def _plot(cls,
ax,
y,
style=None,
bw_method=None,
ind=None,
column_num=None,
stacking_id=None,
**kwds):
# 'y' is a Spark DataFrame that selects one column.
# Using RDD is slow so we might have to change it to Dataset based implementation
# once Spark has that implementation.
sample = y.rdd.map(lambda x: float(x[0]))
kd = KernelDensity()
kd.setSample(sample)
assert isinstance(
bw_method,
(int, float)), "'bw_method' must be set as a scalar number."
if bw_method is not None:
# Match the bandwidth with Spark.
kd.setBandwidth(float(bw_method))
y = kd.estimate(list(map(float, ind)))
lines = PandasMPLPlot._plot(ax, ind, y, style=style, **kwds)
return lines
def plot_series(
data,
kind='line',
ax=None, # Series unique
figsize=None,
use_index=True,
title=None,
grid=None,
legend=False,
style=None,
logx=False,
logy=False,
loglog=False,
xticks=None,
yticks=None,
xlim=None,
ylim=None,
rot=None,
fontsize=None,
colormap=None,
table=False,
yerr=None,
xerr=None,
label=None,
secondary_y=False, # Series unique
**kwds):
# function copied from pandas.plotting._core
# so it calls modified _plot below
import matplotlib.pyplot as plt
if ax is None and len(plt.get_fignums()) > 0:
ax = _gca()
ax = MPLPlot._get_ax_layer(ax)
return _plot(data,
kind=kind,
ax=ax,
figsize=figsize,
use_index=use_index,
title=title,
grid=grid,
legend=legend,
style=style,
logx=logx,
logy=logy,
loglog=loglog,
xticks=xticks,
yticks=yticks,
xlim=xlim,
ylim=ylim,
rot=rot,
fontsize=fontsize,
colormap=colormap,
table=table,
yerr=yerr,
xerr=xerr,
label=label,
secondary_y=secondary_y,
**kwds)
def _plot(cls,
ax,
y,
style=None,
bw_method=None,
ind=None,
column_num=None,
stacking_id=None,
**kwds):
y = KdePlotBase.compute_kde(y, bw_method=bw_method, ind=ind)
lines = PandasMPLPlot._plot(ax, ind, y, style=style, **kwds)
return lines
def plot_series(
data,
kind="line",
ax=None, # Series unique
figsize=None,
use_index=True,
title=None,
grid=None,
legend=False,
style=None,
logx=False,
logy=False,
loglog=False,
xticks=None,
yticks=None,
xlim=None,
ylim=None,
rot=None,
fontsize=None,
colormap=None,
table=False,
yerr=None,
xerr=None,
label=None,
secondary_y=False, # Series unique
**kwds):
"""
Make plots of Series using matplotlib / pylab.
Each plot kind has a corresponding method on the
``Series.plot`` accessor:
``s.plot(kind='line')`` is equivalent to
``s.plot.line()``.
Parameters
----------
data : Series
kind : str
- 'line' : line plot (default)
- 'bar' : vertical bar plot
- 'barh' : horizontal bar plot
- 'hist' : histogram
- 'box' : boxplot
- 'kde' : Kernel Density Estimation plot
- 'density' : same as 'kde'
- 'area' : area plot
- 'pie' : pie plot
ax : matplotlib axes object
If not passed, uses gca()
figsize : a tuple (width, height) in inches
use_index : boolean, default True
Use index as ticks for x axis
title : string or list
Title to use for the plot. If a string is passed, print the string at
the top of the figure. If a list is passed and `subplots` is True,
print each item in the list above the corresponding subplot.
grid : boolean, default None (matlab style default)
Axis grid lines
legend : False/True/'reverse'
Place legend on axis subplots
style : list or dict
matplotlib line style per column
logx : boolean, default False
Use log scaling on x axis
logy : boolean, default False
Use log scaling on y axis
loglog : boolean, default False
Use log scaling on both x and y axes
xticks : sequence
Values to use for the xticks
yticks : sequence
Values to use for the yticks
xlim : 2-tuple/list
ylim : 2-tuple/list
rot : int, default None
Rotation for ticks (xticks for vertical, yticks for horizontal plots)
fontsize : int, default None
Font size for xticks and yticks
colormap : str or matplotlib colormap object, default None
Colormap to select colors from. If string, load colormap with that name
from matplotlib.
colorbar : boolean, optional
If True, plot colorbar (only relevant for 'scatter' and 'hexbin' plots)
position : float
Specify relative alignments for bar plot layout.
From 0 (left/bottom-end) to 1 (right/top-end). Default is 0.5 (center)
table : boolean, Series or DataFrame, default False
If True, draw a table using the data in the DataFrame and the data will
be transposed to meet matplotlib's default layout.
If a Series or DataFrame is passed, use passed data to draw a table.
yerr : DataFrame, Series, array-like, dict and str
See :ref:`Plotting with Error Bars <visualization.errorbars>` for
detail.
xerr : same types as yerr.
label : label argument to provide to plot
secondary_y : boolean or sequence of ints, default False
If True then y-axis will be on the right
mark_right : boolean, default True
When using a secondary_y axis, automatically mark the column
labels with "(right)" in the legend
**kwds : keywords
Options to pass to matplotlib plotting method
Returns
-------
axes : :class:`matplotlib.axes.Axes` or numpy.ndarray of them
Notes
-----
- See matplotlib documentation online for more on this subject
- If `kind` = 'bar' or 'barh', you can specify relative alignments
for bar plot layout by `position` keyword.
From 0 (left/bottom-end) to 1 (right/top-end). Default is 0.5 (center)
"""
# function copied from pandas.plotting._core
# so it calls modified _plot below
import matplotlib.pyplot as plt
if ax is None and len(plt.get_fignums()) > 0:
with plt.rc_context():
ax = plt.gca()
ax = PandasMPLPlot._get_ax_layer(ax)
return _plot(
data,
kind=kind,
ax=ax,
figsize=figsize,
use_index=use_index,
title=title,
grid=grid,
legend=legend,
style=style,
logx=logx,
logy=logy,
loglog=loglog,
xticks=xticks,
yticks=yticks,
xlim=xlim,
ylim=ylim,
rot=rot,
fontsize=fontsize,
colormap=colormap,
table=table,
yerr=yerr,
xerr=xerr,
label=label,
secondary_y=secondary_y,
**kwds,
)