Remove Sequence[str] as type used in DataFrame.to_string() (#47233)

* API: Disallow sets as index and columns argument in DataFrame constructor

* TYP: Remove Sequence[str] from to_string, to_html

* use list[str] for header argument.  Remove dict as index and columns argument for DataFrame.  Define ListLike

* use Axes rather than Sequence[Hashable]

---------

Co-authored-by: Jeff Reback <[email protected]>

Author: Dr-Irv

pandas/_typing.py

@@ -94,6 +94,13 @@
 AnyArrayLike = Union[ArrayLike, "Index", "Series"]
 TimeArrayLike = Union["DatetimeArray", "TimedeltaArray"]
 
+# list-like
+
+# Cannot use `Sequence` because a string is a sequence, and we don't want to
+# accept that.  Could refine if https://github.com/python/typing/issues/256 is
+# resolved to differentiate between Sequence[str] and str
+ListLike = Union[AnyArrayLike, List, range]
+
 # scalars
 
 PythonScalar = Union[str, float, bool]
@@ -130,7 +137,7 @@
 Ordered = Optional[bool]
 JSONSerializable = Optional[Union[PythonScalar, List, Dict]]
 Frequency = Union[str, "BaseOffset"]
-Axes = Union[AnyArrayLike, List, range]
+Axes = ListLike
 
 RandomState = Union[
     int,

pandas/core/frame.py

@@ -1134,9 +1134,9 @@ def _repr_html_(self) -> str | None:
     def to_string(
         self,
         buf: None = ...,
-        columns: Sequence[str] | None = ...,
+        columns: Axes | None = ...,
         col_space: int | list[int] | dict[Hashable, int] | None = ...,
-        header: bool | Sequence[str] = ...,
+        header: bool | list[str] = ...,
         index: bool = ...,
         na_rep: str = ...,
         formatters: fmt.FormattersType | None = ...,
@@ -1159,9 +1159,9 @@ def to_string(
     def to_string(
         self,
         buf: FilePath | WriteBuffer[str],
-        columns: Sequence[str] | None = ...,
+        columns: Axes | None = ...,
         col_space: int | list[int] | dict[Hashable, int] | None = ...,
-        header: bool | Sequence[str] = ...,
+        header: bool | list[str] = ...,
         index: bool = ...,
         na_rep: str = ...,
         formatters: fmt.FormattersType | None = ...,
@@ -1181,8 +1181,8 @@ def to_string(
         ...
 
     @Substitution(
-        header_type="bool or sequence of str",
-        header="Write out the column names. If a list of strings "
+        header_type="bool or list of str",
+        header="Write out the column names. If a list of columns "
         "is given, it is assumed to be aliases for the "
         "column names",
         col_space_type="int, list or dict of int",
@@ -1194,9 +1194,9 @@ def to_string(
     def to_string(
         self,
         buf: FilePath | WriteBuffer[str] | None = None,
-        columns: Sequence[str] | None = None,
+        columns: Axes | None = None,
         col_space: int | list[int] | dict[Hashable, int] | None = None,
-        header: bool | Sequence[str] = True,
+        header: bool | list[str] = True,
         index: bool = True,
         na_rep: str = "NaN",
         formatters: fmt.FormattersType | None = None,
@@ -2965,9 +2965,9 @@ def to_orc(
     def to_html(
         self,
         buf: FilePath | WriteBuffer[str],
-        columns: Sequence[Level] | None = ...,
+        columns: Axes | None = ...,
         col_space: ColspaceArgType | None = ...,
-        header: bool | Sequence[str] = ...,
+        header: bool = ...,
         index: bool = ...,
         na_rep: str = ...,
         formatters: FormattersType | None = ...,
@@ -2994,9 +2994,9 @@ def to_html(
     def to_html(
         self,
         buf: None = ...,
-        columns: Sequence[Level] | None = ...,
+        columns: Axes | None = ...,
         col_space: ColspaceArgType | None = ...,
-        header: bool | Sequence[str] = ...,
+        header: bool = ...,
         index: bool = ...,
         na_rep: str = ...,
         formatters: FormattersType | None = ...,
@@ -3030,9 +3030,9 @@ def to_html(
     def to_html(
         self,
         buf: FilePath | WriteBuffer[str] | None = None,
-        columns: Sequence[Level] | None = None,
+        columns: Axes | None = None,
         col_space: ColspaceArgType | None = None,
-        header: bool | Sequence[str] = True,
+        header: bool = True,
         index: bool = True,
         na_rep: str = "NaN",
         formatters: FormattersType | None = None,

pandas/core/generic.py

@@ -3101,7 +3101,7 @@ def to_latex(
         self,
         buf: None = ...,
         columns: Sequence[Hashable] | None = ...,
-        header: bool_t | Sequence[str] = ...,
+        header: bool_t | list[str] = ...,
         index: bool_t = ...,
         na_rep: str = ...,
         formatters: FormattersType | None = ...,
@@ -3128,7 +3128,7 @@ def to_latex(
         self,
         buf: FilePath | WriteBuffer[str],
         columns: Sequence[Hashable] | None = ...,
-        header: bool_t | Sequence[str] = ...,
+        header: bool_t | list[str] = ...,
         index: bool_t = ...,
         na_rep: str = ...,
         formatters: FormattersType | None = ...,
@@ -3155,7 +3155,7 @@ def to_latex(
         self,
         buf: FilePath | WriteBuffer[str] | None = None,
         columns: Sequence[Hashable] | None = None,
-        header: bool_t | Sequence[str] = True,
+        header: bool_t | list[str] = True,
         index: bool_t = True,
         na_rep: str = "NaN",
         formatters: FormattersType | None = None,

pandas/io/formats/csvs.py

@@ -102,7 +102,7 @@ def decimal(self) -> str:
         return self.fmt.decimal
 
     @property
-    def header(self) -> bool | Sequence[str]:
+    def header(self) -> bool | list[str]:
         return self.fmt.header
 
     @property

pandas/io/formats/format.py

@@ -120,7 +120,7 @@
         ----------
         buf : str, Path or StringIO-like, optional, default None
             Buffer to write to. If None, the output is returned as a string.
-        columns : sequence, optional, default None
+        columns : array-like, optional, default None
             The subset of columns to write. Writes all columns by default.
         col_space : %(col_space_type)s, optional
             %(col_space)s.
@@ -564,9 +564,9 @@ class DataFrameFormatter:
     def __init__(
         self,
         frame: DataFrame,
-        columns: Sequence[Hashable] | None = None,
+        columns: Axes | None = None,
         col_space: ColspaceArgType | None = None,
-        header: bool | Sequence[str] = True,
+        header: bool | list[str] = True,
         index: bool = True,
         na_rep: str = "NaN",
         formatters: FormattersType | None = None,
@@ -686,11 +686,9 @@ def _initialize_justify(self, justify: str | None) -> str:
         else:
             return justify
 
-    def _initialize_columns(self, columns: Sequence[Hashable] | None) -> Index:
+    def _initialize_columns(self, columns: Axes | None) -> Index:
         if columns is not None:
-            # GH 47231 - columns doesn't have to be `Sequence[str]`
-            # Will fix in later PR
-            cols = ensure_index(cast(Axes, columns))
+            cols = ensure_index(columns)
             self.frame = self.frame[cols]
             return cols
         else: