Merge branch 'master' of https://github.com/pandas-dev/pandas into ref-libreduction-5

Author: jbrockmendel

.pre-commit-config.yaml

@@ -30,15 +30,3 @@ repos:
     -   id: isort
         language: python_venv
         exclude: ^pandas/__init__\.py$|^pandas/core/api\.py$
--   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.730
-    hooks:
-     -  id: mypy
-        args:
-          # As long as a some files are excluded from check-untyped-defs
-          # we have to exclude it from the pre-commit hook as the configuration
-          # is based on modules but the hook runs on files.
-          - --no-check-untyped-defs
-          - --follow-imports
-          - skip
-        files: pandas/

doc/source/whatsnew/v1.1.2.rst

@@ -31,7 +31,7 @@ Bug fixes
 - Bug in :class:`Series` constructor raising a ``TypeError`` when constructing sparse datetime64 dtypes (:issue:`35762`)
 - Bug in :meth:`DataFrame.apply` with ``result_type="reduce"`` returning with incorrect index (:issue:`35683`)
 - Bug in :meth:`DateTimeIndex.format` and :meth:`PeriodIndex.format` with ``name=True`` setting the first item to ``"None"`` where it should bw ``""`` (:issue:`35712`)
--
+- Bug in :meth:`Float64Index.__contains__` incorrectly raising ``TypeError`` instead of returning ``False`` (:issue:`35788`)
 
 .. ---------------------------------------------------------------------------
 

pandas/_libs/index.pyx

@@ -80,7 +80,11 @@ cdef class IndexEngine:
             values = self._get_index_values()
 
             self._check_type(val)
-            loc = _bin_search(values, val)  # .searchsorted(val, side='left')
+            try:
+                loc = _bin_search(values, val)  # .searchsorted(val, side='left')
+            except TypeError:
+                # GH#35788 e.g. val=None with float64 values
+                raise KeyError(val)
             if loc >= len(values):
                 raise KeyError(val)
             if values[loc] != val:

pandas/_libs/interval.pyx

@@ -291,12 +291,6 @@ cdef class Interval(IntervalMixin):
     True
     >>> year_2017.length
     Timedelta('365 days 00:00:00')
-
-    And also you can create string intervals
-
-    >>> volume_1 = pd.Interval('Ant', 'Dog', closed='both')
-    >>> 'Bee' in volume_1
-    True
     """
     _typ = "interval"
     __array_priority__ = 1000

pandas/core/indexes/multi.py

@@ -19,7 +19,7 @@
 
 from pandas._libs import algos as libalgos, index as libindex, lib
 from pandas._libs.hashtable import duplicated_int64
-from pandas._typing import AnyArrayLike, Scalar
+from pandas._typing import AnyArrayLike, Label, Scalar
 from pandas.compat.numpy import function as nv
 from pandas.errors import InvalidIndexError, PerformanceWarning, UnsortedIndexError
 from pandas.util._decorators import Appender, cache_readonly, doc
@@ -449,7 +449,12 @@ def from_arrays(cls, arrays, sortorder=None, names=lib.no_default) -> "MultiInde
         )
 
     @classmethod
-    def from_tuples(cls, tuples, sortorder=None, names=None):
+    def from_tuples(
+        cls,
+        tuples,
+        sortorder: Optional[int] = None,
+        names: Optional[Sequence[Label]] = None,
+    ):
         """
         Convert list of tuples to MultiIndex.
 
@@ -490,6 +495,7 @@ def from_tuples(cls, tuples, sortorder=None, names=None):
         elif is_iterator(tuples):
             tuples = list(tuples)
 
+        arrays: List[Sequence[Label]]
         if len(tuples) == 0:
             if names is None:
                 raise TypeError("Cannot infer number of levels from empty list")
@@ -700,8 +706,13 @@ def levels(self):
         return FrozenList(result)
 
     def _set_levels(
-        self, levels, level=None, copy=False, validate=True, verify_integrity=False
-    ):
+        self,
+        levels,
+        level=None,
+        copy: bool = False,
+        validate: bool = True,
+        verify_integrity: bool = False,
+    ) -> None:
         # This is NOT part of the levels property because it should be
         # externally not allowed to set levels. User beware if you change
         # _levels directly
@@ -719,10 +730,10 @@ def _set_levels(
             )
         else:
             level_numbers = [self._get_level_number(lev) for lev in level]
-            new_levels = list(self._levels)
+            new_levels_list = list(self._levels)
             for lev_num, lev in zip(level_numbers, levels):
-                new_levels[lev_num] = ensure_index(lev, copy=copy)._shallow_copy()
-            new_levels = FrozenList(new_levels)
+                new_levels_list[lev_num] = ensure_index(lev, copy=copy)._shallow_copy()
+            new_levels = FrozenList(new_levels_list)
 
         if verify_integrity:
             new_codes = self._verify_integrity(levels=new_levels)
@@ -875,8 +886,13 @@ def codes(self):
         return self._codes
 
     def _set_codes(
-        self, codes, level=None, copy=False, validate=True, verify_integrity=False
-    ):
+        self,
+        codes,
+        level=None,
+        copy: bool = False,
+        validate: bool = True,
+        verify_integrity: bool = False,
+    ) -> None:
         if validate:
             if level is None and len(codes) != self.nlevels:
                 raise ValueError("Length of codes must match number of levels")
@@ -890,11 +906,13 @@ def _set_codes(
             )
         else:
             level_numbers = [self._get_level_number(lev) for lev in level]
-            new_codes = list(self._codes)
+            new_codes_list = list(self._codes)
             for lev_num, level_codes in zip(level_numbers, codes):
                 lev = self.levels[lev_num]
-                new_codes[lev_num] = _coerce_indexer_frozen(level_codes, lev, copy=copy)
-            new_codes = FrozenList(new_codes)
+                new_codes_list[lev_num] = _coerce_indexer_frozen(
+                    level_codes, lev, copy=copy
+                )
+            new_codes = FrozenList(new_codes_list)
 
         if verify_integrity:
             new_codes = self._verify_integrity(codes=new_codes)
@@ -2435,7 +2453,7 @@ def _get_partial_string_timestamp_match_key(self, key):
         if isinstance(key, str) and self.levels[0]._supports_partial_string_indexing:
             # Convert key '2016-01-01' to
             # ('2016-01-01'[, slice(None, None, None)]+)
-            key = tuple([key] + [slice(None)] * (len(self.levels) - 1))
+            key = (key,) + (slice(None),) * (len(self.levels) - 1)
 
         if isinstance(key, tuple):
             # Convert (..., '2016-01-01', ...) in tuple to
@@ -3086,7 +3104,7 @@ def _update_indexer(idxr, indexer=indexer):
             elif is_list_like(k):
                 # a collection of labels to include from this level (these
                 # are or'd)
-                indexers = None
+                indexers: Optional[Int64Index] = None
                 for x in k:
                     try:
                         idxrs = _convert_to_indexer(

pandas/io/excel/_xlwt.py

@@ -1,8 +1,13 @@
+from typing import TYPE_CHECKING, Dict
+
 import pandas._libs.json as json
 
 from pandas.io.excel._base import ExcelWriter
 from pandas.io.excel._util import _validate_freeze_panes
 
+if TYPE_CHECKING:
+    from xlwt import XFStyle
+
 
 class _XlwtWriter(ExcelWriter):
     engine = "xlwt"
@@ -29,12 +34,11 @@ def save(self):
         """
         Save workbook to disk.
         """
-        return self.book.save(self.path)
+        self.book.save(self.path)
 
     def write_cells(
         self, cells, sheet_name=None, startrow=0, startcol=0, freeze_panes=None
     ):
-        # Write the frame cells using xlwt.
 
         sheet_name = self._get_sheet_name(sheet_name)
 
@@ -49,7 +53,7 @@ def write_cells(
             wks.set_horz_split_pos(freeze_panes[0])
             wks.set_vert_split_pos(freeze_panes[1])
 
-        style_dict = {}
+        style_dict: Dict[str, XFStyle] = {}
 
         for cell in cells:
             val, fmt = self._value_with_fmt(cell.val)
@@ -101,14 +105,14 @@ def _style_to_xlwt(
                     f"{key}: {cls._style_to_xlwt(value, False)}"
                     for key, value in item.items()
                 ]
-                out = f"{(line_sep).join(it)} "
+                out = f"{line_sep.join(it)} "
                 return out
             else:
                 it = [
                     f"{key} {cls._style_to_xlwt(value, False)}"
                     for key, value in item.items()
                 ]
-                out = f"{(field_sep).join(it)} "
+                out = f"{field_sep.join(it)} "
                 return out
         else:
             item = f"{item}"

pandas/io/parquet.py

@@ -128,7 +128,7 @@ def write(
             self.api.parquet.write_table(table, path, compression=compression, **kwargs)
 
     def read(
-        self, path, columns=None, storage_options: StorageOptions = None, **kwargs,
+        self, path, columns=None, storage_options: StorageOptions = None, **kwargs
     ):
         if is_fsspec_url(path) and "filesystem" not in kwargs:
             import_optional_dependency("fsspec")
@@ -218,7 +218,7 @@ def write(
             )
 
     def read(
-        self, path, columns=None, storage_options: StorageOptions = None, **kwargs,
+        self, path, columns=None, storage_options: StorageOptions = None, **kwargs
     ):
         if is_fsspec_url(path):
             fsspec = import_optional_dependency("fsspec")

pandas/io/parsers.py

@@ -1967,10 +1967,6 @@ def _do_date_conversions(self, names, data):
 
 
 class CParserWrapper(ParserBase):
-    """
-
-    """
-
     def __init__(self, src, **kwds):
         self.kwds = kwds
         kwds = kwds.copy()

pandas/io/pytables.py

@@ -2931,7 +2931,7 @@ def read_index_node(
         # If the index was an empty array write_array_empty() will
         # have written a sentinel. Here we replace it with the original.
         if "shape" in node._v_attrs and np.prod(node._v_attrs.shape) == 0:
-            data = np.empty(node._v_attrs.shape, dtype=node._v_attrs.value_type,)
+            data = np.empty(node._v_attrs.shape, dtype=node._v_attrs.value_type)
         kind = _ensure_decoded(node._v_attrs.kind)
         name = None
 
@@ -4103,7 +4103,7 @@ def create_description(
         return d
 
     def read_coordinates(
-        self, where=None, start: Optional[int] = None, stop: Optional[int] = None,
+        self, where=None, start: Optional[int] = None, stop: Optional[int] = None
     ):
         """
         select coordinates (row numbers) from a table; return the
@@ -4374,7 +4374,7 @@ def write_data_chunk(
             self.table.flush()
 
     def delete(
-        self, where=None, start: Optional[int] = None, stop: Optional[int] = None,
+        self, where=None, start: Optional[int] = None, stop: Optional[int] = None
     ):
 
         # delete all rows (and return the nrows)
@@ -4805,7 +4805,7 @@ def _convert_index(name: str, index: Index, encoding: str, errors: str) -> Index
     if inferred_type == "date":
         converted = np.asarray([v.toordinal() for v in values], dtype=np.int32)
         return IndexCol(
-            name, converted, "date", _tables().Time32Col(), index_name=index_name,
+            name, converted, "date", _tables().Time32Col(), index_name=index_name
         )
     elif inferred_type == "string":
 
@@ -4821,13 +4821,13 @@ def _convert_index(name: str, index: Index, encoding: str, errors: str) -> Index
 
     elif inferred_type in ["integer", "floating"]:
         return IndexCol(
-            name, values=converted, kind=kind, typ=atom, index_name=index_name,
+            name, values=converted, kind=kind, typ=atom, index_name=index_name
         )
     else:
         assert isinstance(converted, np.ndarray) and converted.dtype == object
         assert kind == "object", kind
         atom = _tables().ObjectAtom()
-        return IndexCol(name, converted, kind, atom, index_name=index_name,)
+        return IndexCol(name, converted, kind, atom, index_name=index_name)
 
 
 def _unconvert_index(

pandas/plotting/_matplotlib/boxplot.py

@@ -1,4 +1,5 @@
 from collections import namedtuple
+from typing import TYPE_CHECKING
 import warnings
 
 from matplotlib.artist import setp
@@ -14,6 +15,9 @@
 from pandas.plotting._matplotlib.style import _get_standard_colors
 from pandas.plotting._matplotlib.tools import _flatten, _subplots
 
+if TYPE_CHECKING:
+    from matplotlib.axes import Axes
+
 
 class BoxPlot(LinePlot):
     _kind = "box"
@@ -150,7 +154,7 @@ def _make_plot(self):
                 labels = [pprint_thing(key) for key in range(len(labels))]
             self._set_ticklabels(ax, labels)
 
-    def _set_ticklabels(self, ax, labels):
+    def _set_ticklabels(self, ax: "Axes", labels):
         if self.orientation == "vertical":
             ax.set_xticklabels(labels)
         else:
@@ -292,7 +296,7 @@ def maybe_color_bp(bp, **kwds):
         if not kwds.get("capprops"):
             setp(bp["caps"], color=colors[3], alpha=1)
 
-    def plot_group(keys, values, ax):
+    def plot_group(keys, values, ax: "Axes"):
         keys = [pprint_thing(x) for x in keys]
         values = [np.asarray(remove_na_arraylike(v), dtype=object) for v in values]
         bp = ax.boxplot(values, **kwds)