3 Pd5g@sddlZddlZddlmZddlZddlZddlZddddgZej dZ ej dZ ej d Z ej d Z ej d Zej d Zej d Zej dZej dZej dZej dZGdddeZGdddeZGdddeZGdddeZGdddeZGdddeZGdddeZGdddeZd d!Zd"d#Z d$d%Z!d?d&d'Z"d(d)Z#d*d+Z$d,d-Z%d.d/Z&d0d1Z'Gd2ddeZ(d3dZ)d4d5Z*d6d7Z+d8d9Z,d:d;Z-dZ2e-e2dS)@N) OrderedDictMetaDataloadarff ArffErrorParseArffErrorz^\s*@z^%z^\s+$z^\s*@\S*z^@[Dd][Aa][Tt][Aa]z*^@[Rr][Ee][Ll][Aa][Tt][Ii][Oo][Nn]\s*(\S*)z2^\s*@[Aa][Tt][Tt][Rr][Ii][Bb][Uu][Tt][Ee]\s*(..*$)z{(.+)}z%[Dd][Aa][Tt][Ee]\s+[\"']?(.+?)[\"']?$z'(..+)'\s+(..+$)z(\S+)\s+(..+$)c@s eZdZdS)rN)__name__ __module__ __qualname__r r J/var/www/html/virt/lib64/python3.6/site-packages/scipy/io/arff/arffread.pyr7sc@s eZdZdS)rN)rrr r r r r r;sc@s4eZdZdZddZeddZddZdd ZdS) AttributeNcCs||_d|_tj|_dS)N)namerangenpobject_dtype)selfr r r r __init__FszAttribute.__init__cCsdS)zj Parse the attribute line if it knows how. Returns the parsed attribute, or None. Nr )clsr attr_stringr r r parse_attributeKszAttribute.parse_attributecCsdS)z- Parse a value of this type. Nr )rdata_strr r r parse_dataSszAttribute.parse_datacCs|jd|jS)z- Parse a value of this type. ,)r type_name)rr r r __str__YszAttribute.__str__) rrr rr classmethodrrrr r r r r Bs  r csHeZdZdZfddZeddZeddZdd Z d d Z Z S) NominalAttributeZnominalcs6tj|||_||_tjtdd|Df|_dS)Ncss|]}t|VqdS)N)len).0ir r r hsz,NominalAttribute.__init__..)superrvaluesrrZstring_maxr)rr r#) __class__r r rds zNominalAttribute.__init__cCs4tj|}|r(t|jd\}}t|StddS)aGiven a string containing a nominal type, returns a tuple of the possible values. A nominal type is defined as something framed between braces ({}). Parameters ---------- atrv : str Nominal type definition Returns ------- poss_vals : tuple possible values Examples -------- >>> get_nom_val("{floup, bouga, fl, ratata}") ('floup', 'bouga', 'fl', 'ratata') z(This does not look like a nominal stringN) r_nominalmatchsplit_data_linegrouptuple ValueError)atrvmattrs_r r r _get_nom_valjs  zNominalAttribute._get_nom_valcCs(|ddkr |j|}|||SdSdS)z Parse the attribute line if it knows how. Returns the parsed attribute, or None. For nominal attributes, the attribute string would be like '{, , }'. r{N)r1)rr rr#r r r rs   z NominalAttribute.parse_attributecCs8||jkr|S|dkr|Stdt|t|jfdS)z- Parse a value of this type. ?z%s value not in %sN)r#r,str)rrr r r rs   zNominalAttribute.parse_datacCsR|jd}x,tt|jdD]}||j|d7}qW||jd7}|d7}|S)Nz,{r&r})r rrr#)rmsgr r r r rs  zNominalAttribute.__str__) rrr rr staticmethodr1rrrr __classcell__r r )r%r r`s     rcs8eZdZfddZeddZddZddZZS) NumericAttributecstj|d|_tj|_dS)Nnumeric)r"rrrZfloat_r)rr )r%r r rs zNumericAttribute.__init__cCsX|jj}|dtddksH|dtddksH|dtddkrP||SdSdS)z Parse the attribute line if it knows how. Returns the parsed attribute, or None. For numeric attributes, the attribute string would be like 'numeric' or 'int' or 'real'. Nr;intreal)lowerstripr)rr rr r r rs z NumericAttribute.parse_attributecCsd|krtjSt|SdS)a Parse a value of this type. Parameters ---------- data_str : str string to convert Returns ------- f : float where float can be nan Examples -------- >>> atr = NumericAttribute('atr') >>> atr.parse_data('1') 1.0 >>> atr.parse_data('1\n') 1.0 >>> atr.parse_data('?\n') nan r3N)rnanfloat)rrr r r rszNumericAttribute.parse_datacCs<|jd|jd}tj|tj|tj|tj||fS)Ng?r&)sizernanminnanmaxmeanstd)rdatanbfacr r r _basic_statsszNumericAttribute._basic_stats) rrr rrrrrIr9r r )r%r r:s  r:cs(eZdZfddZeddZZS)StringAttributecstj|d|_dS)Nstring)r"rr)rr )r%r r rs zStringAttribute.__init__cCs0|jj}|dtddkr(||SdSdS)z Parse the attribute line if it knows how. Returns the parsed attribute, or None. For string attributes, the attribute string would be like 'string'. NrK)r>r?r)rr rr r r rs zStringAttribute.parse_attribute)rrr rrrr9r r )r%r rJs rJcsHeZdZfddZeddZeddZddZfd d Z Z S) DateAttributecs8tj|||_||_d|_||_tjd|j|_dS)Ndater) r"r date_format datetime_unitrrr datetime64r)rr rNrO)r%r r rs  zDateAttribute.__init__cCstj|}|r|jdj}d}d|kr:|jdd}d}n|jdd}d}d|krb|jdd}d }d |krz|jd d }d }d |kr|jd d}d}d|kr|jdd}d}d|kr|jdd}d}d|ksd|krtd|dkrtd||fStddS)Nr&Zyyyyz%YYyyz%yZMMz%mMddz%dDZHHz%Hhmmz%Mr.ssz%SszZz6Date type attributes with time zone not supported, yetz"Invalid or unsupported date formatzInvalid or no date format)r_dater(r*r?replacer,)r-r.patternrOr r r _get_date_format s<        zDateAttribute._get_date_formatcCsB|jj}|dtddkr:|j|\}}||||SdSdS)z Parse the attribute line if it knows how. Returns the parsed attribute, or None. For date attributes, the attribute string would be like 'date '. NrM)r>r?rr_)rr rattr_string_lowerrNrOr r r r1s  zDateAttribute.parse_attributecCsT|jjdjd}|dkr*tjd|jStjj||j}tj|jd|jSdS)z- Parse a value of this type. '"r3ZNaTzdatetime64[%s]N)r?rrPrOdatetimestrptimerNZastype)rrZdate_strdtr r r rCs  zDateAttribute.parse_datacstt|jd|jS)Nr)r"rLrrN)r)r%r r rOszDateAttribute.__str__) rrr rr8r_rrrrr9r r )r%r rLs   '  rLcs<eZdZfddZeddZddZfddZZS) RelationalAttributecs*tj|d|_tj|_g|_d|_dS)N relational)r"rrrrr attributesdialect)rr )r%r r rUs  zRelationalAttribute.__init__cCs0|jj}|dtddkr(||SdSdS)z Parse the attribute line if it knows how. Returns the parsed attribute, or None. For date attributes, the attribute string would be like 'date '. Nrg)r>r?r)rr rr`r r r r\s z#RelationalAttribute.parse_attributecstttj}|jjd}g}xB|jdD]4}t|j\_|j t fdd|Dq0Wt j |ddjDS)Nzunicode-escape cs g|]}j|j|qSr )rhr)rr )rowrr r ysz2RelationalAttribute.parse_data..cSsg|]}|j|jfqSr )r r)rar r r rl|s) listrrrhencodedecodesplitr)riappendr+rarray)rrelemsZescaped_stringZ row_tuplesrawr )rkrr rmszRelationalAttribute.parse_datacs(tt|jddjdd|jDS)Nz css|]}t|VqdS)N)r4)rrmr r r r!sz.RelationalAttribute.__str__..)r"rfrjoinrh)r)r%r r r~szRelationalAttribute.__str__) rrr rrrrrr9r r )r%r rfSs  rfcCsDtttttf}x$|D]}|j||}|dk r|SqWtd|dS)Nzunknown attribute %s)rr:rLrJrfrr)r rZ attr_classesrattrr r r to_attributes  rxcCs8ttdd}|dkr4tjjd}|jdkt_tj}|S)zL Checks if the bug https://bugs.python.org/issue30157 is unpatched. has_bugNz3, 'a'ra)getattrcsv_sniffer_has_bug_last_fieldcsvSniffersniff quotecharry)ryrir r r r{s   r{cCstrd}x8dd|dfD](}tj|tjtjB}|j|}|rPqW||krPdS|j}t|dksft|d}|dd} || } |d d} || } |d d} t || } tjd tj | | d tj} t | j |}| |_ | |kr| |_ ||_| |_dS) zT Workaround for the bug https://bugs.python.org/issue30157 if is unpatched. zG(?P[^\w\n"\'])(?P ?)(?P["\']).*?(?P=quote)(?:$|\n)zI(?P[^\w\n"\'])(?P ?)(?P["\']).*?(?P=quote)(?P=delim)zG(?:^|\n)(?P["\']).*?(?P=quote)(?P[^\w\n"\'])(?P ?)z-(?:^|\n)(?P["\']).*?(?P=quote)(?:$|\n)Nr&rquotedelimspacez]((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$))rr)r{recompileDOTALL MULTILINEfindall groupindexrAssertionErrorboolescapesearchr delimiter doublequoteskipinitialspace) sniff_lineri delimitersZ right_regexrestrregexpmatchesrr.nrrr dq_regexprr r r %workaround_csv_sniffer_bug_last_fields<      rcsd}tjttjd jdd dkr6dd }tfdd|DsX|d7}|dkrtjj||d}t |||d t tj g|}||fS) Nz, r&rjc3s|]}|kVqdS)Nr )rd)liner r r!sz"split_data_line..r)r)rrirr6r6r6) r|field_size_limitr<ctypesc_ulongvalueanyr}r~rnextreader)rrirrrkr )rr r)s  r)cCs|j}tj|}|rj|jd}tj|r@t|\}}t|}qvtj|r`t|\}}t|}qvt dn t d|t ||}|j dkrt |||}||fS)akParse a raw string in header (e.g., starts by @attribute). Given a raw string attribute, try to get the name and type of the attribute. Constraints: * The first line must start with @attribute (case insensitive, and space like characters before @attribute are allowed) * Works also if the attribute is spread on multilines. * Works if empty lines or comments are in between Parameters ---------- attribute : str the attribute string. Returns ------- name : str name of the attribute value : str value of the attribute next : str next line to be parsed Examples -------- If attribute is a string defined in python as r"floupi real", will return floupi as name, and real as value. >>> iterable = iter([0] * 10) # dummy iterator >>> tokenize_attribute(iterable, r"@attribute floupi real") ('floupi', 'real', 0) If attribute is r"'floupi 2' real", will return 'floupi 2' as name, and real as value. >>> tokenize_attribute(iterable, r" @attribute 'floupi 2' real ") ('floupi 2', 'real', 0) r&zmulti line not supported yetzFirst line unparsable: %srg) r? r_attributer(r* r_comattrvaltokenize_single_commar r_wcomattrvaltokenize_single_wcommar,rxr>read_relational_attribute)iterable attributeZsattrZmattrr-r typeZ next_itemr r r tokenize_attributes )             rc Csbtj|}|rNy |jdj}|jdj}WqZtk rJtdYqZXn td|||fS)Nr&rz Error while tokenizing attributez Error while tokenizing single %s)rr(r*r? IndexErrorr,)valr.r rr r r r8s  rc Csbtj|}|rNy |jdj}|jdj}WqZtk rJtdYqZXn td|||fS)Nr&rz Error while tokenizing attributez Error while tokenizing single %s)rr(r*r?rr,)rr.r rr r r rGs  rcCs~tjd|jd}x\|j|sptj|}|rftj|}|rXt||\}}|jj|qnt d|qt |}qWt |}|S)z4Read the nested attributes of a relational attributez^@[Ee][Nn][Dd]\s*z\s*$zError parsing line %s) rrr r( r_headerlinerrrhrrr,r)ofileZrelational_attributer Zr_end_relationalr.isattrrwr r r rVs    rcCst|}xtj|rt|}q Wd}g}x|tj|stj|}|rtj|}|rjt||\}}|j|qtj|}|r|j d}n t d|t|}q*t|}q*W||fS)z&Read the header of the iterable ofile.Nr&zError parsing line %s) r r_commentr( r_datametarrrrr r_relationr*r,)rr Zrelationrhr.rrwZisrelr r r read_headerls&           rc@s@eZdZdZddZddZddZdd Zd d Zd d Z dS)raSmall container to keep useful information on a ARFF dataset. Knows about attributes names and types. Examples -------- :: data, meta = loadarff('iris.arff') # This will print the attributes names of the iris.arff dataset for i in meta: print(i) # This works too meta.names() # Getting attribute type types = meta.types() Methods ------- names types Notes ----- Also maintains the list of attributes in order, i.e., doing for i in meta, where meta is an instance of MetaData, will return the different attribute names in the order they were defined. cCs||_tdd|D|_dS)Ncss|]}|j|fVqdS)N)r )rrmr r r r!sz$MetaData.__init__..)r r _attributes)rrelrwr r r rszMetaData.__init__cCsjd}|d|j7}xR|jD]H}|d||j|jf7}|j|jrZ|dt|j|j7}|d7}qW|S)Nz Dataset: %s z %s's type is %sz , range is %srj)r rrrr4)rr7r r r r __repr__s   zMetaData.__repr__cCs t|jS)N)iterr)rr r r __iter__szMetaData.__iter__cCs|j|}|j|jfS)N)rrr)rkeyrwr r r __getitem__s zMetaData.__getitem__cCs t|jS)zReturn the list of attribute names. Returns ------- attrnames : list of str The attribute names. )rnr)rr r r namesszMetaData.namescsfddjD}|S)zReturn the list of attribute types. Returns ------- attr_types : list of str The attribute types. csg|]}j|jqSr )rr)rr )rr r rlsz"MetaData.types..)r)rZ attr_typesr )rr typess  zMetaData.typesN) rrr __doc__rrrrrrr r r r rs  c Cs:t|dr|}n t|d}zt|S||k r4|jXdS)a Read an arff file. The data is returned as a record array, which can be accessed much like a dictionary of NumPy arrays. For example, if one of the attributes is called 'pressure', then its first 10 data points can be accessed from the ``data`` record array like so: ``data['pressure'][0:10]`` Parameters ---------- f : file-like or str File-like object to read from, or filename to open. Returns ------- data : record array The data of the arff file, accessible by attribute names. meta : `MetaData` Contains information about the arff file such as name and type of attributes, the relation (name of the dataset), etc. Raises ------ ParseArffError This is raised if the given file is not ARFF-formatted. NotImplementedError The ARFF file has an attribute which is not supported yet. Notes ----- This function should be able to read most arff files. Not implemented functionality include: * date type attributes * string type attributes It can read files with numeric and nominal attributes. It cannot read files with sparse data ({} in the file). However, this function can read files with missing data (? in the file), representing the data points as NaNs. Examples -------- >>> from scipy.io import arff >>> from io import StringIO >>> content = """ ... @relation foo ... @attribute width numeric ... @attribute height numeric ... @attribute color {red,green,blue,yellow,black} ... @data ... 5.0,3.25,blue ... 4.5,3.75,green ... 3.0,4.00,red ... """ >>> f = StringIO(content) >>> data, meta = arff.loadarff(f) >>> data array([(5.0, 3.25, 'blue'), (4.5, 3.75, 'green'), (3.0, 4.0, 'red')], dtype=[('width', '>> meta Dataset: foo width's type is numeric height's type is numeric color's type is nominal, range is ('red', 'green', 'blue', 'yellow', 'black') readrtN)hasattropen _loadarffclose)frr r r rsF  c syt|\}Wn6tk rF}zdt|}t|WYdd}~XnXd}xD]}t|trRd}qRWt|}|r~tdtd fdd }t ||}t j |dd D}||fS) Nz'Error while parsing header, error was: FTz*String attributes not supported yet, sorryrc3s`tt}d}xJ|D]B}tj|stj|r0qt||\}tfdd|DVqWdS)Ncsg|]}|j|qSr )r)rr )rwrkr r rlasz0_loadarff..generator..)rnrrr(r_emptyr)r+)Zrow_iterrrtriru)rwni)rkr generatorGs  z_loadarff..generatorcSsg|]}|j|jfqSr )r r)rrmr r r rlesz_loadarff..)r) rr,r4r isinstancerJrNotImplementedErrorrrnrrs) rrer7hasstrrmmetarrGr )rwrr r(s"     rcCs<|jd|jd}tj|tj|tj|tj||fS)Ng?r&)rBrrCrDrErF)rGrHr r r basic_statslsrcCsX|j}|dks|dks|dkrHt|\}}}}td||||||fn tt|dS)Nr;r=integerz%s,%s,%f,%f,%f,%f)rrprintr4)r tprGrminr$rErFr r r print_attributeqs rcCsJt|\}}tt|jt|jx |D]}t|||||q*WdS)N)rrrrrBr)filenamerGrr r r r test_wekazs    rF__main__r&)N)3rrc collectionsrZnumpyrr|r__all__rZr_metarrrrrrr'r\rrIOErrorrrobjectr rr:rJrLrfrxr{rr)rrrrrrrrrrrZ__test__rsysargvrr r r r sZ             K=S3 2 DLQD