B >?[@sVddlmZmZddlmZddlmZeGdddeZddZ e dkrRe d S) )print_functionunicode_literals)FreqDist)python_2_unicode_compatiblec@sDeZdZdZdddZddZddZd d Zdd dZddZ d S)ConfusionMatrixa The confusion matrix between a list of reference values and a corresponding list of test values. Entry *[r,t]* of this matrix is a count of the number of times that the reference value *r* corresponds to the test value *t*. E.g.: >>> from nltk.metrics import ConfusionMatrix >>> ref = 'DET NN VB DET JJ NN NN IN DET NN'.split() >>> test = 'DET VB VB DET NN NN NN IN DET NN'.split() >>> cm = ConfusionMatrix(ref, test) >>> print(cm['NN', 'NN']) 3 Note that the diagonal entries *Ri=Tj* of this matrix corresponds to correct values; and the off-diagonal entries correspond to incorrect values. Fc s t|t|krtd|rPt|t|fdd}tt|||dntt||tddtD}fddDd }xLt||D]>\}}||||d 7<t|||||}qW|_ ||_ |_ ||_ t||_ tfd dttD|_d S) a Construct a new confusion matrix from a list of reference values and a corresponding list of test values. :type reference: list :param reference: An ordered list of reference values. :type test: list :param test: A list of values to compare against the corresponding reference values. :raise ValueError: If ``reference`` and ``length`` do not have the same length. z Lists must have the same length.cs|| S)N)v) ref_fdist test_fdistr;lib/python3.7/site-packages/nltk/metrics/confusionmatrix.pykey6sz%ConfusionMatrix.__init__..key)r css|]\}}||fVqdS)Nr).0ivalrrr >sz+ConfusionMatrix.__init__..csg|]}ddDqS)cSsg|]}dqS)rr)r rrrr Asz7ConfusionMatrix.__init__...r)r r)valuesrr rAsz,ConfusionMatrix.__init__..rc3s|]}||VqdS)Nr)r r) confusionrr rRsN)len ValueErrorrsortedsetdict enumeratezipmax_values_indices _confusion _max_conf_totalsumrange_correct) self referencetest sort_by_countr indicesZmax_confwgr)rr r rr __init__!s(  zConfusionMatrix.__init__cCs*|\}}|j|}|j|}|j||S)z :return: The number of times that value ``li`` was expected and value ``lj`` was given. :rtype: int )rr)r%Z li_lj_tupleliljrjrrr __getitem__Ts  zConfusionMatrix.__getitem__cCsd|j|jfS)Nz )r$r!)r%rrr __repr___szConfusionMatrix.__repr__cCs|S)N) pretty_format)r%rrr __str__bszConfusionMatrix.__str__TNcsj}j}|r$t|fddd}|r4|d|}|rHdd|D}nddtt|D}tdd |D}d t|d } |rd } d } d} n.ttj} d t| d} d| dd} d} x|t|D]p}| d|d7} xR|D]J}||t|kr"| |||t|| d7} q| d| d7} qW| d7} qW| dd|d| dt|f7} xt ||D]\}}j |}| | |7} x|D]}j |}|||dkr| | 7} n:|r| | d|||j 7} n| | |||7} ||kr4| d}| d|d| |ddd} n| d7} qW| d7} qrW| dd|d| dt|f7} | d7} |s| d7} x*t |D]\}}| d|d|f7} qW| S) a :return: A multi-line string representation of this confusion matrix. :type truncate: int :param truncate: If specified, then only show the specified number of values. Any sorting (e.g., sort_by_count) will be performed before truncation. :param sort_by_count: If true, then sort by the count of each label in the reference data. I.e., labels that occur more frequently in the reference label will be towards the left edge of the matrix, and labels that occur less frequently will be towards the right edge. @todo: add marginals? cstjj| S)N)r"rr)r)r%rr sz/ConfusionMatrix.pretty_format..)r NcSsg|] }d|qS)z%sr)r rrrr rsz1ConfusionMatrix.pretty_format..cSsg|]}t|dqS)r)str)r nrrr rscss|]}t|VqdS)N)r)r rrrr rsz0ConfusionMatrix.pretty_format..%zs | z%5.1f%%z .d r.z |z | z %s-+-%s+ -rgY@<>z| z(row = reference; col = test) z Value key: z%6d: %s )rrrr#rrreprr rjustrrr!rfindr)r%Z show_percentsZvalues_in_charttruncater(rrZ value_stringsZvaluelenZ value_formatZentrylenZ entry_formatZzerostrsrrr-r.r/Z prevspacevaluer)r%r r2esd  $ $        &$zConfusionMatrix.pretty_formatcCs\|j}d}ttt|d}dt|d}x(tt|D]}|||||f7}qs   B