TYP: added missing __init__ in pandas/core/methods (#51052)

* TYP: added missing __init__ in pandas/core/methods

* fix most typing issues

* use Sequence[Hashable] more consistenly

---------

Co-authored-by: Matthew Roeschke <[email protected]>

Author: twoertwein

.pre-commit-config.yaml

@@ -135,7 +135,7 @@ repos:
         types: [python]
         stages: [manual]
         additional_dependencies: &pyright_dependencies
-        - [email protected].276
+        - [email protected].284
     -   id: pyright_reportGeneralTypeIssues
         # note: assumes python env is setup and activated
         name: pyright reportGeneralTypeIssues

pandas/_testing/contexts.py

@@ -11,6 +11,11 @@
 )
 import uuid
 
+from pandas._typing import (
+    BaseBuffer,
+    CompressionOptions,
+    FilePath,
+)
 from pandas.compat import PYPY
 from pandas.errors import ChainedAssignmentError
 
@@ -20,7 +25,9 @@
 
 
 @contextmanager
-def decompress_file(path, compression) -> Generator[IO[bytes], None, None]:
+def decompress_file(
+    path: FilePath | BaseBuffer, compression: CompressionOptions
+) -> Generator[IO[bytes], None, None]:
     """
     Open a compressed file and return a file object.
 

pandas/core/frame.py

@@ -9542,7 +9542,7 @@ def _append(
 
     def join(
         self,
-        other: DataFrame | Series | list[DataFrame | Series],
+        other: DataFrame | Series | Iterable[DataFrame | Series],
         on: IndexLabel | None = None,
         how: MergeHow = "left",
         lsuffix: str = "",

pandas/core/methods/__init__.py

@@ -23,7 +23,7 @@ def flex_binary_moment(arg1, arg2, f, pairwise: bool = False):
     elif isinstance(arg1, ABCDataFrame):
         from pandas import DataFrame
 
-        def dataframe_from_int_dict(data, frame_template):
+        def dataframe_from_int_dict(data, frame_template) -> DataFrame:
             result = DataFrame(data, index=frame_template.index)
             if len(result.columns) > 0:
                 result.columns = frame_template.columns[result.columns]

pandas/core/window/common.py

@@ -106,12 +106,12 @@ class BadLineHandleMethod(Enum):
     def __init__(self, kwds) -> None:
 
         self.names = kwds.get("names")
-        self.orig_names: list | None = None
+        self.orig_names: Sequence[Hashable] | None = None
 
         self.index_col = kwds.get("index_col", None)
         self.unnamed_cols: set = set()
         self.index_names: Sequence[Hashable] | None = None
-        self.col_names = None
+        self.col_names: Sequence[Hashable] | None = None
 
         self.parse_dates = _validate_parse_dates_arg(kwds.pop("parse_dates", False))
         self._parse_date_cols: Iterable = []
@@ -269,9 +269,11 @@ def _should_parse_dates(self, i: int) -> bool:
     def _extract_multi_indexer_columns(
         self,
         header,
-        index_names: list | None,
+        index_names: Sequence[Hashable] | None,
         passed_names: bool = False,
-    ):
+    ) -> tuple[
+        Sequence[Hashable], Sequence[Hashable] | None, Sequence[Hashable] | None, bool
+    ]:
         """
         Extract and return the names, index_names, col_names if the column
         names are a MultiIndex.
@@ -1004,7 +1006,7 @@ def _validate_usecols_arg(self, usecols):
             return usecols, usecols_dtype
         return usecols, None
 
-    def _clean_index_names(self, columns, index_col):
+    def _clean_index_names(self, columns, index_col) -> tuple[list | None, list, list]:
         if not is_index_col(index_col):
             return None, columns, index_col
 

pandas/io/parsers/base_parser.py

@@ -104,8 +104,7 @@ def __init__(self, src: ReadCsvBuffer[str], **kwds) -> None:
 
         # error: Cannot determine type of 'names'
         if self.names is None:  # type: ignore[has-type]
-            # error: Cannot determine type of 'names'
-            self.names = list(range(self._reader.table_width))  # type: ignore[has-type]
+            self.names = list(range(self._reader.table_width))
 
         # gh-9755
         #

pandas/io/parsers/c_parser_wrapper.py

@@ -126,7 +126,6 @@ def __init__(self, f: ReadCsvBuffer[str] | list, **kwds) -> None:
         # Now self.columns has the set of columns that we will process.
         # The original set is stored in self.original_columns.
         # error: Cannot determine type of 'index_names'
-        self.columns: list[Hashable]
         (
             self.columns,
             self.index_names,
@@ -915,7 +914,7 @@ def _clear_buffer(self) -> None:
     _implicit_index = False
 
     def _get_index_name(
-        self, columns: list[Hashable]
+        self, columns: Sequence[Hashable]
     ) -> tuple[Sequence[Hashable] | None, list[Hashable], list[Hashable]]:
         """
         Try several cases to get lines: