From 6fd5c886da277b572f470bd80e7755421ff16209 Mon Sep 17 00:00:00 2001
From: Fontrodona Nicolas <nicolas.fontrodona@ens-lyon.fr>
Date: Mon, 15 Mar 2021 18:17:05 +0100
Subject: [PATCH] src/gc_content/stat_annot.py: major pep8 modifications
---
src/gc_content/stat_annot.py | 220 ++++++++++++++++++-----------------
1 file changed, 114 insertions(+), 106 deletions(-)
diff --git a/src/gc_content/stat_annot.py b/src/gc_content/stat_annot.py
index 6223c48..4c45b2d 100644
--- a/src/gc_content/stat_annot.py
+++ b/src/gc_content/stat_annot.py
@@ -1,6 +1,6 @@
#!/usr/bin/env python3
-# -*- coding;: utf-8 -*-
+# -*- coding: UTF-8 -*-
"""
Description:
@@ -9,6 +9,7 @@ Description:
github.com/webermarcolivier/statannot/blob/master/statannot/statannot.py.
"""
+
import matplotlib.pyplot as plt
from matplotlib import lines
import matplotlib.transforms as mtransforms
@@ -19,196 +20,203 @@ from seaborn.utils import remove_na
def add_stat_annotation(ax, data=None, x=None, y=None, hue=None, order=None,
- hue_order=None, boxPairList=None, loc='inside',
- useFixedOffset=False, lineYOffsetToBoxAxesCoord=None,
- lineYOffsetAxesCoord=None, lineHeightAxesCoord=0.02,
- textYOffsetPoints=1, color='0.2', linewidth=1.5,
- fontsize='medium', verbose=1):
+ hue_order=None, box_pair_list=None, loc='inside',
+ use_fixed_offset=False,
+ liney_offset2box_axes_coord=None,
+ liney_offset_axes_coord=None,
+ line_height_axes_coord=0.02,
+ text_y_offset_points=1, color='0.2', linewidth=1.5,
+ fontsize='medium', verbose=1, min_pval = 1e-16):
"""
User should use the same argument for the data, x, y, hue, order, \
hue_order as the seaborn boxplot function.
- boxPairList can be of either form:
+ box_pair_list can be of either form:
boxplot: [(cat1, cat2, pval), (cat3, cat4, pval)]
"""
- def find_x_position_box(boxPlotter, boxName):
+ def find_x_position_box(box_plotter, box_name):
"""
- boxName can be either a name "cat" or a tuple ("cat", "hue")
+ box_name can be either a name "cat" or a tuple ("cat", "hue")
"""
- if boxPlotter.plot_hues is None:
- cat = boxName
- hueOffset = 0
+ if box_plotter.plot_hues is None:
+ cat = box_name
+ hue_offset = 0
else:
- cat = boxName[0]
- hue = boxName[1]
- hueOffset = boxPlotter.hue_offsets[
- boxPlotter.hue_names.index(hue)]
+ cat = box_name[0]
+ chue = box_name[1]
+ hue_offset = box_plotter.hue_offsets[
+ box_plotter.hue_names.index(chue)]
- groupPos = boxPlotter.group_names.index(cat)
- boxPos = groupPos + hueOffset
- return boxPos
+ group_pos = box_plotter.group_names.index(cat)
+ box_pos = group_pos + hue_offset
+ return box_pos
- def get_box_data(boxPlotter, boxName):
+ def get_box_data(cbox_plotter, box_name):
"""
- boxName can be either a name "cat" or a tuple ("cat", "hue")
+ box_name can be either a name "cat" or a tuple ("cat", "hue")
Here we really have to duplicate seaborn code, because there is not
direct access to the
box_data in the BoxPlotter class.
"""
- cat = boxName
- if boxPlotter.plot_hues is None:
+ cat = box_name
+ if cbox_plotter.plot_hues is None:
box_max_l = []
- for cat in boxPlotter.group_names:
- i = boxPlotter.group_names.index(cat)
- group_data = boxPlotter.plot_data[i]
+ for cat in cbox_plotter.group_names:
+ i = cbox_plotter.group_names.index(cat)
+ group_data = cbox_plotter.plot_data[i]
box_data = remove_na(group_data)
- box_max_l.append(np.max(box_data))
+ box_max_l.append(np.mean(box_data))
return max(box_max_l)
else:
- i = boxPlotter.group_names.index(cat[0])
- group_data = boxPlotter.plot_data[i]
+ i = cbox_plotter.group_names.index(cat[0])
+ group_data = cbox_plotter.plot_data[i]
box_data = []
- for hue in boxPlotter.hue_names:
- hue_mask = boxPlotter.plot_hues[i] == hue
+ for chue in cbox_plotter.hue_names:
+ hue_mask = cbox_plotter.plot_hues[i] == chue
box_data.append(np.max(remove_na(group_data[hue_mask])))
return max(box_data)
fig = plt.gcf()
- validList = ['inside', 'outside']
- if loc not in validList:
+ valid_list = ['inside', 'outside']
+ if loc not in valid_list:
raise ValueError(f"loc value should be one of the following: "
- f"{', '.join(validList)}.")
+ f"{', '.join(valid_list)}.")
# Create the same BoxPlotter object as seaborn's boxplot
- boxPlotter = sns.categorical._BoxPlotter(x, y, hue, data, order, hue_order,
- orient=None, width=.8, color=None,
- palette=None, saturation=.75,
- dodge=True, fliersize=5,
- linewidth=None)
+ box_plotter = sns.categorical._BoxPlotter(x, y, hue, data, order,
+ hue_order, orient=None, width=.8,
+ color=None, palette=None,
+ saturation=.75, dodge=True,
+ fliersize=5, linewidth=None)
ylim = ax.get_ylim()
- yRange = ylim[1] - ylim[0]
+ y_range = ylim[1] - ylim[0]
- if lineYOffsetAxesCoord is None:
+ if liney_offset_axes_coord is None:
if loc == 'inside':
- lineYOffsetAxesCoord = 0.005
- if lineYOffsetToBoxAxesCoord is None:
- lineYOffsetToBoxAxesCoord = 0.1
+ liney_offset_axes_coord = 0.005
+ if liney_offset2box_axes_coord is None:
+ liney_offset2box_axes_coord = 0.1
elif loc == 'outside':
- lineYOffsetAxesCoord = 0.03
- lineYOffsetToBoxAxesCoord = lineYOffsetAxesCoord
+ liney_offset_axes_coord = 0.03
+ liney_offset2box_axes_coord = liney_offset_axes_coord
else:
if loc == 'inside':
- if lineYOffsetToBoxAxesCoord is None:
- lineYOffsetToBoxAxesCoord = 0.06
+ if liney_offset2box_axes_coord is None:
+ liney_offset2box_axes_coord = 0.06
elif loc == 'outside':
- lineYOffsetToBoxAxesCoord = lineYOffsetAxesCoord
- yOffset = lineYOffsetAxesCoord * yRange
- yOffsetToBox = lineYOffsetToBoxAxesCoord * yRange
+ liney_offset2box_axes_coord = liney_offset_axes_coord
+ y_offset = liney_offset_axes_coord * y_range
+ y_offset_to_box = liney_offset2box_axes_coord * y_range
- yStack = []
- annList = []
- for box1, box2, pval in boxPairList:
+ y_stack = []
+ ann_list = []
+ max_val = []
+ for box1, box2, pval in box_pair_list:
- groupNames = boxPlotter.group_names
+ group_names = box_plotter.group_names
cat1 = box1
cat2 = box2
if isinstance(cat1, tuple):
- hue_names = boxPlotter.hue_names
- valid = cat1[0] in groupNames and cat2[0] in groupNames and \
- cat1[1] in hue_names and cat2[1] in hue_names
+ hue_names = box_plotter.hue_names
+ valid = cat1[0] in group_names and cat2[0] in group_names and \
+ cat1[1] in hue_names and cat2[1] in hue_names
else:
- valid = cat1 in groupNames and cat2 in groupNames
+ valid = cat1 in group_names and cat2 in group_names
if valid:
# Get position of boxes
- x1 = find_x_position_box(boxPlotter, box1)
- x2 = find_x_position_box(boxPlotter, box2)
- box_data1 = get_box_data(boxPlotter, box1)
- box_data2 = get_box_data(boxPlotter, box2)
+ x1 = find_x_position_box(box_plotter, box1)
+ x2 = find_x_position_box(box_plotter, box2)
+ box_data1 = get_box_data(box_plotter, box1)
+ box_data2 = get_box_data(box_plotter, box2)
ymax1 = box_data1
ymax2 = box_data2
if pval > 1e-16:
text = "p = {:.2e}".format(pval)
else:
- text = "p < 1e-16"
+ text = f"p < {min_pval:.0e}"
if loc == 'inside':
- yRef = max(ymax1, ymax2)
+ y_ref = max(ymax1, ymax2)
else:
- yRef = ylim[1]
- if len(yStack) > 0 and isinstance(box1, str):
- yRef2 = max(yRef, max(yStack))
+ y_ref = ylim[1]
+
+ if len(y_stack) > 0:
+ y_ref2 = max(y_ref, max(y_stack))
else:
- yRef2 = yRef
+ y_ref2 = y_ref
- if len(yStack) == 0 or not isinstance(box1, str):
- y = yRef2 + yOffsetToBox
+ if len(y_stack) == 0:
+ y = y_ref2 + y_offset_to_box
else:
- y = yRef2 + yOffset
- h = lineHeightAxesCoord * yRange
- lineX, lineY = [x1, x1, x2, x2], [y, y + h, y + h, y]
+ y = y_ref2 + y_offset
+ h = line_height_axes_coord * y_range
+ line_x, line_y = [x1, x1, x2, x2], [y, y + h, y + h, y]
if loc == 'inside':
- ax.plot(lineX, lineY, lw=linewidth, c=color)
+ ax.plot(line_x, line_y, lw=linewidth, c=color)
elif loc == 'outside':
- line = lines.Line2D(lineX, lineY, lw=linewidth, c=color,
+ line = lines.Line2D(line_x, line_y, lw=linewidth, c=color,
transform=ax.transData)
line.set_clip_on(False)
ax.add_line(line)
if text is not None:
ann = ax.annotate(text, xy=(np.mean([x1, x2]), y + h),
- xytext=(0, textYOffsetPoints),
+ xytext=(0, text_y_offset_points),
textcoords='offset points',
xycoords='data', ha='center', va='bottom',
- fontsize=fontsize,
- clip_on=False, annotation_clip=False)
- annList.append(ann)
+ fontsize=fontsize, clip_on=False,
+ annotation_clip=False)
+ ann_list.append(ann)
- new_max_ylim = 1.1 * (y + h)
+ new_max_ylim = 1.1*(y + h)
if new_max_ylim > ylim[1]:
- ax.set_ylim((ylim[0], 1.1 * (y + h)))
+ ax.set_ylim((ylim[0], 1.1*(y + h)))
if text is not None:
plt.draw()
- yTopAnnot = None
- gotMatplotlibError = False
- if not useFixedOffset:
+ y_top_annot = None
+ got_matplotlib_error = False
+ if not use_fixed_offset:
try:
bbox = ann.get_window_extent()
bbox_data = bbox.transformed(ax.transData.inverted())
- yTopAnnot = bbox_data.ymax
+ y_top_annot = bbox_data.ymax
except RuntimeError:
- gotMatplotlibError = True
+ got_matplotlib_error = True
- if useFixedOffset or gotMatplotlibError:
+ if use_fixed_offset or got_matplotlib_error:
if verbose >= 1:
print("Warning: cannot get the text bounding box. "
"Falling back to a fixed y offset. Layout may "
"be not optimal.")
- # We will apply a fixed offset in points, based on the font size of the annotation.
- fontsizePoints = FontProperties(
- size='medium').get_size_in_points()
- offsetTrans = mtransforms.offset_copy(ax.transData,
- fig=fig,
- x=0,
- y=1.0 * fontsizePoints + textYOffsetPoints,
- units='points')
- yTopDisplay = offsetTrans.transform((0, y + h))
- yTopAnnot = ax.transData.inverted().transform(yTopDisplay)[
- 1]
+ # We will apply a fixed offset in points,
+ # based on the font size of the annotation.
+ fontsize_points = FontProperties(size='medium'
+ ).get_size_in_points()
+ offset_trans = mtransforms.offset_copy(
+ ax.transData, fig=fig, x=0,
+ y=1.0 * fontsize_points + text_y_offset_points,
+ units='points')
+ y_top_display = offset_trans.transform((0, y + h))
+ y_top_annot = ax.transData.inverted().\
+ transform(y_top_display)[1]
else:
- yTopAnnot = y + h
+ y_top_annot = y + h
- yStack.append(yTopAnnot)
+ y_stack.append(y_top_annot)
+ max_val.append(max(y_stack))
+ if hue is not None and len(y_stack) == len(box_plotter.hue_names):
+ y_stack = []
else:
- raise ValueError("boxPairList contains an unvalid box pair.")
+ raise ValueError("box_pair_list contains an unvalid box pair.")
- yStackMax = max(yStack)
+ y_stack_max = max(max_val + y_stack)
if loc == 'inside':
- if ylim[1] < 1.03 * yStackMax:
- ax.set_ylim((ylim[0], 1.03 * yStackMax))
+ if ylim[1] < 1.03 * y_stack_max:
+ ax.set_ylim((ylim[0], 1.03 * y_stack_max))
elif loc == 'outside':
ax.set_ylim((ylim[0], ylim[1]))
- return ax
+ return ax
\ No newline at end of file
--
GitLab