Unverified Commit c9f0da15 authored by Daiki Nishikawa's avatar Daiki Nishikawa Committed by GitHub
Browse files

Merge pull request #2284 from nd-02110114/update-api-docs-1 

Update API documents for splitter and transformer
parents ec4dd49a 536d0212

deepchem/splits/splitters.py

+20 −20
Original line number Diff line number Diff line
@@ -398,15 +398,15 @@ class RandomGroupSplitter(Splitter): 
      An array indicating the group of each item.

      The length is equals to `len(dataset.X)`



    Notes

    -----

    Note

    ----

    The examples of groups is the following.



    groups    : 3 2 2 0 1 1 2 4 3

    dataset.X : 0 1 2 3 4 5 6 7 8

    | groups    : 3 2 2 0 1 1 2 4 3

    | dataset.X : 0 1 2 3 4 5 6 7 8



    groups    : a b b e q x a a r

    dataset.X : 0 1 2 3 4 5 6 7 8

    | groups    : a b b e q x a a r

    | dataset.X : 0 1 2 3 4 5 6 7 8

    """

    self.groups = groups
@@ -488,8 +488,8 @@ class RandomStratifiedSplitter(Splitter): 
  sparse multitask datasets it usually manages to produces a fairly accurate

  division of the actives for each task.



  Notes

  -----

  Note

  ----

  This splitter is primarily designed for boolean labeled data. It considers

  only whether a label is zero or non-zero. When labels can take on multiple

  non-zero values, it does not try to give each split a proportional fraction
@@ -873,8 +873,8 @@ class MolecularWeightSplitter(Splitter): 
  """

  Class for doing data splits by molecular weight.



  Notes

  -----

  Note

  ----

  This class requires RDKit to be installed.

  """
@@ -946,8 +946,8 @@ class MaxMinSplitter(Splitter): 
  Furthermore, the validation set is comprised of diverse compounds under

  the test set.



  Notes

  -----

  Note

  ----

  This class requires RDKit to be installed.

  """
@@ -1044,8 +1044,8 @@ class ButinaSplitter(Splitter): 
  """Class for doing data splits based on the butina clustering of a bulk tanimoto

  fingerprint matrix.



  Notes

  -----

  Note

  ----

  This class requires RDKit to be installed.

  """
@@ -1166,8 +1166,8 @@ def _generate_scaffold(smiles: str, include_chirality: bool = False) -> str: 
  .. [1] Bemis, Guy W., and Mark A. Murcko. "The properties of known drugs.

     1. Molecular frameworks." Journal of medicinal chemistry 39.15 (1996): 2887-2893.



  Notes

  -----

  Note

  ----

  This function requires RDKit to be installed.

  """

  try:
@@ -1184,8 +1184,8 @@ def _generate_scaffold(smiles: str, include_chirality: bool = False) -> str: 
class ScaffoldSplitter(Splitter):

  """Class for doing data splits based on the scaffold of small molecules.



  Notes

  -----

  Note

  ----

  This class requires RDKit to be installed.

  """
@@ -1285,8 +1285,8 @@ class FingerprintSplitter(Splitter): 
  """Class for doing data splits based on the fingerprints of small

  molecules O(N**2) algorithm.



  Notes

  -----

  Note

  ----

  This class requires RDKit to be installed.

  """

deepchem/trans/transformers.py

+250 −129

File changed.

Preview size limit exceeded, changes collapsed.

docs/source/api_reference/splitters.rst

+65 −30
Original line number Diff line number Diff line
@@ -15,78 +15,113 @@ learning models more rigorously than standard deep models since we're 
looking for the ability to generalize to new domains. Some of the

implemented splitters here may help.



Splitter

--------

The :code:`dc.splits.Splitter` class is the abstract parent class for

all splitters. This class should never be directly instantiated.

.. contents:: Contents

    :local:



.. autoclass:: deepchem.splits.Splitter

  :members:

General Splitters

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



RandomSplitter

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

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



.. autoclass:: deepchem.splits.RandomSplitter

  :members:

  :inherited-members:

  :exclude-members: __init__





RandomGroupSplitter

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



.. autoclass:: deepchem.splits.RandomGroupSplitter

  :members:

  :inherited-members:



RandomStratifiedSplitter

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



.. autoclass:: deepchem.splits.RandomStratifiedSplitter

  :members:

  :inherited-members:

  :exclude-members: __init__



SingletaskStratifiedSplitter

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



.. autoclass:: deepchem.splits.SingletaskStratifiedSplitter

  :members:

  :inherited-members:



IndexSplitter

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

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



.. autoclass:: deepchem.splits.IndexSplitter

  :members:

  :inherited-members:

  :exclude-members: __init__



SpecifiedSplitter

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

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



.. autoclass:: deepchem.splits.SpecifiedSplitter

  :members:

  :inherited-members:



TaskSplitter

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



RandomGroupSplitter

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



.. autoclass:: deepchem.splits.RandomGroupSplitter

.. autoclass:: deepchem.splits.TaskSplitter

  :members:

  :inherited-members:



RandomStratifiedSplitter

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



.. autoclass:: deepchem.splits.RandomStratifiedSplitter

  :members:

Molecule Splitters

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



SingletaskStratifiedSplitter

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

ScaffoldSplitter

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



.. autoclass:: deepchem.splits.SingletaskStratifiedSplitter

.. autoclass:: deepchem.splits.ScaffoldSplitter

  :members:

  :inherited-members:

  :exclude-members: __init__



MolecularWeightSplitter

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

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



.. autoclass:: deepchem.splits.MolecularWeightSplitter

  :members:

  :inherited-members:

  :exclude-members: __init__



MaxMinSplitter

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

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



.. autoclass:: deepchem.splits.MaxMinSplitter

  :members:

  :inherited-members:

  :exclude-members: __init__



ButinaSplitter

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

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



.. autoclass:: deepchem.splits.ButinaSplitter

  :members:

  :inherited-members:



ScaffoldSplitter

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

FingerprintSplitter

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



.. autoclass:: deepchem.splits.ScaffoldSplitter

.. autoclass:: deepchem.splits.FingerprintSplitter

  :members:

  :inherited-members:

  :exclude-members: __init__



FingeprintSplitter

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

Base Splitter (for develop)

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



.. autoclass:: deepchem.splits.FingerprintSplitter

  :members:

The :code:`dc.splits.Splitter` class is the abstract parent class for

all splitters. This class should never be directly instantiated.



.. autoclass:: deepchem.splits.Splitter

  :members:

docs/source/api_reference/transformers.rst

+59 −41
Original line number Diff line number Diff line
@@ -8,101 +8,119 @@ distribution. Real data of course is wild and hard to control. What do 
you do if you have a crazy dataset and need to bring its statistics to

heel? Fear not for you have :code:`Transformer` objects.



Transformer

-----------

The :code:`dc.trans.Transformer` class is the abstract parent class

for all transformers. This class should never be directly initialized,

but contains a number of useful method implementations.

.. contents:: Contents

    :local:



.. autoclass:: deepchem.trans.Transformer

  :members:

General Transformers

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



MinMaxTransformer

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

NormalizationTransformer

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



.. autoclass:: deepchem.trans.MinMaxTransformer

.. autoclass:: deepchem.trans.NormalizationTransformer

  :members:

  :inherited-members:



NormalizationTransformer

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

MinMaxTransformer

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



.. autoclass:: deepchem.trans.NormalizationTransformer

.. autoclass:: deepchem.trans.MinMaxTransformer

  :members:

  :inherited-members:



ClippingTransformer

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

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



.. autoclass:: deepchem.trans.ClippingTransformer

  :members:

  :inherited-members:



LogTransformer

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

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



.. autoclass:: deepchem.trans.LogTransformer

  :members:

  :inherited-members:



CDFTransformer

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



.. autoclass:: deepchem.trans.CDFTransformer

  :members:

  :inherited-members:



PowerTransformer

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



.. autoclass:: deepchem.trans.PowerTransformer

  :members:

  :inherited-members:



BalancingTransformer

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

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



.. autoclass:: deepchem.trans.BalancingTransformer

  :members:

  :inherited-members:



DuplicateBalancingTransformer

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

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



.. autoclass:: deepchem.trans.DuplicateBalancingTransformer

  :members:

  :inherited-members:



CDFTransformer

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

ImageTransformer

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



.. autoclass:: deepchem.trans.CDFTransformer

.. autoclass:: deepchem.trans.ImageTransformer

  :members:

  :inherited-members:



PowerTransformer

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

FeaturizationTransformer

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



.. autoclass:: deepchem.trans.PowerTransformer

.. autoclass:: deepchem.trans.FeaturizationTransformer

  :members:

  :inherited-members:



Specified Usecase Transformers

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



CoulombFitTransformer

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

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



.. autoclass:: deepchem.trans.CoulombFitTransformer

  :members:

  :inherited-members:



IRVTransformer

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

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



.. autoclass:: deepchem.trans.IRVTransformer

  :members:

  :inherited-members:



DAGTransformer

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

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



.. autoclass:: deepchem.trans.DAGTransformer

  :members:



ImageTransformer

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



.. autoclass:: deepchem.trans.ImageTransformer

  :members:

  :inherited-members:



ANITransformer

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

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



.. autoclass:: deepchem.trans.ANITransformer

  :members:

  :inherited-members:



FeaturizationTransformer

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

Base Transformer (for develop)

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



.. autoclass:: deepchem.trans.FeaturizationTransformer

  :members:



DataTransforms

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

The :code:`dc.trans.Transformer` class is the abstract parent class

for all transformers. This class should never be directly initialized,

but contains a number of useful method implementations.



.. autoclass:: deepchem.trans.DataTransforms

.. autoclass:: deepchem.trans.Transformer

  :members:

CRA Git | Maintained and supported by SUSTech CRA and CCSE