x\c@s[ddlmZddlZddlZddljjZddlm Z ddl m Z m Z m Z mZddlmZddlmZddlmZmZmZmZmZmZddlmZdd lmZmZmZm Z m!Z!dd l"m#Z#dd l$m%Z%d d l&m'Z'd dl(m)Z)m*Z*ej+Z+ej,Z,dZ-ddde/dde0de/d Z1de2fdYZ3de3fdYZ4de3fdYZ5de5fdYZ6ddde/e/e/e/e0e0dde0dddZ7defd YZ8d!e2fd"YZ9d#e9fd$YZ:d%e9fd&YZ;dS('i(tisliceN(tiNaT(tStringIOtlongtto_strtu(tAbstractMethodError(tis_period_dtype(t DataFramet MultiIndextSeriestcompattisnat to_datetime(tconcat(t BaseIteratort _get_handlet_infer_compressiont_stringify_pathtget_filepath_or_buffer(t pprint_thing(t_validate_integeri(t_convert_to_line_delimits(tbuild_table_schematparse_table_schemas0.20.0tepochi tmstinferc Cs| r"|dkr"tdnt|}|rO|dkrOtdn|dkrt|tr|jd|jpd}n|dkrt|trt} n<t|trt} n$t|trt } n t d| |d |d |d |d |d |d|d| j } |r9t | } nt|t jrt|dd| \} }z| j | Wd| jXn|dkr| S|j | dS(Ntsplitttables?'index=False' is only valid when 'orient' is 'split' or 'table'trecordss3'lines' keyword only valid when 'orient' is recordstnametvaluess''obj' should be a Series or a DataFrametorientt date_formattdouble_precisiont ensure_asciit date_unittdefault_handlertindextwt compression(RR(t ValueErrorRt isinstanceR tto_frameRRtJSONTableWritert SeriesWritert FrameWritertNotImplementedErrortwriteRR t string_typesRtclosetNone(t path_or_buftobjR!R"R#t force_asciiR%R&tlinesR)R'twritertstfhthandles((s2lib/python2.7/site-packages/pandas/io/json/json.pytto_json!s<         tWritercBs/eZddZdZdZdZRS(c Csw||_|dkr!|j}n||_||_||_||_||_||_||_ d|_ |j dS(N( R6R4t_default_orientR!R"R#R$R%R&R'tis_copyt _format_axes( tselfR6R!R"R#R$R%R'R&((s2lib/python2.7/site-packages/pandas/io/json/json.pyt__init__Ps           cCst|dS(N(R(RB((s2lib/python2.7/site-packages/pandas/io/json/json.pyRAbscCs:|j|j|j|j|j|j|jdk|jS(Ntiso(t_writeR6R!R#R$R%R"R&(RB((s2lib/python2.7/site-packages/pandas/io/json/json.pyR1es cCs.t|d|d|d|d|d|d|S(NR!R#R$R%t iso_datesR&(tdumps(RBR6R!R#R$R%RFR&((s2lib/python2.7/site-packages/pandas/io/json/json.pyREjsN(t__name__t __module__R4RCRAR1RE(((s2lib/python2.7/site-packages/pandas/io/json/json.pyR>Os   R.cBs eZdZdZdZRS(R'cCsA|jjj r=|jdkr=tdjd|jndS(NR's1Series index must be unique for orient='{orient}'R!(R6R't is_uniqueR!R*tformat(RB((s2lib/python2.7/site-packages/pandas/io/json/json.pyRAzs cCs[|j r3|dkr3i|jd6|jd6}ntt|j|||||||S(NRRtdata(R'RR tsuperR.RE(RBR6R!R#R$R%RFR&((s2lib/python2.7/site-packages/pandas/io/json/json.pyREs (RHRIR?RARE(((s2lib/python2.7/site-packages/pandas/io/json/json.pyR.ws R/cBs eZdZdZdZRS(tcolumnscCs~|jjj r=|jdkr=tdjd|jn|jjj rz|jd krztdjd|jndS( s: Try to format axes if they are datelike. R'RNs5DataFrame index must be unique for orient='{orient}'.R!Rs7DataFrame columns must be unique for orient='{orient}'.N(R'RN(R'RNR(R6R'RJR!R*RKRN(RB((s2lib/python2.7/site-packages/pandas/io/json/json.pyRAs    cCsZ|j r2|dkr2|jdd}|d=ntt|j|||||||S(NRR!R'(R'tto_dictRMR/RE(RBR6R!R#R$R%RFR&((s2lib/python2.7/site-packages/pandas/io/json/json.pyREs (RHRIR?RARE(((s2lib/python2.7/site-packages/pandas/io/json/json.pyR/s R-cBs#eZdZddZdZRS(Rc Cstt|j|||||||d||dkr[djd|} t| nt|d|j|_|jdkrt |j t rt dn|jdkr|j t|jjkst|j |jj@rd } t| n|j}|jd d gj } t| rH|| jd || stdropRN(RMR-RCRKR*RR'tschematndimR+RNR R0Rtsettnamestlentcopyt select_dtypestapplymapRt to_timestampt reset_indextTrueR6tFalseR"R!( RBR6R!R"R#R$R%R'R&tmsgt timedeltas((s2lib/python2.7/site-packages/pandas/io/json/json.pyRCs8   ! *      c CsOtt|j|||||||}djdt|jd|} | S(Ns&{{"schema": {schema}, "data": {data}}}RWRL(RMR-RERKRGRW( RBR6R!R#R$R%RFR&RLt serialized((s2lib/python2.7/site-packages/pandas/io/json/json.pyREs  N(RHRIR?R4RCRE(((s2lib/python2.7/site-packages/pandas/io/json/json.pyR-s 1tframecCst|| } t|d| d| \}}} }t|d|d|d|d|d|d|d |d |d | d| d | d | d|  }| r|S|j}|ry|jWqqXn|S(s Convert a JSON string to pandas object. Parameters ---------- path_or_buf : a valid JSON string or file-like, default: None The string could be a URL. Valid URL schemes include http, ftp, s3, gcs, and file. For file URLs, a host is expected. For instance, a local file could be ``file://localhost/path/to/table.json`` orient : string, Indication of expected JSON string format. Compatible JSON strings can be produced by ``to_json()`` with a corresponding orient value. The set of possible orients is: - ``'split'`` : dict like ``{index -> [index], columns -> [columns], data -> [values]}`` - ``'records'`` : list like ``[{column -> value}, ... , {column -> value}]`` - ``'index'`` : dict like ``{index -> {column -> value}}`` - ``'columns'`` : dict like ``{column -> {index -> value}}`` - ``'values'`` : just the values array The allowed and default values depend on the value of the `typ` parameter. * when ``typ == 'series'``, - allowed orients are ``{'split','records','index'}`` - default is ``'index'`` - The Series index must be unique for orient ``'index'``. * when ``typ == 'frame'``, - allowed orients are ``{'split','records','index', 'columns','values', 'table'}`` - default is ``'columns'`` - The DataFrame index must be unique for orients ``'index'`` and ``'columns'``. - The DataFrame columns must be unique for orients ``'index'``, ``'columns'``, and ``'records'``. .. versionadded:: 0.23.0 'table' as an allowed value for the ``orient`` argument typ : type of object to recover (series or frame), default 'frame' dtype : boolean or dict, default True If True, infer dtypes, if a dict of column to dtype, then use those, if False, then don't infer dtypes at all, applies only to the data. convert_axes : boolean, default True Try to convert the axes to the proper dtypes. convert_dates : boolean, default True List of columns to parse for dates; If True, then try to parse datelike columns default is True; a column label is datelike if * it ends with ``'_at'``, * it ends with ``'_time'``, * it begins with ``'timestamp'``, * it is ``'modified'``, or * it is ``'date'`` keep_default_dates : boolean, default True If parsing dates, then parse the default datelike columns numpy : boolean, default False Direct decoding to numpy arrays. Supports numeric data only, but non-numeric column and index labels are supported. Note also that the JSON ordering MUST be the same for each term if numpy=True. precise_float : boolean, default False Set to enable usage of higher precision (strtod) function when decoding string to double values. Default (False) is to use fast but less precise builtin functionality date_unit : string, default None The timestamp unit to detect if converting dates. The default behaviour is to try and detect the correct precision, but if this is not desired then pass one of 's', 'ms', 'us' or 'ns' to force parsing only seconds, milliseconds, microseconds or nanoseconds respectively. encoding : str, default is 'utf-8' The encoding to use to decode py3 bytes. .. versionadded:: 0.19.0 lines : boolean, default False Read the file as a json object per line. .. versionadded:: 0.19.0 chunksize : integer, default None Return JsonReader object for iteration. See the `line-delimted json docs `_ for more information on ``chunksize``. This can only be passed if `lines=True`. If this is None, the file will be read into memory all at once. .. versionadded:: 0.21.0 compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}, default 'infer' For on-the-fly decompression of on-disk data. If 'infer', then use gzip, bz2, zip or xz if path_or_buf is a string ending in '.gz', '.bz2', '.zip', or 'xz', respectively, and no decompression otherwise. If using 'zip', the ZIP file must contain only one data file to be read in. Set to None for no decompression. .. versionadded:: 0.21.0 Returns ------- result : Series or DataFrame, depending on the value of `typ`. See Also -------- DataFrame.to_json Notes ----- Specific to ``orient='table'``, if a :class:`DataFrame` with a literal :class:`Index` name of `index` gets written with :func:`to_json`, the subsequent read operation will incorrectly set the :class:`Index` name to ``None``. This is because `index` is also used by :func:`DataFrame.to_json` to denote a missing :class:`Index` name, and the subsequent :func:`read_json` operation cannot distinguish between the two. The same limitation is encountered with a :class:`MultiIndex` and any names beginning with ``'level_'``. Examples -------- >>> df = pd.DataFrame([['a', 'b'], ['c', 'd']], ... index=['row 1', 'row 2'], ... columns=['col 1', 'col 2']) Encoding/decoding a Dataframe using ``'split'`` formatted JSON: >>> df.to_json(orient='split') '{"columns":["col 1","col 2"], "index":["row 1","row 2"], "data":[["a","b"],["c","d"]]}' >>> pd.read_json(_, orient='split') col 1 col 2 row 1 a b row 2 c d Encoding/decoding a Dataframe using ``'index'`` formatted JSON: >>> df.to_json(orient='index') '{"row 1":{"col 1":"a","col 2":"b"},"row 2":{"col 1":"c","col 2":"d"}}' >>> pd.read_json(_, orient='index') col 1 col 2 row 1 a b row 2 c d Encoding/decoding a Dataframe using ``'records'`` formatted JSON. Note that index labels are not preserved with this encoding. >>> df.to_json(orient='records') '[{"col 1":"a","col 2":"b"},{"col 1":"c","col 2":"d"}]' >>> pd.read_json(_, orient='records') col 1 col 2 0 a b 1 c d Encoding with Table Schema >>> df.to_json(orient='table') '{"schema": {"fields": [{"name": "index", "type": "string"}, {"name": "col 1", "type": "string"}, {"name": "col 2", "type": "string"}], "primaryKey": "index", "pandas_version": "0.20.0"}, "data": [{"index": "row 1", "col 1": "a", "col 2": "b"}, {"index": "row 2", "col 1": "c", "col 2": "d"}]}' tencodingR)R!ttyptdtypet convert_axest convert_datestkeep_default_datestnumpyt precise_floatR%R8t chunksize(RRt JsonReadertreadR3(R5R!RhRiRjRkRlRmRnR%RgR8RoR)tfilepath_or_buffert_t should_closet json_readertresult((s2lib/python2.7/site-packages/pandas/io/json/json.pyt read_jsons$!   RpcBsVeZdZdZdZdZdZdZdZdZ dZ RS( s JsonReader provides an interface for reading in a JSON file. If initialized with ``lines=True`` and ``chunksize``, can be iterated over ``chunksize`` lines at a time. Otherwise, calling ``read`` reads in the whole document. cCs||_||_||_||_||_||_||_||_| |_| |_ | |_ ||_ | |_ | |_ d|_t|_|j dk rtd|j d|_ |j stdqn|j|}|j||_dS(NiRois*chunksize can only be passed if lines=True(R5R!RhRiRjRkRlRmRnR%RgR)R8Rot nrows_seenRbRtR4RR*t_get_data_from_filepatht_preprocess_dataRL(RBRrR!RhRiRjRkRlRmRnR%RgR8RoR)RL((s2lib/python2.7/site-packages/pandas/io/json/json.pyRCs,                 cCsTt|dr(|j r(|j}nt|d rP|jrPt|}n|S(s& At this point, the data either has a `read` attribute (e.g. a file object or a StringIO) or is a string that is a JSON document. If self.chunksize, we prepare the data for the `__next__` method. Otherwise, we read it into memory for the `read` method. Rq(thasattrRoRqR(RBRL((s2lib/python2.7/site-packages/pandas/io/json/json.pyRzs cCs|}t}t|tjrQytjj|}WqQttfk rMqQXn|sf|j dk rt |dd|j d|j \}}t |_||_n|S(sL The function read_json accepts three input types: 1. filepath (string-like) 2. file-like object (e.g. open file object, StringIO) 3. JSON string This method turns (1) into (2) to simplify the rest of the processing. It returns input types (2) and (3) unchanged. trRgR)N(RbR+R R2tostpathtexistst TypeErrorR*R)R4RRgRaRtt open_stream(RBRrRLRRs((s2lib/python2.7/site-packages/pandas/io/json/json.pyRys     cCs0tdtd|}ddj|dS(sG Combines a list of JSON objects into one JSON object. cSs |jS(N(tstrip(RT((s2lib/python2.7/site-packages/pandas/io/json/json.pyRU st[t,t]N(tfilterR4tmaptjoin(RBR8((s2lib/python2.7/site-packages/pandas/io/json/json.pyt_combine_linesscCs}|jr!|jr!t|}nN|jr]t|j}|j|j|jd}n|j|j}|j|S(sA Read the whole JSON input into a pandas object. s ( R8RoRRRLt_get_object_parserRRR3(RBR6RL((s2lib/python2.7/site-packages/pandas/io/json/json.pyRq s  cCs|j}|j}i|jd6|jd6|jd6|jd6|jd6|jd6|jd6|jd6}d }|d krt ||j }n|d ks|d krt |t s||d Parses a json document into a pandas object. R!RiRjRkRlRmRnR%RftseriesN(RhRiR!RjRkRlRmRnR%R4t FrameParsertparseR+tboolt SeriesParser(RBtjsonRhRitkwargsR6((s2lib/python2.7/site-packages/pandas/io/json/json.pyRs       cCs;|jr7y|jjWq7ttfk r3q7XndS(s If we opened a stream earlier, in _get_data_from_filepath, we should close it. If an open stream or file was passed, we leave it open. N(RtRR3tIOErrortAttributeError(RB((s2lib/python2.7/site-packages/pandas/io/json/json.pyR35s  cCstt|j|j}|rz|j|}|j|}t|j|jt||_ |jt|7_|S|j t dS(N( tlistRRLRoRRtrangeRxR[R'R3t StopIteration(RBR8t lines_jsonR6((s2lib/python2.7/site-packages/pandas/io/json/json.pyt__next__Bs" ( RHRIt__doc__RCRzRyRRqRR3R(((s2lib/python2.7/site-packages/pandas/io/json/json.pyRps       tParsercBseZdZiedd6edd6edd6edd6ZeeeeeeddZd Z d Z d Z d Z eed Z dZdZRS(R:Rtustnsi3I,WII- pc Cs||_|dkr!|j}n||_||_|dkrHt}n| dk r| j} | |jkrtdj d|jn|j | |_ n|j d|_ ||_ ||_ ||_||_| |_||_d|_dS(NRs date_unit must be one of {units}tunitsR:(RR4R?R!RiRbtlowert _STAMP_UNITSR*RKt _MIN_STAMPSt min_stampRmRnRjRkR%RlR6( RBRR!RiRjRkRlRmRnR%((s2lib/python2.7/site-packages/pandas/io/json/json.pyRC[s*                cCsdt|jjt|j}|r`dj|}ttdjdt|ndS(sT Checks that dict has only the appropriate keys for orient='split'. s, s+JSON data had unexpected key(s): {bad_keys}tbad_keysN( RYtkeyst differencet _split_keysRR*RRKR(RBtdecodedR((s2lib/python2.7/site-packages/pandas/io/json/json.pytcheck_keys_splitzs $cCs`|j}|r|jn |j|jdkr9dS|jrO|jn|j|jS(N(Rmt _parse_numpyt_parse_no_numpyR6R4Rjt _convert_axest_try_convert_types(RBRm((s2lib/python2.7/site-packages/pandas/io/json/json.pyRs      cCsmxf|jjjD]R}|j||jj|dtdt\}}|rt|j||qqWdS(s& Try to convert axes. t use_dtypesRkN(R6t _AXIS_NUMBERSRt_try_convert_datat _get_axisRbRatsetattr(RBtaxistnew_axisRv((s2lib/python2.7/site-packages/pandas/io/json/json.pyRs cCst|dS(N(R(RB((s2lib/python2.7/site-packages/pandas/io/json/json.pyRscCsT|r|jtkr|tfS|jtkr1qt|jtrU|jj|n|j}|dk ry&tj|}|j|tfSWqt t fk r|tfSXqn|r|j |\}}|r|tfSnt}|jdkr0y|jd}t}Wq0t t fk r,q0Xn|jj dkr|jdkry|jd}t}Wqt t fk rqXqnt |r|jdks|jdkry4|jd}||kjr|}t}nWqt t fk rqXn|jdkrJy|jd}t}WqJt t fk rFqJXn||fS(sO Try to parse a ndarray like into a column by inferring dtype. tobjecttfloat64tftfloattint64tintN(RiRbRaR+tdicttgetR4tnptastypeRR*t_try_convert_to_datetkindR[tall(RBRRLRRkRitnew_dataRv((s2lib/python2.7/site-packages/pandas/io/json/json.pyRsZ -     *  cCs<t|s|tfS|}|jdkr^y|jd}Wq^tttfk rZq^Xnt|jjt j rt |j ||j kB|j tkB}|js|tfSn|jr|jfn|j}xY|D]Q}yt|ddd|}Wn%tk rqntk r&PnX|tfSW|tfS(s Try to parse a ndarray like into a date column. Try to coerce object in epoch/iso formats and integer/float in epoch formats. Return a boolean if parsing was successful. RRterrorstraisetunit(R[RbRiRRR*t OverflowErrort issubclassttypeRtnumberR R RRRR%RR t ExceptionRa(RBRLRtin_ranget date_unitsR%((s2lib/python2.7/site-packages/pandas/io/json/json.pyRs0         cCst|dS(N(R(RB((s2lib/python2.7/site-packages/pandas/io/json/json.pyt_try_convert_datess(R:RRRN(RHRIRRRRaRbR4RCRRRRRRR(((s2lib/python2.7/site-packages/pandas/io/json/json.pyRRs"       I &RcBs/eZdZdZdZdZdZRS(R'RRLcCs|j}|j}|dkrkdtjt|d|jD}|j|tdd||_ n$tt|d|jdd|_ dS(NRcSs%i|]\}}|t|qS((tstr(t.0tktv((s2lib/python2.7/site-packages/pandas/io/json/json.pys s RnRi( RR!R t iteritemstloadsRnRR R4R6(RBRR!R((s2lib/python2.7/site-packages/pandas/io/json/json.pyRs     c Cs|j}|j}|dkrwt|dddtd|j}dtj|D}|j|t ||_ nu|dks|dkrt t|dddtdtd|j|_ n*t t|dddtd|j|_ dS( NRRiRmRncSs%i|]\}}|t|qS((R(RRR((s2lib/python2.7/site-packages/pandas/io/json/json.pys /s RNR'tlabelled( RR!RR4RaRnR RRR R6(RBRR!R((s2lib/python2.7/site-packages/pandas/io/json/json.pyR(s     cCsM|jdkrdS|jd|jd|j\}}|rI||_ndS(NRLRk(R6R4RRk(RBR6Rv((s2lib/python2.7/site-packages/pandas/io/json/json.pyR:s (RR'RL(RHRIR?RRRR(((s2lib/python2.7/site-packages/pandas/io/json/json.pyRs  RcBsDeZdZdZdZdZd dZdZdZ RS( RNR'RLc CsV|j}|j}|dkrt|dddtdtd|j}t|rr|dj|d|df}nt||_ n|d krt|dddtd|j}d t j |D}|j |t||_ ni|d kr"tt|dddtd|j|_ n0tt|dddtdtd|j|_ dS( NRNRiRmRRniiiRcSs%i|]\}}|t|qS((R(RRR((s2lib/python2.7/site-packages/pandas/io/json/json.pys Us R ( RR!RR4RaRnR[tTRR6R RR(RBRR!targsR((s2lib/python2.7/site-packages/pandas/io/json/json.pyRGs(     !    cCs#|j}|j}|dkrEtt|d|jdd|_n|dkrdtjt|d|jD}|j |tdd||_n|dkrtt|d|jddj |_nK|dkrt |d|j|_n$tt|d|jdd|_dS(NRNRnRiRcSs%i|]\}}|t|qS((R(RRR((s2lib/python2.7/site-packages/pandas/io/json/json.pys is R'R( RR!RRRnR4R6R RRRR(RBRR!R((s2lib/python2.7/site-packages/pandas/io/json/json.pyR`s$   $    '  c Cs|dkrd}nt}t}xot|jjD]X\}\}}|||r|||\}} | r|}t}qn|||R.R/R-RwRpRRR(((s2lib/python2.7/site-packages/pandas/io/json/json.pytsB  ".(     +(A   ,