def __init__( self, filepath_or_buffer, orient, typ, dtype, convert_axes, convert_dates, keep_default_dates: bool, numpy: bool, precise_float: bool, date_unit, encoding, lines: bool, chunksize: Optional[int], compression: CompressionOptions, nrows: Optional[int], ): compression_method, compression = get_compression_method(compression) compression = dict(compression, method=compression_method) self.orient = orient self.typ = typ self.dtype = dtype self.convert_axes = convert_axes self.convert_dates = convert_dates self.keep_default_dates = keep_default_dates self.numpy = numpy self.precise_float = precise_float self.date_unit = date_unit self.encoding = encoding self.compression = compression self.lines = lines self.chunksize = chunksize self.nrows_seen = 0 self.should_close = False self.nrows = nrows self.file_handles: List[IO] = [] if self.chunksize is not None: self.chunksize = _validate_integer("chunksize", self.chunksize, 1) if not self.lines: raise ValueError("chunksize can only be passed if lines=True") if self.nrows is not None: self.nrows = _validate_integer("nrows", self.nrows, 0) if not self.lines: raise ValueError("nrows can only be passed if lines=True") data = self._get_data_from_filepath(filepath_or_buffer) self.data = self._preprocess_data(data)
def __init__( self, obj, path_or_buf: Optional[FilePathOrBuffer[str]] = None, sep: str = ",", na_rep: str = "", float_format: Optional[str] = None, cols=None, header: Union[bool, Sequence[Hashable]] = True, index: bool = True, index_label: Optional[Union[bool, Hashable, Sequence[Hashable]]] = None, mode: str = "w", encoding: Optional[str] = None, compression: Union[str, Mapping[str, str], None] = "infer", quoting: Optional[int] = None, line_terminator="\n", chunksize: Optional[int] = None, quotechar='"', date_format: Optional[str] = None, doublequote: bool = True, escapechar: Optional[str] = None, decimal=".", ): self.obj = obj if path_or_buf is None: path_or_buf = StringIO() # Extract compression mode as given, if dict compression, self.compression_args = get_compression_method( compression) self.path_or_buf, _, _, self.should_close = get_filepath_or_buffer( path_or_buf, encoding=encoding, compression=compression, mode=mode) self.sep = sep self.na_rep = na_rep self.float_format = float_format self.decimal = decimal self.header = header self.index = index self.index_label = index_label self.mode = mode if encoding is None: encoding = "utf-8" self.encoding = encoding self.compression = infer_compression(self.path_or_buf, compression) if quoting is None: quoting = csvlib.QUOTE_MINIMAL self.quoting = quoting if quoting == csvlib.QUOTE_NONE: # prevents crash in _csv quotechar = None self.quotechar = quotechar self.doublequote = doublequote self.escapechar = escapechar self.line_terminator = line_terminator or os.linesep self.date_format = date_format self.has_mi_columns = isinstance(obj.columns, ABCMultiIndex) # validate mi options if self.has_mi_columns: if cols is not None: raise TypeError( "cannot specify cols with a MultiIndex on the columns") if cols is not None: if isinstance(cols, ABCIndexClass): cols = cols.to_native_types( na_rep=na_rep, float_format=float_format, date_format=date_format, quoting=self.quoting, ) else: cols = list(cols) self.obj = self.obj.loc[:, cols] # update columns to include possible multiplicity of dupes # and make sure sure cols is just a list of labels cols = self.obj.columns if isinstance(cols, ABCIndexClass): cols = cols.to_native_types( na_rep=na_rep, float_format=float_format, date_format=date_format, quoting=self.quoting, ) else: cols = list(cols) # save it self.cols = cols # preallocate data 2d list self.blocks = self.obj._data.blocks ncols = sum(b.shape[0] for b in self.blocks) self.data = [None] * ncols if chunksize is None: chunksize = (100000 // (len(self.cols) or 1)) or 1 self.chunksize = int(chunksize) self.data_index = obj.index if (isinstance(self.data_index, (ABCDatetimeIndex, ABCPeriodIndex)) and date_format is not None): from pandas import Index self.data_index = Index([ x.strftime(date_format) if notna(x) else "" for x in self.data_index ]) self.nlevels = getattr(self.data_index, "nlevels", 1) if not index: self.nlevels = 0
def read_json( path_or_buf=None, orient=None, typ="frame", dtype=None, convert_axes=None, convert_dates=True, keep_default_dates: bool = True, numpy: bool = False, precise_float: bool = False, date_unit=None, encoding=None, lines: bool = False, chunksize: Optional[int] = None, compression: CompressionOptions = "infer", nrows: Optional[int] = None, storage_options: StorageOptions = None, ): """ 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 handler (e.g. via builtin ``open`` function) or ``StringIO``. orient : str 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 : {'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. .. versionchanged:: 0.25.0 Not applicable for ``orient='table'``. convert_axes : bool, default None Try to convert the axes to the proper dtypes. For all ``orient`` values except ``'table'``, default is True. .. versionchanged:: 0.25.0 Not applicable for ``orient='table'``. 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'``. numpy : bool, 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. .. deprecated:: 1.0.0 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. 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. 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. 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 : dict, optional Extra options that make sense for a particular storage connection, e.g. host, port, username, password, etc., if using a URL that will be parsed by ``fsspec``, e.g., starting "s3://", "gcs://". An error will be raised if providing this argument with a local path or a file-like buffer. See the fsspec and backend storage implementation docs for the set of allowed keys and values .. versionadded:: 1.2.0 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. 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"}]}' """ if orient == "table" and dtype: raise ValueError("cannot pass both dtype and orient='table'") if orient == "table" and convert_axes: raise ValueError("cannot pass both convert_axes and orient='table'") if dtype is None and orient != "table": dtype = True if convert_axes is None and orient != "table": convert_axes = True if encoding is None: encoding = "utf-8" compression_method, compression = get_compression_method(compression) compression_method = infer_compression(path_or_buf, compression_method) compression = dict(compression, method=compression_method) filepath_or_buffer, _, compression, should_close = get_filepath_or_buffer( path_or_buf, encoding=encoding, compression=compression, storage_options=storage_options, ) json_reader = JsonReader( filepath_or_buffer, orient=orient, typ=typ, dtype=dtype, convert_axes=convert_axes, convert_dates=convert_dates, keep_default_dates=keep_default_dates, numpy=numpy, precise_float=precise_float, date_unit=date_unit, encoding=encoding, lines=lines, chunksize=chunksize, compression=compression, nrows=nrows, ) if chunksize: return json_reader result = json_reader.read() if should_close: filepath_or_buffer.close() return result