BUG: Raise ValueError if names and prefix are both defined (pandas-dev#41446)

Author: phofl

doc/source/whatsnew/v1.3.0.rst

@@ -842,6 +842,7 @@ I/O
 - Bug in :func:`read_excel` raising ``AttributeError`` with ``MultiIndex`` header followed by two empty rows and no index, and bug affecting :func:`read_excel`, :func:`read_csv`, :func:`read_table`, :func:`read_fwf`, and :func:`read_clipboard` where one blank row after a ``MultiIndex`` header with no index would be dropped (:issue:`40442`)
 - Bug in :meth:`DataFrame.to_string` misplacing the truncation column when ``index=False`` (:issue:`40907`)
 - Bug in :func:`read_orc` always raising ``AttributeError`` (:issue:`40918`)
+- Bug in :func:`read_csv` and :func:`read_table` silently ignoring ``prefix`` if ``names`` and ``prefix`` are defined, now raising ``ValueError`` (:issue:`39123`)
 - Bug in :func:`read_csv` and :func:`read_excel` not respecting dtype for duplicated column name when ``mangle_dupe_cols`` is set to ``True`` (:issue:`35211`)
 - Bug in :func:`read_csv` and :func:`read_table` misinterpreting arguments when ``sys.setprofile`` had been previously called (:issue:`41069`)
 - Bug in the conversion from pyarrow to pandas (e.g. for reading Parquet) with nullable dtypes and a pyarrow array whose data buffer size is not a multiple of dtype size (:issue:`40896`)

pandas/io/parsers/readers.py

@@ -20,6 +20,7 @@
 import pandas._libs.lib as lib
 from pandas._libs.parsers import STR_NA_VALUES
 from pandas._typing import (
+    ArrayLike,
     DtypeArg,
     FilePathOrBuffer,
     StorageOptions,
@@ -485,11 +486,11 @@ def read_csv(
     delimiter=None,
     # Column and Index Locations and Names
     header="infer",
-    names=None,
+    names=lib.no_default,
     index_col=None,
     usecols=None,
     squeeze=False,
-    prefix=None,
+    prefix=lib.no_default,
     mangle_dupe_cols=True,
     # General Parsing Configuration
     dtype: Optional[DtypeArg] = None,
@@ -546,7 +547,14 @@ def read_csv(
     del kwds["sep"]
 
     kwds_defaults = _refine_defaults_read(
-        dialect, delimiter, delim_whitespace, engine, sep, defaults={"delimiter": ","}
+        dialect,
+        delimiter,
+        delim_whitespace,
+        engine,
+        sep,
+        names,
+        prefix,
+        defaults={"delimiter": ","},
     )
     kwds.update(kwds_defaults)
 
@@ -567,11 +575,11 @@ def read_table(
     delimiter=None,
     # Column and Index Locations and Names
     header="infer",
-    names=None,
+    names=lib.no_default,
     index_col=None,
     usecols=None,
     squeeze=False,
-    prefix=None,
+    prefix=lib.no_default,
     mangle_dupe_cols=True,
     # General Parsing Configuration
     dtype: Optional[DtypeArg] = None,
@@ -627,7 +635,14 @@ def read_table(
     del kwds["sep"]
 
     kwds_defaults = _refine_defaults_read(
-        dialect, delimiter, delim_whitespace, engine, sep, defaults={"delimiter": "\t"}
+        dialect,
+        delimiter,
+        delim_whitespace,
+        engine,
+        sep,
+        names,
+        prefix,
+        defaults={"delimiter": "\t"},
     )
     kwds.update(kwds_defaults)
 
@@ -1174,6 +1189,8 @@ def _refine_defaults_read(
     delim_whitespace: bool,
     engine: str,
     sep: Union[str, object],
+    names: Union[Optional[ArrayLike], object],
+    prefix: Union[Optional[str], object],
     defaults: Dict[str, Any],
 ):
     """Validate/refine default values of input parameters of read_csv, read_table.
@@ -1199,6 +1216,12 @@ def _refine_defaults_read(
     sep : str or object
         A delimiter provided by the user (str) or a sentinel value, i.e.
         pandas._libs.lib.no_default.
+    names : array-like, optional
+        List of column names to use. 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.
+    prefix : str, optional
+        Prefix to add to column numbers when no header, e.g. 'X' for X0, X1, ...
     defaults: dict
         Default values of input parameters.
 
@@ -1232,6 +1255,12 @@ def _refine_defaults_read(
             sep is lib.no_default or sep == delim_default
         )
 
+    if names is not lib.no_default and prefix is not lib.no_default:
+        raise ValueError("Specified named and prefix; you can only specify one.")
+
+    kwds["names"] = None if names is lib.no_default else names
+    kwds["prefix"] = None if prefix is lib.no_default else prefix
+
     # Alias sep -> delimiter.
     if delimiter is None:
         delimiter = sep

pandas/tests/io/parser/common/test_common_basic.py

@@ -740,6 +740,18 @@ def test_read_table_delim_whitespace_non_default_sep(all_parsers, delimiter):
         parser.read_table(f, delim_whitespace=True, delimiter=delimiter)
 
 
+@pytest.mark.parametrize("func", ["read_csv", "read_table"])
+@pytest.mark.parametrize("prefix", [None, "x"])
+@pytest.mark.parametrize("names", [None, ["a"]])
+def test_names_and_prefix_not_lib_no_default(all_parsers, names, prefix, func):
+    # GH#39123
+    f = StringIO("a,b\n1,2")
+    parser = all_parsers
+    msg = "Specified named and prefix; you can only specify one."
+    with pytest.raises(ValueError, match=msg):
+        getattr(parser, func)(f, names=names, prefix=prefix)
+
+
 def test_dict_keys_as_names(all_parsers):
     # GH: 36928
     data = "1,2"