\ qidk-PUdZddlmZddlmZmZddlZddlZddlm Z m Z m Z m Z m Z mZmZmZmZmZddlZddlZddlmZddlmZddlmZmZdd lmZdd lm Z dd l!m"Z"dd l#m$Z$m%Z%m&Z&m'Z'm(Z(dd l)m*Z*ddl+m,Z,ddl-m.Z.ddl/m0Z0m1Z1m2Z2m3Z3ddl4m5Z5ddl6m7Z7m8Z8m9Z9ddl:m;Z;ddlZ>e rDddl?m@Z@mAZAmBZBmCZCmDZDddlEmFZFddlGmHZHmIZImJZJmKZKmLZLmMZMmNZNmOZOmPZPmQZQGddee eMdZRneSZRGddeZTdddddZUdeVd <Gd!d"eZWd#d$dd%ZXd"eVd&<d'hZYd(d)hZZhd*Z[eddd3Z\eddd5Z\eddd7Z\ ddd9Z\dd<Z]dd@Z^ed+dAddHZ_ed+dIddKZ_ed+d+dLddOZ_ed+d+dLddPZ_edQej`dd#ej`dddddddddddddddddddddd#ddRddSejadddddTddUeUd(dddej`dV+ddZ_ed+dAddZbed+dIddZbed+d+dLddZbed+d+dLddZbedQej`dd#ej`dddddddddddddddddddddd#ddRddSejadddddTddUeUd(dddej`dV+ddZbed+d+d+d+dddZced+d+d+d+dddZced+d+d+d+d+dddZcedQd#dd$dddddZcGddGejdZeddZfdddZgddZhddZiddZjddZkdZlddZmddZnddZodS)z Module contains tools for processing files into DataFrames or other objects GH#48849 provides a convenient way of deprecating keyword arguments ) annotations)abc defaultdictN) IO TYPE_CHECKINGAnyGenericLiteralSelf TypedDictUnpackcastoverload)lib) STR_NA_VALUES)AbstractMethodError ParserWarning) set_module)find_stack_level)check_dtype_backend) is_file_likeis_float is_integer is_list_like pandas_dtype)Series) DataFrame) RangeIndex) IOHandles get_handlestringify_pathvalidate_header_arg)ArrowParserWrapper) ParserBase is_index_colparser_defaults)CParserWrapper)FixedWidthFieldParser PythonParser)CallableHashableIterableMappingSequence) TracebackType) CompressionOptions CSVEngineDtypeArg DtypeBackendFilePath HashableT IndexLabel ReadCsvBufferStorageOptionsUsecolsArgTypeceZdZUded<ded<ded<ded<ded <d ed <d ed <ded<ded<ded<ded<ded<ded<ded<ded<ded<ded<ded <ded!<d"ed#<d$ed%<ded&<ded'<d(ed)<d*ed+<d,ed-<d*ed.<d,ed/<ded0<ded1<d*ed2<d*ed3<d*ed4<d*ed5<d6ed7<d,ed8<ded9<ded:<d;ed<<d=ed><d?ed@<dAS)B _read_sharedstr | None | lib.NoDefaultsep delimiter-int | Sequence[int] | None | Literal['infer']header)Sequence[Hashable] | None | lib.NoDefaultnames"IndexLabel | Literal[False] | None index_colr9usecolsDtypeArg | NonedtypeCSVEngine | Noneengine#Mapping[HashableT, Callable] | None converters list | None true_values false_valuesboolskipinitialspace3list[int] | int | Callable[[Hashable], bool] | Noneskiprowsint skipfooter int | NonenrowsLHashable | Iterable[Hashable] | Mapping[Hashable, Iterable[Hashable]] | None na_valueskeep_default_na na_filterskip_blank_lines bool | Sequence[Hashable] | None parse_dates str | dict[Hashable, str] | None date_formatdayfirst cache_datesr0 compression str | None thousandsstrdecimallineterminator quotecharquoting doublequote escapecharcommentencodingencoding_errorsstr | csv.Dialect | Nonedialect on_bad_lines low_memory memory_map.Literal['high', 'legacy', 'round_trip'] | Nonefloat_precisionStorageOptions | Nonestorage_optionsDtypeBackend | lib.NoDefault dtype_backendN__name__ __module__ __qualname____annotations__y/var/www/html/bestrading.cuttalo.com/services/ml-inference/venv/lib/python3.11/site-packages/pandas/io/parsers/readers.pyr;r;`s ('''----====88885555    7777    !!!!EEEE     55555555'''' """" ####))))GGGG....333333rr;F)totalc8eZdZUded<ded<ded<ded<dS) _C_Parser_Defaults Literal[True]rZrrLiteral[False]rsNoneruNrzrrrrrsBrrT)rZrrrsru_c_parser_defaultsc.eZdZUded<ded<ded<dS) _Fwf_DefaultszLiteral['infer']colspecsz Literal[100] infer_nrowsrwidthsNrzrrrrrs1LLLLLrrinferd)rrr _fwf_defaultsrTrrru>rVrlrprir`iterator chunksizerdrKrrrsrTrgrurP.namerevalrmin_valrSreturncdSNrrrrs rvalidate_integerrHKrfloatcdSrrrs rrrrrrUcdSrrrs rrrsTWTWrint | float | Nonec||Sd|dd|d}t|r2t||krt|t|}n$t|r||kst|t|S)a Checks whether the 'name' parameter for parsing is either an integer OR float that can SAFELY be cast to an integer without losing accuracy. Raises a ValueError if that is not the case. Parameters ---------- name : str Parameter name (used for error reporting) val : int or float The value to check min_val : int Minimum allowed value (val < min_val will result in a ValueError) N'sz' must be an integer >=d)rrS ValueErrorr)rrrmsgs rrrs$ { 8d 8 8 8W 8 8 8C}} s88s??S// !#hhoo#..oo s88OrrBSequence[Hashable] | Nonec|vt|tt|krtdt|ds+t |t jstddSdSdS)aZ Raise ValueError if the `names` parameter contains duplicates or has an invalid data type. Parameters ---------- names : array-like or None An array containing a list of the names used for the output DataFrame. Raises ------ ValueError If names are not unique or are not ordered (e.g. set). Nz Duplicate names are not allowed.F) allow_setsz&Names should be an ordered collection.)lensetrr isinstancerKeysView)rBs r_validate_namesrs  u::SZZ ( (?@@ @ 5 1 1 1 G5?s|5T5T GEFF F  G G G Grfilepath_or_buffer4FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str]DataFrame | TextFileReaderc|dd!|ddd|d<nd|d<|dd}|dd}|dd }t|ts$td t |j|d d kr#|rtd |tdnt d|d}|dd}t|ddt|fi|}|s|r|S|5| |cdddS#1swxYwYdS)zGeneric reader of line files.r]Nr_FTrrrnstrictz&encoding_errors must be a string, got rIpyarrowz@The 'iterator' option is not supported with the 'pyarrow' enginezAThe 'chunksize' option is not supported with the 'pyarrow' enginerVrB) getrrertyper{rrTextFileReaderread)rkwdsrrerrorsrVparsers r_readrs  xx t$$, 88M4 ( ( 0"'D  "&D xx E**Hd++IXX' 2 2F fc " "  LT&\\5J L L    xxY&&  R   S  ! %[)Q?? HHWd # #EDHHWd++,,,. 7 7$ 7 7FH ""{{5!!""""""""""""""""""sE00E47E4)rrrrrUnpack[_read_shared[HashableT]]rc dSrrrrrrs rread_csvr5 Sr)rrOc dSrrrs rrr?rr)rrrrc dSrrrs rrrI rc dSrrrs rrrS "%rpandas."rerror)+r=r>r@rBrDrErGrIrKrMrNrPrRrTrVrXrYrZr[r]r_r`rarrrbrdrfrgrhrirjrkrlrmrnrprqrrrsrurwryr=r<r>r@r?rArDrCrEr9rGrFrIrHrKrJrMrLrNrPrRrQrVrXrWrYrZr[r]r\r_r^r`rarbr0rdrcrfrgrhrirjrkrlrmrnrprorqrsrtrwrvryrxc+ t},|,d=|,d=t|%||||&|ddi|+}-|,|-t ||,S)aNV Read a comma-separated values (csv) file into DataFrame. Also supports optionally iterating or breaking of the file into chunks. Additional help can be found in the online docs for `IO Tools `_. Parameters ---------- filepath_or_buffer : 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, gs, and file. For file URLs, a host is expected. A local file could be: file://localhost/path/to/table.csv. 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``. sep : str, default ',' Character or regex pattern to treat as the delimiter. If ``sep=None``, the C engine cannot automatically detect the separator, but the Python parsing engine can, meaning the latter will be used and automatically detect the separator from only the first valid row of the file by Python's builtin sniffer tool, ``csv.Sniffer``. In addition, separators longer than 1 character and different from ``'\s+'`` will be interpreted as regular expressions and will also force the use of the Python parsing engine. Note that regex delimiters are prone to ignoring quoted data. Regex example: ``'\r\t'``. delimiter : str, optional Alias for ``sep``. header : int, Sequence of int, 'infer' or None, default 'infer' Row number(s) containing column labels and marking the start of the data (zero-indexed). Default behavior is to infer the column names: if no ``names`` are passed the behavior is identical to ``header=0`` and column names are inferred from the first line of the file, if column names are passed explicitly to ``names`` then the behavior is identical to ``header=None``. Explicitly pass ``header=0`` to be able to replace existing names. The header can be a list of integers that specify row locations for a :class:`~pandas.MultiIndex` on the columns e.g. ``[0, 1, 3]``. Intervening rows that are not specified will be skipped (e.g. 2 in this example is skipped). Note that this parameter ignores commented lines and empty lines if ``skip_blank_lines=True``, so ``header=0`` denotes the first line of data rather than the first line of the file. When inferred from the file contents, headers are kept distinct from each other by renaming duplicate names with a numeric suffix of the form ``".{{count}}"`` starting from 1, e.g. ``"foo"`` and ``"foo.1"``. Empty headers are named ``"Unnamed: {{i}}"`` or `` "Unnamed: {{i}}_level_{{level}}"`` in the case of MultiIndex columns. names : Sequence of Hashable, optional Sequence of column labels to apply. If the file contains a header row, then you should explicitly pass ``header=0`` to override the column names. Duplicates in this list are not allowed. index_col : Hashable, Sequence of Hashable or False, optional Column(s) to use as row label(s), denoted either by column labels or column indices. If a sequence of labels or indices is given, :class:`~pandas.MultiIndex` will be formed for the row labels. Note: ``index_col=False`` can be used to force pandas to *not* use the first column as the index, e.g., when you have a malformed file with delimiters at the end of each line. usecols : Sequence of Hashable or Callable, optional Subset of columns to select, denoted either by column labels or column indices. If list-like, all elements must either be positional (i.e. integer indices into the document columns) or strings that correspond to column names provided either by the user in ``names`` or inferred from the document header row(s). If ``names`` are given, the document header row(s) are not taken into account. For example, a valid list-like ``usecols`` parameter would be ``[0, 1, 2]`` or ``['foo', 'bar', 'baz']``. Element order is ignored, so ``usecols=[0, 1]`` is the same as ``[1, 0]``. To instantiate a :class:`~pandas.DataFrame` from ``data`` with element order preserved use ``pd.read_csv(data, usecols=['foo', 'bar'])[['foo', 'bar']]`` for columns in ``['foo', 'bar']`` order or ``pd.read_csv(data, usecols=['foo', 'bar'])[['bar', 'foo']]`` for ``['bar', 'foo']`` order. If callable, the callable function will be evaluated against the column names, returning names where the callable function evaluates to ``True``. An example of a valid callable argument would be ``lambda x: x.upper() in ['AAA', 'BBB', 'DDD']``. Using this parameter results in much faster parsing time and lower memory usage. dtype : dtype or dict of {{Hashable : dtype}}, optional Data type(s) to apply to either the whole dataset or individual columns. E.g., ``{{'a': np.float64, 'b': np.int32, 'c': 'Int64'}}`` Use ``str`` or ``object`` together with suitable ``na_values`` settings to preserve and not interpret ``dtype``. If ``converters`` are specified, they will be applied INSTEAD of ``dtype`` conversion. Specify a ``defaultdict`` as input where the default determines the ``dtype`` of the columns which are not explicitly listed. engine : {{'c', 'python', 'pyarrow'}}, optional Parser engine to use. The C and pyarrow engines are faster, while the python engine is currently more feature-complete. Multithreading is currently only supported by the pyarrow engine. Some features of the "pyarrow" engine are unsupported or may not work correctly. converters : dict of {{Hashable : Callable}}, optional Functions for converting values in specified columns. Keys can either be column labels or column indices. true_values : list, optional Values to consider as ``True`` in addition to case-insensitive variants of 'True'. false_values : list, optional Values to consider as ``False`` in addition to case-insensitive variants of 'False'. skipinitialspace : bool, default False Skip spaces after delimiter. skiprows : int, list of int or Callable, optional Line numbers to skip (0-indexed) or number of lines to skip (``int``) at the start of the file. If callable, the callable function will be evaluated against the row indices, returning ``True`` if the row should be skipped and ``False`` otherwise. An example of a valid callable argument would be ``lambda x: x in [0, 2]``. skipfooter : int, default 0 Number of lines at bottom of file to skip (Unsupported with ``engine='c'``). nrows : int, optional Number of rows of file to read. Useful for reading pieces of large files. Refers to the number of data rows in the returned DataFrame, excluding: * The header row containing column names. * Rows before the header row, if ``header=1`` or larger. Example usage: * To read the first 999,999 (non-header) rows: ``read_csv(..., nrows=999999)`` * To read rows 1,000,000 through 1,999,999: ``read_csv(..., skiprows=1000000, nrows=999999)`` na_values : Hashable, Iterable of Hashable or dict of {{Hashable : Iterable}}, optional Additional strings to recognize as ``NA``/``NaN``. If ``dict`` passed, specific per-column ``NA`` values. By default the following values are interpreted as ``NaN``: empty string, "NaN", "N/A", "NULL", and other common representations of missing data. keep_default_na : bool, default True Whether or not to include the default ``NaN`` values when parsing the data. Depending on whether ``na_values`` is passed in, the behavior is as follows: * If ``keep_default_na`` is ``True``, and ``na_values`` are specified, ``na_values`` is appended to the default ``NaN`` values used for parsing. * If ``keep_default_na`` is ``True``, and ``na_values`` are not specified, only the default ``NaN`` values are used for parsing. * If ``keep_default_na`` is ``False``, and ``na_values`` are specified, only the ``NaN`` values specified ``na_values`` are used for parsing. * If ``keep_default_na`` is ``False``, and ``na_values`` are not specified, no strings will be parsed as ``NaN``. Note that if ``na_filter`` is passed in as ``False``, the ``keep_default_na`` and ``na_values`` parameters will be ignored. na_filter : bool, default True Detect missing value markers (empty strings and the value of ``na_values``). In data without any ``NA`` values, passing ``na_filter=False`` can improve the performance of reading a large file. skip_blank_lines : bool, default True If ``True``, skip over blank lines rather than interpreting as ``NaN`` values. parse_dates : bool, None, list of Hashable, default None The behavior is as follows: * ``bool``. If ``True`` -> try parsing the index. * ``None``. Behaves like ``True`` if ``date_format`` is specified. * ``list`` of ``int`` or names. e.g. If ``[1, 2, 3]`` -> try parsing columns 1, 2, 3 each as a separate date column. If a column or index cannot be represented as an array of ``datetime``, say because of an unparsable value or a mixture of timezones, the column or index will be returned unaltered as an ``object`` data type. For non-standard ``datetime`` parsing, use :func:`~pandas.to_datetime` after :func:`~pandas.read_csv`. Note: A fast-path exists for iso8601-formatted dates. date_format : str or dict of column -> format, optional Format to use for parsing dates and/or times when used in conjunction with ``parse_dates``. The strftime to parse time, e.g. :const:`"%d/%m/%Y"`. See `strftime documentation `_ for more information on choices, though note that :const:`"%f"`` will parse all the way up to nanoseconds. You can also pass: - "ISO8601", to parse any `ISO8601 `_ time string (not necessarily in exactly the same format); - "mixed", to infer the format for each element individually. This is risky, and you should probably use it along with `dayfirst`. .. versionadded:: 2.0.0 dayfirst : bool, default False DD/MM format dates, international and European format. cache_dates : bool, default True If ``True``, use a cache of unique, converted dates to apply the ``datetime`` conversion. May produce significant speed-up when parsing duplicate date strings, especially ones with timezone offsets. iterator : bool, default False Return ``TextFileReader`` object for iteration or getting chunks with ``get_chunk()``. chunksize : int, optional Number of lines to read from the file per chunk. Passing a value will cause the function to return a ``TextFileReader`` object for iteration. See the `IO Tools docs `_ for more information on ``iterator`` and ``chunksize``. compression : str or dict, default 'infer' For on-the-fly decompression of on-disk data. If 'infer' and 'filepath_or_buffer' is path-like, then detect compression from the following extensions: '.gz', '.bz2', '.zip', '.xz', '.zst', '.tar', '.tar.gz', '.tar.xz' or '.tar.bz2' (otherwise no compression). If using 'zip' or 'tar', the ZIP file must contain only one data file to be read in. Set to ``None`` for no decompression. Can also be a dict with key ``'method'`` set to one of {``'zip'``, ``'gzip'``, ``'bz2'``, ``'zstd'``, ``'xz'``, ``'tar'``} and other key-value pairs are forwarded to ``zipfile.ZipFile``, ``gzip.GzipFile``, ``bz2.BZ2File``, ``zstandard.ZstdDecompressor``, ``lzma.LZMAFile`` or ``tarfile.TarFile``, respectively. As an example, the following could be passed for Zstandard decompression using a custom compression dictionary: ``compression={'method': 'zstd', 'dict_data': my_compression_dict}``. thousands : str (length 1), optional Character acting as the thousands separator in numerical values. decimal : str (length 1), default '.' Character to recognize as decimal point (e.g., use ',' for European data). lineterminator : str (length 1), optional Character used to denote a line break. Only valid with C parser. quotechar : str (length 1), optional Character used to denote the start and end of a quoted item. Quoted items can include the ``delimiter`` and it will be ignored. quoting : {{0 or csv.QUOTE_MINIMAL, 1 or csv.QUOTE_ALL, 2 or csv.QUOTE_NONNUMERIC, 3 or csv.QUOTE_NONE}}, default csv.QUOTE_MINIMAL Control field quoting behavior per ``csv.QUOTE_*`` constants. Default is ``csv.QUOTE_MINIMAL`` (i.e., 0) which implies that only fields containing special characters are quoted (e.g., characters defined in ``quotechar``, ``delimiter``, or ``lineterminator``. doublequote : bool, default True When ``quotechar`` is specified and ``quoting`` is not ``QUOTE_NONE``, indicate whether or not to interpret two consecutive ``quotechar`` elements INSIDE a field as a single ``quotechar`` element. escapechar : str (length 1), optional Character used to escape other characters. comment : str (length 1), optional Character indicating that the remainder of line should not be parsed. If found at the beginning of a line, the line will be ignored altogether. This parameter must be a single character. Like empty lines (as long as ``skip_blank_lines=True``), fully commented lines are ignored by the parameter ``header`` but not by ``skiprows``. For example, if ``comment='#'``, parsing ``#empty\na,b,c\n1,2,3`` with ``header=0`` will result in ``'a,b,c'`` being treated as the header. encoding : str, optional, default 'utf-8' Encoding to use for UTF when reading/writing (ex. ``'utf-8'``). `List of Python standard encodings `_ . encoding_errors : str, optional, default 'strict' How encoding errors are treated. `List of possible values `_ . dialect : str or csv.Dialect, optional If provided, this parameter will override values (default or not) for the following parameters: ``delimiter``, ``doublequote``, ``escapechar``, ``skipinitialspace``, ``quotechar``, and ``quoting``. If it is necessary to override values, a ``ParserWarning`` will be issued. See ``csv.Dialect`` documentation for more details. on_bad_lines : {{'error', 'warn', 'skip'}} or Callable, default 'error' Specifies what to do upon encountering a bad line (a line with too many fields). Allowed values are: - ``'error'``, raise an Exception when a bad line is encountered. - ``'warn'``, raise a warning when a bad line is encountered and skip that line. - ``'skip'``, skip bad lines without raising or warning when they are encountered. - Callable, function that will process a single bad line. - With ``engine='python'``, function with signature ``(bad_line: list[str]) -> list[str] | None``. ``bad_line`` is a list of strings split by the ``sep``. If the function returns ``None``, the bad line will be ignored. If the function returns a new ``list`` of strings with more elements than expected, a ``ParserWarning`` will be emitted while dropping extra elements. - With ``engine='pyarrow'``, function with signature as described in pyarrow documentation: `invalid_row_handler `_. .. versionchanged:: 2.2.0 Callable for ``engine='pyarrow'`` low_memory : bool, default True Internally process the file in chunks, resulting in lower memory use while parsing, but possibly mixed type inference. To ensure no mixed types either set ``False``, or specify the type with the ``dtype`` parameter. Note that the entire file is read into a single :class:`~pandas.DataFrame` regardless, use the ``chunksize`` or ``iterator`` parameter to return the data in chunks. (Only valid with C parser). memory_map : bool, default False If a filepath is provided for ``filepath_or_buffer``, map the file object directly onto memory and access the data directly from there. Using this option can improve performance because there is no longer any I/O overhead. float_precision : {{'high', 'legacy', 'round_trip'}}, optional Specifies which converter the C engine should use for floating-point values. The options are ``None`` or ``'high'`` for the ordinary converter, ``'legacy'`` for the original lower precision pandas converter, and ``'round_trip'`` for the round-trip converter. storage_options : dict, optional Extra options that make sense for a particular storage connection, e.g. host, port, username, password, etc. For HTTP(S) URLs the key-value pairs are forwarded to ``urllib.request.Request`` as header options. For other URLs (e.g. starting with "s3://", and "gcs://") the key-value pairs are forwarded to ``fsspec.open``. Please see ``fsspec`` and ``urllib`` for more details, and for more examples on storage options refer `here `_. dtype_backend : {{'numpy_nullable', 'pyarrow'}} Back-end data type applied to the resultant :class:`DataFrame` (still experimental). If not specified, the default behavior is to not use nullable data types. If specified, the behavior is as follows: * ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame` * ``"pyarrow"``: returns pyarrow-backed nullable :class:`ArrowDtype` :class:`DataFrame` .. versionadded:: 2.0 Returns ------- DataFrame or TextFileReader A comma-separated values (csv) file is returned as two-dimensional data structure with labeled axes. See Also -------- DataFrame.to_csv : Write DataFrame to a comma-separated values (csv) file. read_table : Read general delimited file into DataFrame. read_fwf : Read a table of fixed-width formatted lines into DataFrame. Examples -------- >>> pd.read_csv("data.csv") # doctest: +SKIP Name Value 0 foo 1 1 bar 2 2 #baz 3 Index and header can be specified via the `index_col` and `header` arguments. >>> pd.read_csv("data.csv", header=None) # doctest: +SKIP 0 1 0 Name Value 1 foo 1 2 bar 2 3 #baz 3 >>> pd.read_csv("data.csv", index_col="Value") # doctest: +SKIP Name Value 1 foo 2 bar 3 #baz Column types are inferred but can be explicitly specified using the dtype argument. >>> pd.read_csv("data.csv", dtype={{"Value": float}}) # doctest: +SKIP Name Value 0 foo 1.0 1 bar 2.0 2 #baz 3.0 True, False, and NA values, and thousands separators have defaults, but can be explicitly specified, too. Supply the values you would like as strings or lists of strings! >>> pd.read_csv("data.csv", na_values=["foo", "bar"]) # doctest: +SKIP Name Value 0 NaN 1 1 NaN 2 2 #baz 3 Comment lines in the input file can be skipped using the `comment` argument. >>> pd.read_csv("data.csv", comment="#") # doctest: +SKIP Name Value 0 foo 1 1 bar 2 By default, columns with dates will be read as ``object`` rather than ``datetime``. >>> df = pd.read_csv("tmp.csv") # doctest: +SKIP >>> df # doctest: +SKIP col 1 col 2 col 3 0 10 10/04/2018 Sun 15 Jan 2023 1 20 15/04/2018 Fri 12 May 2023 >>> df.dtypes # doctest: +SKIP col 1 int64 col 2 object col 3 object dtype: object Specific columns can be parsed as dates by using the `parse_dates` and `date_format` arguments. >>> df = pd.read_csv( ... "tmp.csv", ... parse_dates=[1, 2], ... date_format={{"col 2": "%d/%m/%Y", "col 3": "%a %d %b %Y"}}, ... ) # doctest: +SKIP >>> df.dtypes # doctest: +SKIP col 1 int64 col 2 datetime64[ns] col 3 datetime64[ns] dtype: object rr=r>,defaultsrylocalscopy_refine_defaults_readupdater.rr=r>r@rBrDrErGrIrKrMrNrPrRrTrVrXrYrZr[r]r_r`rarrrbrdrfrgrhrirjrkrlrmrnrprqrrrsrurwryr kwds_defaultss. rrr]s|x 88==??D !" U )  s##   M KK  #T * **rc dSrrrs r read_tablerlrrc dSrrrs rrrvrrc dSrrrs rrrrrc dSrrrs rrrrrc+ t},|,d=|,d=t|%||||&|ddi|+}-|,|-t ||,S)amV Read general delimited file into DataFrame. Also supports optionally iterating or breaking of the file into chunks. Additional help can be found in the online docs for `IO Tools `_. Parameters ---------- filepath_or_buffer : 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, gs, and file. For file URLs, a host is expected. A local file could be: file://localhost/path/to/table.csv. 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``. sep : str, default '\t' (tab-stop) Character or regex pattern to treat as the delimiter. If ``sep=None``, the C engine cannot automatically detect the separator, but the Python parsing engine can, meaning the latter will be used and automatically detect the separator from only the first valid row of the file by Python's builtin sniffer tool, ``csv.Sniffer``. In addition, separators longer than 1 character and different from ``'\s+'`` will be interpreted as regular expressions and will also force the use of the Python parsing engine. Note that regex delimiters are prone to ignoring quoted data. Regex example: ``'\r\t'``. delimiter : str, optional Alias for ``sep``. header : int, Sequence of int, 'infer' or None, default 'infer' Row number(s) containing column labels and marking the start of the data (zero-indexed). Default behavior is to infer the column names: if no ``names`` are passed the behavior is identical to ``header=0`` and column names are inferred from the first line of the file, if column names are passed explicitly to ``names`` then the behavior is identical to ``header=None``. Explicitly pass ``header=0`` to be able to replace existing names. The header can be a list of integers that specify row locations for a :class:`~pandas.MultiIndex` on the columns e.g. ``[0, 1, 3]``. Intervening rows that are not specified will be skipped (e.g. 2 in this example is skipped). Note that this parameter ignores commented lines and empty lines if ``skip_blank_lines=True``, so ``header=0`` denotes the first line of data rather than the first line of the file. When inferred from the file contents, headers are kept distinct from each other by renaming duplicate names with a numeric suffix of the form ``".{{count}}"`` starting from 1, e.g. ``"foo"`` and ``"foo.1"``. Empty headers are named ``"Unnamed: {{i}}"`` or ``"Unnamed: {{i}}_level_{{level}}"`` in the case of MultiIndex columns. names : Sequence of Hashable, optional Sequence of column labels to apply. If the file contains a header row, then you should explicitly pass ``header=0`` to override the column names. Duplicates in this list are not allowed. index_col : Hashable, Sequence of Hashable or False, optional Column(s) to use as row label(s), denoted either by column labels or column indices. If a sequence of labels or indices is given, :class:`~pandas.MultiIndex` will be formed for the row labels. Note: ``index_col=False`` can be used to force pandas to *not* use the first column as the index, e.g., when you have a malformed file with delimiters at the end of each line. usecols : Sequence of Hashable or Callable, optional Subset of columns to select, denoted either by column labels or column indices. If list-like, all elements must either be positional (i.e. integer indices into the document columns) or strings that correspond to column names provided either by the user in ``names`` or inferred from the document header row(s). If ``names`` are given, the document header row(s) are not taken into account. For example, a valid list-like ``usecols`` parameter would be ``[0, 1, 2]`` or ``['foo', 'bar', 'baz']``. Element order is ignored, so ``usecols=[0, 1]`` is the same as ``[1, 0]``. To instantiate a :class:`~pandas.DataFrame` from ``data`` with element order preserved use ``pd.read_csv(data, usecols=['foo', 'bar'])[['foo', 'bar']]`` for columns in ``['foo', 'bar']`` order or ``pd.read_csv(data, usecols=['foo', 'bar'])[['bar', 'foo']]`` for ``['bar', 'foo']`` order. If callable, the callable function will be evaluated against the column names, returning names where the callable function evaluates to ``True``. An example of a valid callable argument would be ``lambda x: x.upper() in ['AAA', 'BBB', 'DDD']``. Using this parameter results in much faster parsing time and lower memory usage. dtype : dtype or dict of {{Hashable : dtype}}, optional Data type(s) to apply to either the whole dataset or individual columns. E.g., ``{{'a': np.float64, 'b': np.int32, 'c': 'Int64'}}`` Use ``str`` or ``object`` together with suitable ``na_values`` settings to preserve and not interpret ``dtype``. If ``converters`` are specified, they will be applied INSTEAD of ``dtype`` conversion. Specify a ``defaultdict`` as input where the default determines the ``dtype`` of the columns which are not explicitly listed. engine : {{'c', 'python', 'pyarrow'}}, optional Parser engine to use. The C and pyarrow engines are faster, while the python engine is currently more feature-complete. Multithreading is currently only supported by the pyarrow engine. The 'pyarrow' engine is an *experimental* engine, and some features are unsupported, or may not work correctly, with this engine. converters : dict of {{Hashable : Callable}}, optional Functions for converting values in specified columns. Keys can either be column labels or column indices. true_values : list, optional Values to consider as ``True`` in addition to case-insensitive variants of 'True'. false_values : list, optional Values to consider as ``False`` in addition to case-insensitive variants of 'False'. skipinitialspace : bool, default False Skip spaces after delimiter. skiprows : int, list of int or Callable, optional Line numbers to skip (0-indexed) or number of lines to skip (``int``) at the start of the file. If callable, the callable function will be evaluated against the row indices, returning ``True`` if the row should be skipped and ``False`` otherwise. An example of a valid callable argument would be ``lambda x: x in [0, 2]``. skipfooter : int, default 0 Number of lines at bottom of file to skip (Unsupported with ``engine='c'``). nrows : int, optional Number of rows of file to read. Useful for reading pieces of large files. Refers to the number of data rows in the returned DataFrame, excluding: * The header row containing column names. * Rows before the header row, if ``header=1`` or larger. Example usage: * To read the first 999,999 (non-header) rows: ``read_csv(..., nrows=999999)`` * To read rows 1,000,000 through 1,999,999: ``read_csv(..., skiprows=1000000, nrows=999999)`` na_values : Hashable, Iterable of Hashable or dict of {{Hashable : Iterable}}, optional Additional strings to recognize as ``NA``/``NaN``. If ``dict`` passed, specific per-column ``NA`` values. By default the following values are interpreted as ``NaN``: empty string, "NaN", "N/A", "NULL", and other common representations of missing data. keep_default_na : bool, default True Whether or not to include the default ``NaN`` values when parsing the data. Depending on whether ``na_values`` is passed in, the behavior is as follows: * If ``keep_default_na`` is ``True``, and ``na_values`` are specified, ``na_values`` is appended to the default ``NaN`` values used for parsing. * If ``keep_default_na`` is ``True``, and ``na_values`` are not specified, only the default ``NaN`` values are used for parsing. * If ``keep_default_na`` is ``False``, and ``na_values`` are specified, only the ``NaN`` values specified ``na_values`` are used for parsing. * If ``keep_default_na`` is ``False``, and ``na_values`` are not specified, no strings will be parsed as ``NaN``. Note that if ``na_filter`` is passed in as ``False``, the ``keep_default_na`` and ``na_values`` parameters will be ignored. na_filter : bool, default True Detect missing value markers (empty strings and the value of ``na_values``). In data without any ``NA`` values, passing ``na_filter=False`` can improve the performance of reading a large file. skip_blank_lines : bool, default True If ``True``, skip over blank lines rather than interpreting as ``NaN`` values. parse_dates : bool, None, list of Hashable, default None The behavior is as follows: * ``bool``. If ``True`` -> try parsing the index. * ``None``. Behaves like ``True`` if ``date_format`` is specified. * ``list`` of ``int`` or names. e.g. If ``[1, 2, 3]`` -> try parsing columns 1, 2, 3 each as a separate date column. If a column or index cannot be represented as an array of ``datetime``, say because of an unparsable value or a mixture of timezones, the column or index will be returned unaltered as an ``object`` data type. For non-standard ``datetime`` parsing, use :func:`~pandas.to_datetime` after :func:`~pandas.read_csv`. Note: A fast-path exists for iso8601-formatted dates. date_format : str or dict of column -> format, optional Format to use for parsing dates and/or times when used in conjunction with ``parse_dates``. The strftime to parse time, e.g. :const:`"%d/%m/%Y"`. See `strftime documentation `_ for more information on choices, though note that :const:`"%f"`` will parse all the way up to nanoseconds. You can also pass: - "ISO8601", to parse any `ISO8601 `_ time string (not necessarily in exactly the same format); - "mixed", to infer the format for each element individually. This is risky, and you should probably use it along with `dayfirst`. .. versionadded:: 2.0.0 dayfirst : bool, default False DD/MM format dates, international and European format. cache_dates : bool, default True If ``True``, use a cache of unique, converted dates to apply the ``datetime`` conversion. May produce significant speed-up when parsing duplicate date strings, especially ones with timezone offsets. iterator : bool, default False Return ``TextFileReader`` object for iteration or getting chunks with ``get_chunk()``. chunksize : int, optional Number of lines to read from the file per chunk. Passing a value will cause the function to return a ``TextFileReader`` object for iteration. See the `IO Tools docs `_ for more information on ``iterator`` and ``chunksize``. compression : str or dict, default 'infer' For on-the-fly decompression of on-disk data. If 'infer' and 'filepath_or_buffer' is path-like, then detect compression from the following extensions: '.gz', '.bz2', '.zip', '.xz', '.zst', '.tar', '.tar.gz', '.tar.xz' or '.tar.bz2' (otherwise no compression). If using 'zip' or 'tar', the ZIP file must contain only one data file to be read in. Set to ``None`` for no decompression. Can also be a dict with key ``'method'`` set to one of {``'zip'``, ``'gzip'``, ``'bz2'``, ``'zstd'``, ``'xz'``, ``'tar'``} and other key-value pairs are forwarded to ``zipfile.ZipFile``, ``gzip.GzipFile``, ``bz2.BZ2File``, ``zstandard.ZstdDecompressor``, ``lzma.LZMAFile`` or ``tarfile.TarFile``, respectively. As an example, the following could be passed for Zstandard decompression using a custom compression dictionary: ``compression={'method': 'zstd', 'dict_data': my_compression_dict}``. thousands : str (length 1), optional Character acting as the thousands separator in numerical values. decimal : str (length 1), default '.' Character to recognize as decimal point (e.g., use ',' for European data). lineterminator : str (length 1), optional Character used to denote a line break. Only valid with C parser. quotechar : str (length 1), optional Character used to denote the start and end of a quoted item. Quoted items can include the ``delimiter`` and it will be ignored. quoting : {{0 or csv.QUOTE_MINIMAL, 1 or csv.QUOTE_ALL, 2 or csv.QUOTE_NONNUMERIC, 3 or csv.QUOTE_NONE}}, default csv.QUOTE_MINIMAL Control field quoting behavior per ``csv.QUOTE_*`` constants. Default is ``csv.QUOTE_MINIMAL`` (i.e., 0) which implies that only fields containing special characters are quoted (e.g., characters defined in ``quotechar``, ``delimiter``, or ``lineterminator``. doublequote : bool, default True When ``quotechar`` is specified and ``quoting`` is not ``QUOTE_NONE``, indicate whether or not to interpret two consecutive ``quotechar`` elements INSIDE a field as a single ``quotechar`` element. escapechar : str (length 1), optional Character used to escape other characters. comment : str (length 1), optional Character indicating that the remainder of line should not be parsed. If found at the beginning of a line, the line will be ignored altogether. This parameter must be a single character. Like empty lines (as long as ``skip_blank_lines=True``), fully commented lines are ignored by the parameter ``header`` but not by ``skiprows``. For example, if ``comment='#'``, parsing ``#empty\na,b,c\n1,2,3`` with ``header=0`` will result in ``'a,b,c'`` being treated as the header. encoding : str, optional, default 'utf-8' Encoding to use for UTF when reading/writing (ex. ``'utf-8'``). `List of Python standard encodings `_ . encoding_errors : str, optional, default 'strict' How encoding errors are treated. `List of possible values `_ . dialect : str or csv.Dialect, optional If provided, this parameter will override values (default or not) for the following parameters: ``delimiter``, ``doublequote``, ``escapechar``, ``skipinitialspace``, ``quotechar``, and ``quoting``. If it is necessary to override values, a ``ParserWarning`` will be issued. See ``csv.Dialect`` documentation for more details. on_bad_lines : {{'error', 'warn', 'skip'}} or Callable, default 'error' Specifies what to do upon encountering a bad line (a line with too many fields). Allowed values are: - ``'error'``, raise an Exception when a bad line is encountered. - ``'warn'``, raise a warning when a bad line is encountered and skip that line. - ``'skip'``, skip bad lines without raising or warning when they are encountered. - Callable, function that will process a single bad line. - With ``engine='python'``, function with signature ``(bad_line: list[str]) -> list[str] | None``. ``bad_line`` is a list of strings split by the ``sep``. If the function returns ``None``, the bad line will be ignored. If the function returns a new ``list`` of strings with more elements than expected, a ``ParserWarning`` will be emitted while dropping extra elements. - With ``engine='pyarrow'``, function with signature as described in pyarrow documentation: `invalid_row_handler `_. .. versionadded:: 2.2.0 Callable for ``engine='pyarrow'`` low_memory : bool, default True Internally process the file in chunks, resulting in lower memory use while parsing, but possibly mixed type inference. To ensure no mixed types either set ``False``, or specify the type with the ``dtype`` parameter. Note that the entire file is read into a single :class:`~pandas.DataFrame` regardless, use the ``chunksize`` or ``iterator`` parameter to return the data in chunks. (Only valid with C parser). memory_map : bool, default False If a filepath is provided for ``filepath_or_buffer``, map the file object directly onto memory and access the data directly from there. Using this option can improve performance because there is no longer any I/O overhead. float_precision : {{'high', 'legacy', 'round_trip'}}, optional Specifies which converter the C engine should use for floating-point values. The options are ``None`` or ``'high'`` for the ordinary converter, ``'legacy'`` for the original lower precision pandas converter, and ``'round_trip'`` for the round-trip converter. storage_options : dict, optional Extra options that make sense for a particular storage connection, e.g. host, port, username, password, etc. For HTTP(S) URLs the key-value pairs are forwarded to ``urllib.request.Request`` as header options. For other URLs (e.g. starting with "s3://", and "gcs://") the key-value pairs are forwarded to ``fsspec.open``. Please see ``fsspec`` and ``urllib`` for more details, and for more examples on storage options refer `here `_. dtype_backend : {{'numpy_nullable', 'pyarrow'}} Back-end data type applied to the resultant :class:`DataFrame` (still experimental). If not specified, the default behavior is to not use nullable data types. If specified, the behavior is as follows: * ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame` * ``"pyarrow"``: returns pyarrow-backed nullable :class:`ArrowDtype` :class:`DataFrame` .. versionadded:: 2.0 Returns ------- DataFrame or TextFileReader A comma-separated values (csv) file is returned as two-dimensional data structure with labeled axes. See Also -------- DataFrame.to_csv : Write DataFrame to a comma-separated values (csv) file. read_csv : Read a comma-separated values (csv) file into DataFrame. read_fwf : Read a table of fixed-width formatted lines into DataFrame. Examples -------- >>> pd.read_table("data.csv") # doctest: +SKIP Name Value 0 foo 1 1 bar 2 2 #baz 3 Index and header can be specified via the `index_col` and `header` arguments. >>> pd.read_table("data.csv", header=None) # doctest: +SKIP 0 1 0 Name Value 1 foo 1 2 bar 2 3 #baz 3 >>> pd.read_table("data.csv", index_col="Value") # doctest: +SKIP Name Value 1 foo 2 bar 3 #baz Column types are inferred but can be explicitly specified using the dtype argument. >>> pd.read_table("data.csv", dtype={{"Value": float}}) # doctest: +SKIP Name Value 0 foo 1.0 1 bar 2.0 2 #baz 3.0 True, False, and NA values, and thousands separators have defaults, but can be explicitly specified, too. Supply the values you would like as strings or lists of strings! >>> pd.read_table("data.csv", na_values=["foo", "bar"]) # doctest: +SKIP Name Value 0 NaN 1 1 NaN 2 2 #baz 3 Comment lines in the input file can be skipped using the `comment` argument. >>> pd.read_table("data.csv", comment="#") # doctest: +SKIP Name Value 0 foo 1 1 bar 2 By default, columns with dates will be read as ``object`` rather than ``datetime``. >>> df = pd.read_table("tmp.csv") # doctest: +SKIP >>> df # doctest: +SKIP col 1 col 2 col 3 0 10 10/04/2018 Sun 15 Jan 2023 1 20 15/04/2018 Fri 12 May 2023 >>> df.dtypes # doctest: +SKIP col 1 int64 col 2 object col 3 object dtype: object Specific columns can be parsed as dates by using the `parse_dates` and `date_format` arguments. >>> df = pd.read_table( ... "tmp.csv", ... parse_dates=[1, 2], ... date_format={{"col 2": "%d/%m/%Y", "col 3": "%a %d %b %Y"}}, ... ) # doctest: +SKIP >>> df.dtypes # doctest: +SKIP col 1 int64 col 2 datetime64[ns] col 3 datetime64[ns] dtype: object rr=r> rrrs. rrrs|p 88==??D !" U )  t$#   M KK  #T * **r)rrrrr&Sequence[tuple[int, int]] | str | NonerSequence[int] | Nonerc dSrrrrrrrrrs rread_fwfr Sr)rrrrc dSrrrs rrrrr)rrrrrc dSrrrs rrrs rc  ||td|dvr|td|(gd}}|D]!}||||zf||z }"|J|d} | | tjurt | t |kr|dkrd} |dJ|d} | d ur1t | sd } n| tjusJt | } |d 2t | | zt |krtd t|d tjt||||d||dzS)ap Read a table of fixed-width formatted lines into DataFrame. Also supports optionally iterating or breaking of the file into chunks. Additional help can be found in the `online docs for IO Tools `_. Parameters ---------- filepath_or_buffer : str, path object, or file-like object String, path object (implementing ``os.PathLike[str]``), or file-like object implementing a text ``read()`` function.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.csv``. colspecs : list of tuple (int, int) or 'infer'. optional A list of tuples giving the extents of the fixed-width fields of each line as half-open intervals (i.e., [from, to] ). String value 'infer' can be used to instruct the parser to try detecting the column specifications from the first 100 rows of the data which are not being skipped via skiprows (default='infer'). widths : list of int, optional A list of field widths which can be used instead of 'colspecs' if the intervals are contiguous. infer_nrows : int, default 100 The number of rows to consider when letting the parser determine the `colspecs`. iterator : bool, default False Return ``TextFileReader`` object for iteration or getting chunks with ``get_chunk()``. chunksize : int, optional Number of lines to read from the file per chunk. **kwds : optional Optional keyword arguments can be passed to ``TextFileReader``. Returns ------- DataFrame or TextFileReader A comma-separated values (csv) file is returned as two-dimensional data structure with labeled axes. See Also -------- DataFrame.to_csv : Write DataFrame to a comma-separated values (csv) file. read_csv : Read a comma-separated values (csv) file into DataFrame. Examples -------- >>> pd.read_fwf("data.csv") # doctest: +SKIP Nz&Must specify either colspecs or widths)Nrz4You must specify only one of 'widths' and 'colspecs'rrBrrDFrrEz-Length of colspecs must match length of namesry python-fwf)rrrIrr) rappendrr no_defaultrrr setdefaultr) rrrrrrrcolwrB len_indexrDs rrrs@FNABBB&&6+=OPPPA#  A OOS#'N + + + 1HCC     HHW  E U#.88 u::X & &8w+>+>Ixx $$0!%+!6!6 E))' 223$%  )>>>>$' NN xx ""*s5zzI/EX/V/V !PQQQHHIII   &" "       rc~eZdZdZ d'd(d Zd)d Zd*d Zd+dZd,dZd-dZ d.d/dZ d)dZ d'd0dZ d'd1dZ d2dZd3d&ZdS)4rzF Passed dialect overrides any of the related parser options Nf;FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str] | listrIrHrrc |d}nd}d}||_|d||_t|t |}|%|dkrt dt ||}|dddkr|d d nd|d<||_d |_| |}|d d|d <| d d|_ | d d|_ | |||||\|_|_d|vr|d|jd<d|_|||j|_dS)NTpythonFengine_specifiedrz?The 'dialect' option is not supported with the 'pyarrow' enginer@rrBrrwrrVhas_index_names)rIr_engine_specified_validate_skipfooter_extract_dialectr_merge_with_dialect_properties orig_options_currow_get_options_with_defaultspoprrV_check_file_or_buffer_clean_optionsoptionshandles _make_engine_engine)selfrrIrrrprs r__init__zTextFileReader.__init__@s  #  F$  !%*<>N!O!OT""""4((  "" U2'4@@D 88Hg & &' 1 1"&((7"3"3";QQDN  11&99%)XX.?%F%F!" [$77[[$//  ""1f---$($7$7$H$H! dk  $ $.23D.EDL* +)- ((DK88 rcx|j|j|jdSr)rcloserrs rrzTextFileReader.closeos8 < # L    rr1dict[str, Any]cX|j}i}tjD]]\}}|||}|dkr7|tvr.||kr(|t |d|krt d|d|||<^tD]W\}}||vrG||}|dkr8||kr2d|vr |tvrn'd|vr |tvrnt d|d|dn|}|||<X|d kr8tD]\}}|||||<|S) NrvaluezThe z2 option is not supported with the 'pyarrow' enginecrz" option is not supported with the z enginer) rr&itemsr_pyarrow_unsupportedgetattrrr_python_unsupportedr)rrIrrargnamedefaultr s rrz)TextFileReader._get_options_with_defaultsts !0 5 7 7 % % GWHHWg..E)##333W$$WUGW==== X7XXX %GG   2 8 8 : : % % GW$W S==Ug%5%56))g=P.P.P"f,,@T1T1T(1711%111  $GG   \ ! !$1$7$7$9$9 > > #'88GW#=#=  rc Nt|r%|dkrt|dstdt|dr\|j}|jdd}|dup|du}||kr.|s.t |dd}td|d|d|d dSdSdS) Nr __iter__zrz\s+Tdelim_whitespace)rrzthe 'zr' engine does not support regex separators (separators > 1 char and different from '\s+' are interpreted as regex)utf-8Fzthe separator encoded in z is > 1 char long, and the 'z)' engine does not support such separatorsrhzNord(quotechar) > 127, meaning the quotechar is larger than one byte, and the 'z)' engine does not support such quotecharsz,Falling back to the 'python' engine because z, but this causes z= to be ignored as it is not supported by the 'python' engine.z;; you can avoid this warning by specifying engine='python'. stacklevelrDrBrKrXrRr@z)The value of index_col couldn't be 'True'z8Type converters must be a dict or subclass, input was a rYr)floatifyz@skiprows argument must be an integer when using engine='pyarrow' na_fvalues)#rrsysgetfilesystemencodingencodeUnicodeDecodeErrorrrebytesordrr_c_unsupportedrrrwarningswarnrrr"r%listtuplenpndarraydict TypeErrorrr{_clean_na_valuesrrangercallable)rrrIresultfallback_reasonr= encodeablermrhargrDrBrKrXrRrYrr s rrzTextFileReader._clean_optionss S==|$q(("N!k" ?s3xx!||}}-1)*;''777FFFFF " _J022=gH #szz(++,,q00!&J% # # #"  # "&0H"H"H77728777 "K(  Z C<%H%H I!## NNS((":::R &RRR "  .t5 ._-- - S==%  3KK v  *  "vc{6H6L6LS6Q6Q'Q'Q$Q*QQ>AQQQ 3KK   M'&'''+--    K(  \* K( :&GH-...   HII I  " " (i$rz)BCC (&K '{$0U e  !j$// ?#' #3#3#<??  J""34Y& 0 ! ! !  : Y  h'' H,@ V(## + ??55h'' )x== w)|'{)|%zv~s(B// B>=B>rcr |S#t$r|wxYwr) get_chunk StopIterationrrs r__next__zTextFileReader.__next__HsB >>## #    JJLLL  s 6r @FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str] | list | IOr$c ttttd}||vr(t d|d|dt |tsd}d}|dkrd}d }nR|d krL|j d d d kr-t t|tr d}d |vr|d z }t|||j d d|j dd|j dd||j dd|j dd|_ |j J|j j}n'|dkr!dt|}t | |||fi|jS#t $r"|j |j wxYw)N)r rrrzUnknown engine: z (valid options are )TrrFrbr rmrbrbrsrnrrw)rmrbrsis_textrrwrz)Invalid file path or buffer object type: )r'r)r#r(rkeysrr*rrr!rer rhandler Exceptionr)rrrImappingrAmoders rrzTextFileReader._make_engineOs  ")/ 0 0   P6PPw||~~PPP !T"" "GD""# L$$Z99WDD~a00#66E  d??CKD%))*d;; L,,]DAA<++L%@@|''(98DD $ 0 01BD I I   DL<+++ #AA x  Gd1ggGGCS// ! "76?155 55 5   |' ""$$$  s F**,Gc t|r)rrs r_failover_to_pythonz"TextFileReader._failover_to_pythons!$'''rrVrUc |jdkr? |j}n#t$r|wxYwt d|} |j|\}}}n##t$r|wxYw|^|rYt tt| }t|j |j |z}nd}nt |}t|dr|j dd nd t t r&t#d}| n> :t' t(jt(jfvrt# fd}nd}|ji}|D]R\} } t'|| t(jt(jfvr|| nd} t1| || d || <Sn|}t3|||d }|xj |z c_ |S) NrrVrrrGcdSrrrrrz%TextFileReader.read..sDrcSrr) dtype_argsrrKz%TextFileReader.read..sIrF)indexrGr)columnsrNr)rIrrrDrrrnextitervaluesrrrrrrr.rrrr,str_object_r rr) rrVdfrNrOcol_dictnew_rowsrG new_col_dictkvrrMs @rrzTextFileReader.reads ;) # # \&&((     %We44E  L%% H     }!"4X__->->(?(?#@#@AAH&t|T\H5LMMEE HHu::t^,, ! -11'4@@  )T** #LL11 Y''''&< +B+B G,,$$5$5$5$566 ! $NN,,RRDAq(a11bgrz5JJJa! '-Qe15&Q&Q&QLOO R (  B LLH $LL s) A A<< Bsizec||j}|jF|j|jkrt||j|jz }nt ||j|jz }||S)N)rV)rrVrr9minr)rr[s rr8zTextFileReader.get_chunksl <>D : !|tz))##|zDL04dl!:;;yyty$$$rr c|Srrrs r __enter__zTextFileReader.__enter__s rexc_typetype[BaseException] | None exc_valueBaseException | None tracebackTracebackType | Nonec.|dSr)r)rr`rbrds r__exit__zTextFileReader.__exit__s rr)rrrIrHrr)rr)rIr1rr)rIr1rr)rrrIr1rr)rr)r )rr;rIr1rr$)rVrUrr)r[rUrr)rr )r`rarbrcrdrerr)r{r|r}__doc__rrrrrr:rrHrr8r_rgrrrrr9s:$(-9-9-9-9-9^ ,,,,\*OOOOb 77777r((((EEEEEN % % % % %rc$d|d<t|i|S)a Converts lists of lists/tuples into DataFrames with proper type inference and optional (e.g. string to datetime) conversion. Also enables iterating lazily over chunks of large files Parameters ---------- data : file-like object or list delimiter : separator character to use dialect : str or csv.Dialect instance, optional Ignored if delimiter is longer than 1 character names : sequence, default header : int, default 0 Row to use to parse column labels. Defaults to the first row. Prior rows will be discarded index_col : int or list, optional Column or columns to use as the (possibly hierarchical) index has_index_names: bool, default False True if the cols defined in index_col have an index name and are not in the header. na_values : scalar, str, list-like, or dict, optional Additional strings to recognize as NA/NaN. keep_default_na : bool, default True thousands : str, optional Thousands separator comment : str, optional Comment out remainder of line parse_dates : bool, default False date_format : str or dict of column -> format, default ``None`` .. versionadded:: 2.0.0 skiprows : list of integers Row numbers to skip skipfooter : int Number of line at bottom of file to skip converters : dict, optional Dict of functions for converting values in certain columns. Keys can either be integers or column labels, values are functions that take one input argument, the cell (not column) content, and return the transformed content. encoding : str, optional Encoding to use for UTF when reading/writing (ex. 'utf-8') float_precision : str, optional Specifies which converter the C engine should use for floating-point values. The options are `None` or `high` for the ordinary converter, `legacy` for the original lower precision pandas converter, and `round_trip` for the round-trip converter. rrI)r)argsrs r TextParserrks!bDN 4 (4 ( ((rrc|'|rt}nt}t}nt|tr|}i}|D]C\}}t |s|g}|rt|tz}t||||<Dd|D}n=t |s|g}t||}|r |tz}t|}||fS)Nc4i|]\}}|t|Sr)_floatify_na_values).0rYrZs r z$_clean_na_values..7s'NNNDAqa,Q//NNNr) rrrr.rr r_stringify_na_valuesrn)rXrYrr  old_na_valuesrYrZs rr0r0s#  %IIIUU It $ $4!((  "'')) = =DAq?? C +FF]*/8<N sep_overridez:Specified a sep and a delimiter; you can only specify one.rB zSpecified \n as separator or delimiter. This forces the python engine which does not accept a line terminator. Hence it is not allowed to use the line terminator as separator.Trr rIFrrqr)skip)rrzKon_bad_line can only be a callable function if engine='python' or 'pyarrow'z Argument z is invalid for on_bad_linesry) rrrr$BadLineHandleMethodERRORWARNSKIPr2r) rpr>rIr=rqrBrry delim_defaultrs rrrlsV[)MD(D0 3> ! 9SM%9 ^Wc//UVVV!S^33DDDM D 0   CN"")[%[ #'   X#(  w)=C^   )=B^   )=B^ ,  Q . . .2  ,^O\OOOPPP &&&)D Krdict[str, str | csv.Dialect]csv.Dialect | Nonecb|ddS|d}t|trQ|tjvr>(#### '""" W-- Or)r>rjrkrPrhricsv.Dialect | strc`tD]%}t||std|d&dS)zx Validate csv dialect instance. Raises ------ ValueError If incorrect dialect is provided. zInvalid dialect z providedN)MANDATORY_DIALECT_ATTRSrr)rpparams rrrsT)DDw&& DBBBBCC C DDDr csv.Dialectc|}tD]}t||}t|}|||}g}|||fvr=d|d|d|d}|dkr|dds|||r;tjd |tt |||<|S) a Merge default kwargs in TextFileReader with dialect parameters. Parameters ---------- dialect : csv.Dialect Concrete csv dialect. See csv.Dialect documentation for more details. defaults : dict Keyword arguments passed to TextFileReader. Returns ------- kwds : dict Updated keyword arguments, merged with dialect parameters. zConflicting values for 'z': 'z+' was provided, but the dialect specifies 'z%'. Using the dialect-specified value.r>r}Fz r) rrr r&rrrr(r)joinrr) rprrr dialect_valparser_defaultprovided conflict_msgsrs rrr s& ==??D(""gu-- (/88E>22  NK8 8 85555h558C555 [((TXXne-L-L($$S)))   M M**MFVFXFX    "U Krc|dr]|ds|drtd|drtddSdS)a Check whether skipfooter is compatible with other kwargs in TextFileReader. Parameters ---------- kwds : dict Keyword arguments passed to TextFileReader. Raises ------ ValueError If skipfooter is not compatible with other parameters. rTrrz('skipfooter' not supported for iterationrVz''skipfooter' not supported with 'nrows'N)rr)rs rrrC s xx H 88J   I488K#8#8 IGHH H 88G   HFGG G HH H Hr).)rrerrrrSrr)rrerrrrSrrS)rrerrUrrSrrU)r)rrerrrrSrrU)rBrrr)rrrr) rrrrrrUrrrr) rrrrOrrSrrrr) rrrrrrrrrr) rrrrOrrUrrrr)Zrrr=r<r>r<r@r?rBrArDrCrEr9rGrFrIrHrKrJrMrLrNrLrPrOrRrQrTrSrVrUrXrWrYrOrZrOr[rOr]r\r_r^r`rOrarOrrOrrUrbr0rdrcrfrergrcrhrerirSrjrOrkrcrlrcrmrcrnrcrprorqrerrrOrsrOrurtrwrvryrxrr)rrrrrrrrSrrrrUrrrr)rrrrrrrrSrrOrrSrrrr)rrrrrrrrSrrrrrrrr)rrrrrrrrSrrOrrUrrrr)rr)TT)rYrOrrO)rrs)rrOrrx)rpror>r<rIrHr=r<rqr{rBrArrryrx)rrrr)rprrr)rprrrrr)rrrr)prh __future__r collectionsrrrr!typingrrrr r r r r rrr(numpyr, pandas._libsrpandas._libs.parsersr pandas.errorsrrpandas.util._decoratorsrpandas.util._exceptionsrpandas.util._validatorsrpandas.core.dtypes.commonrrrrrrrpandas.core.framerpandas.core.indexes.apirpandas.io.commonrr r!r"&pandas.io.parsers.arrow_parser_wrapperr#pandas.io.parsers.base_parserr$r%r&"pandas.io.parsers.c_parser_wrapperr'pandas.io.parsers.python_parserr(r)collections.abcr*r+r,r-r.typesr/pandas._typingr0r1r2r3r4r5r6r7r8r9r;r.rrr~rrr'rr rrrrr QUOTE_MINIMALrrIteratorrrkr0rnrqrrrrrrrrrrss  #"""""                         ......544444777777''''''...... FEEEEE >===== G$#####                        -4-4-4-4-4y')"4E-4-4-4-4-4`L **I -4CSWXX XXXX#%67& KKKK K KKKK K WWWW W89@GGGG00"0"0"0"f       #    %%%%% % H'*n,0