def stacked_area_chart(
data: dict,
ax: mpl.axes,
domains_in_focus: Optional[list] = None,
percentage: bool = False,
colormap: Optional[mpl.colors.LinearSegmentedColormap] = None,
color_default: Optional[np.array] = None,
):
"""
Parameters
----------
data : Dictionary with a format {'x_axis_labels': {'y_axis_labels': y_values}}
domains_in_focus :
percentage :
"""
x = list(data.keys())
y = data_transformation(data, percentage)
ylabels = get_ylabels(data)
colors = utils.create_color_palette(
ylabels,
domains_in_focus,
colormap,
include_dof=True,
return_dict=False,
)
ax.stackplot(
x,
y,
colors=colors,
)
ax.set_xlim(np.min(x), np.max(x))
ax.set_ylim(np.min(y), np.max(y))
return ax
def makePowerSpectrum(
self, freqs: np.array, power: np.array, sm_power: np.array,
band_max_power: float, freq_at_band_max_power: float,
max_freq: int = 50, theta_range: tuple = [6, 12],
ax: matplotlib.axes = None, **kwargs) -> matplotlib.axes:
# downsample frequencies and power
freqs = freqs[0::50]
power = power[0::50]
sm_power = sm_power[0::50]
if ax is None:
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(freqs, power, alpha=0.5, color=[0.8627, 0.8627, 0.8627])
ax.plot(freqs, sm_power)
ax.set_xlim(0, max_freq)
ylim = [0, band_max_power / 0.8]
if 'ylim' in kwargs:
ylim = kwargs['ylim']
ax.set_ylim(ylim)
ax.set_ylabel('Power')
ax.set_xlabel('Frequency')
ax.text(
x=theta_range[1] / 0.9, y=band_max_power,
s=str(freq_at_band_max_power)[0:4], fontsize=20)
from matplotlib.patches import Rectangle
r = Rectangle((
theta_range[0], 0), width=np.diff(theta_range)[0],
height=np.diff(ax.get_ylim())[0], alpha=0.25, color='r', ec='none')
ax.add_patch(r)
return ax
def evolution_of_participation_1D(
data: dict,
ax: mpl.axes,
entity_in_focus: Optional[list] = None,
percentage: bool = False,
colormap: mpl.colors.LinearSegmentedColormap = mpl.cm.jet,
) -> mpl.axes:
"""
Parameters
----------
data : Dictionary with a format {'x_axis_labels': {'y_axis_labels': y_values}}
entity_in_focus :
percentage :
"""
x = list(data.keys())
ylabels = stackedareachart.get_ylabels(data)
y = stackedareachart.data_transformation(data, ylabels, percentage)
colors = utils.create_color_palette(
ylabels,
entity_in_focus,
colormap,
include_dof=False,
return_dict=True,
)
for iy, ylab in enumerate(ylabels):
if ylab in entity_in_focus:
ax.plot(
x,
y[iy, :],
color="w",
linewidth=4,
zorder=1,
)
ax.plot(
x,
y[iy, :],
color=colors[ylab],
linewidth=3,
zorder=1,
label=ylab,
)
else:
ax.plot(
x,
y[iy, :],
color="grey",
linewidth=1,
zorder=0,
alpha=0.2,
)
if np.isfinite(np.max(x)):
ax.set_xlim(np.min(x), np.max(x))
if np.isfinite(np.max(y)):
ax.set_ylim(np.min(y), np.max(y))
return ax
def plotTTPMat(ax: axes,
toa: np.array,
ttp: np.array,
title: str = None,
plot_ylabel: bool = False) -> None:
ax.scatter(toa, ttp, marker='o', c=ttp, alpha=0.75)
ax.set_ylim(PRI_DETECTED_RANGE[0], PRI_DETECTED_RANGE[1])
ax.xaxis.get_major_formatter().set_powerlimits((0, 1))
ax.set_title(title, fontsize=10)
ax.set_xlabel('toa[us]', fontsize=8, loc='right')
if plot_ylabel:
ax.set_ylabel('pri[us]', fontsize=9)
def plot_chromatograph(
seq: SeqRecord, region: Tuple[int, int] = None, ax: mpl.axes = None
) -> plt.axes:
"""Plot Sanger chromatograph.
region: include both start and end (1-based)
"""
if seq is None:
return ax
if region is None:
# turn into 0 based for better indexing
region_start, region_end = 0, len(seq)
else:
region_start = max(region[0], 0)
region_end = min(region[1], len(seq) - 1)
if ax is None:
_, ax = plt.subplots(1, 1, figsize=(16, 6))
_colors = defaultdict(
lambda: "purple", {"A": "g", "C": "b", "G": "k", "T": "r"}
)
# Get signals
peaks = seq.annotations["peak positions"]
trace_x = seq.annotations["trace_x"]
traces_y = [seq.annotations["channel " + str(i)] for i in range(1, 5)]
bases = seq.annotations["channels"]
xlim_left, xlim_right = peaks[region_start] - 1, peaks[region_end] + 0.5
# subset peak and sequence
# TODO: this might fix the bug
peak_start = peaks[0]
peak_zip = [
(p, s)
for i, (p, s) in enumerate(zip(peaks, seq))
if region_start <= i <= region_end
]
peaks, seq = list(zip(*peak_zip))
# subset trace_x and traces_y together
trace_zip = [
(x + peak_start, *ys)
for x, *ys in zip(trace_x, *traces_y)
if xlim_left <= x <= xlim_right
]
if not trace_zip:
return ax
trace_x, *traces_y = list(zip(*trace_zip))
# Plot traces
trmax = max(map(max, traces_y))
for base in bases:
trace_y = [1.0 * ci / trmax for ci in traces_y[bases.index(base)]]
ax.plot(trace_x, trace_y, color=_colors[base], lw=2, label=base)
ax.fill_between(
trace_x, 0, trace_y, facecolor=_colors[base], alpha=0.125
)
# Plot bases at peak positions
for i, peak in enumerate(peaks):
# LOGGER.debug(f"{i}, {peak}, {seq[i]}, {xlim_left + i}")
ax.text(
peak,
-0.11,
seq[i],
color=_colors[seq[i]],
va="center",
ha="center",
alpha=0.66,
fontsize="x-large",
fontweight="bold",
)
ax.set_ylim(bottom=-0.15, top=1.05)
# peaks[0] - max(2, 0.02 * (peaks[-1] - peaks[0])),
# right=peaks[-1] + max(2, 0.02 * (peaks[-1] - peaks[0])),
ax.set_xlim(xlim_left + 0.5, xlim_right)
ax.set_xticks(peaks)
ax.set_xticklabels(list(range(region_start + 1, region_end + 2)))
# hide y axis
ax.set_yticklabels([])
ax.get_yaxis().set_visible(False)
# hide border
ax.spines["left"].set_visible(False)
ax.spines["right"].set_visible(False)
ax.spines["top"].set_visible(False)
# hide grid
ax.grid(False)
# set legend
ax.legend(loc="upper left", bbox_to_anchor=(0.95, 0.99))
return ax
def evolution_of_participation_2D(
xdata: dict,
ydata: dict,
ax: mpl.axes,
entity_in_focus: Optional[list] = None,
percentage: bool = False,
colormap: mpl.colors.LinearSegmentedColormap = mpl.cm.jet,
) -> mpl.axes:
"""
Parameters
----------
data : Dictionary with a format {'x_axis_labels': {'y_axis_labels': y_values}}
entity_in_focus :
percentage :
"""
# TODO: include time indication
xlabels = stackedareachart.get_ylabels(xdata)
ylabels = stackedareachart.get_ylabels(ydata)
# ensure uniform order
labels = list(set(xlabels + ylabels))
xindx = [xlabels.index(lab) if lab in xlabels else None for lab in labels]
xlabels = [xlabels[i] if i is not None else None for i in xindx]
yindx = [ylabels.index(lab) if lab in ylabels else None for lab in labels]
ylabels = [ylabels[i] if i is not None else None for i in yindx]
# create arrays with format (# of ylabels, # of xlabels)
x = stackedareachart.data_transformation(xdata, xlabels, percentage)
y = stackedareachart.data_transformation(ydata, ylabels, percentage)
colors = utils.create_color_palette(
ylabels,
entity_in_focus,
colormap,
include_dof=False,
return_dict=True,
)
ax.plot([0, np.max(y)], [0, np.max(y)], c="k", linestyle="--", zorder=0)
for i, lab in enumerate(labels):
if lab in entity_in_focus:
ax.plot(
x[i, :],
y[i, :],
color="w",
linewidth=4,
zorder=1,
)
ax.plot(
x[i, :],
y[i, :],
color=colors[lab],
linewidth=3,
zorder=1,
label=lab,
)
else:
ax.plot(
x[i, :],
y[i, :],
color="grey",
linewidth=1,
zorder=0,
alpha=0.2,
)
ax.set_xlim(np.min(x), np.max(x))
ax.set_ylim(np.min(y), np.max(y))
return ax
def cohort_bar(cohort_averages: dict,
cohort_data: dict,
observable: str,
yaxis_upper: int = None,
ax: matplotlib.axes = None,
labelsize: int = 12,
ticksize: int = 10,
legendsize: int = 8,
markersize=15) -> None:
"""Plots either the V- or J-gene usages.
Parameters
----------
cohort_averages : dict
Dictionary of averages and variations within a cohort for all severities.
cohort_dict : dict
Dictionary of all statistics of all individuals in a cohort for all severities.
observable : str
The quantity which is going to be plotted.
yaxis_upper : int, optional
Specifies the upper limit of the y-axis on the plot.
ax : matplotlib.axes, optional
Used to modify an already existing axes when creating a figure with a grid.
labelsize : int, optional
Size of axes labels.
ticksize : int, optional
Size of tick labels.
legendsize : int, optional
Specifies font size of strings in legend.
Returns
-------
None
"""
if ax is None:
fig = plt.figure(dpi=300, figsize=(16, 4))
ax = fig.add_subplot(111)
# Give the bars for each gene some space among each other.
width = 1.0 / len(cohort_averages) - 0.02
bars = []
if 'Asymptomatic' in cohort_averages:
ordering = ['Healthy', 'Mild', 'Moderate', 'Severe', 'Asymptomatic']
else:
ordering = sorted(cohort_averages.keys())
# Sort the genes by descending usage in the healthy cohort.
if 'Briney/GRP' in cohort_averages:
sorted_genes = [
gene for _, gene in sorted(zip(
cohort_averages['Briney/GRP'][observable][0],
cohort_averages['Briney/GRP'][observable][-1]),
key=lambda pair: pair[0],
reverse=True)
]
else:
sorted_genes = [
gene for _, gene in sorted(zip(
cohort_averages['Healthy'][observable][0],
cohort_averages['Healthy'][observable][-1]),
key=lambda pair: pair[0],
reverse=True)
]
# Because there are so many V genes, plot only those which have at least
# 1% average usage in at least one cohort.
if 'v' in observable:
good_genes = []
for gene in sorted_genes:
bools = 0
for severity in cohort_averages:
idx = cohort_averages[severity][observable][-1].index(gene)
value = cohort_averages[severity][observable][0][idx]
bools += value >= 0.01
if bools != 0:
good_genes.append(gene)
else:
good_genes = sorted_genes
xlabels = good_genes
default_x = np.arange(0, len(good_genes), 1)
xs, ys = [], []
for i, severity in enumerate(ordering):
x = default_x + width * i
xs.append(x)
indices = [
cohort_averages[severity][observable][-1].index(gene)
for gene in good_genes
]
y = [cohort_averages[severity][observable][0][k] for k in indices]
ys.append(y)
if observable == 'v gene':
ax.set_xlim(-0.3, xs[0][-1] + 1.0)
if yaxis_upper is not None:
ax.set_ylim(0, yaxis_upper)
else:
ax.set_ylim(0, 0.35)
else:
ax.set_xlim(-0.3, xs[0][-1] + 1.0)
if yaxis_upper is not None:
ax.set_ylim(0, yaxis_upper)
else:
ax.set_ylim(0, 0.55)
# Specifiy location of xticks as being in the middle of the grouping of bars.
middle = np.mean(np.arange(0, len(cohort_averages)))
middle_xticks = default_x + middle * width
ax.set_xticks(middle_xticks)
ax.set_xticklabels(xlabels, rotation=90, family='Arial')
ax.set_ylabel('relative counts', fontname="Arial")
# Plot the bars.
for i, severity in enumerate(ordering):
bar = ax.bar(xs[i],
ys[i],
width,
color=colors[severity],
label=severity)
for d in cohort_data[severity][observable]:
# Plot the full distributions of values to get a better sense
# of variation within cohorts.
for gidx, rect in enumerate(bar):
ax.scatter(xs[i][gidx],
d[good_genes[gidx]],
marker='.',
color=lightercolors[severity],
zorder=3,
s=markersize,
edgecolors='black',
linewidths=0.3)
format_axes(ax,
labelsize=labelsize,
ticksize=ticksize,
legendsize=legendsize)