nltk.misc.minimalset.MinimalSet

class documentation

class MinimalSet(object): (source)

Constructor: MinimalSet(parameters)

Find contexts where more than one possible target value can appear. E.g. if targets are word-initial letters, and contexts are the remainders of words, then we would like to find cases like "fat" vs "cat", and "training" vs "draining". If targets are parts-of-speech and contexts are words, then we would like to find cases like wind (noun) 'air in rapid motion', vs wind (verb) 'coil, wrap'.

Method	`__init__`	Create a new minimal set.
Method	`add`	Add a new item to the minimal set, having the specified context, target, and display form.
Method	`contexts`	Determine which contexts occurred with enough distinct targets.
Method	`display`	Undocumented
Method	`display_all`	Undocumented
Method	`targets`	Undocumented
Instance Variable	`_contexts`	Undocumented
Instance Variable	`_displays`	Undocumented
Instance Variable	`_seen`	Undocumented
Instance Variable	`_targets`	Undocumented

def __init__(self, parameters=None): (source) ¶

Create a new minimal set.

Parameters
parameters:list(tuple(str, str, str))	The (context, target, display) tuples for the item

def add(self, context, target, display): (source) ¶

Add a new item to the minimal set, having the specified context, target, and display form.

Parameters
context:str	The context in which the item of interest appears
target:str	The item of interest
display:str	The information to be reported for each item

def contexts(self, minimum=2): (source) ¶

Determine which contexts occurred with enough distinct targets.

:rtype list

Parameters
minimum:int	the minimum number of distinct target forms

def display(self, context, target, default=''): (source) ¶

Undocumented

def display_all(self, context): (source) ¶

Undocumented

def targets(self): (source) ¶

Undocumented

_contexts = (source) ¶

Undocumented

_displays: dict = (source) ¶

Undocumented

_seen = (source) ¶

Undocumented

_targets = (source) ¶

Undocumented