TYP: make the type annotations of read_csv & read_table discoverable

Author: topper-123

pandas/io/parsers.py

@@ -530,10 +530,16 @@ def _read(filepath_or_buffer: FilePathOrBuffer, kwds):
 _deprecated_args: Set[str] = set()
 
 
-def _make_parser_function(name, default_sep=","):
-    def parser_f(
+@Appender(
+    _doc_read_csv_and_table.format(
+        func_name="read_csv",
+        summary="Read a comma-separated values (csv) file into DataFrame.",
+        _default_sep="','",
+    )
+)
+def read_csv(
         filepath_or_buffer: FilePathOrBuffer,
-        sep=default_sep,
+        sep=",",
         delimiter=None,
         # Column and Index Locations and Names
         header="infer",
@@ -589,117 +595,164 @@ def parser_f(
         low_memory=_c_parser_defaults["low_memory"],
         memory_map=False,
         float_precision=None,
-    ):
-
-        # gh-23761
-        #
-        # When a dialect is passed, it overrides any of the overlapping
-        # parameters passed in directly. We don't want to warn if the
-        # default parameters were passed in (since it probably means
-        # that the user didn't pass them in explicitly in the first place).
-        #
-        # "delimiter" is the annoying corner case because we alias it to
-        # "sep" before doing comparison to the dialect values later on.
-        # Thus, we need a flag to indicate that we need to "override"
-        # the comparison to dialect values by checking if default values
-        # for BOTH "delimiter" and "sep" were provided.
-        if dialect is not None:
-            sep_override = delimiter is None and sep == default_sep
-            kwds = dict(sep_override=sep_override)
-        else:
-            kwds = dict()
-
-        # Alias sep -> delimiter.
-        if delimiter is None:
-            delimiter = sep
-
-        if delim_whitespace and delimiter != default_sep:
-            raise ValueError(
-                "Specified a delimiter with both sep and "
-                "delim_whitespace=True; you can only specify one."
-            )
+):
+    # gh-23761
+    #
+    # When a dialect is passed, it overrides any of the overlapping
+    # parameters passed in directly. We don't want to warn if the
+    # default parameters were passed in (since it probably means
+    # that the user didn't pass them in explicitly in the first place).
+    #
+    # "delimiter" is the annoying corner case because we alias it to
+    # "sep" before doing comparison to the dialect values later on.
+    # Thus, we need a flag to indicate that we need to "override"
+    # the comparison to dialect values by checking if default values
+    # for BOTH "delimiter" and "sep" were provided.
+    default_sep = ","
+
+    if dialect is not None:
+        sep_override = delimiter is None and sep == default_sep
+        kwds = dict(sep_override=sep_override)
+    else:
+        kwds = dict()
 
-        if engine is not None:
-            engine_specified = True
-        else:
-            engine = "c"
-            engine_specified = False
+    # Alias sep -> delimiter.
+    if delimiter is None:
+        delimiter = sep
 
-        kwds.update(
-            delimiter=delimiter,
-            engine=engine,
-            dialect=dialect,
-            compression=compression,
-            engine_specified=engine_specified,
-            doublequote=doublequote,
-            escapechar=escapechar,
-            quotechar=quotechar,
-            quoting=quoting,
-            skipinitialspace=skipinitialspace,
-            lineterminator=lineterminator,
-            header=header,
-            index_col=index_col,
-            names=names,
-            prefix=prefix,
-            skiprows=skiprows,
-            skipfooter=skipfooter,
-            na_values=na_values,
-            true_values=true_values,
-            false_values=false_values,
-            keep_default_na=keep_default_na,
-            thousands=thousands,
-            comment=comment,
-            decimal=decimal,
-            parse_dates=parse_dates,
-            keep_date_col=keep_date_col,
-            dayfirst=dayfirst,
-            date_parser=date_parser,
-            cache_dates=cache_dates,
-            nrows=nrows,
-            iterator=iterator,
-            chunksize=chunksize,
-            converters=converters,
-            dtype=dtype,
-            usecols=usecols,
-            verbose=verbose,
-            encoding=encoding,
-            squeeze=squeeze,
-            memory_map=memory_map,
-            float_precision=float_precision,
-            na_filter=na_filter,
-            delim_whitespace=delim_whitespace,
-            warn_bad_lines=warn_bad_lines,
-            error_bad_lines=error_bad_lines,
-            low_memory=low_memory,
-            mangle_dupe_cols=mangle_dupe_cols,
-            infer_datetime_format=infer_datetime_format,
-            skip_blank_lines=skip_blank_lines,
+    if delim_whitespace and delimiter != default_sep:
+        raise ValueError(
+            "Specified a delimiter with both sep and "
+            "delim_whitespace=True; you can only specify one."
         )
 
-        return _read(filepath_or_buffer, kwds)
-
-    parser_f.__name__ = name
-
-    return parser_f
+    if engine is not None:
+        engine_specified = True
+    else:
+        engine = "c"
+        engine_specified = False
+
+    kwds.update(
+        delimiter=delimiter,
+        engine=engine,
+        dialect=dialect,
+        compression=compression,
+        engine_specified=engine_specified,
+        doublequote=doublequote,
+        escapechar=escapechar,
+        quotechar=quotechar,
+        quoting=quoting,
+        skipinitialspace=skipinitialspace,
+        lineterminator=lineterminator,
+        header=header,
+        index_col=index_col,
+        names=names,
+        prefix=prefix,
+        skiprows=skiprows,
+        skipfooter=skipfooter,
+        na_values=na_values,
+        true_values=true_values,
+        false_values=false_values,
+        keep_default_na=keep_default_na,
+        thousands=thousands,
+        comment=comment,
+        decimal=decimal,
+        parse_dates=parse_dates,
+        keep_date_col=keep_date_col,
+        dayfirst=dayfirst,
+        date_parser=date_parser,
+        cache_dates=cache_dates,
+        nrows=nrows,
+        iterator=iterator,
+        chunksize=chunksize,
+        converters=converters,
+        dtype=dtype,
+        usecols=usecols,
+        verbose=verbose,
+        encoding=encoding,
+        squeeze=squeeze,
+        memory_map=memory_map,
+        float_precision=float_precision,
+        na_filter=na_filter,
+        delim_whitespace=delim_whitespace,
+        warn_bad_lines=warn_bad_lines,
+        error_bad_lines=error_bad_lines,
+        low_memory=low_memory,
+        mangle_dupe_cols=mangle_dupe_cols,
+        infer_datetime_format=infer_datetime_format,
+        skip_blank_lines=skip_blank_lines,
+    )
 
+    return _read(filepath_or_buffer, kwds)
 
-read_csv = _make_parser_function("read_csv", default_sep=",")
-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(
+@Appender(
     _doc_read_csv_and_table.format(
         func_name="read_table",
         summary="Read general delimited file into DataFrame.",
         _default_sep=r"'\\t' (tab-stop)",
     )
-)(read_table)
+)
+def read_table(
+        filepath_or_buffer: FilePathOrBuffer,
+        sep="\t",
+        delimiter=None,
+        # Column and Index Locations and Names
+        header="infer",
+        names=None,
+        index_col=None,
+        usecols=None,
+        squeeze=False,
+        prefix=None,
+        mangle_dupe_cols=True,
+        # General Parsing Configuration
+        dtype=None,
+        engine=None,
+        converters=None,
+        true_values=None,
+        false_values=None,
+        skipinitialspace=False,
+        skiprows=None,
+        skipfooter=0,
+        nrows=None,
+        # NA and Missing Data Handling
+        na_values=None,
+        keep_default_na=True,
+        na_filter=True,
+        verbose=False,
+        skip_blank_lines=True,
+        # Datetime Handling
+        parse_dates=False,
+        infer_datetime_format=False,
+        keep_date_col=False,
+        date_parser=None,
+        dayfirst=False,
+        cache_dates=True,
+        # Iteration
+        iterator=False,
+        chunksize=None,
+        # Quoting, Compression, and File Format
+        compression="infer",
+        thousands=None,
+        decimal: str = ".",
+        lineterminator=None,
+        quotechar='"',
+        quoting=csv.QUOTE_MINIMAL,
+        doublequote=True,
+        escapechar=None,
+        comment=None,
+        encoding=None,
+        dialect=None,
+        # Error Handling
+        error_bad_lines=True,
+        warn_bad_lines=True,
+        # Internal
+        delim_whitespace=False,
+        low_memory=_c_parser_defaults["low_memory"],
+        memory_map=False,
+        float_precision=None,
+):
+    return read_csv(**locals())
 
 
 def read_fwf(

pandas/tests/io/parser/test_common.py

@@ -5,6 +5,7 @@
 import codecs
 import csv
 from datetime import datetime
+from inspect import signature
 from io import StringIO
 import os
 import platform
@@ -2071,6 +2072,27 @@ def test_read_csv_raises_on_header_prefix(all_parsers):
         parser.read_csv(s, header=0, prefix="_X")
 
 
+def test_read_table_same_signature_as_read_csv(all_parsers):
+    # GH-XXXXXX
+    from pandas import read_csv, read_table
+    table_sign = signature(read_table)
+    csv_sign = signature(read_csv)
+
+    assert table_sign.parameters.keys() == csv_sign.parameters.keys()
+    assert table_sign.return_annotation == csv_sign.return_annotation
+
+    for key, csv_param in csv_sign.parameters.items():
+        table_param = table_sign.parameters[key]
+        if key == "sep":
+            assert csv_param.default == ","
+            assert table_param.default == "\t"
+            assert table_param.annotation == csv_param.annotation
+            assert table_param.kind == csv_param.kind
+            continue
+        else:
+            assert table_param == csv_param
+
+
 def test_read_table_equivalency_to_read_csv(all_parsers):
     # see gh-21948
     # As of 0.25.0, read_table is undeprecated