o ?Hhd@sddlZddlZddlZddlZddlZ gdZedZedZ edZ edZ edZ edZ ed Zed Zed Zed Zed ZGdddeZGdddeZGdddZGdddeZGdddeZGdddeZGdddeZGdddeZddZd d!Zd"d#Zd6d$d%Zd&d'Z d(d)Z!d*d+Z"d,d-Z#d.d/Z$Gd0d1d1Z%d2d3Z&d4d5Z'dS)7N)MetaDataloadarff 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+(..+$)c@ eZdZdS)rN__name__ __module__ __qualname__r r W/home/air/sanwanet/gpt-api/venv/lib/python3.10/site-packages/scipy/io/arff/_arffread.pyr6rc@r)rNrr r r r r:r rc@s4eZdZdZddZeddZddZdd ZdS) AttributeNcCs||_d|_tj|_dSN)namerangenpobject_dtypeselfrr r r __init__Es zAttribute.__init__cCdS)zj Parse the attribute line if it knows how. Returns the parsed attribute, or None. Nr clsr attr_stringr r r parse_attributeJszAttribute.parse_attributecCr)- Parse a value of this type. Nr rdata_strr r r parse_dataRszAttribute.parse_datacCs|jd|jS)r,)r type_namerr r r __str__XszAttribute.__str__) rr r r"r classmethodrr r$r r r r rAs  rcsHeZdZdZfddZeddZeddZdd Z d d Z Z S) NominalAttributenominalcs6t|||_||_tjtdd|Df|_dS)Ncs|]}t|VqdSr)len.0ir r r gz,NominalAttribute.__init__..)superrvaluesrrbytes_maxr)rrr0 __class__r r rcs zNominalAttribute.__init__cCs0t|}|rt|d\}}t|Std)a8Given 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 -------- >>> from scipy.io.arff._arffread import NominalAttribute >>> NominalAttribute._get_nom_val("{floup, bouga, fl, ratata}") ('floup', 'bouga', 'fl', 'ratata') z(This does not look like a nominal string) r_nominalmatchsplit_data_linegrouptuple ValueError)atrvmattrs_r r r _get_nom_valis zNominalAttribute._get_nom_valcCs$|ddkr||}|||SdS)z Parse the attribute line if it knows how. Returns the parsed attribute, or None. For nominal attributes, the attribute string would be like '{, , }'. r{N)r@)rrrr0r r r rs  z NominalAttribute.parse_attributecCs6||jvr|S|dkr |Stt|dt|j)r?z value not in )r0r;strrr r r r s zNominalAttribute.parse_datacCsN|jd}tt|jdD] }||j|d7}q||jd7}|d7}|S)Nz,{r5r!})rrr)r0rmsgr,r r r r$s zNominalAttribute.__str__) rr r r"r staticmethodr@r%rr r$ __classcell__r r r3r r&_s    r&cs8eZdZfddZeddZddZddZZS) NumericAttributecst|d|_tj|_dS)Nnumeric)r/rr"rfloat64rrr3r r rs  zNumericAttribute.__init__cCsT|}|dtddks$|dtddks$|dtddkr(||SdS)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'. NrKintreallowerstripr)rr r r rs z NumericAttribute.parse_attributecCsd|vrtjSt|S)a Parse a value of this type. Parameters ---------- data_str : str string to convert Returns ------- f : float where float can be nan Examples -------- >>> from scipy.io.arff._arffread import NumericAttribute >>> atr = NumericAttribute('atr') >>> atr.parse_data('1') 1.0 >>> atr.parse_data('1\n') 1.0 >>> atr.parse_data('?\n') nan rB)rnanfloatrr r r r szNumericAttribute.parse_datacCs<|jd|jd}t|t|t|t||fS)Ng?r5)sizernanminnanmaxmeanstd)rdatanbfacr r r _basic_statsszNumericAttribute._basic_stats) rr r rr%rr r[rIr r r3r rJs   rJcs(eZdZfddZeddZZS)StringAttributecst|d|_dS)Nstring)r/rr"rr3r r rs  zStringAttribute.__init__cCs,|}|dtddkr||SdS)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'. Nr]rOrr r r r zStringAttribute.parse_attribute)rr r rr%rrIr r r3r r\s r\csHeZdZfddZeddZeddZddZfd d Z Z S) DateAttributecs8t|||_||_d|_||_td|j|_dS)Ndater) r/r date_format datetime_unitr"rr datetime64r)rrrarbr3r r rs zDateAttribute.__init__cCst|}|rz|d}d}d|vr|dd}d}n |dd}d}d|vr2|dd}d }d |vr>|d d }d }d |vrJ|d d}d}d|vrV|dd}d}d|vrb|dd}d}d|vsjd|vrntd|durvtd||fStd)Nr5yyyyz%YYyyz%yMMz%mMddz%dDHHz%Hhmmz%Mr=ssz%SszZz6Date type attributes with time zone not supported, yetz"Invalid or unsupported date formatzInvalid or no date format)r_dater7r9rQreplacer;)r<r=patternrbr r r _get_date_format s>        zDateAttribute._get_date_formatcCs>|}|dtddkr||\}}||||SdS) Parse the attribute line if it knows how. Returns the parsed attribute, or None. For date attributes, the attribute string would be like 'date '. Nr`)rPrQr)ru)rrrattr_string_lowerrarbr r r r1s  zDateAttribute.parse_attributecCsT|dd}|dkrtd|jStj||j}t|d|jdS)r'"rBNaTz datetime64[])rQrrcrbdatetimestrptimeraastype)rrdate_strdtr r r r Cs  zDateAttribute.parse_datacstd|jS)Nr!)r/r$rar#r3r r r$OszDateAttribute.__str__) rr r rrHrur%rr r$rIr r r3r r_s  &  r_cs<eZdZfddZeddZddZfddZZS) RelationalAttributecs*t|d|_tj|_g|_d|_dS)N relational)r/rr"rrr attributesdialectrr3r r rUs  zRelationalAttribute.__init__cCs,|}|dtddkr||SdS)rvNrrO)rrrrwr r r r\r^z#RelationalAttribute.parse_attributecs|tttj}|d}g}|dD]}t|j\_| t fdd|Dqt |ddjDS)Nzunicode-escape cs g|] }j||qSr )rr r*rowrr r ys z2RelationalAttribute.parse_data..cSg|]}|j|jfqSr rrr+ar r r r|) listrr)rencodedecodesplitr8rappendr:rarray)rrelemsescaped_string row_tuplesrawr rr r mszRelationalAttribute.parse_datacs$tdddd|jDS)Nz csr(r)rCrr r r r-r.z.RelationalAttribute.__str__..)r/r$joinrr#r3r r r$~s zRelationalAttribute.__str__) rr r rr%rr r$rIr r r3r rSs   rcCsBtttttf}|D]}|||}|dur|Sq td|)Nzunknown attribute )r&rJr_r\rrr)rr attr_classesrattrr r r to_attributes rcCs8ttdd}|durtd}|jdkt_tj}|S)zL Checks if the bug https://bugs.python.org/issue30157 is unpatched. has_bugNz3, 'a'rx)getattrcsv_sniffer_has_bug_last_fieldcsvSniffersniff quotecharr)rrr r r rs  rcCs4trd}dd|dfD]}t|tjtjB}||}|r nq ||kr'dS|j}t|dks2J|d}|dd} || } |d d} || } |d d} t|| } td t | d | d t | d| d t | d| dt | dtj} t| |}| |_ | |vr| |_ ||_ | |_dSdS)zT Workaround for the bug https://bugs.python.org/issue30157 if is unpatched. zG(?P[^\w\n"\'])(?P ?)(?P["\']).*?(?P=quote)(?:$|\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)(?:$|\n)Nr5rquotedelimspacez((z)|^)\W*z[^z\n]*z\W*((z)|$))rrecompileDOTALL MULTILINEfindall groupindexr)boolescapesearchr delimiter doublequoteskipinitialspace) sniff_liner delimiters right_regexrestrregexpmatchesrr=nrrr dq_regexprr r r %workaround_csv_sniffer_bug_last_fieldsB     J rcsd}tttdjdddkrdd}tfdd|Ds0|d7}|durDtj ||d}t |||d t t g|}||fS) Nz, rDrc3s|]}|vVqdSrr )r+dliner r r-r.z"split_data_line..r!)r)rrr) rfield_size_limitrMctypesc_ulongvaluerQanyrrrnextreader)rrrrrr rr r8s   r8cCs|}t|}|r4|d}t|r t|\}}t|}nt|r0t|\}}t|}n t dt d|t ||}| dkrLt |||}||fS)aParse 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. >>> from scipy.io.arff._arffread import tokenize_attribute >>> 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) r5zmulti line not supported yetzFirst line unparsable: r) rQ r_attributer7r9 r_comattrvaltokenize_single_commar r_wcomattrvaltokenize_single_wcommar;rrPread_relational_attribute)iterable attributesattrmattrr<rtype next_itemr r r tokenize_attributes *           rc Cft|}|r,z|d}|d}W||fSty+}ztd|d}~wwtd|Nr5rz Error while tokenizing attributezError while tokenizing single )rr7r9rQ IndexErrorr;valr=rrer r r r<  rc Crr)rr7r9rQrr;rr r r rKrrcCstd|jd}||s;t|}|r2t|}|r+t||\}}|j|n t d|t |}||rt |}|S)z4Read the nested attributes of a relational attributez^@[Ee][Nn][Dd]\s*z\s*$Error parsing line ) rrrr7 r_headerlinerrrrr;r)ofilerelational_attributer,r_end_relationalr=isattrrr r r rZs"     rcCst|}t|rt|}t|s d}g}t|sXt|}|rOt|}|r6t||\}}||nt|}|rC| d}nt d|t|}nt|}t|r||fS)z&Read the header of the iterable ofile.Nr5r) r r_commentr7 r_datametarrrr r_relationr9r;)rr,relationrr=rrisrelr r r read_headerps*          rc@s@eZdZdZddZddZddZdd Zd d Zd d Z dS)raSmall container to keep useful information on a ARFF dataset. Knows about attributes names and types. Examples -------- :: data, meta = loadarff('iris.arff') # This will print the attributes names of the iris.arff dataset for i in meta: print(i) # This works too meta.names() # Getting attribute type types = meta.types() Methods ------- names types Notes ----- Also maintains the list of attributes in order, i.e., doing for i in meta, where meta is an instance of MetaData, will return the different attribute names in the order they were defined. cCs||_dd|D|_dS)NcSsi|]}|j|qSr )rrr r r sz%MetaData.__init__..)r _attributes)rrelrr r r rszMetaData.__init__cCspd}|d|jd7}|jD]'}|d|d|j|j7}|j|jr1|dt|j|j7}|d7}q|S)Nz Dataset: r z 's type is z , range is )rrr"rrCrFr r r __repr__s   zMetaData.__repr__cC t|jSr)iterrr#r r r __iter__s zMetaData.__iter__cCs|j|}|j|jfSr)rr"r)rkeyrr r r __getitem__s  zMetaData.__getitem__cCr)zReturn the list of attribute names. Returns ------- attrnames : list of str The attribute names. )rrr#r r r namess zMetaData.namescsfddjD}|S)zReturn the list of attribute types. Returns ------- attr_types : list of str The attribute types. csg|]}j|jqSr )rr")r+rr#r r rsz"MetaData.types..)r)r attr_typesr r#r typess zMetaData.typesN) rr r __doc__rrrrrrr r r r rs  rcCsJt|dr|}nt|}zt|W||ur|SS||ur$|ww)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') read)hasattropen _loadarffclose)frr r r rs F  rc szt|\}Wnty}z dt|}t||d}~wwd}D] }t|tr-d}q$t|}|r9tdtd fdd }t ||}t |dd D}||fS) Nz'Error while parsing header, error was: FTz*String attributes not supported yet, sorryr!c3s^tt}d}|D]!}t|st|rq t||\}tfdd|DVq dS)Ncsg|] }||qSr )r r*)rrr r rcsz0_loadarff..generator..)rrrr7r_emptyr8r:)row_iterrrrrrni)rr generatorIs z_loadarff..generatorcSrr rrr r r rgrz_loadarff..)r!) rr;rCr isinstancer\rNotImplementedErrorr)rrr) rrrrGhasstrrmetarrYr rr r*s(      rr)(rr|numpyrrr__all__rr_metarrrrrrr6rrrrOSErrorrrrr&rJr\r_rrrrr8rrrrrrrrr r r r sL           K>S3  2#EJ Q