

      return self._cached_shards[i].y

    row = self.metadata_df.iloc[i]

    return np.array(

        load_from_disk(os.path.join(self.data_dir, row['y'])), dtype=object)

  def get_shard_w(self, i):

    """Retrieves the weights for the i-th shard from disk.

    Parameters

    ----------

    i: int

      Shard index for shard to retrieve weights from

    """

    if self._cached_shards is not None and self._cached_shards[i] is not None:

      return self._cached_shards[i].w

    row = self.metadata_df.iloc[i]

    return np.array(

        load_from_disk(os.path.join(self.data_dir, row['w'])), dtype=object)

  def add_shard(self, X, y, w, ids):

    """Adds a data shard."""

    metadata_rows = self.metadata_df.values.tolist()

  @property

  def y(self):

    """Get the y vector for this dataset as a single numpy array."""

    if len(self) == 0:

      return np.array([])

    ys = []

    one_dimensional = False

    for (_, y_b, _, _) in self.itershards():

    for i in range(self.get_number_shards()):

      y_b = self.get_shard_y(i)

      ys.append(y_b)

      if len(y_b.shape) == 1:

        one_dimensional = True

    """Get the weight vector for this dataset as a single numpy array."""

    ws = []

    one_dimensional = False

    for (_, _, w_b, _) in self.itershards():

      ws.append(np.array(w_b))

    for i in range(self.get_number_shards()):

      w_b = self.get_shard_w(i)

      ws.append(w_b)

      if len(w_b.shape) == 1:

        one_dimensional = True

    if not one_dimensional:

import numpy as np

import deepchem as dc

def test_y_property():

  """Test that dataset.y works."""

  num_datapoints = 10

  num_features = 10

  num_tasks = 1

  X = np.random.rand(num_datapoints, num_features)

  y = np.random.randint(2, size=(num_datapoints, num_tasks))

  w = np.ones((num_datapoints, num_tasks))

  ids = np.array(["id"] * num_datapoints)

  dataset = dc.data.DiskDataset.from_numpy(X, y, w, ids)

  y_out = dataset.y

  np.testing.assert_array_equal(y, y_out)

def test_w_property():

  """Test that dataset.y works."""

  num_datapoints = 10

  num_features = 10

  num_tasks = 1

  X = np.random.rand(num_datapoints, num_features)

  y = np.random.randint(2, size=(num_datapoints, num_tasks))

  w = np.ones((num_datapoints, num_tasks))

  ids = np.array(["id"] * num_datapoints)

  dataset = dc.data.DiskDataset.from_numpy(X, y, w, ids)

  w_out = dataset.w

  np.testing.assert_array_equal(w, w_out)

def extract_active_site(protein_file, ligand_file, cutoff=4):

  """Extracts a box for the active site.

  Params

  ------

  Parameters

  ----------

  protein_file: str

    Location of protein PDB

  ligand_file: str

    face of the hull is converted into a coordinate box used for

    binding.

    Params

    ------

    Parameters

    ----------

    macromolecule_file: str

      Location of the macromolecule file to load

  def __init__(self, sixty_four_bits=True, pocket_finder=None):

    """Initializes Vina Pose Generator

    Params

    ------

    Parameters

    ----------

    sixty_four_bits: bool, optional (default True)

      Specifies whether this is a 64-bit machine. Needed to download

      the correct executable.