fcapy.mvcontext.MVContext

class fcapy.mvcontext.MVContext(data=None, pattern_types=None, object_names=None, attribute_names=None, **kwargs)

A class used to represent Many Valued Context object from FCA theory.

__init__(data=None, pattern_types=None, object_names=None, attribute_names=None, **kwargs)

Initialize the MVContext

Parameters

• data (list of list of PatternStructure intents) – The data for MVContext to work with

• pattern_types (dict of type {name of an attribute: Pattern Structure type}) – The types of PatternStructure to describe each “column” of the data

• object_names (list of str) – The names of objects (default values are [‘0’,’1’,’2’,…]

• attribute_names (list of str) – The names of attributes, i.e. pattern structures (default values are [‘0’, ‘1’, ‘2’, …])

• kwargs –

  description: str

  A human readable description of the context

  target: list of float

  A target values to use in Supervised ML scenario

Methods

__init__([data, pattern_types, …])	Initialize the MVContext
assemble_pattern_structures(data, pattern_types)	Return pattern_structures based on data and the pattern_types
extension(descriptions[, base_objects])	Return a subset of objects of base_objects_i which falls into descriptions
extension_i(descriptions_i[, base_objects_i])	Return a subset of objects of base_objects_i which falls into descriptions_i
from_pandas(dataframe)	Create MVContext from Pandas dataframe
generators_by_intent_difference(new_intent, …)	Return the set of generators to select the new_intent from old_intent
get_minimal_generators(intent[, …])	Get a set of minimal generators for closed intent intent
hash_fixed()	Hash value of FormalContext which do not differ between sessions
intention(objects)	Return a common description of objects from objects.
intention_i(object_indexes)	Return a common description of objects from object_indexes.
leq_descriptions(a, b)	Check If description a is ‘smaller’ (more general) then description b
read_csv([path])	Convert the MVContext into csv file format (save if path is given)
read_json([path, json_data, pattern_types])	Read MVContext from .json file .json formatted string data
to_numeric()	Return MVContext data in the form of numeric columns and their names
to_pandas()	Convert the FormalContext into pandas.DataFrame object
write_json([path])	Convert the FormalContext into json file format (save if path is given)

Attributes

attribute_names	The names of attributes (i.e.
data	The data for MVContext to work with.
description	Get or set the human readable description of the context
n_attributes	Get the number of pattern structures (attributes) in the context (i.e.
n_objects	Get the number of objects in the context (i.e.
object_names	The names of objects in the context
pattern_structures	A list of pattern structures kept in a context
pattern_types	A dictionary to map the names of attributes (pattern structures) and their types
target	A list of target values for Supervised ML scenarios

assemble_pattern_structures(data, pattern_types)

Return pattern_structures based on data and the pattern_types

property attribute_names

The names of attributes (i.e. pattern structures) in the context

property data

The data for MVContext to work with. List of datas of Pattern Structures of the context

property description

Get or set the human readable description of the context

JSON is the only file format to store this information. The description will be lost when saving context to .cxt or .csv

Parameters

value (str, None) – The human readable description of the context

Raises

AssertionError – If the given value is not None and not of type str

extension(descriptions, base_objects=None)

Return a subset of objects of base_objects_i which falls into descriptions

Parameters

• descriptions (dict of type {pattern_structure_name: description}) – Descriptions to filter objects

• base_objects (list of str) – Names of objects to select extension from (default value is the set of all object names)

Returns

extent_i – A list of names of objects described by descriptions_i

Return type

list of str

extension_i(descriptions_i, base_objects_i=None)

Return a subset of objects of base_objects_i which falls into descriptions_i

Parameters

• descriptions_i (dict of type {pattern_structure_index: description}) – Descriptions to filter objects

• base_objects_i (list of int) – Indexes of objects to select extension from (default value is the set of all object indexes)

Returns

extent_i – A list of indexes of objects described by descriptions_i

Return type

list of int

static from_pandas(dataframe)

Create MVContext from Pandas dataframe

WARNING: Does not implemented yet

generators_by_intent_difference(new_intent, old_intent)

Return the set of generators to select the new_intent from old_intent

get_minimal_generators(intent, base_generator=None, base_objects=None, use_indexes=False, ps_to_iterate=None, projection_to_start=1)

Get a set of minimal generators for closed intent intent

WARNING: The current algorithm looks for mimimUM generators instead of mimimAL

Parameters

• intent (dict with PatternStructure intents) – A dict of PatternStructure description to construct generators for.

• base_generator (dict with PatternStructure intents) – A dict of PatternStructure descriptions which should be included in each constructed generator

• base_objects (list of string or int) – A set of object names (or indexes if use_indexes set to True) used to check the generators

• use_indexes (bool) – A flag whether to use object and attribute names (if set to False) or indexes (otherwise)

• ps_to_iterate (list of string or int) – A list of pattern structures names (or indexes if use_indexes set to True) to construct generators on

• projection_to_start (int) – A number of PatternStructures projection to construct generators on

Returns

min_gens – A list of mimimUM generators of a closed intent

Return type

list of dict of type {pattern_structure_index/name: description}

Notes

An idea of generators for FormalContext is described in the function fcapy.context.formal_context.get_minimal_generators()

hash_fixed()

Hash value of FormalContext which do not differ between sessions

intention(objects)

Return a common description of objects from objects. Pat. structures are denoted by their names

intention_i(object_indexes)

Return a common description of objects from object_indexes. Pat. structures are denoted by their indexes

leq_descriptions(a: dict, b: dict) → bool

Check If description a is ‘smaller’ (more general) then description b

property n_attributes

Get the number of pattern structures (attributes) in the context (i.e. len(MVContext.pattern_structures))

property n_objects

Get the number of objects in the context (i.e. len(MVContext.data))

property object_names

The names of objects in the context

property pattern_structures

A list of pattern structures kept in a context

property pattern_types

A dictionary to map the names of attributes (pattern structures) and their types

read_csv(path=None, **kwargs)

Convert the MVContext into csv file format (save if path is given)

WARNING: Does not implemented yet

Parameters

• path (str or None) – Path to save a context

• **kwargs –

  sepstr

  Field delimiter for the output file

Returns

context – If path is None, the string with .csv file data is returned. If path is given - return None

Return type

str

static read_json(path: Optional[str] = None, json_data: Optional[str] = None, pattern_types: Optional[Tuple[fcapy.mvcontext.pattern_structure.AbstractPS]] = None)

Read MVContext from .json file .json formatted string data

Parameters

• path (str) – A path to .json file

• json_data (str) – A json encoded data

• pattern_types (tuple[AbstractPS]) – Tuple of additional Pattern Structures not defined in fcapy.mvcontext.pattern_structure

Returns

mvK

Return type

MVContext

property target

A list of target values for Supervised ML scenarios

to_numeric()

Return MVContext data in the form of numeric columns and their names

to_pandas()

Convert the FormalContext into pandas.DataFrame object

WARNING: Does not implemented yet

Returns

df – The dataframe with boolean variables, object_names turned into df.index, attribute_names turned into df.columns

Return type

pandas.DataFrame

write_json(path=None)

Convert the FormalContext into json file format (save if path is given)

WARNING: Does not implemented yet

Parameters

path (str or None) – Path to save a context

Returns

context – If path is None, the string with .json file data is returned. If path is given - return None

Return type

str