diff --git a/pandas/io/parsers.py b/pandas/io/parsers.py index a1f02165f8d3d..acb9bca2545c0 100755 --- a/pandas/io/parsers.py +++ b/pandas/io/parsers.py @@ -1,6 +1,7 @@ """ Module contains tools for processing files into DataFrames or other objects """ + from __future__ import print_function from collections import defaultdict @@ -52,7 +53,10 @@ # so we need to remove it if we see it. _BOM = u('\ufeff') -_parser_params = r"""Also supports optionally iterating or breaking of the file +_doc_read_csv_and_table = r""" +{summary} + +Also supports optionally iterating or breaking of the file into chunks. Additional help can be found in the `online docs for IO Tools @@ -70,16 +74,17 @@ 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``. -%s -delim_whitespace : boolean, default False - Specifies whether or not whitespace (e.g. ``' '`` or ``'\t'``) will be - used as the sep. Equivalent to setting ``sep='\s+'``. If this option - is set to True, nothing should be passed in for the ``delimiter`` - parameter. - - .. versionadded:: 0.18.1 support for the Python parser. - -header : int or list of ints, default 'infer' +sep : str, default {_default_sep} + Delimiter to use. If sep is 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 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, default ``None`` + Alias for sep. +header : int, list of int, default 'infer' Row number(s) to use as the column names, and the start of the data. Default behavior is to infer the column names: if no names are passed the behavior is identical to ``header=0`` and column @@ -91,24 +96,24 @@ 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 + ``skip_blank_lines=True``, so ``header=0`` denotes the first line of data rather than the first line of the file. -names : array-like, default None +names : array-like, optional List of column names to use. If file contains no header row, then you - should explicitly pass header=None. Duplicates in this list will cause + should explicitly pass ``header=None``. Duplicates in this list will cause a ``UserWarning`` to be issued. -index_col : int or sequence or False, default None +index_col : int, sequence or bool, optional Column to use as the row labels of the DataFrame. If a sequence is given, a MultiIndex is used. If you have a malformed file with delimiters at the end - of each line, you might consider index_col=False to force pandas to _not_ - use the first column as the index (row names) -usecols : list-like or callable, default None + of each line, you might consider ``index_col=False`` to force pandas to + not use the first column as the index (row names). +usecols : list-like or callable, optional Return a subset of the columns. 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). 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]``. + `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 DataFrame from ``data`` with element order preserved use ``pd.read_csv(data, usecols=['foo', 'bar'])[['foo', 'bar']]`` for columns in ``['foo', 'bar']`` order or @@ -120,31 +125,33 @@ 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. -squeeze : boolean, default False - If the parsed data only contains one column then return a Series -prefix : str, default None +squeeze : bool, default False + If the parsed data only contains one column then return a Series. +prefix : str, optional Prefix to add to column numbers when no header, e.g. 'X' for X0, X1, ... -mangle_dupe_cols : boolean, default True +mangle_dupe_cols : bool, default True Duplicate columns will be specified as 'X', 'X.1', ...'X.N', rather than 'X'...'X'. Passing in False will cause data to be overwritten if there are duplicate names in the columns. -dtype : Type name or dict of column -> type, default None - Data type for data or columns. E.g. {'a': np.float64, 'b': np.int32} +dtype : Type name or dict of column -> type, optional + Data type for data or columns. E.g. {{'a': np.float64, 'b': np.int32}} 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. -%s -converters : dict, default None +engine : {{'c', 'python'}}, optional + Parser engine to use. The C engine is faster while the python engine is + currently more feature-complete. +converters : dict, optional Dict of functions for converting values in certain columns. Keys can either - be integers or column labels -true_values : list, default None - Values to consider as True -false_values : list, default None - Values to consider as False -skipinitialspace : boolean, default False + be integers or column labels. +true_values : list, optional + Values to consider as True. +false_values : list, optional + Values to consider as False. +skipinitialspace : bool, default False Skip spaces after delimiter. -skiprows : list-like or integer or callable, default None +skiprows : list-like, int or callable, optional Line numbers to skip (0-indexed) or number of lines to skip (int) at the start of the file. @@ -152,10 +159,10 @@ 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, default None - Number of rows of file to read. Useful for reading pieces of large files -na_values : scalar, str, list-like, or dict, default None + 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. +na_values : scalar, str, list-like, or dict, 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: '""" + fill("', '".join(sorted(_NA_VALUES)), @@ -175,39 +182,40 @@ Note that if `na_filter` is passed in as False, the `keep_default_na` and `na_values` parameters will be ignored. -na_filter : boolean, default True +na_filter : bool, default True Detect missing value markers (empty strings and the value of na_values). In data without any NAs, passing na_filter=False can improve the performance - of reading a large file -verbose : boolean, default False - Indicate number of NA values placed in non-numeric columns -skip_blank_lines : boolean, default True - If True, skip over blank lines rather than interpreting as NaN values -parse_dates : boolean or list of ints or names or list of lists or dict, \ + of reading a large file. +verbose : bool, default False + Indicate number of NA values placed in non-numeric columns. +skip_blank_lines : bool, default True + If True, skip over blank lines rather than interpreting as NaN values. +parse_dates : bool or list of int or names or list of lists or dict, \ default False + The behavior is as follows: * boolean. If True -> try parsing the index. - * list of ints or names. e.g. If [1, 2, 3] -> try parsing columns 1, 2, 3 + * list of int or names. e.g. If [1, 2, 3] -> try parsing columns 1, 2, 3 each as a separate date column. * list of lists. e.g. If [[1, 3]] -> combine columns 1 and 3 and parse as a single date column. - * dict, e.g. {'foo' : [1, 3]} -> parse columns 1, 3 as date and call result - 'foo' + * dict, e.g. {{'foo' : [1, 3]}} -> parse columns 1, 3 as date and call + result 'foo' If a column or index contains an unparseable date, the entire column or index will be returned unaltered as an object data type. For non-standard datetime parsing, use ``pd.to_datetime`` after ``pd.read_csv`` Note: A fast-path exists for iso8601-formatted dates. -infer_datetime_format : boolean, default False +infer_datetime_format : bool, default False If True and `parse_dates` is enabled, pandas will attempt to infer the format of the datetime strings in the columns, and if it can be inferred, switch to a faster method of parsing them. In some cases this can increase the parsing speed by 5-10x. -keep_date_col : boolean, default False +keep_date_col : bool, default False If True and `parse_dates` specifies combining multiple columns then keep the original columns. -date_parser : function, default None +date_parser : function, optional Function to use for converting a sequence of string columns to an array of datetime instances. The default uses ``dateutil.parser.parser`` to do the conversion. Pandas will try to call `date_parser` in three different ways, @@ -217,17 +225,17 @@ and pass that; and 3) call `date_parser` once for each row using one or more strings (corresponding to the columns defined by `parse_dates`) as arguments. -dayfirst : boolean, default False - DD/MM format dates, international and European format -iterator : boolean, default False +dayfirst : bool, default False + DD/MM format dates, international and European format. +iterator : bool, default False Return TextFileReader object for iteration or getting chunks with ``get_chunk()``. -chunksize : int, default None +chunksize : int, optional Return TextFileReader object for iteration. See the `IO Tools docs `_ for more information on ``iterator`` and ``chunksize``. -compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}, default 'infer' +compression : {{'infer', 'gzip', 'bz2', 'zip', 'xz', None}}, 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', or '.xz' (otherwise no @@ -236,16 +244,11 @@ .. versionadded:: 0.18.1 support for 'zip' and 'xz' compression. -thousands : str, default None - Thousands separator +thousands : str, optional + Thousands separator. decimal : str, default '.' Character to recognize as decimal point (e.g. use ',' for European data). -float_precision : string, default None - Specifies which converter the C engine should use for floating-point - values. The options are `None` for the ordinary converter, - `high` for the high-precision converter, and `round_trip` for the - round-trip converter. -lineterminator : str (length 1), default None +lineterminator : str (length 1), optional Character to break file into lines. Only valid with C parser. quotechar : str (length 1), optional The character used to denote the start and end of a quoted item. Quoted @@ -253,13 +256,13 @@ quoting : int or csv.QUOTE_* instance, default 0 Control field quoting behavior per ``csv.QUOTE_*`` constants. Use one of QUOTE_MINIMAL (0), QUOTE_ALL (1), QUOTE_NONNUMERIC (2) or QUOTE_NONE (3). -doublequote : boolean, default ``True`` +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), default None +escapechar : str (length 1), optional One-character string used to escape delimiter when quoting is QUOTE_NONE. -comment : str, default None +comment : str, optional Indicates 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``), @@ -267,102 +270,73 @@ `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, default None +encoding : str, optional Encoding to use for UTF when reading/writing (ex. 'utf-8'). `List of Python standard encodings - `_ -dialect : str or csv.Dialect instance, default None + `_ . +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. -tupleize_cols : boolean, default False +tupleize_cols : bool, default False + Leave a list of tuples on columns as is (default is to convert to + a MultiIndex on the columns). + .. deprecated:: 0.21.0 This argument will be removed and will always convert to MultiIndex - Leave a list of tuples on columns as is (default is to convert to - a MultiIndex on the columns) -error_bad_lines : boolean, default True +error_bad_lines : bool, default True Lines with too many fields (e.g. a csv line with too many commas) will by default cause an exception to be raised, and no DataFrame will be returned. If False, then these "bad lines" will dropped from the DataFrame that is returned. -warn_bad_lines : boolean, default True +warn_bad_lines : bool, default True If error_bad_lines is False, and warn_bad_lines is True, a warning for each "bad line" will be output. -low_memory : boolean, default True +delim_whitespace : bool, default False + Specifies whether or not whitespace (e.g. ``' '`` or ``'\t'``) will be + used as the sep. Equivalent to setting ``sep='\\s+'``. If this option + is set to True, nothing should be passed in for the ``delimiter`` + parameter. + + .. versionadded:: 0.18.1 support for the Python parser. + +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 DataFrame regardless, use the `chunksize` or `iterator` parameter to return the data in chunks. - (Only valid with C parser) -memory_map : boolean, default False + (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 : str, optional + Specifies which converter the C engine should use for floating-point + values. The options are `None` for the ordinary converter, + `high` for the high-precision converter, and `round_trip` for the + round-trip converter. Returns ------- -result : DataFrame or TextParser +DataFrame or TextParser + A comma-separated values (csv) file is returned as two-dimensional + data structure with labeled axes. + +See Also +-------- +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.{func_name}('data.csv') # doctest: +SKIP """ -# engine is not used in read_fwf() so is factored out of the shared docstring -_engine_doc = """engine : {'c', 'python'}, optional - Parser engine to use. The C engine is faster while the python engine is - currently more feature-complete.""" - -_sep_doc = r"""sep : str, default {default} - Delimiter to use. If sep is 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 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, default ``None`` - Alternative argument name for sep.""" - -_read_csv_doc = """ -Read CSV (comma-separated) file into DataFrame - -%s -""" % (_parser_params % (_sep_doc.format(default="','"), _engine_doc)) - -_read_table_doc = """ - -.. deprecated:: 0.24.0 - Use :func:`pandas.read_csv` instead, passing ``sep='\t'`` if necessary. - -Read general delimited file into DataFrame - -%s -""" % (_parser_params % (_sep_doc.format(default="\\t (tab-stop)"), - _engine_doc)) - -_fwf_widths = """\ -colspecs : list of pairs (int, int) or 'infer'. optional - A list of pairs (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 ints. optional - A list of field widths which can be used instead of 'colspecs' if - the intervals are contiguous. -delimiter : str, default ``'\t' + ' '`` - Characters to consider as filler characters in the fixed-width file. - Can be used to specify the filler character of the fields - if it is not spaces (e.g., '~'). -""" - -_read_fwf_doc = """ -Read a table of fixed-width formatted lines into DataFrame - -%s -""" % (_parser_params % (_fwf_widths, '')) - def _validate_integer(name, val, min_val=0): """ @@ -468,10 +442,10 @@ def _read(filepath_or_buffer, kwds): _parser_defaults = { 'delimiter': None, - 'doublequote': True, 'escapechar': None, 'quotechar': '"', 'quoting': csv.QUOTE_MINIMAL, + 'doublequote': True, 'skipinitialspace': False, 'lineterminator': None, @@ -480,14 +454,16 @@ def _read(filepath_or_buffer, kwds): 'names': None, 'prefix': None, 'skiprows': None, + 'skipfooter': 0, + 'nrows': None, 'na_values': None, + 'keep_default_na': True, + 'true_values': None, 'false_values': None, 'converters': None, 'dtype': None, - 'skipfooter': 0, - 'keep_default_na': True, 'thousands': None, 'comment': None, 'decimal': b'.', @@ -497,10 +473,8 @@ def _read(filepath_or_buffer, kwds): 'keep_date_col': False, 'dayfirst': False, 'date_parser': None, - 'usecols': None, - 'nrows': None, # 'iterator': False, 'chunksize': None, 'verbose': False, @@ -573,6 +547,7 @@ def parser_f(filepath_or_buffer, false_values=None, skipinitialspace=False, skiprows=None, + skipfooter=0, nrows=None, # NA and Missing Data Handling @@ -600,6 +575,7 @@ def parser_f(filepath_or_buffer, lineterminator=None, quotechar='"', quoting=csv.QUOTE_MINIMAL, + doublequote=True, escapechar=None, comment=None, encoding=None, @@ -610,10 +586,7 @@ def parser_f(filepath_or_buffer, error_bad_lines=True, warn_bad_lines=True, - skipfooter=0, - # Internal - doublequote=True, delim_whitespace=False, low_memory=_c_parser_defaults['low_memory'], memory_map=False, @@ -683,6 +656,7 @@ def parser_f(filepath_or_buffer, names=names, prefix=prefix, skiprows=skiprows, + skipfooter=skipfooter, na_values=na_values, true_values=true_values, false_values=false_values, @@ -699,7 +673,6 @@ def parser_f(filepath_or_buffer, nrows=nrows, iterator=iterator, chunksize=chunksize, - skipfooter=skipfooter, converters=converters, dtype=dtype, usecols=usecols, @@ -727,14 +700,77 @@ def parser_f(filepath_or_buffer, read_csv = _make_parser_function('read_csv', default_sep=',') -read_csv = Appender(_read_csv_doc)(read_csv) +read_csv = Appender(_doc_read_csv_and_table.format( + func_name='read_csv', + summary=('Read a comma-separated values (csv) file ' + 'into DataFrame.'), + _default_sep="','") + )(read_csv) read_table = _make_parser_function('read_table', default_sep='\t') -read_table = Appender(_read_table_doc)(read_table) +read_table = Appender(_doc_read_csv_and_table.format( + func_name='read_table', + summary="""Read general delimited file into DataFrame. + +.. deprecated:: 0.24.0 +Use :func:`pandas.read_csv` instead, passing ``sep='\\t'`` if necessary.""", + _default_sep=r"'\\t' (tab-stop)") + )(read_table) + +def read_fwf(filepath_or_buffer, colspecs='infer', + widths=None, **kwds): + + r""" + 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 + 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.csv. + + If you want to pass in a path object, pandas accepts either + ``pathlib.Path`` or ``py._path.local.LocalPath``. + + 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``. + 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. + **kwds : optional + Optional keyword arguments can be passed to ``TextFileReader``. + + Returns + ------- + DataFrame or TextParser + A comma-separated values (csv) file is returned as two-dimensional + data structure with labeled axes. + + See Also + -------- + 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 + """ -@Appender(_read_fwf_doc) -def read_fwf(filepath_or_buffer, colspecs='infer', widths=None, **kwds): # Check input arguments. if colspecs is None and widths is None: raise ValueError("Must specify either colspecs or widths") @@ -2018,45 +2054,45 @@ def TextParser(*args, **kwds): ---------- data : file-like object or list delimiter : separator character to use - dialect : str or csv.Dialect instance, default None + 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, default None + index_col : int or list, optional Column or columns to use as the (possibly hierarchical) index - has_index_names: boolean, default False + 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, default None + 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, default None + thousands : str, optional Thousands separator - comment : str, default None + comment : str, optional Comment out remainder of line - parse_dates : boolean, default False - keep_date_col : boolean, default False - date_parser : function, default None + parse_dates : bool, default False + keep_date_col : bool, default False + date_parser : function, optional skiprows : list of integers Row numbers to skip skipfooter : int Number of line at bottom of file to skip - converters : dict, default None + 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 : string, default None + encoding : str, optional Encoding to use for UTF when reading/writing (ex. 'utf-8') - squeeze : boolean, default False - returns Series if only one column - infer_datetime_format: boolean, default False + squeeze : bool, default False + returns Series if only one column. + infer_datetime_format: bool, default False If True and `parse_dates` is True for a column, try to infer the datetime format based on the first datetime string. If the format can be inferred, there often will be a large parsing speed-up. - float_precision : string, default None + float_precision : str, optional Specifies which converter the C engine should use for floating-point values. The options are None for the ordinary converter, 'high' for the high-precision converter, and 'round_trip' for the