o
    rZhP                     @   s   d dl Z d dlmZ d dlmZ d dlmZ d dlm	Z	 dd ZG dd	 d	Z
d
d Z	d&ddZe dZd'ddZdd Z	d(ddZdd Ze de jZe dZdd Zg d dfd!d"Zd#d$ Zed%kroe  dS dS ))    N)accuracy)map_tag)	str2tuple)Treec                 C   sB   g }g }|D ]}|  | }|t|7 }|t|7 }qt||S )a|  
    Score the accuracy of the chunker against the gold standard.
    Strip the chunk information from the gold standard and rechunk it using
    the chunker, then compute the accuracy score.

    :type chunker: ChunkParserI
    :param chunker: The chunker being evaluated.
    :type gold: tree
    :param gold: The chunk structures to score the chunker on.
    :rtype: float
    )parseflattentree2conlltags	_accuracy)ZchunkerZgoldZ	gold_tagsZ	test_tagsZ	gold_treeZ	test_tree r
   >/var/www/auris/lib/python3.10/site-packages/nltk/chunk/util.pyr      s   
r   c                   @   s   e Zd ZdZdd Zdd Zdd Zdd	 Zd
d Zdd Z	d ddZ
dd Zdd Zdd Zdd Zdd Zdd Zdd ZdS )!
ChunkScorea;  
    A utility class for scoring chunk parsers.  ``ChunkScore`` can
    evaluate a chunk parser's output, based on a number of statistics
    (precision, recall, f-measure, misssed chunks, incorrect chunks).
    It can also combine the scores from the parsing of multiple texts;
    this makes it significantly easier to evaluate a chunk parser that
    operates one sentence at a time.

    Texts are evaluated with the ``score`` method.  The results of
    evaluation can be accessed via a number of accessor methods, such
    as ``precision`` and ``f_measure``.  A typical use of the
    ``ChunkScore`` class is::

        >>> chunkscore = ChunkScore()           # doctest: +SKIP
        >>> for correct in correct_sentences:   # doctest: +SKIP
        ...     guess = chunkparser.parse(correct.leaves())   # doctest: +SKIP
        ...     chunkscore.score(correct, guess)              # doctest: +SKIP
        >>> print('F Measure:', chunkscore.f_measure())       # doctest: +SKIP
        F Measure: 0.823

    :ivar kwargs: Keyword arguments:

        - max_tp_examples: The maximum number actual examples of true
          positives to record.  This affects the ``correct`` member
          function: ``correct`` will not return more than this number
          of true positive examples.  This does *not* affect any of
          the numerical metrics (precision, recall, or f-measure)

        - max_fp_examples: The maximum number actual examples of false
          positives to record.  This affects the ``incorrect`` member
          function and the ``guessed`` member function: ``incorrect``
          will not return more than this number of examples, and
          ``guessed`` will not return more than this number of true
          positive examples.  This does *not* affect any of the
          numerical metrics (precision, recall, or f-measure)

        - max_fn_examples: The maximum number actual examples of false
          negatives to record.  This affects the ``missed`` member
          function and the ``correct`` member function: ``missed``
          will not return more than this number of examples, and
          ``correct`` will not return more than this number of true
          negative examples.  This does *not* affect any of the
          numerical metrics (precision, recall, or f-measure)

        - chunk_label: A regular expression indicating which chunks
          should be compared.  Defaults to ``'.*'`` (i.e., all chunks).

    :type _tp: list(Token)
    :ivar _tp: List of true positives
    :type _fp: list(Token)
    :ivar _fp: List of false positives
    :type _fn: list(Token)
    :ivar _fn: List of false negatives

    :type _tp_num: int
    :ivar _tp_num: Number of true positives
    :type _fp_num: int
    :ivar _fp_num: Number of false positives
    :type _fn_num: int
    :ivar _fn_num: Number of false negatives.
    c                 K   s   t  | _t  | _t  | _t  | _t  | _|dd| _|dd| _|dd| _	|dd| _
d| _d| _d| _d| _d| _d| _d	| _d S )
NZmax_tp_examplesd   Zmax_fp_examplesZmax_fn_exampleschunk_labelz.*r   g        F)set_correct_guessed_tp_fp_fngetZ_max_tpZ_max_fpZ_max_fn_chunk_label_tp_num_fp_num_fn_num_count_tags_correct_tags_total_measuresNeedUpdate)selfkwargsr
   r
   r   __init__r   s    
zChunkScore.__init__c                 C   sb   | j r/| j| j@ | _| j| j | _| j| j | _t| j| _t| j| _t| j| _	d| _ d S d S )NF)
r   r   r   r   r   r   lenr   r   r   r   r
   r
   r   _updateMeasures   s   
zChunkScore._updateMeasuresc                 C   s   |  j t|| j| jO  _ |  jt|| j| jO  _|  jd7  _d| _z
t|}t|}W n ty;   d }}Y nw |  jt	|7  _|  j
tdd t||D 7  _
dS )aU  
        Given a correctly chunked sentence, score another chunked
        version of the same sentence.

        :type correct: chunk structure
        :param correct: The known-correct ("gold standard") chunked
            sentence.
        :type guessed: chunk structure
        :param guessed: The chunked sentence to be scored.
           Tr
   c                 s   s     | ]\}}||krd V  qdS )r$   Nr
   ).0tgr
   r
   r   	<genexpr>   s    z#ChunkScore.score.<locals>.<genexpr>N)r   
_chunksetsr   r   r   r   r   
ValueErrorr   r!   r   sumzip)r   correctguessedZcorrect_tagsZguessed_tagsr
   r
   r   score   s   zChunkScore.scorec                 C   s   | j dkrdS | j| j  S )z
        Return the overall tag-based accuracy for all text that have
        been scored by this ``ChunkScore``, using the IOB (conll2000)
        tag encoding.

        :rtype: float
        r   r$   )r   r   r"   r
   r
   r   r      s   
zChunkScore.accuracyc                 C   *   |    | j| j }|dkrdS | j| S )z
        Return the overall precision for all texts that have been
        scored by this ``ChunkScore``.

        :rtype: float
        r   )r#   r   r   r   divr
   r
   r   	precision   
   
zChunkScore.precisionc                 C   r0   )z
        Return the overall recall for all texts that have been
        scored by this ``ChunkScore``.

        :rtype: float
        r   r#   r   r   r1   r
   r
   r   recall   r4   zChunkScore.recall      ?c                 C   sD   |    |  }|  }|dks|dkrdS d|| d| |   S )a  
        Return the overall F measure for all texts that have been
        scored by this ``ChunkScore``.

        :param alpha: the relative weighting of precision and recall.
            Larger alpha biases the score towards the precision value,
            while smaller alpha biases the score towards the recall
            value.  ``alpha`` should have a value in the range [0,1].
        :type alpha: float
        :rtype: float
        r   r$   )r#   r3   r6   )r   alphaprr
   r
   r   	f_measure   s   zChunkScore.f_measurec                 C       |    t| j}dd |D S )z
        Return the chunks which were included in the
        correct chunk structures, but not in the guessed chunk
        structures, listed in input order.

        :rtype: list of chunks
        c                 S      g | ]}|d  qS r$   r
   r%   cr
   r
   r   
<listcomp>       z%ChunkScore.missed.<locals>.<listcomp>)r#   listr   r   chunksr
   r
   r   missed   s   
zChunkScore.missedc                 C   r<   )z
        Return the chunks which were included in the guessed chunk structures,
        but not in the correct chunk structures, listed in input order.

        :rtype: list of chunks
        c                 S   r=   r>   r
   r?   r
   r
   r   rA      rB   z(ChunkScore.incorrect.<locals>.<listcomp>)r#   rC   r   rD   r
   r
   r   	incorrect   s   
zChunkScore.incorrectc                 C      t | j}dd |D S )z
        Return the chunks which were included in the correct
        chunk structures, listed in input order.

        :rtype: list of chunks
        c                 S   r=   r>   r
   r?   r
   r
   r   rA     rB   z&ChunkScore.correct.<locals>.<listcomp>)rC   r   rD   r
   r
   r   r-         
zChunkScore.correctc                 C   rH   )z
        Return the chunks which were included in the guessed
        chunk structures, listed in input order.

        :rtype: list of chunks
        c                 S   r=   r>   r
   r?   r
   r
   r   rA     rB   z&ChunkScore.guessed.<locals>.<listcomp>)rC   r   rD   r
   r
   r   r.     rI   zChunkScore.guessedc                 C   s   |    | j| j S )Nr5   r"   r
   r
   r   __len__  s   zChunkScore.__len__c                 C   s   dt t|  d S )z`
        Return a concise representation of this ``ChunkScoring``.

        :rtype: str
        z<ChunkScoring of z chunks>)reprr!   r"   r
   r
   r   __repr__  s   zChunkScore.__repr__c                 C   s\   dd|   d dd d|  d dd d|  d dd d|  d dd	 S )
a-  
        Return a verbose representation of this ``ChunkScoring``.
        This representation includes the precision, recall, and
        f-measure scores.  For other information about the score,
        use the accessor methods (e.g., ``missed()`` and ``incorrect()``).

        :rtype: str
        zChunkParse score:
z    IOB Accuracy: r   z5.1fz%%
z    Precision:    z    Recall:       z    F-Measure:    z%%)r   r3   r6   r;   r"   r
   r
   r   __str__  s   
zChunkScore.__str__N)r7   )__name__
__module____qualname____doc__r    r#   r/   r   r3   r6   r;   rF   rG   r-   r.   rJ   rL   rM   r
   r
   r
   r   r   3   s     >



r   c                 C   sd   d}g }| D ]'}t |tr)t|| r |||f| f |t| 7 }q|d7 }qt	|S )Nr   r$   )

isinstancer   rematchlabelappendfreezer!   leavesr   )r&   countr   posrE   childr
   r
   r   r)   2  s   

r)   NPS/c                 C   s(  t d}t|g g}|| D ]o}| }	|	d dkr>t|dkr,td| dt|g }
|d |
 ||
 q|	d dkrYt|d	krTtd
| d|	  q|du re|d |	 qt
|	|\}}|rv|rvt|||}|d ||f qt|dkrtdt| d|d S )aB  
    Divide a string of bracketted tagged text into
    chunks and unchunked tokens, and produce a Tree.
    Chunks are marked by square brackets (``[...]``).  Words are
    delimited by whitespace, and each word should have the form
    ``text/tag``.  Words that do not contain a slash are
    assigned a ``tag`` of None.

    :param s: The string to be converted
    :type s: str
    :param chunk_label: The label to use for chunk nodes
    :type chunk_label: str
    :param root_label: The label to use for the root of the tree
    :type root_label: str
    :rtype: Tree
    z\[|\]|[^\[\]\s]+r   [r$   zUnexpected [ at char d]   zUnexpected ] at char NzExpected ] at char )rS   compiler   finditergroupr!   r*   startrV   popr   r   )sr   
root_labelsepZsource_tagsetZtarget_tagsetZWORD_OR_BRACKETstackrT   textchunkwordtagr
   r
   r   tagstr2tree?  s.   


rq   z(\S+)\s+(\S+)\s+([IOB])-?(\S+)?r\   PPZVPc                 C   s   t |g g}t| dD ]h\}}| sqt|}|du r'td|d| \}}}	}
|dur9|
|vr9d}	|	dkoD|
|d  k}|	dv sK|rUt	|d	krU|
  |	d
ks[|rlt |
g }|d | || |d ||f q|d S )a*  
    Return a chunk structure for a single sentence
    encoded in the given CONLL 2000 style string.
    This function converts a CoNLL IOB string into a tree.
    It uses the specified chunk types
    (defaults to NP, PP and VP), and creates a tree rooted at a node
    labeled S (by default).

    :param s: The CoNLL string to be converted.
    :type s: str
    :param chunk_types: The chunk types to be converted.
    :type chunk_types: tuple
    :param root_label: The node label to use for the root.
    :type root_label: str
    :rtype: Tree
    
NzError on line r`   OIra   ZBOrc   Br   )r   	enumeratesplitstrip_LINE_RErT   r*   groupsrU   r!   rh   rV   )ri   chunk_typesrj   rl   linenolinerT   ro   rp   stateZ
chunk_typeZ
mismatch_Irn   r
   r
   r   conllstr2treeu  s(   


r   c              	   C   s   g }| D ]=}z&|  }d}|D ]}t|trtd||d |d || f d}qW q tyA   ||d |d df Y qw |S )z
    Return a list of 3-tuples containing ``(word, tag, IOB-tag)``.
    Convert a tree to the CoNLL IOB tag format.

    :param t: The tree to be converted.
    :type t: Tree
    :rtype: list(tuple)
    B-z7Tree is too deeply nested to be printed in CoNLL formatr   r$   I-ru   )rU   rR   r   r*   rV   AttributeError)r&   tagsr[   categoryprefixcontentsr
   r
   r   r     s"   

r   Fc                 C   s  t |g }| D ]|\}}}|du r|rtd|||f q|dr3|t |dd ||fg q|drqt|dksQt|d t rQ|d  |dd krg|rWtd|t |dd ||fg q|d ||f q|dkr}|||f qtd	||S )
z1
    Convert the CoNLL IOB format to a tree.
    NzBad conll tag sequencer   rc   r   r   ra   ru   zBad conll tag )r   r*   rV   
startswithr!   rR   rU   )Zsentencer}   rj   stricttreero   ZpostagZchunktagr
   r
   r   conlltags2tree  s*   

 
 r   c                 C   s   dd t | D }d|S )z
    Return a multiline string where each line contains a word, tag and IOB tag.
    Convert a tree to the CoNLL IOB string format

    :param t: The tree to be converted.
    :type t: Tree
    :rtype: str
    c                 S   s   g | ]}d  |qS ) )join)r%   tokenr
   r
   r   rA     s    z!tree2conllstr.<locals>.<listcomp>rt   )r   r   )r&   linesr
   r
   r   tree2conllstr  s   	
r   a   <DOC>\s*(<DOCNO>\s*(?P<docno>.+?)\s*</DOCNO>\s*)?(<DOCTYPE>\s*(?P<doctype>.+?)\s*</DOCTYPE>\s*)?(<DATE_TIME>\s*(?P<date_time>.+?)\s*</DATE_TIME>\s*)?<BODY>\s*(<HEADLINE>\s*(?P<headline>.+?)\s*</HEADLINE>\s*)?<TEXT>(?P<text>.*?)</TEXT>\s*</BODY>\s*</DOC>\s*z#<b_\w+\s+[^>]*?type="(?P<type>\w+)"c                 C   s   t |g g}| d u rg S td| D ][}| }z;|drAt|}|d u r,td| t |dg }|d | || n|drK|	  n|d | W q t
tfym } ztd| dd	|d }~ww t|d
krxtd|d S )Nz<[^>]+>|[^\s<]+z<b_ZXXXXtypera   z<e_z$Bad IEER string (error at character r`   )r$   zBad IEER stringr   )r   rS   re   rf   r   _IEER_TYPE_RErT   printrV   rh   
IndexErrorr*   rg   r!   )ri   rj   rl   Zpiece_mZpiecemrn   er
   r
   r   _ieer_read_text  s8   




r   )	ZLOCATIONZORGANIZATIONZPERSONZDURATIONZDATEZCARDINALPERCENTZMONEYZMEASUREc                 C   sR   t | }|r$t|d||d|d|dt|d|dS t| |S )ap  
    Return a chunk structure containing the chunked tagged text that is
    encoded in the given IEER style string.
    Convert a string of chunked tagged text in the IEER named
    entity format into a chunk structure.  Chunks are of several
    types, LOCATION, ORGANIZATION, PERSON, DURATION, DATE, CARDINAL,
    PERCENT, MONEY, and MEASURE.

    :rtype: Tree
    rm   docnodoctype	date_timeheadline)rm   r   r   r   r   )_IEER_DOC_RErT   r   rf   )ri   r}   rj   r   r
   r
   r   ieerstr2tree'  s   


r   c                  C   sd   d} dd l }|jj| dd}|  t  d} t| dd}|  td t|j| t  d S )	Nzd[ Pierre/NNP Vinken/NNP ] ,/, [ 61/CD years/NNS ] old/JJ ,/, will/MD join/VB [ the/DT board/NN ] ./.r   r\   )r   av  
These DT B-NP
research NN I-NP
protocols NNS I-NP
offer VBP B-VP
to TO B-PP
the DT B-NP
patient NN I-NP
not RB O
only RB O
the DT B-NP
very RB I-NP
best JJS I-NP
therapy NN I-NP
which WDT B-NP
we PRP B-NP
have VBP B-VP
established VBN I-VP
today NN B-NP
but CC B-NP
also RB I-NP
the DT B-NP
hope NN I-NP
of IN B-PP
something NN B-NP
still RB B-ADJP
better JJR I-ADJP
. . O
)r\   rs   )r}   zCoNLL output:)nltkrn   rq   pprintr   r   r   )ri   r   r&   Z
conll_treer
   r
   r   demoR  s   
r   __main__)r\   r]   r^   NN)rr   r]   )rr   r]   F)rS   Znltk.metricsr   r	   Znltk.tag.mappingr   Znltk.tag.utilr   Z	nltk.treer   r   r)   rq   rd   r{   r   r   r   r   DOTALLr   r   r   r   r   rN   r
   r
   r
   r   <module>   s>     

3
5
$
"
+/
