U _{j2J@sdZddlZddlZddlmZddlmZddlmZddl Z ddl Z ddl mZddlmZdd lmZmZmZeeed d d Zeee jd d dZddZdddZdddZdddZdS)z9Implementation of ARFF parsers: via LIAC-ARFF and pandas.N) OrderedDict) Generator)List)_arff)ArffSparseDataType)_chunk_generatorcheck_pandas_supportget_chunk_n_rows) arff_datainclude_columnsreturncCstttf}ddt|D}t|d|d|dD]@\}}}||kr:|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_idxrr\/var/www/html/bwave/python/venv/lib/python3.8/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]"\}}}||krV|||||f<qV|S)NrcSsi|]\}}||qSrrrrrrr>sz)_sparse_data_to_array..dtyperr)maxlenrnpemptyfloat64r) r r num_obsZy_shaperyrrrrrr_sparse_data_to_array7s "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_frameIs   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 djtjd}~~i}|jD]P}|d}|dkrzd||<n&|dkrd||<n|j|||<qR||}t|||\}n| d }fdd|D}fdd|D}t|trt|dkr 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|kr||qSr) isinstancer)rnamecatcolumns_to_selectrrrs  z%_liac_arff_parser.. attributeszfetch_openml with as_frame=TruedataF)columnscopyT)deepcsg|]}|kr|qSrrrcolr6rr sz%_liac_arff_parser..rrr)Z ignore_index)value data_typeintegerInt64nominalcategorycsg|]}t|dqSindexintrcol_nameopenml_columns_inforrr?scsg|]}t|dqSrFrHrJrLrrr?sNz6shape must be provided when arr['data'] is a Generatorr#)rcount)shaperz-Unexpected type for data obtained from arff: csh|] }|kqSrrrJ) categoriesrr sz$_liac_arff_parser..c sJg|]B\}}ttj|dddd||dfjtddqS)OrNrF)r;)r!ZtakeZasarraypopastyperI)rirK)rQr%rrr?s  zAMix of nominal and non-nominal targets is not currently supported)rN)0rZCOOZ DENSE_GENloadr rrkeysnextZ DataFrameZ memory_usagesumr rrr rUdtypesconcatZfillnar!nanr:lowerr)r3r ValueErrorZfromiter itertoolschain from_iterableZreshapetuplerrspr/Z coo_matrixr#Ztocsrr&typeallZhstackranyrP)"r,output_arrays_typerMfeature_names_to_selecttarget_names_to_selectrPr.streamr1r2Zarff_containerpdZ columns_infoZ columns_names first_rowZfirst_dfZ row_bytes chunksizecolumns_to_keepdfsr9r'r[r4 column_dtyper(r Zfeature_indices_to_selectZtarget_indices_to_selectrOZ arff_data_Xr$ZX_shapeZis_classificationr)rQr7rMr%r_liac_arff_parseris7                               rrc sddl|D]}|ddr q*q i|D]:}||d}|dkrXd|<q2|dkr2d |<q2fd d t|D} dd d gd dddd| d } | |pi}j|f|} zdd|D| _Wn0tk r} zj d| W5d} ~ XYnX||fdd| jD} | | } t dfdd}fdd| j D}|D]}| |j|| |<qTt| ||\}}|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@datarArBrCrDrEcs"i|]\}}|kr||qSrr)rrr4)r[rrr~sz'_pandas_arff_parser..F?%"T\) headerZ index_colZ na_valuesZkeep_default_nacomment quotecharskipinitialspace escapecharrcSsg|]}|qSrr)rr4rrrr?sz'_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|]}|kr|qSrrr=r6rrr?sz^'(?P.*)'$cs"t|}|dkr|S|dS)Ncontents)researchgroup)Z input_stringmatch)single_quote_patternrrstrip_single_quotess z0_pandas_arff_parser..strip_single_quotescs g|]\}}t|jr|qSr)r3CategoricalDtyperr4rrlrrr?s r0cs(i|] \}}t|jr||jqSr)r3rrQtolistrrrrrs )r0r+r^ startswithrZread_csvr:r_errorsZ ParserErrorr}compiler[itemsr5Zrename_categoriesr)Zto_numpy)r,rhrMrirjread_csv_kwargsr-r4rqZdtypes_positionalZdefault_read_csv_kwargsr'excrorZcategorical_columnsr>r(r%rQr)r7r[rlrr_pandas_arff_parser4sh8             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-arffr0zUnknown parser: 'z%'. Should be 'liac-arff' or 'pandas'.N)rrrr_)r,parser output_typerMrirjrPrrrrload_arff_from_gzip_files*;  r)N)N)NN)__doc__r`r} collectionsrcollections.abcrtypingrnumpyr!ZscipyrdZ externalsrZexternals._arffrutilsrr r rZndarrayr&r)rrrrrrrrs8      $ & R