TYP: pandas/plotting annotations from pandas-stubs (#47827)

* TYP: pandas/plotting annotations from pandas-stubs

* xticks + pyright

Author: twoertwein

.pre-commit-config.yaml

@@ -93,7 +93,7 @@ repos:
         types: [python]
         stages: [manual]
         additional_dependencies: &pyright_dependencies
-        - [email protected].258
+        - [email protected].262
     -   id: pyright_reportGeneralTypeIssues
         name: pyright reportGeneralTypeIssues
         entry: pyright --skipunannotated -p pyright_reportGeneralTypeIssues.json

pandas/core/arrays/arrow/array.py

@@ -444,7 +444,7 @@ def dropna(self: ArrowExtensionArrayT) -> ArrowExtensionArrayT:
         else:
             return type(self)(pc.drop_null(self._data))
 
-    def isin(self: ArrowExtensionArrayT, values) -> npt.NDArray[np.bool_]:
+    def isin(self, values) -> npt.NDArray[np.bool_]:
         if pa_version_under2p0:
             fallback_performancewarning(version="2")
             return super().isin(values)

pandas/plotting/_core.py

@@ -27,6 +27,8 @@
 from pandas.core.base import PandasObject
 
 if TYPE_CHECKING:
+    from matplotlib.axes import Axes
+
     from pandas import DataFrame
 
 
@@ -463,16 +465,16 @@ def hist_frame(
 @Substitution(backend="")
 @Appender(_boxplot_doc)
 def boxplot(
-    data,
-    column=None,
-    by=None,
-    ax=None,
-    fontsize=None,
-    rot=0,
-    grid=True,
-    figsize=None,
-    layout=None,
-    return_type=None,
+    data: DataFrame,
+    column: str | list[str] | None = None,
+    by: str | list[str] | None = None,
+    ax: Axes | None = None,
+    fontsize: float | str | None = None,
+    rot: int = 0,
+    grid: bool = True,
+    figsize: tuple[float, float] | None = None,
+    layout: tuple[int, int] | None = None,
+    return_type: str | None = None,
     **kwargs,
 ):
     plot_backend = _get_plot_backend("matplotlib")
@@ -499,8 +501,8 @@ def boxplot_frame(
     by=None,
     ax=None,
     fontsize=None,
-    rot=0,
-    grid=True,
+    rot: int = 0,
+    grid: bool = True,
     figsize=None,
     layout=None,
     return_type=None,
@@ -525,16 +527,16 @@ def boxplot_frame(
 
 def boxplot_frame_groupby(
     grouped,
-    subplots=True,
+    subplots: bool = True,
     column=None,
     fontsize=None,
-    rot=0,
-    grid=True,
+    rot: int = 0,
+    grid: bool = True,
     ax=None,
     figsize=None,
     layout=None,
-    sharex=False,
-    sharey=True,
+    sharex: bool = False,
+    sharey: bool = True,
     backend=None,
     **kwargs,
 ):
@@ -1041,7 +1043,7 @@ def __call__(self, *args, **kwargs):
     )
     @Substitution(kind="line")
     @Appender(_bar_or_line_doc)
-    def line(self, x=None, y=None, **kwargs):
+    def line(self, x=None, y=None, **kwargs) -> PlotAccessor:
         """
         Plot Series or DataFrame as lines.
 
@@ -1128,7 +1130,7 @@ def line(self, x=None, y=None, **kwargs):
     )
     @Substitution(kind="bar")
     @Appender(_bar_or_line_doc)
-    def bar(self, x=None, y=None, **kwargs):
+    def bar(self, x=None, y=None, **kwargs) -> PlotAccessor:
         """
         Vertical bar plot.
 
@@ -1214,7 +1216,7 @@ def bar(self, x=None, y=None, **kwargs):
     )
     @Substitution(kind="bar")
     @Appender(_bar_or_line_doc)
-    def barh(self, x=None, y=None, **kwargs):
+    def barh(self, x=None, y=None, **kwargs) -> PlotAccessor:
         """
         Make a horizontal bar plot.
 
@@ -1226,7 +1228,7 @@ def barh(self, x=None, y=None, **kwargs):
         """
         return self(kind="barh", x=x, y=y, **kwargs)
 
-    def box(self, by=None, **kwargs):
+    def box(self, by=None, **kwargs) -> PlotAccessor:
         r"""
         Make a box plot of the DataFrame columns.
 
@@ -1293,7 +1295,7 @@ def box(self, by=None, **kwargs):
         """
         return self(kind="box", by=by, **kwargs)
 
-    def hist(self, by=None, bins=10, **kwargs):
+    def hist(self, by=None, bins: int = 10, **kwargs) -> PlotAccessor:
         """
         Draw one histogram of the DataFrame's columns.
 
@@ -1355,7 +1357,7 @@ def hist(self, by=None, bins=10, **kwargs):
         """
         return self(kind="hist", by=by, bins=bins, **kwargs)
 
-    def kde(self, bw_method=None, ind=None, **kwargs):
+    def kde(self, bw_method=None, ind=None, **kwargs) -> PlotAccessor:
         """
         Generate Kernel Density Estimate plot using Gaussian kernels.
 
@@ -1465,7 +1467,7 @@ def kde(self, bw_method=None, ind=None, **kwargs):
 
     density = kde
 
-    def area(self, x=None, y=None, **kwargs):
+    def area(self, x=None, y=None, **kwargs) -> PlotAccessor:
         """
         Draw a stacked area plot.
 
@@ -1538,7 +1540,7 @@ def area(self, x=None, y=None, **kwargs):
         """
         return self(kind="area", x=x, y=y, **kwargs)
 
-    def pie(self, **kwargs):
+    def pie(self, **kwargs) -> PlotAccessor:
         """
         Generate a pie plot.
 
@@ -1593,7 +1595,7 @@ def pie(self, **kwargs):
             raise ValueError("pie requires either y column or 'subplots=True'")
         return self(kind="pie", **kwargs)
 
-    def scatter(self, x, y, s=None, c=None, **kwargs):
+    def scatter(self, x, y, s=None, c=None, **kwargs) -> PlotAccessor:
         """
         Create a scatter plot with varying marker point size and color.
 
@@ -1699,7 +1701,9 @@ def scatter(self, x, y, s=None, c=None, **kwargs):
 
         return self(kind="scatter", x=x, y=y, **kwargs)
 
-    def hexbin(self, x, y, C=None, reduce_C_function=None, gridsize=None, **kwargs):
+    def hexbin(
+        self, x, y, C=None, reduce_C_function=None, gridsize=None, **kwargs
+    ) -> PlotAccessor:
         """
         Generate a hexagonal binning plot.
 

pandas/plotting/_matplotlib/boxplot.py

@@ -48,7 +48,7 @@ class BP(NamedTuple):
         ax: Axes
         lines: dict[str, list[Line2D]]
 
-    def __init__(self, data, return_type="axes", **kwargs) -> None:
+    def __init__(self, data, return_type: str = "axes", **kwargs) -> None:
         # Do not call LinePlot.__init__ which may fill nan
         if return_type not in self._valid_return_types:
             raise ValueError("return_type must be {None, 'axes', 'dict', 'both'}")
@@ -117,7 +117,7 @@ def _validate_color_args(self):
     def _get_colors(self, num_colors=None, color_kwds="color"):
         pass
 
-    def maybe_color_bp(self, bp):
+    def maybe_color_bp(self, bp) -> None:
         if isinstance(self.color, dict):
             boxes = self.color.get("boxes", self._boxes_c)
             whiskers = self.color.get("whiskers", self._whiskers_c)
@@ -292,8 +292,8 @@ def boxplot(
     by=None,
     ax=None,
     fontsize=None,
-    rot=0,
-    grid=True,
+    rot: int = 0,
+    grid: bool = True,
     figsize=None,
     layout=None,
     return_type=None,
@@ -443,8 +443,8 @@ def boxplot_frame(
     by=None,
     ax=None,
     fontsize=None,
-    rot=0,
-    grid=True,
+    rot: int = 0,
+    grid: bool = True,
     figsize=None,
     layout=None,
     return_type=None,
@@ -471,16 +471,16 @@ def boxplot_frame(
 
 def boxplot_frame_groupby(
     grouped,
-    subplots=True,
+    subplots: bool = True,
     column=None,
     fontsize=None,
-    rot=0,
-    grid=True,
+    rot: int = 0,
+    grid: bool = True,
     ax=None,
     figsize=None,
     layout=None,
-    sharex=False,
-    sharey=True,
+    sharex: bool = False,
+    sharey: bool = True,
     **kwds,
 ):
     if subplots is True:

pandas/plotting/_matplotlib/converter.py

@@ -10,6 +10,8 @@
 import functools
 from typing import (
     Any,
+    Final,
+    Iterator,
     cast,
 )
 
@@ -56,14 +58,14 @@
 import pandas.core.tools.datetimes as tools
 
 # constants
-HOURS_PER_DAY = 24.0
-MIN_PER_HOUR = 60.0
-SEC_PER_MIN = 60.0
+HOURS_PER_DAY: Final = 24.0
+MIN_PER_HOUR: Final = 60.0
+SEC_PER_MIN: Final = 60.0
 
-SEC_PER_HOUR = SEC_PER_MIN * MIN_PER_HOUR
-SEC_PER_DAY = SEC_PER_HOUR * HOURS_PER_DAY
+SEC_PER_HOUR: Final = SEC_PER_MIN * MIN_PER_HOUR
+SEC_PER_DAY: Final = SEC_PER_HOUR * HOURS_PER_DAY
 
-MUSEC_PER_DAY = 10**6 * SEC_PER_DAY
+MUSEC_PER_DAY: Final = 10**6 * SEC_PER_DAY
 
 _mpl_units = {}  # Cache for units overwritten by us
 
@@ -94,7 +96,7 @@ def wrapper(*args, **kwargs):
 
 
 @contextlib.contextmanager
-def pandas_converters():
+def pandas_converters() -> Iterator[None]:
     """
     Context manager registering pandas' converters for a plot.
 
@@ -115,7 +117,7 @@ def pandas_converters():
             deregister()
 
 
-def register():
+def register() -> None:
     pairs = get_pairs()
     for type_, cls in pairs:
         # Cache previous converter if present
@@ -126,7 +128,7 @@ def register():
         units.registry[type_] = cls()
 
 
-def deregister():
+def deregister() -> None:
     # Renamed in pandas.plotting.__init__
     for type_, cls in get_pairs():
         # We use type to catch our classes directly, no inheritance
@@ -187,7 +189,7 @@ class TimeFormatter(Formatter):
     def __init__(self, locs) -> None:
         self.locs = locs
 
-    def __call__(self, x, pos=0) -> str:
+    def __call__(self, x, pos: int = 0) -> str:
         """
         Return the time of day as a formatted string.
 
@@ -339,7 +341,7 @@ def axisinfo(unit: tzinfo | None, axis) -> units.AxisInfo:
 
 
 class PandasAutoDateFormatter(dates.AutoDateFormatter):
-    def __init__(self, locator, tz=None, defaultfmt="%Y-%m-%d") -> None:
+    def __init__(self, locator, tz=None, defaultfmt: str = "%Y-%m-%d") -> None:
         dates.AutoDateFormatter.__init__(self, locator, tz, defaultfmt)
 
 
@@ -937,12 +939,12 @@ class TimeSeries_DateLocator(Locator):
     def __init__(
         self,
         freq: BaseOffset,
-        minor_locator=False,
-        dynamic_mode=True,
-        base=1,
-        quarter=1,
-        month=1,
-        day=1,
+        minor_locator: bool = False,
+        dynamic_mode: bool = True,
+        base: int = 1,
+        quarter: int = 1,
+        month: int = 1,
+        day: int = 1,
         plot_obj=None,
     ) -> None:
         freq = to_offset(freq)
@@ -1053,7 +1055,7 @@ def _set_default_format(self, vmin, vmax):
         self.formatdict = {x: f for (x, _, _, f) in format}
         return self.formatdict
 
-    def set_locs(self, locs):
+    def set_locs(self, locs) -> None:
         """Sets the locations of the ticks"""
         # don't actually use the locs. This is just needed to work with
         # matplotlib. Force to use vmin, vmax
@@ -1068,7 +1070,7 @@ def set_locs(self, locs):
             (vmin, vmax) = (vmax, vmin)
         self._set_default_format(vmin, vmax)
 
-    def __call__(self, x, pos=0) -> str:
+    def __call__(self, x, pos: int = 0) -> str:
 
         if self.formatdict is None:
             return ""
@@ -1103,7 +1105,7 @@ def format_timedelta_ticks(x, pos, n_decimals: int) -> str:
             s = f"{int(d):d} days {s}"
         return s
 
-    def __call__(self, x, pos=0) -> str:
+    def __call__(self, x, pos: int = 0) -> str:
         (vmin, vmax) = tuple(self.axis.get_view_interval())
         n_decimals = int(np.ceil(np.log10(100 * 10**9 / abs(vmax - vmin))))
         if n_decimals > 9: