a jL@sdZddlZddlZddlmZddlmZddlmZddl Z ddl Z ddl mZddlmZdd lmZmZdd lmZdd lmZeeed d dZeee jd ddZddZdddZdddZdddZdS)z9Implementation of ARFF parsers: via LIAC-ARFF and pandas.N) OrderedDict) Generator)List)_arff)ArffSparseDataType)chunk_generatorget_chunk_n_rows)check_pandas_support) pd_fillna) arff_datainclude_columnsreturncCstttf}ddt|D}t|d|d|dD]@\}}}||vr:|d||d||d||q:|S)aObtains several columns from sparse ARFF representation. Additionally, the column indices are re-labelled, given the columns that are not included. (e.g., when including [1, 2, 3], the columns will be relabelled to [0, 1, 2]). Parameters ---------- arff_data : tuple A tuple of three lists of equal size; first list indicating the value, second the x coordinate and the third the y coordinate. include_columns : list A list of columns to include. Returns ------- arff_data_new : tuple Subset of arff data with only the include columns indicated by the include_columns argument. cSsi|]\}}||qSr.0Z array_idxZ column_idxrrCE:\soccer\ml_env\Lib\site-packages\sklearn/datasets/_arff_parser.py .sz)_split_sparse_columns..rr)list enumeratezipappend)r r Z arff_data_newreindexed_columnsvalrow_idxcol_idxrrr_split_sparse_columnss"rc Cs~t|dd}|t|f}ddt|D}tj|tjd}t|d|d|dD]"\}}}||vrV|||||f<qV|S)NrcSsi|]\}}||qSrrrrrrr@sz)_sparse_data_to_array..dtyperr)maxlenrnpemptyfloat64r) r r num_obsZy_shaperyrrrrrr_sparse_data_to_array9s "r'cCsD||}t|dkr||}nt|dkr8||d}nd}||fS)a Post process a dataframe to select the desired columns in `X` and `y`. Parameters ---------- frame : dataframe The dataframe to split into `X` and `y`. feature_names : list of str The list of feature names to populate `X`. target_names : list of str The list of target names to populate `y`. Returns ------- X : dataframe The dataframe containing the features. y : {series, dataframe} or None The series or dataframe containing the target. rrrN)r!)frameZ feature_namesZ target_namesXr&rrr_post_process_frameKs   r*c"sdd}||}|dkrtjntj}|dk } tj||| d} ||fdd| dD|dkrtd } t| d} t| } t| d }| j |g| d d }|j d d }t |}fdd| D}||g}t | d |D]}|| j || d d |qt|dkr,|d|dj|d<| j|d d}t| |}~~i}|jD]P}|d}|dkrzd||<n&|dkrd||<n|j|||<qR||}t|||\}n| d }fdd|D}fdd|D}t|trt|dur td|ddkr d}n|d|d}tjtj|d|d }|j|}|dd|f}|dd|fnt|t rt!||}t"|dd}|t|f} t#j$j%|d|d|dff| tj&d!}|'}t(||ntd"t)|fd#d$|D}!|!sn._io_to_generatorsparsepandas) return_typeencode_nominalcs(i|] \}}t|tr|vr||qSr) isinstancer)rnamecatcolumns_to_selectrrrsz%_liac_arff_parser.. attributeszfetch_openml with as_frame=TruedataF)columnscopyT)deepcsg|]}|vr|qSrrrcolr7rr z%_liac_arff_parser..rrr)Z ignore_index data_typeintegerInt64nominalcategorycsg|]}t|dqSindexintrcol_nameopenml_columns_inforrr@scsg|]}t|dqSrGrIrKrMrrr@sNz6shape must be provided when arr['data'] is a Generatorr$)rcount)shaperz-Unexpected type for data obtained from arff: csh|] }|vqSrrrK) categoriesrr sz$_liac_arff_parser..c sJg|]B\}}ttj|dddd||dfjtddqS)OrNrF)r<)r"ZtakeZasarraypopastyperJ)rirL)rRr&rrr@s  zAMix of nominal and non-nominal targets is not currently supported)rO)/rZCOOZ DENSE_GENloadr rrkeysnextZ DataFrameZ memory_usagesumr rrr!rVdtypesconcatr r;lowerr*r4r ValueErrorr"Zfromiter itertoolschain from_iterableZreshapetuplerr spr0Z coo_matrixr$Ztocsrr'typeallZhstackranyrQ)"r-output_arrays_typerNfeature_names_to_selecttarget_names_to_selectrQr/streamr2r3Zarff_containerpdZ columns_infoZ columns_names first_rowZfirst_dfZ row_bytes chunksizecolumns_to_keepdfsr:r(r\r5 column_dtyper)r Zfeature_indices_to_selectZtarget_indices_to_selectrPZ arff_data_Xr%ZX_shapeZis_classificationr)rRr8rNr&r_liac_arff_parserks7                                rrc sddl|D]}|ddr q*q i|D]:}||d}|dkrXd|<q2|dkr2d |<q2fd d t|D} dd d gd dddd| d } i| |pi}j|fi|} zdd|D| _Wn4ty} zj d| WYd} ~ n d} ~ 00||fdd| jD} | | } t dfdd}fdd| j D}|D]}| |j|| |<q`t| ||\}}|dkr||| dfS||}}fdd | j D}||d|fS)a^ARFF parser using `pandas.read_csv`. This parser uses the metadata fetched directly from OpenML and skips the metadata headers of ARFF file itself. The data is loaded as a CSV file. Parameters ---------- gzip_file : GzipFile instance The GZip compressed file with the ARFF formatted payload. output_arrays_type : {"numpy", "sparse", "pandas"} The type of the arrays that will be returned. The possibilities are: - `"numpy"`: both `X` and `y` will be NumPy arrays; - `"sparse"`: `X` will be sparse matrix and `y` will be a NumPy array; - `"pandas"`: `X` will be a pandas DataFrame and `y` will be either a pandas Series or DataFrame. openml_columns_info : dict The information provided by OpenML regarding the columns of the ARFF file. feature_names_to_select : list of str A list of the feature names to be selected to build `X`. target_names_to_select : list of str A list of the target names to be selected to build `y`. read_csv_kwargs : dict, default=None Keyword arguments to pass to `pandas.read_csv`. It allows to overwrite the default options. Returns ------- X : {ndarray, sparse matrix, dataframe} The data matrix. y : {ndarray, dataframe, series} The target. frame : dataframe or None A dataframe containing both `X` and `y`. `None` if `output_array_type != "pandas"`. categories : list of str or None The names of the features that are categorical. `None` if `output_array_type == "pandas"`. rNr+z@datarBrCrDrErFcs"i|]\}}|vr||qSrr)rrr5)r\rrrsz'_pandas_arff_parser..F?%"T\) headerZ index_colZ na_valuesZkeep_default_nacomment quotecharskipinitialspace escapecharrcSsg|]}|qSrr)rr5rrrr@rAz'_pandas_arff_parser..zwThe number of columns provided by OpenML does not match the number of columns inferred by pandas when reading the file.csg|]}|vr|qSrrr>r7rrr@rAz^'(?P.*)'$cs"t|}|dur|S|dS)Ncontents)researchgroup)Z input_stringmatch)single_quote_patternrrstrip_single_quotess z0_pandas_arff_parser..strip_single_quotescs g|]\}}t|jr|qSr)r4CategoricalDtyperr5rrlrrr@s r1cs(i|] \}}t|jr||jqSr)r4rrRtolistrrrrrs )r1r,r^ startswithrZread_csvr;r_errorsZ ParserErrorr}compiler\itemsr6Zrename_categoriesr*Zto_numpy)r-rhrNrirjread_csv_kwargsr.r5rqZdtypes_positionalZdefault_read_csv_kwargsr(excrorZcategorical_columnsr?r)r&rRr)r8r\rlrr_pandas_arff_parser7sh8             rcCsH|dkrt||||||S|dkr4t||||||Std|ddS)a6Load a compressed ARFF file using a given parser. Parameters ---------- gzip_file : GzipFile instance The file compressed to be read. parser : {"pandas", "liac-arff"} The parser used to parse the ARFF file. "pandas" is recommended but only supports loading dense datasets. output_type : {"numpy", "sparse", "pandas"} The type of the arrays that will be returned. The possibilities ara: - `"numpy"`: both `X` and `y` will be NumPy arrays; - `"sparse"`: `X` will be sparse matrix and `y` will be a NumPy array; - `"pandas"`: `X` will be a pandas DataFrame and `y` will be either a pandas Series or DataFrame. openml_columns_info : dict The information provided by OpenML regarding the columns of the ARFF file. feature_names_to_select : list of str A list of the feature names to be selected. target_names_to_select : list of str A list of the target names to be selected. read_csv_kwargs : dict, default=None Keyword arguments to pass to `pandas.read_csv`. It allows to overwrite the default options. Returns ------- X : {ndarray, sparse matrix, dataframe} The data matrix. y : {ndarray, dataframe, series} The target. frame : dataframe or None A dataframe containing both `X` and `y`. `None` if `output_array_type != "pandas"`. categories : list of str or None The names of the features that are categorical. `None` if `output_array_type == "pandas"`. z liac-arffr1zUnknown parser: 'z%'. Should be 'liac-arff' or 'pandas'.N)rrrr_)r-parser output_typerNrirjrQrrrrload_arff_from_gzip_files*;  r)N)N)NN)__doc__r`r} collectionsrcollections.abcrtypingrnumpyr"ZscipyrdZ externalsrZexternals._arffrZutils._chunkingrr Zutils._optional_dependenciesr Z utils.fixesr rZndarrayr'r*rrrrrrrrs8        $ & S