aEj%SSKrSSKrSSKJrJrJrJrJrJ r J r J r J r J r JrJrJrJrJrJrJr SSKJr "SS\R,5rSr\S-S-r"SS \R45r"S S \R85r"S S \R<5rSr Sr!SS.Sjr"S\S3\"l#SSS.Sjr$SSS.Sjr%S\S3\%l#S SSS.Sjjr&SSS.Sjr'SS.Sjr(g)!N)IpcReadOptionsIpcWriteOptions ReadStats WriteStatsMessage MessageReaderRecordBatchReader_ReadPandasMixinMetadataVersion Alignment read_messageread_record_batch read_schema read_tensor write_tensorget_record_batch_sizeget_tensor_sizec(\rSrSrSrSSS.SjrSrg)RecordBatchStreamReader"a Reader for the Arrow streaming binary format. Parameters ---------- source : bytes/buffer-like, pyarrow.NativeFile, or file-like Python object Either an in-memory buffer, or a readable file object. If you want to use memory map use MemoryMappedFile as source. options : pyarrow.ipc.IpcReadOptions Options for IPC deserialization. If None, default values will be used. memory_pool : MemoryPool, default None If None, default memory pool is used. Noptions memory_poolc:[U5nURXUS9 g)Nr _ensure_default_ipc_read_options_open)selfsourcerrs H/home/mande/repo/quber/.venv/lib/python3.13/site-packages/pyarrow/ipc.py__init__ RecordBatchStreamReader.__init__2s27; 6 D__name__ __module__ __qualname____firstlineno____doc__r!__static_attributes__r$r#r rr"s +/DEEr#raOParameters ---------- sink : str, pyarrow.NativeFile, or file-like Python object Either a file path, or a writable file object. schema : pyarrow.Schema The Arrow schema for data to be written to the file. options : pyarrow.ipc.IpcWriteOptions Options for IPC serialization. If None, default values will be used: the legacy format will not be used unless overridden by setting the environment variable ARROW_PRE_0_15_IPC_FORMAT=1, and the V5 metadata version will be used unless overridden by setting the environment variable ARROW_PRE_1_0_METADATA_VERSION=1. zmetadata : dict | pyarrow.KeyValueMetadata, optional Key/value pairs (both must be bytes-like) that will be stored in the file footer and are retrievable via pyarrow.ipc.open_file(...).metadata.c,\rSrSrS\3rSS.SjrSrg)RecordBatchStreamWriterSz.Writer for the Arrow streaming binary format Nrc:[U5nURXUS9 gNr0_get_legacy_format_defaultr)rsinkschemars r r! RecordBatchStreamWriter.__init__Xs,W5 4 1r#r$)r&r'r(r)_ipc_writer_class_docr*r!r+r$r#r r.r.Ss#G1522r#r.c,\rSrSrSrSSSS.SjjrSrg)RecordBatchFileReader]a Class for reading Arrow record batch data from the Arrow binary file format Parameters ---------- source : bytes/buffer-like, pyarrow.NativeFile, or file-like Python object Either an in-memory buffer, or a readable file object. If you want to use memory map use MemoryMappedFile as source. footer_offset : int, default None If the file is embedded in some larger file, this is the byte offset to the very end of the file data options : pyarrow.ipc.IpcReadOptions Options for IPC serialization. If None, default values will be used. memory_pool : MemoryPool, default None If None, default memory pool is used. Nrc:[U5nURXX4S9 g)N footer_offsetrrr)rrr>rrs r r!RecordBatchFileReader.__init__ps"27; 6"  =r#r$Nr%r$r#r r:r:]s$=d!==r#r:c.\rSrSrS\3rSSS.SjrSrg)RecordBatchFileWriterwz/Writer to create the Arrow binary file format Nrmetadatac:[U5nURXX4S9 gNrDr3)rr5r6rrEs r r!RecordBatchFileWriter.__init__}s,W5 4 Dr#r$)r&r'r(r)_ipc_file_writer_class_docr*r!r+r$r#r rBrBws' G15tEEr#rBcU(a.[U[5(d[S[U535eU$[R n[ [[RRSS555n[ [[RRSS555(a[Rn[UUS9$)Nzexpected IpcWriteOptions, got ARROW_PRE_0_15_IPC_FORMAT0ARROW_PRE_1_0_METADATA_VERSION)use_legacy_formatmetadata_version) isinstancer TypeErrortyper V5boolintosenvirongetV4)rrOrNs r r4r4s'?33,< >>r#cU(a,[U[5(d[S[U535eU=(d [5$)Nzexpected IpcReadOptions, got )rPrrQrRr0s r rrs6z'>::7W GHH  &n&&r#r0c[XUS9$r2)r.)r5r6rs r new_streamr\s "4+2 44r#z5Create an Arrow columnar IPC stream writer instance zS Returns ------- writer : RecordBatchStreamWriter A writer for the given sink rc[XUS9$)a Create reader for Arrow streaming format. Parameters ---------- source : bytes/buffer-like, pyarrow.NativeFile, or file-like Python object Either an in-memory buffer, or a readable file object. options : pyarrow.ipc.IpcReadOptions Options for IPC serialization. If None, default values will be used. memory_pool : MemoryPool, default None If None, default memory pool is used. Returns ------- reader : RecordBatchStreamReader A reader for the given source r)r)rrrs r open_streamr^s& #6/: <rrs r open_filerbs, ! 22r#nthreadspreserve_indexc<[RRXUS9n[R"5n[R"XCR 5nUR U5 SSS5 UR5$!,(df  UR5$=f)a` Serialize a pandas DataFrame into a buffer protocol compatible object. Parameters ---------- df : pandas.DataFrame nthreads : int, default None Number of threads to use for conversion to Arrow, default all CPUs. preserve_index : bool, default None The default of None will store the index as a column, except for RangeIndex which is stored as metadata only. If True, always preserve the pandas index data as a column. If False, no index information is saved and the result will have a default RangeIndex. Returns ------- buf : buffer An object compatible with the buffer protocol. rcN)pa RecordBatch from_pandasBufferOutputStreamr.r6 write_batchgetvalue)dfrdrebatchr5writers r serialize_pandasrpsy( NN & &r6D ' FE "D # #D,, 765! 8 ==? 8 7 ==?s A>> BT use_threadsc[R"U5n[R"U5nUR5nSSS5 WR US9$!,(df  N=f)aZDeserialize a buffer protocol compatible object into a pandas DataFrame. Parameters ---------- buf : buffer An object compatible with the buffer protocol. use_threads : bool, default True Whether to parallelize the conversion using multiple threads. Returns ------- df : pandas.DataFrame The buffer deserialized as pandas DataFrame Nrq)rg BufferReaderrread_all to_pandas)bufrr buffer_readerreadertables r deserialize_pandasr{sMOOC(M # #M 2f! 3 ??{? 33 3 2s A A#r@))rVpyarrowrg pyarrow.librrrrrrr r r r r rrrrrrlib_RecordBatchStreamReaderrr8rI_RecordBatchStreamWriterr._RecordBatchFileReaderr:_RecordBatchFileWriterrBr4rr\r*r^r`rbrpr{r$r#r rs)( AAAAAEc::E*)$  ,,2c::2=C66=4EC66E >' )-4   $(T<.'+TS 2Tt26&*$8,04r#