+ JV-j&^RIHt^RIt^RIHt^RIHtHtHtH t ^RIH t ^RI H t ^RIHt!RR4tR t0R mtRR ltRR ltRR ltR#))SequenceN) _pandas_api)CodecTable concat_tablesschema)_feather) FeatherErrorcHa]tRt^toRtRRltR RltRtR RltRt Vt R#) FeatherDatasetz Encapsulates details of reading a list of Feather files. Parameters ---------- path_or_paths : List[str] A list of file names validate_schema : bool, default True Check that individual file schemas are all the same / compatible cWnW nR#N)pathsvalidate_schema)self path_or_pathsrs&&&`/Volumes/fast/ai/experiments/ui-tars-smoke/.venv/lib/python3.14/site-packages/pyarrow/feather.py__init__FeatherDataset.__init__*s " .Nc b\VP^,VR7pV.VnVPVnVPR,FMp\W1R7pVP'dVP W44VPP V4KO \VP4#)z Read multiple feather files as a single pyarrow.Table Parameters ---------- columns : List[str] Names of columns to read from the file Returns ------- pyarrow.Table Content of the file as a table (of columns) columns:NN) read_tabler_tablesrrvalidate_schemasappendr)rr_filpathtables&& rrFeatherDataset.read_table.s$**Q-9v kk JJrNNDt5E###%%d2 LL   & # T\\**rcVPPVP4'g)\RV RVP RVP 24hR#)z Schema in z was different. z vs N)requals ValueError)rpiecer!s&&&rrFeatherDataset.validate_schemasGsQ{{!!%,,//z%0B $ }Ju||nFG G0rc FVPVR7PVR7#)aA Read multiple Parquet files as a single pandas DataFrame Parameters ---------- columns : List[str] Names of columns to read from the file use_threads : bool, default True Use multiple threads when converting to pandas Returns ------- pandas.DataFrame Content of the file as a pandas DataFrame (of columns) r) use_threadsr to_pandas)rrr)s&&&r read_pandasFeatherDataset.read_pandasLs* w/99#:% %r)rrrr)Tr)NT) __name__ __module__ __qualname____firstlineno____doc__rrrr,__static_attributes____classdictcell__) __classdict__s@rr r s$ /+2G %%rr cVP^8XdR#VP\P!4\P!439d\ RV R24h\ RV RVP R24h)rNzColumn 'zg' exceeds 2GB maximum capacity of a Feather binary column. This restriction may be lifted in the futurez ' of type zU was chunked on conversion to Arrow and cannot be currently written to Feather format) num_chunkstypeextbinarystringr%)namecols&&rcheck_chunked_overflowr>`sw ~~ xxCJJL#**,//8D6*001 1 tfJsxxj1@ @  rc D\P'dQ\P'd;\V\PP 4'dVP 4p\P!V4'dzV^8XdRpMV^8XdRpM \R4h\P!WR7pV^8Xd<\VPP4FwrWx,p \W4K MTpV^8Xda\VP 4\\#VP 448d \R4hVe \R4hVe \R4hMGVf \$P&!R4'dR pM$Ve!V\(9d\R V R \( 24h\*P,!WqVVWER 7R# \.dL\T\04'd4\2P4!T4h \2P6dhi;ihi;i) aF Write a pandas.DataFrame to Feather format. Parameters ---------- df : pandas.DataFrame or pyarrow.Table Data to write out as Feather format. dest : str Local destination path. compression : string, default None Can be one of {"zstd", "lz4", "uncompressed"}. The default of None uses LZ4 for V2 files if it is available, otherwise uncompressed. compression_level : int, default None Use a compression level particular to the chosen compressor. If None use the default compression level chunksize : int, default None For V2 files, the internal maximum size of Arrow RecordBatch chunks when writing the Arrow IPC file format. None means use the default, which is currently 64K version : int, default 2 Feather file version. Version 2 is the current. Version 1 is the more limited legacy format FNz%Version value should either be 1 or 2)preserve_indexz'cannot serialize duplicate column namesz2Feather V1 files do not support compression optionz0Feather V1 files do not support chunksize option lz4_framelz4z compression="z " not supported, must be one of ) compressioncompression_level chunksizeversion)r have_pandas has_sparse isinstancepdSparseDataFrameto_dense is_data_framer%r from_pandas enumeraternamesr>len column_namessetr is_available_FEATHER_SUPPORTED_CODECSr write_feather Exceptionstrosremoveerror) dfdestrCrDrErFr@r!ir<r=s &&&&&& rrVrVss2  " " "2{~~==>>B  $$ a<"N \!NDE E!!"D a<$U\\%7%78h&t19!| u!! "SU-?-?)@%A AFG G  "&' '  &' ' !  5#5#5k#B#BK%!::}[M:''@&ACD D u 1B)2 E  dC   $ 88    s0-G !H+HHHHHHc B\WVVR7P!RRV/VB#)aN Read a pandas.DataFrame from Feather format. To read as pyarrow.Table use feather.read_table. Parameters ---------- source : str file path, or file-like object You can use MemoryMappedFile as source, for explicitly use memory map. columns : sequence, optional Only read a specific set of columns. If not provided, all columns are read. use_threads : bool, default True Whether to parallelize reading using multiple threads. If false the restriction is used in the conversion to Pandas as well as in the reading from Feather format. memory_map : boolean, default False Use memory mapping when opening file on disk, when source is a str. **kwargs Additional keyword arguments passed on to `pyarrow.Table.to_pandas`. Returns ------- df : pandas.DataFrame The contents of the Feather file as a pandas.DataFrame )r memory_mapr)r)r*)sourcerr)r`kwargss&&&&,r read_featherrds<6 J !!* + N7B NFL NOrc\P!WVR7pVfVP4#\V\4'g.\ RP \V4P44hVUu.uFp\V4NK pp\\RV44'dVPV4pMY\\RV44'dVPV4pM+VUu.uFqPNK p p\ RV RV 24hVP^8dV#\\V44V8XdV#VP!V4#uupiuupi)aO Read a pyarrow.Table from Feather format Parameters ---------- source : str file path, or file-like object You can use MemoryMappedFile as source, for explicitly use memory map. columns : sequence, optional Only read a specific set of columns. If not provided, all columns are read. memory_map : boolean, default False Use memory mapping when opening file on disk, when source is a str use_threads : bool, default True Whether to parallelize reading using multiple threads. Returns ------- table : pyarrow.Table The contents of the Feather file as a pyarrow.Table )use_memory_mapr)z&Columns must be a sequence but, got {}cV\8H#r)intts&rread_table..scrcV\8H#r)rXris&rrkrls18rz.Columns must be indices or names. Got columns z of types )r FeatherReaderreadrIr TypeErrorformatr8r.allmap read_indices read_namesrFsortedrSselect) rbrr`r)readercolumn column_typesr!rjcolumn_type_namess &&&& rrrs@* # #{DF{{} gx ( (@W 6 679 9077wVDLwL7 3!< 011##G, S#\ 2 3 3!!'*1=>AZZ>''.iz:K9LNO O~~ G  ( ||G$$%8 ?s 4E*E>rBzstd uncompressed)NNN)NTF)NFT)collections.abcrrYpyarrow.pandas_compatr pyarrow.librrrrlibr9pyarrowr pyarrow._featherr r r>rUrVrdrrarrrsN&% -00)?%?%D  <PfO@1%r