def test_desaturate():
"""Test color desaturation."""
out1 = utils.desaturate("red", .5)
assert out1 == (.75, .25, .25)
out2 = utils.desaturate("#00FF00", .5)
assert out2 == (.25, .75, .25)
out3 = utils.desaturate((0, 0, 1), .5)
assert out3 == (.25, .25, .75)
out4 = utils.desaturate("red", .5)
assert out4 == (.75, .25, .25)
def _box_colors(vals, color):
"""Find colors to use for boxplots or violinplots."""
if color is None:
colors = husl_palette(len(vals), l=.7)
else:
try:
color = mpl.colors.colorConverter.to_rgb(color)
colors = [color for _ in vals]
except ValueError:
colors = color_palette(color, len(vals))
# Desaturate a bit because these are patches
colors = [mpl.colors.colorConverter.to_rgb(c) for c in colors]
colors = [desaturate(c, .7) for c in colors]
# Determine the gray color for the lines
light_vals = [colorsys.rgb_to_hls(*c)[1] for c in colors]
l = min(light_vals) * .6
gray = (l, l, l)
return colors, gray
def _box_colors(vals, color):
"""Find colors to use for boxplots or violinplots."""
if color is None:
colors = husl_palette(len(vals), l=.7)
else:
try:
color = mpl.colors.colorConverter.to_rgb(color)
colors = [color for _ in vals]
except ValueError:
colors = color_palette(color, len(vals))
# Desaturate a bit because these are patches
colors = [mpl.colors.colorConverter.to_rgb(c) for c in colors]
colors = [desaturate(c, .7) for c in colors]
# Determine the gray color for the lines
light_vals = [colorsys.rgb_to_hls(*c)[1] for c in colors]
l = min(light_vals) * .6
gray = (l, l, l)
return colors, gray
def test_desaturation_prop():
"""Test that pct outside of [0, 1] raises exception."""
with pytest.raises(ValueError):
utils.desaturate("blue", 50)
def violin(vals,
groupby=None,
inner="box",
color=None,
positions=None,
names=None,
widths=.8,
alpha=None,
join_rm=False,
kde_thresh=1e-2,
inner_kws=None,
ax=None,
**kwargs):
"""Create a violin plot (a combination of boxplot and KDE plot).
Parameters
----------
vals : array or sequence of arrays
data to plot
groupby : grouping object
if `vals` is a Series, this is used to group
inner : box | sticks | points
plot quartiles or individual sample values inside violin
color : mpl color, sequence of colors, or seaborn palette name
inner violin colors
positions : number or sequence of numbers
position of first violin or positions of each violin
widths : float
width of each violin at maximum density
alpha : float, optional
transparancy of violin fill
join_rm : boolean, optional
if True, positions in the input arrays are treated as repeated
measures and are joined with a line plot
names : list of strings, optional
names to plot on x axis, otherwise plots numbers
kde_thresh : float, optional
proportion of maximum at which to threshold the KDE curve
inner_kws : dict, optional
keyword arugments for inner plot
ax : matplotlib axis, optional
axis to plot on, otherwise creates new one
Returns
-------
ax : matplotlib axis
axis with violin plot
"""
if ax is None:
ax = plt.gca()
if isinstance(vals, pd.DataFrame):
if names is None:
names = vals.columns
if vals.columns.name is not None:
xlabel = vals.columns.name
else:
xlabel = None
ylabel = None
vals = vals.values
elif isinstance(vals, pd.Series) and groupby is not None:
if hasattr(groupby, "name"):
xlabel = groupby.name
if names is None:
names = np.sort(pd.unique(groupby))
ylabel = vals.name
grouped_vals = pd.groupby(vals, groupby).values
vals = grouped_vals.values
else:
xlabel = None
ylabel = None
if hasattr(vals, 'shape'):
if len(vals.shape) == 1:
if hasattr(vals[0], 'shape'):
vals = list(vals)
else:
vals = [vals]
elif len(vals.shape) == 2:
nr, nc = vals.shape
if nr == 1:
vals = [vals]
elif nc == 1:
vals = [vals.ravel()]
else:
vals = [vals[:, i] for i in xrange(nc)]
else:
raise ValueError("Input x can have no more than 2 dimensions")
if not hasattr(vals[0], '__len__'):
vals = [vals]
vals = [np.asarray(a, float) for a in vals]
if color is None:
colors = husl_palette(len(vals), l=.7)
else:
if hasattr(color, "__iter__") and not isinstance(color, tuple):
colors = color
else:
try:
color = mpl.colors.colorConverter.to_rgb(color)
colors = [color for _ in vals]
except ValueError:
colors = color_palette(color, len(vals))
colors = [mpl.colors.colorConverter.to_rgb(c) for c in colors]
colors = [desaturate(c, .7) for c in colors]
light_vals = [colorsys.rgb_to_hls(*c)[1] for c in colors]
l = min(light_vals) * .6
gray = (l, l, l)
if inner_kws is None:
inner_kws = {}
if positions is None:
positions = np.arange(1, len(vals) + 1)
elif not hasattr(positions, "__iter__"):
positions = np.arange(positions, len(vals) + positions)
in_alpha = inner_kws.pop("alpha", .6 if inner == "points" else 1)
in_alpha *= 1 if alpha is None else alpha
in_color = inner_kws.pop("color", gray)
in_marker = inner_kws.pop("marker", ".")
in_lw = inner_kws.pop("lw", 1.5 if inner == "box" else .8)
for i, a in enumerate(vals):
x = positions[i]
kde = stats.gaussian_kde(a)
y = _kde_support(a, kde, 1000, kde_thresh)
dens = kde(y)
scl = 1 / (dens.max() / (widths / 2))
dens *= scl
ax.fill_betweenx(y, x - dens, x + dens, alpha=alpha, color=colors[i])
if inner == "box":
for quant in moss.percentiles(a, [25, 75]):
q_x = kde(quant) * scl
q_x = [x - q_x, x + q_x]
ax.plot(q_x, [quant, quant],
color=in_color,
linestyle=":",
linewidth=in_lw,
**inner_kws)
med = np.median(a)
m_x = kde(med) * scl
m_x = [x - m_x, x + m_x]
ax.plot(m_x, [med, med],
color=in_color,
linestyle="--",
linewidth=in_lw,
**inner_kws)
elif inner == "stick":
x_vals = kde(a) * scl
x_vals = [x - x_vals, x + x_vals]
ax.plot(x_vals, [a, a],
color=in_color,
linewidth=in_lw,
alpha=in_alpha,
**inner_kws)
elif inner == "points":
x_vals = [x for _ in a]
ax.plot(x_vals,
a,
in_marker,
color=in_color,
alpha=in_alpha,
mew=0,
**inner_kws)
for side in [-1, 1]:
ax.plot((side * dens) + x, y, c=gray, linewidth=1.5)
if join_rm:
ax.plot(range(1, len(vals) + 1), vals, color=in_color, alpha=2. / 3)
ax.set_xticks(positions)
if names is not None:
if len(vals) != len(names):
raise ValueError("Length of names list must match nuber of bins")
ax.set_xticklabels(names)
ax.set_xlim(positions[0] - .5, positions[-1] + .5)
if xlabel is not None:
ax.set_xlabel(xlabel)
if ylabel is not None:
ax.set_ylabel(ylabel)
ax.xaxis.grid(False)
return ax
def boxplot(vals,
groupby=None,
names=None,
join_rm=False,
color=None,
alpha=None,
fliersize=3,
linewidth=1.5,
widths=.8,
ax=None,
**kwargs):
"""Wrapper for matplotlib boxplot that allows better color control.
Parameters
----------
vals : sequence of data containers
data for plot
groupby : grouping object
if `vals` is a Series, this is used to group
names : list of strings, optional
names to plot on x axis, otherwise plots numbers
join_rm : boolean, optional
if True, positions in the input arrays are treated as repeated
measures and are joined with a line plot
color : mpl color, sequence of colors, or seaborn palette name
inner box color
alpha : float
transparancy of the inner box color
fliersize : float, optional
markersize for the fliers
linewidth : float, optional
width for the box outlines and whiskers
ax : matplotlib axis, optional
will plot in axis, or create new figure axis
kwargs : additional keyword arguments to boxplot
Returns
-------
ax : matplotlib axis
axis where boxplot is plotted
"""
if ax is None:
ax = plt.gca()
if isinstance(vals, pd.DataFrame):
if names is None:
names = vals.columns
if vals.columns.name is not None:
xlabel = vals.columns.name
else:
xlabel = None
vals = vals.values
ylabel = None
elif isinstance(vals, pd.Series) and groupby is not None:
if names is None:
names = np.sort(pd.unique(groupby))
if hasattr(groupby, "name"):
xlabel = groupby.name
ylabel = vals.name
grouped_vals = pd.groupby(vals, groupby).values
vals = grouped_vals.values
else:
xlabel = None
ylabel = None
boxes = ax.boxplot(vals, patch_artist=True, widths=widths, **kwargs)
vals = np.atleast_2d(vals).T
if color is None:
colors = husl_palette(len(vals), l=.7)
else:
if hasattr(color, "__iter__") and not isinstance(color, tuple):
colors = color
else:
try:
color = mpl.colors.colorConverter.to_rgb(color)
colors = [color for _ in vals]
except ValueError:
colors = color_palette(color, len(vals))
colors = [mpl.colors.colorConverter.to_rgb(c) for c in colors]
colors = [desaturate(c, .7) for c in colors]
light_vals = [colorsys.rgb_to_hls(*c)[1] for c in colors]
l = min(light_vals) * .6
gray = (l, l, l)
for i, box in enumerate(boxes["boxes"]):
box.set_color(colors[i])
if alpha is not None:
box.set_alpha(alpha)
box.set_edgecolor(gray)
box.set_linewidth(linewidth)
for i, whisk in enumerate(boxes["whiskers"]):
whisk.set_color(gray)
whisk.set_linewidth(linewidth)
whisk.set_linestyle("-")
for i, cap in enumerate(boxes["caps"]):
cap.set_color(gray)
cap.set_linewidth(linewidth)
for i, med in enumerate(boxes["medians"]):
med.set_color(gray)
med.set_linewidth(linewidth)
for i, fly in enumerate(boxes["fliers"]):
fly.set_color(gray)
fly.set_marker("d")
fly.set_markeredgecolor(gray)
fly.set_markersize(fliersize)
if join_rm:
ax.plot(range(1, len(vals.T) + 1), vals.T, color=gray, alpha=2. / 3)
if names is not None:
ax.set_xticklabels(names)
if xlabel is not None:
ax.set_xlabel(xlabel)
if ylabel is not None:
ax.set_ylabel(ylabel)
ax.xaxis.grid(False)
return ax
def boxplot(vals, groupby=None, names=None, join_rm=False, color=None,
alpha=None, fliersize=3, linewidth=1.5, widths=.8, ax=None,
**kwargs):
"""Wrapper for matplotlib boxplot that allows better color control.
Parameters
----------
vals : sequence of data containers
data for plot
groupby : grouping object
if `vals` is a Series, this is used to group
names : list of strings, optional
names to plot on x axis, otherwise plots numbers
join_rm : boolean, optional
if True, positions in the input arrays are treated as repeated
measures and are joined with a line plot
color : mpl color, sequence of colors, or seaborn palette name
inner box color
alpha : float
transparancy of the inner box color
fliersize : float, optional
markersize for the fliers
linewidth : float, optional
width for the box outlines and whiskers
ax : matplotlib axis, optional
will plot in axis, or create new figure axis
kwargs : additional keyword arguments to boxplot
Returns
-------
ax : matplotlib axis
axis where boxplot is plotted
"""
if ax is None:
ax = plt.gca()
if isinstance(vals, pd.DataFrame):
if names is None:
names = vals.columns
if vals.columns.name is not None:
xlabel = vals.columns.name
else:
xlabel = None
vals = vals.values
ylabel = None
elif isinstance(vals, pd.Series) and groupby is not None:
if names is None:
names = pd.unique(groupby)
if hasattr(groupby, "name"):
xlabel = groupby.name
ylabel = vals.name
grouped_vals = pd.groupby(vals, groupby).values
if names is None:
names = grouped_vals.index
vals = grouped_vals.values
else:
xlabel = None
ylabel = None
boxes = ax.boxplot(vals, patch_artist=True, widths=widths, **kwargs)
vals = np.atleast_2d(vals).T
if color is None:
colors = husl_palette(len(vals), l=.7)
else:
if hasattr(color, "__iter__") and not isinstance(color, tuple):
colors = color
else:
try:
color = mpl.colors.colorConverter.to_rgb(color)
colors = [color for _ in vals]
except ValueError:
colors = color_palette(color, len(vals))
colors = [mpl.colors.colorConverter.to_rgb(c) for c in colors]
colors = [desaturate(c, .7) for c in colors]
light_vals = [colorsys.rgb_to_hls(*c)[1] for c in colors]
l = min(light_vals) * .6
gray = (l, l, l)
for i, box in enumerate(boxes["boxes"]):
box.set_color(colors[i])
if alpha is not None:
box.set_alpha(alpha)
box.set_edgecolor(gray)
box.set_linewidth(linewidth)
for i, whisk in enumerate(boxes["whiskers"]):
whisk.set_color(gray)
whisk.set_linewidth(linewidth)
whisk.set_linestyle("-")
for i, cap in enumerate(boxes["caps"]):
cap.set_color(gray)
cap.set_linewidth(linewidth)
for i, med in enumerate(boxes["medians"]):
med.set_color(gray)
med.set_linewidth(linewidth)
for i, fly in enumerate(boxes["fliers"]):
fly.set_color(gray)
fly.set_marker("d")
fly.set_markeredgecolor(gray)
fly.set_markersize(fliersize)
if join_rm:
ax.plot(range(1, len(vals.T) + 1), vals.T,
color=gray, alpha=2. / 3)
if names is not None:
ax.set_xticklabels(names)
if xlabel is not None:
ax.set_xlabel(xlabel)
if ylabel is not None:
ax.set_ylabel(ylabel)
ax.xaxis.grid(False)
return ax
def violin(vals, groupby=None, inner="box", color=None, positions=None,
names=None, widths=.8, alpha=None, join_rm=False, kde_thresh=1e-2,
inner_kws=None, ax=None, **kwargs):
"""Create a violin plot (a combination of boxplot and KDE plot).
Parameters
----------
vals : array or sequence of arrays
data to plot
groupby : grouping object
if `vals` is a Series, this is used to group
inner : box | sticks | points
plot quartiles or individual sample values inside violin
color : mpl color, sequence of colors, or seaborn palette name
inner violin colors
positions : number or sequence of numbers
position of first violin or positions of each violin
widths : float
width of each violin at maximum density
alpha : float, optional
transparancy of violin fill
join_rm : boolean, optional
if True, positions in the input arrays are treated as repeated
measures and are joined with a line plot
names : list of strings, optional
names to plot on x axis, otherwise plots numbers
kde_thresh : float, optional
proportion of maximum at which to threshold the KDE curve
inner_kws : dict, optional
keyword arugments for inner plot
ax : matplotlib axis, optional
axis to plot on, otherwise creates new one
Returns
-------
ax : matplotlib axis
axis with violin plot
"""
if ax is None:
ax = plt.gca()
if isinstance(vals, pd.DataFrame):
if names is None:
names = vals.columns
if vals.columns.name is not None:
xlabel = vals.columns.name
else:
xlabel = None
ylabel = None
vals = vals.values
elif isinstance(vals, pd.Series) and groupby is not None:
if hasattr(groupby, "name"):
xlabel = groupby.name
ylabel = vals.name
grouped_vals = pd.groupby(vals, groupby).values
if names is None:
names = grouped_vals.index
vals = grouped_vals.values
else:
xlabel = None
ylabel = None
if hasattr(vals, 'shape'):
if len(vals.shape) == 1:
if hasattr(vals[0], 'shape'):
vals = list(vals)
else:
vals = [vals]
elif len(vals.shape) == 2:
nr, nc = vals.shape
if nr == 1:
vals = [vals]
elif nc == 1:
vals = [vals.ravel()]
else:
vals = [vals[:, i] for i in xrange(nc)]
else:
raise ValueError("Input x can have no more than 2 dimensions")
if not hasattr(vals[0], '__len__'):
vals = [vals]
vals = [np.asarray(a, float) for a in vals]
if color is None:
colors = husl_palette(len(vals), l=.7)
else:
if hasattr(color, "__iter__") and not isinstance(color, tuple):
colors = color
else:
try:
color = mpl.colors.colorConverter.to_rgb(color)
colors = [color for _ in vals]
except ValueError:
colors = color_palette(color, len(vals))
colors = [mpl.colors.colorConverter.to_rgb(c) for c in colors]
colors = [desaturate(c, .7) for c in colors]
light_vals = [colorsys.rgb_to_hls(*c)[1] for c in colors]
l = min(light_vals) * .6
gray = (l, l, l)
if inner_kws is None:
inner_kws = {}
if positions is None:
positions = np.arange(1, len(vals) + 1)
elif not hasattr(positions, "__iter__"):
positions = np.arange(positions, len(vals) + positions)
in_alpha = inner_kws.pop("alpha", .6 if inner == "points" else 1)
in_alpha *= 1 if alpha is None else alpha
in_color = inner_kws.pop("color", gray)
in_marker = inner_kws.pop("marker", ".")
in_lw = inner_kws.pop("lw", 1.5 if inner == "box" else .8)
for i, a in enumerate(vals):
x = positions[i]
kde = stats.gaussian_kde(a)
y = _kde_support(a, kde, 1000, kde_thresh)
dens = kde(y)
scl = 1 / (dens.max() / (widths / 2))
dens *= scl
ax.fill_betweenx(y, x - dens, x + dens, alpha=alpha, color=colors[i])
if inner == "box":
for quant in moss.percentiles(a, [25, 75]):
q_x = kde(quant) * scl
q_x = [x - q_x, x + q_x]
ax.plot(q_x, [quant, quant], color=in_color,
linestyle=":", linewidth=in_lw, **inner_kws)
med = np.median(a)
m_x = kde(med) * scl
m_x = [x - m_x, x + m_x]
ax.plot(m_x, [med, med], color=in_color,
linestyle="--", linewidth=in_lw, **inner_kws)
elif inner == "stick":
x_vals = kde(a) * scl
x_vals = [x - x_vals, x + x_vals]
ax.plot(x_vals, [a, a], color=in_color,
linewidth=in_lw, alpha=in_alpha, **inner_kws)
elif inner == "points":
x_vals = [x for _ in a]
ax.plot(x_vals, a, in_marker, color=in_color,
alpha=in_alpha, mew=0, **inner_kws)
for side in [-1, 1]:
ax.plot((side * dens) + x, y, c=gray, linewidth=1.5)
if join_rm:
ax.plot(range(1, len(vals) + 1), vals,
color=in_color, alpha=2. / 3)
ax.set_xticks(positions)
if names is not None:
if len(vals) != len(names):
raise ValueError("Length of names list must match nuber of bins")
ax.set_xticklabels(names)
ax.set_xlim(positions[0] - .5, positions[-1] + .5)
if xlabel is not None:
ax.set_xlabel(xlabel)
if ylabel is not None:
ax.set_ylabel(ylabel)
ax.xaxis.grid(False)
return ax
