TYP: mostly missing return annotations in IO (#44801)

Author: twoertwein

pandas/io/clipboards.py

@@ -1,4 +1,6 @@
 """ io on the clipboard """
+from __future__ import annotations
+
 from io import StringIO
 import warnings
 
@@ -10,7 +12,7 @@
 )
 
 
-def read_clipboard(sep=r"\s+", **kwargs):  # pragma: no cover
+def read_clipboard(sep: str = r"\s+", **kwargs):  # pragma: no cover
     r"""
     Read text from clipboard and pass to read_csv.
 
@@ -83,7 +85,9 @@ def read_clipboard(sep=r"\s+", **kwargs):  # pragma: no cover
     return read_csv(StringIO(text), sep=sep, **kwargs)
 
 
-def to_clipboard(obj, excel=True, sep=None, **kwargs):  # pragma: no cover
+def to_clipboard(
+    obj, excel: bool | None = True, sep: str | None = None, **kwargs
+) -> None:  # pragma: no cover
     """
     Attempt to write text representation of object to the system clipboard
     The clipboard can be then pasted into Excel for example.

pandas/io/common.py

@@ -174,7 +174,7 @@ def _expand_user(filepath_or_buffer: str | BaseBufferT) -> str | BaseBufferT:
     return filepath_or_buffer
 
 
-def validate_header_arg(header) -> None:
+def validate_header_arg(header: object) -> None:
     if isinstance(header, bool):
         raise TypeError(
             "Passing a bool to header is invalid. Use header=None for no header or "
@@ -662,8 +662,7 @@ def get_handle(
         mode += "b"
 
     # validate encoding and errors
-    if isinstance(encoding, str):
-        codecs.lookup(encoding)
+    codecs.lookup(encoding)
     if isinstance(errors, str):
         codecs.lookup_error(errors)
 

pandas/io/date_converters.py

@@ -103,13 +103,13 @@ def generic_parser(parse_func, *cols):
     return results
 
 
-def _maybe_cast(arr):
+def _maybe_cast(arr: np.ndarray) -> np.ndarray:
     if not arr.dtype.type == np.object_:
         arr = np.array(arr, dtype=object)
     return arr
 
 
-def _check_columns(cols):
+def _check_columns(cols) -> int:
     if not len(cols):
         raise AssertionError("There must be at least 1 column")
 

pandas/io/html.py

@@ -12,6 +12,7 @@
 from typing import (
     Pattern,
     Sequence,
+    cast,
 )
 
 from pandas._typing import (
@@ -47,7 +48,7 @@
 _HAS_HTML5LIB = False
 
 
-def _importers():
+def _importers() -> None:
     # import things we need
     # but make this done on a first use basis
 
@@ -93,7 +94,7 @@ def _remove_whitespace(s: str, regex: Pattern = _RE_WHITESPACE) -> str:
     return regex.sub(" ", s.strip())
 
 
-def _get_skiprows(skiprows: int | Sequence[int] | slice | None):
+def _get_skiprows(skiprows: int | Sequence[int] | slice | None) -> int | Sequence[int]:
     """
     Get an iterator given an integer, slice or container.
 
@@ -116,7 +117,7 @@ def _get_skiprows(skiprows: int | Sequence[int] | slice | None):
         start, step = skiprows.start or 0, skiprows.step or 1
         return list(range(start, skiprows.stop, step))
     elif isinstance(skiprows, numbers.Integral) or is_list_like(skiprows):
-        return skiprows
+        return cast("int | Sequence[int]", skiprows)
     elif skiprows is None:
         return 0
     raise TypeError(f"{type(skiprows).__name__} is not a valid type for skipping rows")

pandas/io/parquet.py

@@ -109,7 +109,7 @@ def _get_path_or_handle(
 
 class BaseImpl:
     @staticmethod
-    def validate_dataframe(df: DataFrame):
+    def validate_dataframe(df: DataFrame) -> None:
 
         if not isinstance(df, DataFrame):
             raise ValueError("to_parquet only supports IO with DataFrames")
@@ -139,7 +139,7 @@ def validate_dataframe(df: DataFrame):
     def write(self, df: DataFrame, path, compression, **kwargs):
         raise AbstractMethodError(self)
 
-    def read(self, path, columns=None, **kwargs):
+    def read(self, path, columns=None, **kwargs) -> DataFrame:
         raise AbstractMethodError(self)
 
 
@@ -164,7 +164,7 @@ def write(
         storage_options: StorageOptions = None,
         partition_cols: list[str] | None = None,
         **kwargs,
-    ):
+    ) -> None:
         self.validate_dataframe(df)
 
         from_pandas_kwargs: dict[str, Any] = {"schema": kwargs.pop("schema", None)}
@@ -206,7 +206,7 @@ def read(
         use_nullable_dtypes=False,
         storage_options: StorageOptions = None,
         **kwargs,
-    ):
+    ) -> DataFrame:
         kwargs["use_pandas_metadata"] = True
 
         to_pandas_kwargs = {}
@@ -266,7 +266,7 @@ def write(
         partition_cols=None,
         storage_options: StorageOptions = None,
         **kwargs,
-    ):
+    ) -> None:
         self.validate_dataframe(df)
         # thriftpy/protocol/compact.py:339:
         # DeprecationWarning: tostring() is deprecated.
@@ -309,7 +309,7 @@ def write(
 
     def read(
         self, path, columns=None, storage_options: StorageOptions = None, **kwargs
-    ):
+    ) -> DataFrame:
         parquet_kwargs: dict[str, Any] = {}
         use_nullable_dtypes = kwargs.pop("use_nullable_dtypes", False)
         if Version(self.api.__version__) >= Version("0.7.1"):
@@ -442,7 +442,7 @@ def read_parquet(
     storage_options: StorageOptions = None,
     use_nullable_dtypes: bool = False,
     **kwargs,
-):
+) -> DataFrame:
     """
     Load a parquet object from the file path, returning a DataFrame.
 

pandas/io/pickle.py

@@ -30,7 +30,7 @@ def to_pickle(
     compression: CompressionOptions = "infer",
     protocol: int = pickle.HIGHEST_PROTOCOL,
     storage_options: StorageOptions = None,
-):
+) -> None:
     """
     Pickle (serialize) object to file.