ó šxŠ\c@sådZddlmZddlmZddlmZddlmZddl m Z m Z ddl m Z mZd„Zd efd „ƒYZd efd „ƒYZd efd„ƒYZddddd„Zddd„ZdS(s parquet compat iÿÿÿÿ(t LooseVersion(tcatch_warnings(t string_types(tAbstractMethodError(t DataFramet get_option(tget_filepath_or_buffert is_s3_urlcCs¹|dkrtdƒ}n|dkrty tƒSWntk rEnXy tƒSWntk rdnXtdƒ‚n|dkrtdƒ‚n|dkr¢tƒS|dkrµtƒSdS( s return our implementation tautosio.parquet.engines}Unable to find a usable engine; tried using: 'pyarrow', 'fastparquet'. pyarrow or fastparquet is required for parquet supporttpyarrowt fastparquets.engine must be one of 'pyarrow', 'fastparquet'N(R R (Rt PyArrowImplt ImportErrortFastParquetImplt ValueError(tengine((s0lib/python2.7/site-packages/pandas/io/parquet.pyt get_engines$         tBaseImplcBs2eZdZed„ƒZd„Zdd„ZRS(cCszt|tƒstdƒ‚n|jjddhkrEtdƒ‚ntd„|jjDƒƒ}|svtdƒ‚ndS(Ns+to_parquet only supports IO with DataFrameststringtunicodes%parquet must have string column namescss*|] }|dk rt|tƒVqdS(N(tNonet isinstanceR(t.0tname((s0lib/python2.7/site-packages/pandas/io/parquet.pys >ss!Index level names must be strings(RRRtcolumnst inferred_typetalltindextnames(tdft valid_names((s0lib/python2.7/site-packages/pandas/io/parquet.pytvalidate_dataframe2scKst|ƒ‚dS(N(R(tselfRtpatht compressiontkwargs((s0lib/python2.7/site-packages/pandas/io/parquet.pytwriteEscKst|ƒ‚dS(N(R(R R!RR#((s0lib/python2.7/site-packages/pandas/io/parquet.pytreadHsN(t__name__t __module__Rtapit staticmethodRR$R%(((s0lib/python2.7/site-packages/pandas/io/parquet.pyR.s R cBs2eZd„Zddddd„Zdd„ZRS(cCsmyddl}ddl}Wntk r;tdƒ‚nXt|jƒdkr`tdƒ‚n||_dS(Niÿÿÿÿs‹pyarrow is required for parquet support you can install via conda conda install pyarrow -c conda-forge or via pip pip install -U pyarrow s0.9.0s”pyarrow >= 0.9.0 is required for parquet support you can install via conda conda install pyarrow -c conda-forge or via pip pip install -U pyarrow (R tpyarrow.parquetR Rt __version__R((R R ((s0lib/python2.7/site-packages/pandas/io/parquet.pyt__init__Ns    tsnappytmsc KsÈ|j|ƒt|ddƒ\}}}}|dkr@i} n i|d6} |jjj|| } |dk rŸ|jjj| |d|d|d||n%|jjj| |d|d||dS(Ntmodetwbtpreserve_indexR"tcoerce_timestampstpartition_cols( RRRR(tTablet from_pandastparquettwrite_to_datasett write_table( R RR!R"R2RR3R#t_tfrom_pandas_kwargsttable((s0lib/python2.7/site-packages/pandas/io/parquet.pyR$gs        cKskt|ƒ\}}}}t|d<|jjj|d||jƒ}|rgy|jƒWqgqgXn|S(Ntuse_pandas_metadataR(RtTrueR(R6t read_tablet to_pandastclose(R R!RR#R9t should_closetresult((s0lib/python2.7/site-packages/pandas/io/parquet.pyR%|s N(R&R'R,RR$R%(((s0lib/python2.7/site-packages/pandas/io/parquet.pyR Ls R cBs/eZd„Zdddd„Zdd„ZRS(cCsayddl}Wntk r/tdƒ‚nXt|jƒdkrTtdƒ‚n||_dS(Niÿÿÿÿs–fastparquet is required for parquet support you can install via conda conda install fastparquet -c conda-forge or via pip pip install -U fastparquets0.2.1sŸfastparquet >= 0.2.1 is required for parquet support you can install via conda conda install fastparquet -c conda-forge or via pip pip install -U fastparquet(R R RR+R((R R ((s0lib/python2.7/site-packages/pandas/io/parquet.pyR,s   R-cKsÿ|j|ƒd|kr4|dk r4tdƒ‚nd|krR|jdƒ}n|dk rkd|d¼st open_withtrecordR"t write_index( RRRtpopRRRR=R(R$(R RR!R"RR3R#R9((s0lib/python2.7/site-packages/pandas/io/parquet.pyR$¥s      cKs”t|ƒrWt|ƒ\}}}}z"|jj|d|jjƒ}Wd|jƒXn*t|ƒ\}}}}|jj|ƒ}|jd||S(NRGR(RRR(t ParquetFilets3topenR@R?(R R!RR#RLR9RAt parquet_file((s0lib/python2.7/site-packages/pandas/io/parquet.pyR%Ås "N(R&R'R,RR$R%(((s0lib/python2.7/site-packages/pandas/io/parquet.pyR ‹s  RR-c Ks1t|ƒ}|j||d|d|d||S(sÒ Write a DataFrame to the parquet format. Parameters ---------- path : str File path or Root Directory path. Will be used as Root Directory path while writing a partitioned dataset. .. versionchanged:: 0.24.0 engine : {'auto', 'pyarrow', 'fastparquet'}, default 'auto' Parquet library to use. If 'auto', then the option ``io.parquet.engine`` is used. The default ``io.parquet.engine`` behavior is to try 'pyarrow', falling back to 'fastparquet' if 'pyarrow' is unavailable. compression : {'snappy', 'gzip', 'brotli', None}, default 'snappy' Name of the compression to use. Use ``None`` for no compression. index : bool, default None If ``True``, include the dataframe's index(es) in the file output. If ``False``, they will not be written to the file. If ``None``, the engine's default behavior will be used. .. versionadded 0.24.0 partition_cols : list, optional, default None Column names by which to partition the dataset Columns are partitioned in the order they are given .. versionadded:: 0.24.0 kwargs Additional keyword arguments passed to the engine R"RR3(RR$(RR!RR"RR3R#timpl((s0lib/python2.7/site-packages/pandas/io/parquet.pyt to_parquetÖs$ cKs"t|ƒ}|j|d||S(s¦ Load a parquet object from the file path, returning a DataFrame. .. versionadded 0.21.0 Parameters ---------- path : string File path columns : list, default=None If not None, only these columns will be read from the file. .. versionadded 0.21.1 engine : {'auto', 'pyarrow', 'fastparquet'}, default 'auto' Parquet library to use. If 'auto', then the option ``io.parquet.engine`` is used. The default ``io.parquet.engine`` behavior is to try 'pyarrow', falling back to 'fastparquet' if 'pyarrow' is unavailable. kwargs are passed to the engine Returns ------- DataFrame R(RR%(R!RRR#RO((s0lib/python2.7/site-packages/pandas/io/parquet.pyt read_parquetÿs N(t__doc__tdistutils.versionRtwarningsRt pandas.compatRt pandas.errorsRtpandasRRtpandas.io.commonRRRtobjectRR R RRPRQ(((s0lib/python2.7/site-packages/pandas/io/parquet.pyts ?K  (