feat: add Series.plot.hist method

Author: chelsea-lin

bigframes/operations/plot.py

@@ -0,0 +1,108 @@
+# Copyright 2023 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from typing import Sequence
+
+import matplotlib.pyplot as plt
+
+import bigframes.constants as constants
+import third_party.bigframes_vendored.pandas.plotting._core as vendordt
+
+
+class PlotAccessor:
+    __doc__ = vendordt.PlotAccessor.__doc__
+
+    def __init__(self, data) -> None:
+        self._parent = data
+
+    def hist(self, by: Sequence[str] | None = None, bins: int = 10, **kwargs):
+        if by is not None:
+            raise NotImplementedError(
+                f"Non-none `by` argument is not yet supported. {constants.FEEDBACK_LINK}"
+            )
+        if kwargs.pop("backend", None) is not None:
+            raise NotImplementedError(
+                f"Only support matplotlib backend for now. {constants.FEEDBACK_LINK}"
+            )
+        import bigframes.dataframe as dataframe
+
+        if isinstance(self._parent, dataframe.DataFrame):
+            raise NotImplementedError(
+                f"`Dataframe.plot.hist` is not implemented yet. {constants.FEEDBACK_LINK}"
+            )
+
+        return self._hist_series(
+            by=by,
+            bins=bins,
+            **kwargs,
+        )
+
+    def _hist_series(
+        self,
+        by: Sequence[str] | None = None,
+        bins: int = 10,
+        **kwargs,
+    ):
+        # Only supported some arguments to adorn plots.
+        ax = kwargs.pop("ax", None)
+        figsize = kwargs.pop("figsize", None)
+        legend = kwargs.pop("legend", False)
+        grid = kwargs.pop("grid", None)
+        xticks = kwargs.pop("xticks", None)
+        yticks = kwargs.pop("yticks", None)
+
+        # Calculates the bins' values and weights through BigQuery
+        import bigframes.pandas as bpd
+
+        series = self._parent.copy()
+        binned = bpd.cut(series, bins=bins, labels=None)
+        binned_data = (
+            binned.struct.explode()
+            .value_counts()
+            .to_pandas()
+            .sort_index(level="left_exclusive")
+        )
+        weights = binned_data.values
+        left_bins = binned_data.index.get_level_values("left_exclusive")
+        right_bins = binned_data.index.get_level_values("right_inclusive")
+        bin_edges = left_bins.union(right_bins, sort=True)
+
+        # This code takes the hist_series function from pandas and tweaks it a bit.
+        if kwargs.get("layout", None) is not None:
+            raise ValueError("The 'layout' keyword is not supported when 'by' is None")
+
+        fig = kwargs.pop(
+            "figure", plt.gcf() if plt.get_fignums() else plt.figure(figsize=figsize)
+        )
+        if figsize is not None and tuple(figsize) != tuple(fig.get_size_inches()):
+            fig.set_size_inches(*figsize, forward=True)
+
+        ax = kwargs.pop("ax", None)
+        if ax is None:
+            ax = fig.gca()
+        elif ax.get_figure() != fig:
+            raise AssertionError("passed axis not bound to passed figure")
+
+        if legend:
+            kwargs["label"] = series.name
+        ax.hist(x=left_bins, bins=bin_edges, weights=weights, **kwargs)
+        if legend:
+            ax.legend()
+        if grid is not None:
+            ax.grid(grid)
+        if xticks is not None:
+            ax.set_xticks(xticks)
+        if yticks is not None:
+            ax.set_yticks(yticks)
+
+        return ax

bigframes/plotting/__init__.py

@@ -0,0 +1,102 @@
+# Copyright 2023 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from typing import Iterable
+
+from matplotlib.axes import Axes
+import matplotlib.pyplot as plt
+import numpy as np
+
+
+def hist_series(
+    series,
+    by=None,
+    ax=None,
+    grid: bool = True,
+    xlabelsize: int | None = None,
+    xrot: float | None = None,
+    ylabelsize: int | None = None,
+    yrot: float | None = None,
+    figsize=None,
+    bins: int = 10,
+    legend: bool = False,
+    **kwargs,
+):
+    import bigframes.pandas as bpd
+
+    # Calculates the bins' values and weights through BigQuery
+    binned = bpd.cut(series, bins=bins, labels=None)
+    binned_data = (
+        binned.struct.explode()
+        .value_counts()
+        .to_pandas()
+        .sort_index(level="left_exclusive")
+    )
+
+    weights = binned_data.values
+    left_bins = binned_data.index.get_level_values("left_exclusive")
+    right_bins = binned_data.index.get_level_values("right_inclusive")
+    bin_edges = left_bins.union(right_bins, sort=True)
+
+    # This code takes the hist_series function from pandas and tweaks it a bit.
+    if kwargs.get("layout", None) is not None:
+        raise ValueError("The 'layout' keyword is not supported when 'by' is None")
+    # hack until the plotting interface is a bit more unified
+    fig = kwargs.pop(
+        "figure", plt.gcf() if plt.get_fignums() else plt.figure(figsize=figsize)
+    )
+    if figsize is not None and tuple(figsize) != tuple(fig.get_size_inches()):
+        fig.set_size_inches(*figsize, forward=True)
+    if ax is None:
+        ax = fig.gca()
+    elif ax.get_figure() != fig:
+        raise AssertionError("passed axis not bound to passed figure")
+    if legend:
+        kwargs["label"] = series.name
+    ax.hist(x=left_bins, bins=bin_edges, weights=weights, **kwargs)
+    if legend:
+        ax.legend()
+    ax.grid(grid)
+    axes = np.array([ax])
+
+    _set_ticks_props(
+        axes,
+        xlabelsize=xlabelsize,
+        xrot=xrot,
+        ylabelsize=ylabelsize,
+        yrot=yrot,
+    )
+
+    if hasattr(axes, "ndim"):
+        if axes.ndim == 1 and len(axes) == 1:
+            return axes[0]
+    return axes
+
+
+def _set_ticks_props(
+    axes: Iterable[Axes],
+    xlabelsize: int | None = None,
+    xrot=None,
+    ylabelsize: int | None = None,
+    yrot=None,
+):
+    for ax in axes:
+        if xlabelsize is not None:
+            plt.setp(ax.get_xticklabels(), fontsize=xlabelsize)
+        if xrot is not None:
+            plt.setp(ax.get_xticklabels(), rotation=xrot)
+        if ylabelsize is not None:
+            plt.setp(ax.get_yticklabels(), fontsize=ylabelsize)
+        if yrot is not None:
+            plt.setp(ax.get_yticklabels(), rotation=yrot)
+    return axes

bigframes/series.py

@@ -50,6 +50,7 @@
 import bigframes.operations.aggregations as agg_ops
 import bigframes.operations.base
 import bigframes.operations.datetimes as dt
+import bigframes.operations.plot as plot
 import bigframes.operations.strings as strings
 import bigframes.operations.structs as structs
 import third_party.bigframes_vendored.pandas.core.series as vendored_pandas_series
@@ -1551,6 +1552,10 @@ def __array_ufunc__(
     def str(self) -> strings.StringMethods:
         return strings.StringMethods(self._block)
 
+    @property
+    def plot(self):
+        return plot.PlotAccessor(self)
+
     def _slice(
         self,
         start: typing.Optional[int] = None,

setup.py

@@ -58,6 +58,7 @@
     "tabulate >= 0.9",
     "ipywidgets >=7.7.1",
     "humanize >= 4.6.0",
+    "matplotlib >= 3.7.1",
 ]
 extras = {
     # Optional test dependencies packages. If they're missed, may skip some tests.

tests/system/small/operations/test_plot.py

@@ -0,0 +1,50 @@
+# Copyright 2023 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import pandas._testing as tm
+
+
+def test_series_hist_bins(scalars_dfs):
+    scalars_df, scalars_pandas_df = scalars_dfs
+    ax = scalars_df["int64_col"].plot.hist(bins=5)
+    pd_ax = scalars_pandas_df["int64_col"].hist(bins=5)
+
+    # Check hist has same height compared to the pandas one.
+    assert len(ax.patches) == len(pd_ax.patches)
+    for i in range(len(ax.patches)):
+        assert ax.patches[i].xy == pd_ax.patches[i].xy
+        assert ax.patches[i]._height == pd_ax.patches[i]._height
+
+
+def test_series_hist_ticks_props(scalars_dfs):
+    scalars_df, scalars_pandas_df = scalars_dfs
+
+    xticks = [20, 18]
+    yticks = [30, 40]
+
+    ax = scalars_df["float64_col"].plot.hist(xticks=xticks, yticks=yticks)
+    pd_ax = scalars_pandas_df["float64_col"].plot.hist(xticks=xticks, yticks=yticks)
+    xlabels = ax.get_xticklabels()
+    pd_xlables = pd_ax.get_xticklabels()
+    assert len(xlabels) == len(pd_xlables)
+    for i in range(len(pd_xlables)):
+        tm.assert_almost_equal(xlabels[i].get_fontsize(), pd_xlables[i].get_fontsize())
+        tm.assert_almost_equal(xlabels[i].get_rotation(), pd_xlables[i].get_rotation())
+
+    ylabels = ax.get_yticklabels()
+    pd_ylables = pd_ax.get_yticklabels()
+    assert len(xlabels) == len(pd_xlables)
+    for i in range(len(pd_xlables)):
+        tm.assert_almost_equal(ylabels[i].get_fontsize(), pd_ylables[i].get_fontsize())
+        tm.assert_almost_equal(ylabels[i].get_rotation(), pd_ylables[i].get_rotation())

third_party/bigframes_vendored/pandas/core/series.py

@@ -3111,6 +3111,17 @@ def str(self):
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
+    @property
+    def plot(self):
+        """
+        Make plots of Series.
+
+        Returns:
+            bigframes.operations.plot.PlotAccessor:
+                An accessor making plots.
+        """
+        raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
+
     def isin(self, values):
         """
         Whether elements in Series are contained in values.

third_party/bigframes_vendored/pandas/plotting/_core.py

@@ -0,0 +1,53 @@
+from typing import Sequence
+
+from bigframes import constants
+
+
+class PlotAccessor:
+    def hist(self, by: Sequence[str] | None = None, bins: int = 10, **kwargs):
+        """
+        Draw histogram of the input series using matplotlib.
+
+        Parameters
+        ----------
+        by : str or sequence, optional
+            If passed, then used to form histograms for separate groups.
+            Currently, it is not supported yet.
+        bins : int, default 10
+            Number of histogram bins to be used.
+        ax : matplotlib axes object, default None
+            An axes of the current figure.
+        grid : bool, default None (matlab style default)
+            Axis grid lines.
+        xticks : sequence
+            Values to use for the xticks.
+        yticks : sequence
+            Values to use for the yticks.
+        figsize : a tuple (width, height) in inches
+            Size of a figure object.
+        backend : str, default None
+            Backend to use instead of the backend specified in the option
+            ``plotting.backend``. Currently, only `matplotlib` is not supported yet.
+        legend : bool, default False
+            Place legend on axis subplots.
+        **kwargs
+            Options to pass to matplotlib plotting method.
+
+        Returns
+        -------
+        class:`matplotlib.Axes`
+            A histogram plot.
+
+        Examples
+        --------
+        For Series:
+
+        .. plot::
+            :context: close-figs
+
+            >>> import bigframes.pandas as bpd
+            >>> lst = ['a', 'a', 'a', 'b', 'b', 'b']
+            >>> ser = bpd.Series([1, 2, 2, 4, 6, 6], index=lst)
+            >>> hist = ser.plot.hist()
+        """
+        raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)