Skip to content

Adding style option to ecdf function #3888

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Aaron-c wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Adding style option to ecdf function #3888

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 49 additions & 3 deletions doc/_docstrings/ecdfplot.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,15 @@
"sns.ecdfplot(data=penguins, x=\"flipper_length_mm\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"penguins"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down Expand Up @@ -78,6 +87,43 @@
"sns.ecdfplot(data=penguins, x=\"bill_length_mm\", hue=\"species\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"or if you prefer separation by style that is also possible"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sns.ecdfplot(data=penguins, x=\"bill_length_mm\", style=\"species\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Or you can do both at the same time, however this can get confusing if too many variables are used"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sns.ecdfplot(data=penguins, x=\"bill_length_mm\", hue=\"species\", style='sex')"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down Expand Up @@ -120,9 +166,9 @@
],
"metadata": {
"kernelspec": {
"display_name": "py310",
"display_name": ".venv (3.13.7)",
"language": "python",
"name": "py310"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
Expand All @@ -134,7 +180,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.6"
"version": "3.13.7"
}
},
"nbformat": 4,
Expand Down
113 changes: 90 additions & 23 deletions seaborn/distributions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,8 @@
from matplotlib.cbook import normalize_kwargs
from matplotlib.colors import to_rgba
from matplotlib.collections import LineCollection
import matplotlib.patches as mpatches


from ._base import VectorPlotter

Expand Down Expand Up @@ -140,32 +142,65 @@ def _add_legend(
# TODO note that this doesn't handle numeric mappings like the relational plots
handles = []
labels = []
for level in self._hue_map.levels:
color = self._hue_map(level)

kws = self._artist_kws(
artist_kws, fill, element, multiple, color, alpha
)

# color gets added to the kws to workaround an issue with barplot's color
# cycle integration but it causes problems in this context where we are
# setting artist properties directly, so pop it off here
if "facecolor" in kws:
kws.pop("color", None)

handles.append(artist(**kws))
labels.append(level)
hasBothStyleAndHue = (self._hue_map.levels is not None) and (self._style_map.levels is not None)
legendTitle = None
if (not hasBothStyleAndHue):
legendTitle = self.variables.get("hue", None) or self.variables.get("style", None)
if (self._hue_map.levels is not None):
# when both style and hue exist we have this hack to add titles as 'invisible' handles
# otherwise we use titles
if (hasBothStyleAndHue):
fakeInvisibleTitleHandle= mpatches.Patch(color='none')
handles.append(fakeInvisibleTitleHandle)
labels.append(self.variables["hue"])

for level in self._hue_map.levels or []:
color = self._hue_map(level)
kws = self._artist_kws(
artist_kws, fill, element, multiple, color, alpha
)

# color gets added to the kws to workaround an issue with barplot's color
# cycle integration but it causes problems in this context where we are
# setting artist properties directly, so pop it off here
if "facecolor" in kws:
kws.pop("color", None)

handles.append(artist(**kws))
labels.append(level)
if (self._style_map.levels is not None):
if (hasBothStyleAndHue):
fakeInvisibleTitleHandle= mpatches.Patch(color='none')
handles.append(fakeInvisibleTitleHandle)
labels.append(self.variables["style"])
# deal with the case where style is None
for level in self._style_map.levels:
style = self._style_map(level)
# use black as te color for style legend
color = "black"
kws = self._artist_kws(
artist_kws, fill, element, multiple, color, alpha
)
kws.update(style)
# color gets added to the kws to workaround an issue with barplot's color
# cycle integration but it causes problems in this context where we are
# setting artist properties directly, so pop it off here
if "facecolor" in kws:
kws.pop("color", None)

handles.append(artist(**kws))
labels.append(level)
if isinstance(ax_obj, mpl.axes.Axes):
ax_obj.legend(handles, labels, title=self.variables["hue"], **legend_kws)
ax_obj.legend(handles, labels, title=legendTitle, **legend_kws)
else: # i.e. a FacetGrid. TODO make this better
legend_data = dict(zip(labels, handles))
ax_obj.add_legend(
legend_data,
title=self.variables["hue"],
title=legendTitle,
label_order=self.var_levels["hue"],
**legend_kws
)
)

def _artist_kws(self, kws, fill, element, multiple, color, alpha):
"""Handle differences between artists in filled/unfilled plots."""
Expand Down Expand Up @@ -1216,8 +1251,10 @@ def plot_univariate_ecdf(self, estimate_kws, legend, **plot_kws):
plot_kws["drawstyle"] = drawstyles[self.data_variable]

# Loop through the subsets, transform and plot the data
grouping_vars = "hue", "size", "style"

for sub_vars, sub_data in self.iter_data(
"hue", reverse=True, from_comp_data=True,
grouping_vars, reverse=True, from_comp_data=True,
):

# Compute the ECDF
Expand All @@ -1230,8 +1267,16 @@ def plot_univariate_ecdf(self, estimate_kws, legend, **plot_kws):

# Assign attributes based on semantic mapping
artist_kws = plot_kws.copy()


if "hue" in self.variables:
artist_kws["color"] = self._hue_map(sub_vars["hue"])
# Apply style mapping (dashes, marker) if requested
if "style" in self.variables:
attributes = self._style_map(sub_vars["style"])
for var in ('marker', 'dashes'):
if (var in attributes):
artist_kws[var] = attributes[var]

# Return the data variable to the linear domain
ax = self._get_axes(sub_vars)
Expand All @@ -1257,6 +1302,9 @@ def plot_univariate_ecdf(self, estimate_kws, legend, **plot_kws):

# Draw the line for this subset
artist, = ax.plot(*plot_args, **artist_kws)



sticky_edges = getattr(artist.sticky_edges, stat_variable)
sticky_edges[:] = 0, top_edge

Expand All @@ -1270,14 +1318,20 @@ def plot_univariate_ecdf(self, estimate_kws, legend, **plot_kws):
default_x = stat
self._add_axis_labels(ax, default_x, default_y)

if "hue" in self.variables and legend:
if self._need_legend() and legend:
artist = partial(mpl.lines.Line2D, [], [])
alpha = plot_kws.get("alpha", 1)
ax_obj = self.ax if self.ax is not None else self.facets
self._add_legend(
ax_obj, artist, False, False, None, alpha, plot_kws, {},
)

def _need_legend(self):
"""
true if this plot has been configured with a seetting that could generate a legend
"""
return "hue" in self.variables or "style" in self.variables

def plot_rug(self, height, expand_margins, legend, **kws):

for sub_vars, sub_data, in self.iter_data(from_comp_data=True):
Expand Down Expand Up @@ -1358,11 +1412,13 @@ def _plot_single_rug(self, sub_data, var, height, ax, kws):
def histplot(
data=None, *,
# Vector variables
x=None, y=None, hue=None, weights=None,
x=None, y=None, hue=None, weights=None, style=None,
# Histogram computation parameters
stat="count", bins="auto", binwidth=None, binrange=None,
discrete=None, cumulative=False, common_bins=True, common_norm=True,
# Histogram appearance parameters
# Style mapping parameters
markers=None, dashes=None, style_order=None,
multiple="layer", element="bars", fill=True, shrink=1,
# Histogram smoothing with a kernel density estimate
kde=False, kde_kws=None, line_kws=None,
Expand All @@ -1378,10 +1434,11 @@ def histplot(

p = _DistributionPlotter(
data=data,
variables=dict(x=x, y=y, hue=hue, weights=weights),
variables=dict(x=x, y=y, hue=hue, style=style, weights=weights),
)

p.map_hue(palette=palette, order=hue_order, norm=hue_norm)
p.map_style(markers=markers, dashes=dashes, order=style_order)

if ax is None:
ax = plt.gca()
Expand Down Expand Up @@ -1861,11 +1918,13 @@ def kdeplot(
def ecdfplot(
data=None, *,
# Vector variables
x=None, y=None, hue=None, weights=None,
x=None, y=None, hue=None, style=None, weights=None,
# Computation parameters
stat="proportion", complementary=False,
# Hue mapping parameters
palette=None, hue_order=None, hue_norm=None,
# Style mapping parameters
markers=False, dashes=True, style_order=None,
# Axes information
log_scale=None, legend=True, ax=None,
# Other appearance keywords
Expand All @@ -1874,10 +1933,11 @@ def ecdfplot(

p = _DistributionPlotter(
data=data,
variables=dict(x=x, y=y, hue=hue, weights=weights),
variables=dict(x=x, y=y, hue=hue, style=style, weights=weights),
)

p.map_hue(palette=palette, order=hue_order, norm=hue_norm)
p.map_style(markers=markers, dashes=dashes, order=style_order)

# We could support other semantics (size, style) here fairly easily
# But it would make distplot a bit more complicated.
Expand Down Expand Up @@ -2236,6 +2296,13 @@ def displot(
ecdf_kws["estimate_kws"] = estimate_kws
ecdf_kws["color"] = color

# Allow displot(..., kind="ecdf") to accept style parameters
p.map_style(
markers=ecdf_kws.pop("markers", None),
dashes=ecdf_kws.pop("dashes", None),
order=ecdf_kws.pop("style_order", None),
)

if p.univariate:

_assign_default_kwargs(ecdf_kws, p.plot_univariate_ecdf, ecdfplot)
Expand Down