Lg&SSKrSSKJr SSKJrJrJrJr SSKJr SSK J r SSK J r "SS5rSr1S krS S jrSS jrSS jrg)N) _pandas_api)CodecTable concat_tablesschema)_feather) FeatherErrorc<\rSrSrSrS SjrS SjrSrS SjrSr g) 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 cXlX lgN)pathsvalidate_schema)self path_or_pathsrs /lib/python3.12/site-packages/pyarrow/feather.py__init__FeatherDataset.__init__)s " .NcD[URSUS9nU/UlURUlURSSHIn[X1S9nUR(aUR X45 URR U5 MK [UR5$)z Read multiple feather files as a single pyarrow.Table Parameters ---------- columns : List[str] Names of columns to read from the file Returns ------- pyarrow.Table Content of the file as a table (of columns) rcolumnsN) read_tabler_tablesrrvalidate_schemasappendr)rr_filpathtables rrFeatherDataset.read_table-s$**Q-9v kk JJqrNDt5E##%%d2 LL   & # T\\**rcURRUR5(d/[SRXRUR55eg)Nz-Schema in {!s} was different. {!s} vs {!s})requals ValueErrorformat)rpiecer!s rrFeatherDataset.validate_schemasFsI{{!!%,,//2$fUKK%*\\34 40rc:URUS9RUS9$)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_pandasMs* w/99#:% %r)rrrr)Tr)NT) __name__ __module__ __qualname____firstlineno____doc__rrrr-__static_attributes__rrr r s /+24%rr c$URS:XagUR[R"5[R"54;a[ SR U55e[ SR U[UR555e)NrzqColumn '{}' exceeds 2GB maximum capacity of a Feather binary column. This restriction may be lifted in the futurezkColumn '{}' of type {} was chunked on conversion to Arrow and cannot be currently written to Feather format) num_chunkstypeextbinarystringr%r&str)namecols rcheck_chunked_overflowr?ass ~~ xxCJJL#**,//006t > > **0&s388}*EG Gr>lz4zstd uncompressedc [R(aN[R(a9[U[RR 5(aUR 5n[R"U5(aoUS:XaSnOUS:XaSnO [S5e[R"XS9nUS:Xa7[URR5HupXxn [X5 M OUnUS:Xa][UR 5[[#UR 55:a [S5eUb [S5eUb [S 5eOMUc[$R&"S 5(aS nO,Ub)U[(;a[S R+U[(55e[,R."XqUUXES 9 g![0aI [U[25(a2[4R6"U5 e![4R8a ef=fef=f)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 rFNz%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_framer@z1compression="{}" 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&r write_feather Exceptionr<osremoveerror) dfdestrGrHrIrJrEr!ir=r>s rrZrZss2  " "2{~~==>>B  $$ a<"N \!NDE E!!"D a<$U\\%7%78h&t19!| u!! "SU-?-?)@%A AFG G  "&' '  &' ' !  5#5#5k#B#BK%!::))/ 0I*KL L u 1B)2 E  dC   $ 88    s0!F99H G0/H 0HH HH c <[XUUS9R"SSU0UD6$)aN Read a pandas.DataFrame from Feather format. To read as pyarrow.Table use feather.read_table. Parameters ---------- source : str file path, or file-like object You can use MemoryMappedFile as source, for explicitly use memory map. columns : sequence, optional Only read a specific set of columns. If not provided, all columns are read. use_threads : bool, default True Whether to parallelize reading using multiple threads. If false the restriction is used in the conversion to Pandas as well as in the reading from Feather format. memory_map : boolean, default False Use memory mapping when opening file on disk, when source is a str. **kwargs Additional keyword arguments passed on to `pyarrow.Table.to_pandas`. Returns ------- df : pandas.DataFrame The contents of the Feather file as a pandas.DataFrame )r memory_mapr*r*r5r+)sourcerr*rckwargss r read_featherrfs<6 J !!* + N7B NFL NOrc4[R"XUS9nUcUR5$UVs/sHn[U5PM nn[ [ SU55(aUR U5nOb[ [ SU55(aURU5nO5UVs/sHoRPM n n[SRX55eURS:aU$[[U55U:XaU$URU5$s snfs snf)aO Read a pyarrow.Table from Feather format Parameters ---------- source : str file path, or file-like object You can use MemoryMappedFile as source, for explicitly use memory map. columns : sequence, optional Only read a specific set of columns. If not provided, all columns are read. memory_map : boolean, default False Use memory mapping when opening file on disk, when source is a str use_threads : bool, default True Whether to parallelize reading using multiple threads. Returns ------- table : pyarrow.Table The contents of the Feather file as a pyarrow.Table )use_memory_mapr*cU[:H$r)intts rread_table..scrcU[:H$r)r<rks rrmrns18rzAZZ>5;= = ~~ G  ( ||G$$'8 ?s D"D)NNNrD)NTF)NFT)r\pyarrow.pandas_compatr pyarrow.librrrrlibr9pyarrowrpyarrow._featherr r r?rYrZrfrr5rrrs`& -00)A%A%H G<AE*+Qh48!O@.%r