子类pandas.plotting._core.PlanePlot导致ValueError

Question

背景

在下面的示例中，我尝试将自己的绘图方法添加到pandas.DataFrame.plot中，我从熊猫那里复制并粘贴了ScatterPlot，并将名称更改为VscatterPlot。然后，我将这个类连同对应辅助函数到pandas.DataFrame.plot添加到他们各自的位置(参见下面)。

示例类VscatterPlot

import pandas
import numpy as np


class VscatterPlot(pandas.plotting._core.PlanePlot):
    _kind = 'vscatter'

    def __init__(self, data, x, y, s=None, c=None, **kwargs):
        if s is None:
            # hide the matplotlib default for size, in case we want to change
            # the handling of this argument later
            s = 20
        
        super(VscatterPlot, self).__init__(data, x, y, s=s, **kwargs)
        
        if is_integer(c) and not self.data.columns.holds_integer():
            c = self.data.columns[c]
        
        self.c = c

    def _make_plot(self):
        x, y, c, data = self.x, self.y, self.c, self.data
        ax = self.axes[0]

        c_is_column = is_hashable(c) and c in self.data.columns

        # plot a colorbar only if a colormap is provided or necessary
        cb = self.kwds.pop('colorbar', self.colormap or c_is_column)

        # pandas uses colormap, matplotlib uses cmap.
        cmap = self.colormap or 'Greys'
        cmap = self.plt.cm.get_cmap(cmap)
        color = self.kwds.pop("color", None)
        
        if c is not None and color is not None:
            raise TypeError('Specify exactly one of `c` and `color`')
        
        elif c is None and color is None:
            c_values = self.plt.rcParams['patch.facecolor']
        
        elif color is not None:
            c_values = color
        
        elif c_is_column:
            c_values = self.data[c].values
        
        else:
            c_values = c

        if self.legend and hasattr(self, 'label'):
            label = self.label
        
        else:
            label = None
        
        scatter = ax.scatter(data[x].values, data[y].values, c=c_values,
                             label=label, cmap=cmap, **self.kwds)
        
        if cb:
            img = ax.collections[0]
            kws = dict(ax=ax)
            if self.mpl_ge_1_3_1():
                kws['label'] = c if c_is_column else ''
            self.fig.colorbar(img, **kws)

        if label is not None:
            self._add_legend_handle(scatter, label)
        
        else:
            self.legend = False

        errors_x = self._get_errorbars(label=x, index=0, yerr=False)
        errors_y = self._get_errorbars(label=y, index=0, xerr=False)
        
        if len(errors_x) > 0 or len(errors_y) > 0:
            err_kwds = dict(errors_x, **errors_y)
            err_kwds['ecolor'] = scatter.get_facecolor()[0]
            ax.errorbar(data[x].values, data[y].values,
                        linestyle='none', **err_kwds)

修正pandas.plotting._core

# Set VscatterPlot as an attribute of pandas.plotting._core
setattr(pandas.plotting._core, "VscatterPlot", VscatterPlot)

# Create the vscatter helper function
def vscatter(self, x, y, s=None, c=None, **kwds):
    return self(kind='vscatter', x=x, y=y, c=c, s=s, **kwds)

# Set the helper function
setattr(pandas.plotting._core.FramePlotMethods, "vscatter", vscatter)

# Append the class to pandas.plotting._core._klasses
pandas.plotting._core._klasses.append(pandas.plotting._core.VscatterPlot)

# Add the class to the pandas.plotting._core._plot_klass dict
pandas.plotting._core._plot_klass[VscatterPlot._kind] = pandas.plotting._core.VscatterPlot

测试

example = pandas.DataFrame(np.random.random((5,2)), columns=["x", "y"])
example.plot.vscatter(x="x", y="y")

输出

ValueError: 'vscatter' is not a valid plot kind

问题

我在这里遗漏了什么？vscatter在pandas.plotting._core._plot_klass，所以它为什么要抛出这个ValueError？

Answer 1

pandas.plotting._core中有两个列表，它们决定如何实例化类。您需要将"vscatter"放在这些列表中。

pandas.plotting._core._dataframe_kinds.append("vscatter")
pandas.plotting._core._all_kinds.append("vscatter")

此外，还有一些进口品不见了。以下代码

import matplotlib.pyplot as plt
import pandas
import numpy as np
from pandas.core.dtypes.common import is_integer, is_hashable


class VscatterPlot(pandas.plotting._core.PlanePlot):
    _kind = 'vscatter'

    def __init__(self, data, x, y, s=None, c=None, **kwargs):
        if s is None:
            # hide the matplotlib default for size, in case we want to change
            # the handling of this argument later
            s = 20

        super(VscatterPlot, self).__init__(data, x, y, s=s, **kwargs)

        if is_integer(c) and not self.data.columns.holds_integer():
            c = self.data.columns[c]

        self.c = c

    def _make_plot(self):
        x, y, c, data = self.x, self.y, self.c, self.data
        ax = self.axes[0]

        c_is_column = is_hashable(c) and c in self.data.columns

        # plot a colorbar only if a colormap is provided or necessary
        cb = self.kwds.pop('colorbar', self.colormap or c_is_column)

        # pandas uses colormap, matplotlib uses cmap.
        cmap = self.colormap or 'Greys'
        cmap = self.plt.cm.get_cmap(cmap)
        color = self.kwds.pop("color", None)

        if c is not None and color is not None:
            raise TypeError('Specify exactly one of `c` and `color`')

        elif c is None and color is None:
            c_values = self.plt.rcParams['patch.facecolor']

        elif color is not None:
            c_values = color

        elif c_is_column:
            c_values = self.data[c].values

        else:
            c_values = c

        if self.legend and hasattr(self, 'label'):
            label = self.label

        else:
            label = None

        scatter = ax.scatter(data[x].values, data[y].values, c=c_values,
                             label=label, cmap=cmap, **self.kwds)

        if cb:
            img = ax.collections[0]
            kws = dict(ax=ax)
            if self.mpl_ge_1_3_1():
                kws['label'] = c if c_is_column else ''
            self.fig.colorbar(img, **kws)

        if label is not None:
            self._add_legend_handle(scatter, label)

        else:
            self.legend = False

        errors_x = self._get_errorbars(label=x, index=0, yerr=False)
        errors_y = self._get_errorbars(label=y, index=0, xerr=False)

        if len(errors_x) > 0 or len(errors_y) > 0:
            err_kwds = dict(errors_x, **errors_y)
            err_kwds['ecolor'] = scatter.get_facecolor()[0]
            ax.errorbar(data[x].values, data[y].values,
                        linestyle='none', **err_kwds)

#Amending the pandas.plotting._core
# Set VscatterPlot as an attribute of pandas.plotting._core
setattr(pandas.plotting._core, "VscatterPlot", VscatterPlot)

# Create the vscatter helper function
def vscatter(self, x, y, s=None, c=None, **kwds):
    return self(kind='vscatter', x=x, y=y, c=c, s=s, **kwds)

# Set the helper function
setattr(pandas.plotting._core.FramePlotMethods, "vscatter", vscatter)

# Append the class to pandas.plotting._core._klasses
pandas.plotting._core._klasses.append(pandas.plotting._core.VscatterPlot)

# Add the class to the pandas.plotting._core._plot_klass dict
pandas.plotting._core._plot_klass[VscatterPlot._kind] = pandas.plotting._core.VscatterPlot

pandas.plotting._core._dataframe_kinds.append("vscatter")
pandas.plotting._core._all_kinds.append("vscatter")
#Testing
example = pandas.DataFrame(np.random.random((5,2)), columns=["x", "y"])
example.plot.vscatter(x="x", y="y")

plt.show()

产生这个输出

​

​