:mod:`sourced.ml.core.algorithms`
=================================

.. py:module:: sourced.ml.core.algorithms


Subpackages
-----------
.. toctree::
   :titlesonly:
   :maxdepth: 3

   id_splitter/index.rst
   



Submodules
----------
.. toctree::
   :titlesonly:
   :maxdepth: 1

   id_embedding/index.rst
   
   swivel/index.rst
   
   tf_idf/index.rst
   
   token_parser/index.rst
   
   uast_id_distance/index.rst
   
   uast_ids_to_bag/index.rst
   
   uast_inttypes_to_graphlets/index.rst
   
   uast_inttypes_to_nodes/index.rst
   
   uast_struct_to_bag/index.rst
   
   uast_to_bag/index.rst
   
   uast_to_id_sequence/index.rst
   
   uast_to_role_id_pairs/index.rst
   




Package Contents
----------------






.. function:: log_tf_log_idf(tf, df, ndocs)

   









.. py:class:: UastIds2Bag(token2index=None, token_parser=None)

   Bases::class:`sourced.ml.core.algorithms.uast_ids_to_bag.UastTokens2Bag`

   

   Converts a UAST to a bag-of-identifiers.


   

   

   .. attribute:: XPATH
      :annotation: = //*[@roleIdentifier] 

      



   

   

   









.. function:: uast2sequence(root)

   









.. py:class:: UastRandomWalk2Bag(p_explore_neighborhood=0.79, q_leave_neighborhood=0.82, n_walks=2, n_steps=10, stride=1, seq_len=(2, 3), seed=42)

   Bases::class:`sourced.ml.core.algorithms.uast_struct_to_bag.Uast2StructBagBase`

   

   

   









.. py:class:: UastSeq2Bag(stride=1, seq_len=(3, 4), node2index=None)

   Bases::class:`sourced.ml.core.algorithms.uast_struct_to_bag.Uast2StructBagBase`

   

   DFS traversal + preserves the order of node children.


   

   

   









.. py:class:: Uast2QuantizedChildren(npartitions: int = 20)

   Bases::class:`sourced.ml.core.algorithms.uast_to_bag.Uast2BagThroughSingleScan`

   

   Converts a UAST to a bag of children counts.


   

   

   

   .. method:: node2key(self, node: bblfsh.Node)

      
      Return the key for a given Node.

      :param node: a node in UAST.
      :return: The string which consists of the internal type of the node and its number of
          children.

      



   

   .. method:: quantize(self, frequencies: Iterable[Tuple[str, Iterable[Tuple[int, int]]]])

      



   

   .. method:: quantize_unwrapped(self, children_freq: Iterable[Tuple[int, int]])

      
      Builds the quantization partition P that is a vector of length nb_partitions
      whose entries are in strictly ascending order.
      Quantization of x is defined as:

          0 if x <= P[0]
          m if P[m-1] < x <= P[m]
          n if P[n] <= x

      :param children_freq: distribution of the number of children.
      :return: The array with quantization levels.

      











.. py:class:: Uast2GraphletBag

   Bases::class:`sourced.ml.core.algorithms.uast_ids_to_bag.Uast2BagBase`

   

   Converts a UAST to a bag of graphlets.
   The graphlet of a UAST node is composed from the node itself, its parent and its children.
   Each node is represented by the internal role string.


   

   

   

   .. method:: uast2graphlets(self, uast)

      
      :param uast: The UAST root node.
      :generate: The nodes which compose the UAST.
          :class: 'Node' is used to access the nodes of the graphlets.

      



   

   .. method:: node2key(self, node)

      
      Builds the string joining internal types of all the nodes
      in the node's graphlet in the following order:
      parent_node_child1_child2_child3. The children are sorted by alphabetic order.
      str format is required for BagsExtractor.

      :param node: a node of UAST
      :return: The string key of node

      



   









.. py:class:: Uast2RoleIdPairs(token2index=None, token_parser=None)

   Bases::class:`sourced.ml.core.algorithms.uast_ids_to_bag.UastIds2Bag`

   

   Converts a UAST to a list of pairs. Pair is identifier and role, where role is Node role
   where identifier was found.

   __call__ is overridden here and returns list instead of bag-of-words (dist).


   

   

   

   

   

   .. staticmethod:: merge_roles(roles: Iterable[int])

      











.. py:class:: Uast2IdLineDistance

   Bases::class:`sourced.ml.core.algorithms.uast_id_distance.Uast2IdDistance`

   

   Converts a UAST to a list of identifiers pair and code line distance between where applicable.

   __call__ is overridden here and return list instead of bag-of-words (dist).


   

   

   

   .. method:: distance(self, point1, point2)

      











.. py:class:: Uast2IdTreeDistance

   Bases::class:`sourced.ml.core.algorithms.uast_id_distance.Uast2IdDistance`

   

   Converts a UAST to a list of identifiers pair and UAST tree distance between.

   __call__ is overridden here and return list instead of bag-of-words (dist).


   

   

   

   .. method:: distance(self, point1, point2)

      



   

   .. staticmethod:: calc_tree_distance(last_common_level, level1, level2)

      











.. py:class:: Uast2IdSequence

   Bases::class:`sourced.ml.core.algorithms.uast_id_distance.Uast2IdLineDistance`

   

   Converts a UAST to a sorted sequence of identifiers.
   Identifiers are sorted by position in code.
   We do not change the order if positions are not present.

   __call__ is overridden here and return list instead of bag-of-words (dist).


   

   

   

   .. staticmethod:: concat(id_sequence: Iterable)