U
|
¬ý°dµ ã @ s¸ d dl mZ d dlmZmZ d dlmZ d dlmZ d dlm Z d dl
|
m Z d dl m Z mZmZmZmZmZmZmZ d dlZd d lmZ d d
|
lmZmZ d d l m Z d d l m Z m Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z( d d l)m*Z* d dl+m,Z, d dl-m.Z. d dl/m0Z0 d dl1m2Z2m3Z3 d dl4m5Z5 d dl6m7Z7m8Z8m9Z9m:Z:m;Z;m<Z<m=Z= d dl>m?Z? d dl@mAZA d dlBmCZCmDZDmEZEmFZFmGZGmHZHmIZImJZJmKZK d dlLmMZM d dlNmOZOmPZP d dlQmRZR e rÂd dlSmTZT eded d ZUedgd d d!d"d#d$d"d%d$d&d$d#d'd(d)d*d+d,ZVedhd)d d!d"d#d$d"d%d$d&d$d#d'd(d"d*d-d,ZVdid5d d!d"d#d$d"d%d$d&d$d#d'd(d!d*d6d,ZVG d7d8 d8eZWG d9d: d:eWZXG d;d< d<eWZYG d=d> d>eYZZed d d d d d d d d d d d d d d d d?d@d!dAdBdCd$d$d!d!d!d$d#d&dDd'dEdFdGdHdIdJZ[ed d d d d d d d d d d d d d d dKd@d!dLdBdCd$d$d!d!d!d$d#d&dDd'dEdFdMdHdNdJZ[ed d d d d d d d d d d d d d d d dOd@d!dLdBdCd$d$d!d!d!d$d)d&dDd'dEdFdPdHdQdJZ[ed d d d d d d d d d d d d d d d d dRd@d!dAdBdCd$d$d!d!d!d$d)d&dDd'dEdFdSdHdTdJZ[e.eAdU eAdV dW dXddYddd0d0d2dddZd2dd3ddej\d[dRd@d!d\dBdCd$d$d!d!d!d$dDd&dDd'dEdFd]dHd^dJZ[G d_d` d`ej]eeU Z^G dadb dbZ_G dcdd dde_Z`G dedf dfe_ZadS )jé )Ú annotations)ÚABCÚabstractmethod)Úabc)ÚStringIO)Úislice)Ú TracebackType)Ú TYPE_CHECKINGÚAnyÚCallableÚGenericÚLiteralÚMappingÚTypeVarÚoverloadN)Úlib)ÚdumpsÚloads)ÚiNaT)
|
ÚCompressionOptionsÚDtypeArgÚ DtypeBackendÚFilePathÚ
|
IndexLabelÚ
|
JSONEngineÚJSONSerializableÚ
|
ReadBufferÚStorageOptionsÚ WriteBuffer)Úimport_optional_dependency©ÚAbstractMethodError)Údoc)Úcheck_dtype_backend)Ú
|
ensure_strÚis_period_dtype)ÚABCIndex)Ú
|
ArrowDtypeÚ DataFrameÚ
|
MultiIndexÚSeriesÚisnaÚnotnaÚ to_datetime)Úconcat)Ú _shared_docs) Ú IOHandlesÚ dedup_namesÚextension_to_compressionÚ file_existsÚ
|
get_handleÚ is_fsspec_urlÚis_potential_multi_indexÚis_urlÚstringify_path)Úconvert_to_line_delimits)Úbuild_table_schemaÚparse_table_schema)Úvalidate_integer)ÚNDFrameÚFrameSeriesStrT)ÚframeÚseries)Úbound.z0FilePath | WriteBuffer[str] | WriteBuffer[bytes]r= ú
|
str | NoneÚstrÚintÚboolú(Callable[[Any], JSONSerializable] | Noner r zLiteral[('a', 'w')]ÚNone)Ú path_or_bufÚobjÚorientÚ date_formatÚdouble_precisionÚ force_asciiÚ date_unitÚdefault_handlerÚlinesÚ compressionÚindexÚindentÚstorage_optionsÚmodeÚreturnc C s d S ©N© ©rH rI rJ rK rL rM rN rO rP rQ rR rS rT rU rX rX úKd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/io/json/_json.pyÚto_jsonZ s r[ c C s d S rW rX rY rX rX rZ r[ n s Úepoché
|
TÚmsFÚinferÚwz7FilePath | WriteBuffer[str] | WriteBuffer[bytes] | Nonec C s. |
|
s|dkrt d|r(|dkr(t d| dkrDd| d}t || dkrd|rX|dkrdd }t ||d
|
krt|tr|j|jpd d }|d
|
kr t|tr t}n(t|tr°t}nt|trÀt}nt d |||||||||
|
| d
|
¡ }|ròt |}| d k r&t | | | | d}|j
|
|¡ W 5 Q R X n|S d S )N)ÚsplitÚtablez?'index=False' is only valid when 'orient' is 'split' or 'table'Úrecordsz3'lines' keyword only valid when 'orient' is records)Úar` zmode=z@ is not a valid option.Only 'w' and 'a' are currently supported.rd zMmode='a' (append) is only supported whenlines is True and orient is 'records'rb Úvalues)Únamez''obj' should be a Series or a DataFrame)rJ rK rL Ú ensure_asciirN rO rR rS )rQ rT )Ú
|
ValueErrorÚ
|
isinstancer* Zto_framerf r( ÚJSONTableWriterÚ SeriesWriterÚ FrameWriterÚNotImplementedErrorÚwriter9 r4 Úhandle)rH rI rJ rK rL rM rN rO rP rQ rR rS rT rU ÚmsgÚwriterÚsÚhandlesrX rX rZ r[ s^ ÿ
|
ÿÿ
|
|
÷
|
|
ÿc @ sd e Zd ZU ded< ddddddddd dd
|
d
|
d d Zdd ZddddZeeddddZ dS )ÚWriterrC Ú_default_orientNr r= rB rD rE rF rG )
|
rI rJ rK rL rg rN rR rO rS rV c
|
|
C sV || _ |d kr| j}|| _|| _|| _|| _|| _|| _|| _| | _ d | _
|
| ¡ d S rW ) rI ru rJ rK rL rg rN rO rR rS Zis_copyÚ _format_axes)
|
ÚselfrI rJ rK rL rg rN rR rO rS rX rX rZ Ú__init__Ò s zWriter.__init__c C s t | d S rW r ©rw rX rX rZ rv ï s zWriter._format_axes©rV c
|
C s0 | j dk}t| j| j| j| j| j|| j| jdS )NÚiso)rJ rL rg rN Ú iso_datesrO rS ) rK r Ú obj_to_writerJ rL rg rN rO rS )rw r| rX rX rZ rn ò s
|
øz Writer.writeú"NDFrame | Mapping[IndexLabel, Any]c C s dS )z Object to write in JSON format.NrX ry rX rX rZ r} ÿ s zWriter.obj_to_write)Nr )
|
Ú__name__Ú
|
__module__Ú __qualname__Ú__annotations__rx rv rn Úpropertyr r} rX rX rX rZ rt Ï s
|
ö" rt c @ s* e Zd ZdZeddddZdd ZdS ) rk rR r~ rz c C s, | j s"| jdkr"| jj| jjdS | jS d S )Nra )rf Údata)rR rJ rI rf re ry rX rX rZ r} s zSeriesWriter.obj_to_writec C s* | j jjs&| jdkr&td| j dd S )NrR z(Series index must be unique for orient='ú')rI rR Ú is_uniquerJ rh ry rX rX rZ rv s zSeriesWriter._format_axesN©r r r ru r r} rv rX rX rX rZ rk s rk c @ s* e Zd ZdZeddddZdd ZdS ) rl Úcolumnsr~ rz c C s0 | j s&| jdkr&| jjdd}|d= n| j}|S )Nra )rJ rR )rR rJ rI Úto_dict)rw r} rX rX rZ r} s
|
zFrameWriter.obj_to_writec C sP | j jjs&| jdkr&td| j d| j jjsL| jdkrLtd| j ddS )z:
|
Try to format axes if they are datelike.
|
)rR r z+DataFrame index must be unique for orient='z'.)rR r rc z-DataFrame columns must be unique for orient='N)rI rR r rJ rh r ry rX rX rZ rv s ÿ ÿzFrameWriter._format_axesNr rX rX rX rZ rl s rl c sJ e Zd ZdZdddddddddd d
|
fd d Zed dddZ ZS )rj rc Nr rB rC rD rE rF rG ) rJ rK rL rg rN rR rO rS rV c
|
s. t j||||||||| d |dkr:d| d}
|
t|
|
t|| jd| _|jdkrht|jt rht
|
d|jdkr|j t |jj kst|j |jj ¡r¤d }
|
t|
|
| ¡ }|jd
|
gd j} t| rÚ|| d d ¡|| < t|jjrò|j ¡ |_| js
|
|jdd| _n|jdd| _d| _d| _|| _dS )zù
|
Adds a `schema` attribute with the Table Schema, resets
|
the index (can't do in caller, because the schema inference needs
|
to know what the index is, forces orient to records, and forces
|
date_format to 'iso'.
|
)rO rS r{ z8Trying to write with `orient='table'` and `date_format='zH'`. Table Schema requires dates to be formatted with `date_format='iso'`©rR é z6orient='table' is not supported for MultiIndex columnsé z/Overlapping names between the index and columnsÚ timedelta)Úincludec S s | ¡ S rW )Ú isoformat)ÚxrX rX rZ Ú<lambda>o ó z*JSONTableWriter.__init__.<locals>.<lambda>T)ZdropFrc N)Úsuperrx rh r: rR ÚschemaÚndimri r r) rm rf ÚsetÚnamesÚlenÚ intersectionÚcopyZ select_dtypesZapplymapr% ÚdtypeZ to_timestampZ reset_indexrI rK rJ ) rw rI rJ rK rL rg rN rR rO rS rp Z
|
timedeltas©Ú __class__rX rZ rx 5 sP ÷
|
ÿÿÿþý zJSONTableWriter.__init__r~ rz c C s | j | jdS )N)r r )r rI ry rX rX rZ r} } s z JSONTableWriter.obj_to_write)Nr )r r r ru rx r r} Ú __classcell__rX rX r rZ rj 2 s ö$Hrj )rJ Útypr Ú convert_axesÚ convert_datesÚkeep_default_datesÚ precise_floatrN ÚencodingÚencoding_errorsrP rQ ÚnrowsrT Ú dtype_backendÚenginez.FilePath | ReadBuffer[str] | ReadBuffer[bytes]zLiteral['frame']úDtypeArg | Noneúbool | list[str]ú
|
int | Noneú DtypeBackend | lib.NoDefaultr ú JsonReader[Literal['frame']])rH rJ r r r¡ r¢ r£ rN r¤ r¥ rP Ú chunksizerQ r¦ rT r§ r¨ rV c C s d S rW rX ©rH rJ r r r r¡ r¢ r£ rN r¤ r¥ rP r® rQ r¦ rT r§ r¨ rX rX rZ Ú read_json s r° )rJ r r r¡ r¢ r£ rN r¤ r¥ rP rQ r¦ rT r§ r¨ zLiteral['series']ú JsonReader[Literal['series']]c C s d S rW rX r¯ rX rX rZ r° s )rJ r r r¡ r¢ r£ rN r¤ r¥ rP r® rQ r¦ rT r§ r¨ r* c C s d S rW rX r¯ rX rX rZ r° ´ s )rJ r r r r¡ r¢ r£ rN r¤ r¥ rP r® rQ r¦ rT r§ r¨ r( c C s d S rW rX r¯ rX rX rZ r° Í s rT Údecompression_optionsrH )rT r² r? ÚstrictÚujsonz Literal[('frame', 'series')]z DataFrame | Series | JsonReaderc C s |dkr|rt d|dkr(|r(t dt| |dkrD|dkrDd}|dkrX|dkrXd}t| ||||||||| | | | |||
|
||d}| r|S | ¡ S dS )a
|
Convert a JSON string to pandas object.
|
|
Parameters
|
----------
|
path_or_buf : a valid JSON str, path object or file-like object
|
Any valid string path is acceptable. The string could be a URL. Valid
|
URL schemes include http, ftp, s3, and file. For file URLs, a host is
|
expected. A local file could be:
|
``file://localhost/path/to/table.json``.
|
|
If you want to pass in a path object, pandas accepts any
|
``os.PathLike``.
|
|
By file-like object, we refer to objects with a ``read()`` method,
|
such as a file handle (e.g. via builtin ``open`` function)
|
or ``StringIO``.
|
orient : str, optional
|
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'``.
|
|
typ : {{'frame', 'series'}}, default 'frame'
|
The type of object to recover.
|
|
dtype : bool or dict, default None
|
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.
|
|
For all ``orient`` values except ``'table'``, default is True.
|
|
convert_axes : bool, default None
|
Try to convert the axes to the proper dtypes.
|
|
For all ``orient`` values except ``'table'``, default is True.
|
|
convert_dates : bool or list of str, default True
|
If True then default datelike columns may be converted (depending on
|
keep_default_dates).
|
If False, no dates will be converted.
|
If a list of column names, then those columns will be converted and
|
default datelike columns may also be converted (depending on
|
keep_default_dates).
|
|
keep_default_dates : bool, default True
|
If parsing dates (convert_dates is not False), then try to parse the
|
default datelike columns.
|
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'``.
|
|
precise_float : bool, 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 : str, 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.
|
|
encoding_errors : str, optional, default "strict"
|
How encoding errors are treated. `List of possible values
|
<https://docs.python.org/3/library/codecs.html#error-handlers>`_ .
|
|
.. versionadded:: 1.3.0
|
|
lines : bool, default False
|
Read the file as a json object per line.
|
|
chunksize : int, optional
|
Return JsonReader object for iteration.
|
See the `line-delimited json docs
|
<https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#line-delimited-json>`_
|
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.
|
|
.. versionchanged:: 1.2
|
|
``JsonReader`` is a context manager.
|
|
{decompression_options}
|
|
.. versionchanged:: 1.4.0 Zstandard support.
|
|
nrows : int, optional
|
The number of lines from the line-delimited jsonfile that has to be read.
|
This can only be passed if `lines=True`.
|
If this is None, all the rows will be returned.
|
|
.. versionadded:: 1.1
|
|
{storage_options}
|
|
.. versionadded:: 1.2.0
|
|
dtype_backend : {{"numpy_nullable", "pyarrow"}}, defaults to NumPy backed DataFrames
|
Which dtype_backend to use, e.g. whether a DataFrame should have NumPy
|
arrays, nullable dtypes are used for all dtypes that have a nullable
|
implementation when "numpy_nullable" is set, pyarrow is used for all
|
dtypes if "pyarrow" is set.
|
|
The dtype_backends are still experimential.
|
|
.. versionadded:: 2.0
|
|
engine : {{"ujson", "pyarrow"}}, default "ujson"
|
Parser engine to use. The ``"pyarrow"`` engine is only available when
|
``lines=True``.
|
|
.. versionadded:: 2.0
|
|
Returns
|
-------
|
Series or DataFrame
|
The type returned depends on the value of `typ`.
|
|
See Also
|
--------
|
DataFrame.to_json : Convert a DataFrame to a JSON string.
|
Series.to_json : Convert a Series to a JSON string.
|
json_normalize : Normalize semi-structured JSON data into a flat table.
|
|
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":"1.4.0"}},"data":[{{"index":"row 1","col 1":"a","col 2":"b"}},{{"index":"row 2","col 1":"c","col 2":"d"}}]}}'
|
rb z)cannot pass both dtype and orient='table'z0cannot pass both convert_axes and orient='table'NT)rJ r r r r¡ r¢ r£ rN r¤ rP r® rQ r¦ rT r¥ r§ r¨ )rh r# Ú
|
JsonReaderÚread)rH rJ r r r r¡ r¢ r£ rN r¤ r¥ rP r® rQ r¦ rT r§ r¨ Z json_readerrX rX rZ r° æ sD îc @ s@ e Zd ZdZddejdfdddddddd d
|
d d d d ddZdd Zdd ZddddZ e
|
dddd d Z e
|
d d dd d Z e
|
d!d"dd#d Z d"dd$d Z d"dd%d&Z d dd'd(Z d)d)dd*d+Ze
|
dddd,d-Ze
|
d d dd.d-Ze
|
d!d"dd/d-Zd"dd0d-Zd)dd1d2Zd3d4d5d d6d7d8ZdS )9rµ zö
|
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.
|
Nr³ r´ r> rE r« r r rB r¬ r rG ) r r¢ r£ rP r® rQ r¦ rT r¥ r§ r¨ rV c C s: || _ || _|| _|| _|| _|| _|| _| | _|
|
| _|| _ | | _
|
|| _ | | _ | | _ d| _|| _|| _d | _|| _| j dkrtd| j d| j d k rÈtd| j d| _ | j s¶td| j dkrÈtd | jd k rðtd
|
| jd| _| j sðtd | j dkr| j s td || _n"| j d kr6| |¡}| |¡| _d S )Nr > Úpyarrowr´ zThe engine type z is currently not supported.r® r z*chunksize can only be passed if lines=Truer· z<currently pyarrow engine doesn't support chunksize parameterr¦ z&nrows can only be passed if lines=TruezEcurrently pyarrow engine only supports the line-delimited JSON formatr´ )rJ r r r r¡ r¢ r£ rN r¤ r¨ rQ rT rP r® Ú
|
nrows_seenr¦ r¥ rs r§ rh r< r Ú_get_data_from_filepathÚ_preprocess_data)rw Úfilepath_or_bufferrJ r r r r¡ r¢ r£ rN r¤ rP r® rQ r¦ rT r¥ r§ r¨ r rX rX rZ rx sX
|
ÿ
|
|
ÿ
|
ÿ
|
zJsonReader.__init__c C sP t |dr.| js.| js.| | ¡ }W 5 Q R X t |dsL| jsD| jrLt|}|S )a&
|
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.
|
r¶ )Úhasattrr® r¦ r¶ r )rw r rX rX rZ rº ` s zJsonReader._preprocess_datac C s t |}t|tr*t|s*t|s*t|rRt|d| j| j| j | j
|
d| _ | j j }nBt|tr| ¡ dtdd tD ¡rt|std| d|S )aÝ
|
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.
|
|
It raises FileNotFoundError if the input is a string ending in
|
one of .json, .json.gz, .json.bz2, etc. but no such file exists.
|
Úr)r¤ rQ rT Úerrors)ú.jsonc s s | ]}d | V qdS )r¿ NrX )Ú.0ÚcrX rX rZ Ú <genexpr> s z5JsonReader._get_data_from_filepath.<locals>.<genexpr>zFile z does not exist)r8 ri rC r7 r5 r3 r4 r¤ rQ rT r¥ rs ro ÚlowerÚendswithÚtupler2 ÚFileNotFoundError)rw r» rX rX rZ r¹ p s8 ÿþýüú
|
ÿÿþûz"JsonReader._get_data_from_filepathrC rz c C s& dd dd dd |D D ¡ dS )zG
|
Combines a list of JSON objects into one JSON object.
|
ú[ú,c S s g | ] }|r|qS rX rX ©rÀ ÚlinerX rX rZ Ú
|
<listcomp> s z-JsonReader._combine_lines.<locals>.<listcomp>c s s | ]}| ¡ V qd S rW )ÚstriprÉ rX rX rZ r s z,JsonReader._combine_lines.<locals>.<genexpr>ú])Újoin)rw rP rX rX rZ Ú_combine_lines s $ÿzJsonReader._combine_linesr r( )rw rV c C s d S rW rX ry rX rX rZ r¶ ¡ s zJsonReader.readr± r* c C s d S rW rX ry rX rX rZ r¶ ¥ s z(JsonReader[Literal[('frame', 'series')]]zDataFrame | Seriesc C s d S rW rX ry rX rX rZ r¶ © s c
|
|
C s< | , | j dkrrtd}| | j¡}| jdkr6t}n$| jdkrVddlm} | j}nd}|j |dW 5 Q R £ S | j dkr.| j
|
rè| j rt | }qô| j rÂtt| j| j }| |¡}| |¡}qôt| j}| d ¡} | | | ¡¡}n | | j¡}| jtjk r |jd
|
| jd W 5 Q R £ S |W 5 Q R £ S W 5 Q R X dS ) zA
|
Read the whole JSON input into a pandas object.
|
r· z pyarrow.jsonZnumpy_nullabler )Ú_arrow_dtype_mappingN)Z types_mapperr´ Ú
|
F©Z infer_objectsr§ )r¨ r r° r r§ r' Zpandas.io._utilrÐ ÚgetZ to_pandasrP r® r. r¦ Úlistr rÏ Ú_get_object_parserr$ ra r Ú
|
no_defaultÚconvert_dtypes)
|
rw Z pyarrow_jsonZpa_tableÚmappingrÐ rI rP Ú
|
lines_jsonr Z
|
data_linesrX rX rZ r¶ s:
|
|
|
|
|
|
|
|
ÿc C s | j }| j}| j| j| j| j| j| j| j| jd}d}|dkrNt |f|
|
¡ }|dks^|dkrt |t sp||d< t |f|
|
¡ }|S )z>
|
Parses a json document into a pandas object.
|
)rJ r r r¡ r¢ r£ rN r§ Nr? r@ r )r r rJ r r¡ r¢ r£ rN r§ Ú FrameParserÚparseri rE Ú SeriesParser)rw Újsonr r ÚkwargsrI rX rX rZ rÕ × s& ø
|
|
z JsonReader._get_object_parserc C s | j dk r| j ¡ dS )z©
|
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)rs Úclosery rX rX rZ rß ò s
|
zJsonReader.closezJsonReader[FrameSeriesStrT]c C s | S rW rX ry rX rX rZ Ú__iter__ü s zJsonReader.__iter__c C s d S rW rX ry rX rX rZ Ú__next__ÿ s zJsonReader.__next__c C s d S rW rX ry rX rX rZ rá s c C s d S rW rX ry rX rX rZ rá s c
|
C sÖ | j r | j| j kr | ¡ ttt| j| j}|s@| ¡ tzB| |¡}| |¡}t
|
| j| jt | |_ | jt |7 _W n. t k
|
r° } z| ¡ |W 5 d }~X Y nX | jtjk rÎ|jd| jdS |S d S )NFrÒ )r¦ r¸ rß Ú StopIterationrÔ r r r® rÏ rÕ Úranger rR Ú Exceptionr§ r rÖ r× )rw rP rÙ rI ÚexrX rX rZ rá s*
|
|
ÿc C s | S rW rX ry rX rX rZ Ú __enter__' s zJsonReader.__enter__ztype[BaseException] | NonezBaseException | NonezTracebackType | None)Úexc_typeÚ exc_valueÚ tracebackrV c C s | ¡ d S rW )rß )rw rç rè ré rX rX rZ Ú__exit__* s zJsonReader.__exit__)r r r Ú__doc__r rÖ rx rº r¹ rÏ r r¶ rÕ rß rà rá ræ rê rX rX rX rZ rµ s8 í&D)*
|
rµ c @ s² e Zd ZU ded< ded< dZdddd dZd
|
d d d d d
|
ejfd dddddddddZddddZ dd Z
|
dd Z ddd d Z d d Z d'ddd d!d"Zd#d$ Zd%d& Zd
|
S )(ÚParserztuple[str, ...]Ú _split_keysrC ru )rr r^ ÚusÚnsi3ál ,b/ l `'ºrl F[L'NTFr© rE rª r¬ rG )r r r¡ r¢ r£ r§ rV c
|
|
C s || _ |d kr| j}|| _|| _|d k rX| ¡ }|| jkrJtd| j | j| | _n | jd | _|| _ || _
|
|| _ || _ || _ d | _| | _d S )Nzdate_unit must be one of rr )rÝ ru rJ r rÃ Ú _STAMP_UNITSrh Ú _MIN_STAMPSÚ min_stampr£ r r¡ rN r¢ rI r§ )
|
rw rÝ rJ r r r¡ r¢ r£ rN r§ rX rX rZ rx ? s$
|
zParser.__init__rz c C s8 t | ¡ t | j¡}|r4d |¡}td| dS )zT
|
Checks that dict has only the appropriate keys for orient='split'.
|
z, z!JSON data had unexpected key(s): N)r ÚkeysÚ
|
differencerí rÎ rh )rw ÚdecodedZbad_keysZbad_keys_joinedrX rX rZ Úcheck_keys_splitd s
|
zParser.check_keys_splitc C s2 | ¡ | jd krd S | jr$| ¡ | ¡ | jS rW )Ú_parserI r Ú _convert_axesÚ_try_convert_typesry rX rX rZ rÛ m s
|
z Parser.parsec C s t | d S rW r ry rX rX rZ r÷ w s z Parser._parsec C sP | j }|dk st|jD ]2}| j|| |¡ddd\}}|rt| j || qdS )z&
|
Try to convert axes.
|
NFT)rf r Ú
|
use_dtypesr¡ )rI ÚAssertionErrorZ _AXIS_ORDERSÚ_try_convert_dataZ _get_axisÚsetattr)rw rI Z axis_nameZnew_axisÚresultrX rX rZ rø z s
|
ü
|
zParser._convert_axesc C s t | d S rW r ry rX rX rZ rù s zParser._try_convert_types)rú r¡ c
|
C s |r| j s.tt|r |dfS | tj¡dfS | j dkr:nXt| j trR| j |¡n| j }|dk rz| |¡dfW S t
|
t fk
|
r |df Y S X |r°| |¡\}}|r°|dfS | j tjk rÎt|tsÎ|dfS |j dkrz| d¡}W n t
|
t fk
|
r Y nX |j jdkrH|j dkrHz| d¡}W n t
|
t fk
|
rF Y nX t|r|j dkrz | d¡}||k ¡ r||}W n t
|
t tfk
|
r Y nX |j d krÒz| d¡}W n t
|
t fk
|
rÐ Y nX |d
|
krút|rú| jd krú|dfS |dfS ) zO
|
Try to parse a ndarray like into a column by inferring dtype.
|
FTNÚobjectÚfloat64Úf)Úfloatrÿ Úint64rD rR ra )r Úallr, ZfillnaÚnpÚnanri ÚdictrÓ ÚastypeÚ TypeErrorrh Ú_try_convert_to_dater§ r rÖ r& Úkindr Ú OverflowErrorrJ )rw rf r rú r¡ r Únew_datarþ rX rX rZ rü s^
|
ÿ
|
zParser._try_convert_datac C s t |s|dfS |}|jdkr`z| d¡}W n2 tk
|
rH |df Y S ttfk
|
r^ Y nX t|jjtj rt
|
|j || j kB |j t kB }| ¡ s|dfS | jr¬| jfn| j}|D ]@}zt|d|d}W n tttfk
|
rê Y q¶Y nX |df S |dfS )zÌ
|
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.
|
Frÿ r Úraise)r¾ ÚunitT)r r r r r rh Ú
|
issubclassÚtyper Únumberr+ Z_valuesrò r r rN rð r- )rw r r Zin_rangeZ
|
date_unitsrN rX rX rZ r
|
Û s6
|
ÿþÿ
|
zParser._try_convert_to_datec C s t | d S rW r ry rX rX rZ Ú_try_convert_dates s zParser._try_convert_dates)TT)r r r r rð rñ r rÖ rx rö rÛ r÷ rø rù rü r
|
r rX rX rX rZ rì 3 s4
|
ü ö %
|
ûN'rì c @ s0 e Zd ZdZdZddddZddddZd S )
|
rÜ rR )rf rR r rG rz c C sR t | j| jd}| jdkrDdd | ¡ D }| |¡ tf || _n
|
t|| _d S )N©r£ ra c S s i | ]\}}t ||qS rX ©rC ©rÀ ÚkÚvrX rX rZ Ú
|
<dictcomp> s z'SeriesParser._parse.<locals>.<dictcomp>)r rÝ r£ rJ Úitemsrö r* rI )rw r rõ rX rX rZ r÷
|
s
|
|
zSeriesParser._parsec C s4 | j d krd S | jd| j | jd\}}|r0|| _ d S )Nr ©r¡ )rI rü r¡ )rw rI rþ rX rX rZ rù s
|
ÿ
|
z SeriesParser._try_convert_typesN)r r r ru rí r÷ rù rX rX rX rZ rÜ s
|
rÜ c @ sN e Zd ZdZdZddddZddddd Zddd
|
d Zddd d ZdS )rÚ r )r rR r rG rz c C sô | j }| j}|dkr.tt|| jdd d| _nÂ|dkrdd t|| jd ¡ D }| |¡ dd |d D }t|t |d |d< tf d d i|| _nX|d
|
kr¾tj
|
t|| jdd d
|
d | _n2|d krØt || jd| _ntt|| jdd d| _d S ) Nr r )r ra c S s i | ]\}}t ||qS rX r r rX rX rZ r + s ÿ z&FrameParser._parse.<locals>.<dictcomp>c S s" g | ]}t |trt|n|qS rX )ri rÔ rÅ )rÀ ÚcolrX rX rZ rË 0 s ÿz&FrameParser._parse.<locals>.<listcomp>r rR )r rJ rb ) rÝ rJ r( r r£ rI r rö r1 r6 Ú from_dictr; )rw rÝ rJ rõ Z
|
orig_namesrX rX rZ r÷ " s@ ÿ
|
þ
|
þþ ý
|
ÿzFrameParser._parseNc C s |dkrdd }| j }|dk s"td}i }t| ¡ D ]8\}\}}|||rf|||\} }
|
|
|
rf| }d}|||< q6|rt||jd} |j| _| | _ dS )zM
|
Take a conversion function and possibly recreate the frame.
|
Nc S s dS )NTrX ©r rÁ rX rX rZ r K r z0FrameParser._process_converter.<locals>.<lambda>FTr )rI rû Ú enumerater r( rR r ) rw r ZfiltrI Z needs_new_objZnew_objÚir rÁ r rþ Z new_framerX rX rZ Ú_process_converterF s"
|
|
z FrameParser._process_converterc s2 j d krd S jr ¡ fdd¡ d S )Nc s j | |ddS )NFr )rü r ry rX rZ r g r z0FrameParser._try_convert_types.<locals>.<lambda>)rI r¡ r r! ry rX ry rZ rù ` s
|
|
ÿz FrameParser._try_convert_typesc s\ j d krd S j}t|tr"g }t| dddd fdd fdd¡ d S )NrE rz c S sT t | tsdS | ¡ }| d¡sL| d¡sL|dksL|dksL|dksL| d¡rPdS dS ) zK
|
Return if this col is ok to try for a date parse.
|
FZ_atÚ_timeÚmodifiedÚdateÚdatetimeÚ timestampT)ri rC rà rÄ Ú
|
startswith)r Z col_lowerrX rX rZ Úis_okt s"
|
ÿþýüûúz-FrameParser._try_convert_dates.<locals>.is_okc s
|
|¡S rW )r
|
r ry rX rZ r r z0FrameParser._try_convert_dates.<locals>.<lambda>c s j r| p| kS rW )r¢ r ©r¡ r( rw rX rZ r s )rI r¡ ri rE r r! )rw Zconvert_dates_list_boolrX r) rZ r j s
|
|
|
þz FrameParser._try_convert_dates)N) r r r ru rí r÷ r! rù r rX rX rX rZ rÚ s $
|
rÚ ) ............) ............) Nr\ r] Tr^ NFr_ Tr Nr` )bÚ
|
__future__r r r r Ú collectionsÚior Ú itertoolsr Útypesr Útypingr r
|
r r r r r r Únumpyr Z pandas._libsr Zpandas._libs.jsonr r Zpandas._libs.tslibsr Zpandas._typingr r r r r r r r r r Zpandas.compat._optionalr Z pandas.errorsr! Zpandas.util._decoratorsr" Zpandas.util._validatorsr# Zpandas.core.dtypes.commonr$ r% Zpandas.core.dtypes.genericr& Zpandasr' r( r) r* r+ r, r- Zpandas.core.reshape.concatr. Zpandas.core.shared_docsr/ Zpandas.io.commonr0 r1 r2 r3 r4 r5 r6 r7 r8 Zpandas.io.json._normalizer9 Z pandas.io.json._table_schemar: r; Zpandas.io.parsers.readersr< Zpandas.core.genericr= r> r[ rt rk rl rj r° rÖ ÚIteratorrµ rì rÜ rÚ rX rX rX rZ Ú<module> s^ ( 0 $ , ò. ò. ò,M6 Pí6í6í6í6
|
þí6 + " T
|
