matplotlib's legend() method has an ncol parameter to lay out the content in multiple columns.
I want to do the same thing in a text annotation.
I can pass multi-line text string (i.e., one that contains \ns) to annotate(), but how can I array the content in two columns?
use tab characters? They don't seem to do anything
use two separate text annotations? But I want a round border (bbox) around the two columns
use something like ncol? It can wrap columns according to the number of columns I've asked for
I couln't find an nice way to do this so I wrote a function that gets the jobs done. Try it out and see if it does what you need.
def place_column_text(ax, text, xy, wrap_n, shift, bbox=False, **kwargs):
""" Creates a text annotation with the text in columns.
The text columns are provided by a list of strings.
A surrounding box can be added via bbox=True parameter.
If so, FancyBboxPatch kwargs can be specified.
The width of the column can be specified by wrap_n,
the shift parameter determines how far apart the columns are.
The axes are specified by the ax parameter.
Requires:
import textwrap
import matplotlib.patches as mpatches
"""
# place the individual text boxes, with a bbox to extract details from later
x,y = xy
n = 0
text_boxes = []
for i in text:
text = textwrap.fill(i, wrap_n)
box = ax.text(x = x + n, y = y, s=text, va='top', ha='left',
bbox=dict(alpha=0, boxstyle='square,pad=0'))
text_boxes.append(box)
n += shift
if bbox == True: # draw surrounding box
# extract box data
plt.draw() # so we can extract real bbox data
# first let's calulate the height of the largest bbox
heights=[]
for box in text_boxes:
heights.append(box.get_bbox_patch().get_extents().transformed(ax.transData.inverted()).bounds[3])
max_height=max(heights)
# then calculate the furthest x value of the last bbox
end_x = text_boxes[-1].get_window_extent().transformed(ax.transData.inverted()).xmax
# draw final
width = end_x - x
fancypatch_y = y - max_height
rect = mpatches.FancyBboxPatch(xy=(x,fancypatch_y), width=width, height=max_height, **kwargs)
ax.add_patch(rect)
Here is it in use:
import matplotlib.patches as mpatches
import textwrap
fig, ax = plt.subplots(2,2,sharex=True, sharey=True,figsize=(16,12))
fig.subplots_adjust(hspace=0.05, wspace=0.05)
ax1, ax2, ax3, ax4 = ax.flatten()
for a in ax.flatten():
a.plot(range(0,20),range(0,20), alpha=0)
# the text to be split into columns and annotated
col_text = ['Colum 1 text is this sentence here.',
'The text for column two is going to be longer',
'Column 3 is the third column.',
'And last but not least we have column 4. In fact this text is the longest.']
# use the function to place the text
place_column_text(ax=ax1,text=col_text, xy=(1,10), wrap_n=10, shift=4.2)
place_column_text(ax=ax2,text=col_text, xy=(0,19), wrap_n=17, bbox=True, shift=5, ec='red', fc='w', boxstyle='square')
place_column_text(ax=ax3,text=col_text, xy=(2,18), wrap_n=6, bbox=True, shift=2.7, ec='blue', fc = 'blue' , alpha=0.3, boxstyle='round,pad=1')
place_column_text(ax=ax4,text=col_text, xy=(3,12), wrap_n=10, bbox=True, shift=3, ec='red', fc='w', boxstyle='circle, pad=3')
plt.show()
Result:
Related
My dataset is in the form of :
Data[0] = [headValue,x0,x1,..xN]
Data[1] = [headValue_ya,ya0,ya1,..yaN]
Data[2] = [headValue_yb,yb0,yb1,..ybN]
...
Data[n] = [headvalue_yz,yz0,yz1,..yzN]
I want to plot f(y*) = x, so I can visualize all Lineplots in the same figure with different colors, each color determined by the headervalue_y*.
I also want to add a colorbar whose color matching the lines and therefore the header values, so we can link visually which header value leads to which behaviour.
Here is what I am aiming for :(Plot from Lacroix B, Letort G, Pitayu L, et al. Microtubule Dynamics Scale with Cell Size to Set Spindle Length and Assembly Timing. Dev Cell. 2018;45(4):496–511.e6. doi:10.1016/j.devcel.2018.04.022)
I have trouble adding the colorbar, I have tried to extract N colors from a colormap (N is my number of different headValues, or column -1) and then adding for each line plot the color corresponding here is my code to clarify:
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
Data = [['Time',0,0.33,..200],[0.269,4,4.005,...11],[0.362,4,3.999,...16.21],...[0.347,4,3.84,...15.8]]
headValues = [0.269,0.362,0.335,0.323,0.161,0.338,0.341,0.428,0.245,0.305,0.305,0.314,0.299,0.395,0.32,0.437,0.203,0.41,0.392,0.347]
# the differents headValues_y* of each column here in a list but also in Data
# with headValue[0] = Data[1][0], headValue[1] = Data[2][0] ...
cmap = mpl.cm.get_cmap('rainbow') # I choose my colormap
rgba = [] # the color container
for value in headValues:
rgba.append(cmap(value)) # so rgba will contain a different color for each headValue
fig, (ax,ax1) = plt.subplots(2,1) # creating my figure and two axes to put the Lines and the colorbar
c = 0 # index for my colors
for i in range(1, len(Data)):
ax.plot( Data[0][1:], Data[i][1:] , color = rgba[c])
# Data[0][1:] is x, Data[i][1:] is y, and the color associated with Data[i][0]
c += 1
fig.colorbar(mpl.cm.ScalarMappable(cmap= mpl.colors.ListedColormap(rgba)), cax=ax1, orientation='horizontal')
# here I create my scalarMappable for my lineplot and with the previously selected colors 'rgba'
plt.show()
The current result:
How to add the colorbar on the side or the bottom of the first axis ?
How to properly add a scale to this colorbar correspondig to different headValues ?
How to make the colorbar scale and colors match to the different lines on the plot with the link One color = One headValue ?
I have tried to work with scatterplot which are more convenient to use with scalarMappable but no solution allows me to do all these things at once.
Here is a possible approach. As the 'headValues' aren't sorted, nor equally spaced and one is even used twice, it is not fully clear what the most-desired result would be.
Some remarks:
The standard way of creating a colorbar in matplotlib doesn't need a separate subplot. Matplotlib will reduce the existing plot a bit and put the colorbar next to it (or below for a vertical bar).
Converting the 'headValues' to a numpy array allows for compact code, e.g. writing rgba = cmap(headValues) directly calculates the complete array.
Calling cmap on unchanged values will map 0 to the lowest color and 1 to the highest color, so for values only between 0.16 and 0.44 they all will be mapped to quite similar colors. One approach is to create a norm to map 0.16 to the lowest color and 0.44 to the highest. In code: norm = plt.Normalize(headValues.min(), headValues.max()) and then calculate rgba = cmap(norm(headValues)).
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
headValues = np.array([0.269, 0.362, 0.335, 0.323, 0.161, 0.338, 0.341, 0.428, 0.245, 0.305, 0.305, 0.314, 0.299, 0.395, 0.32, 0.437, 0.203, 0.41, 0.392, 0.347])
x = np.linspace(0, 200, 500)
# create Data similar to the data in the question
Data = [['Time'] + list(x)] + [[val] + list(np.sqrt(4 * x) * val + 4) for val in headValues]
headValues = np.array([d[0] for d in Data[1:]])
order = np.argsort(headValues)
inverse_order = np.argsort(order)
cmap = mpl.cm.get_cmap('rainbow')
rgba = cmap(np.linspace(0, 1, len(headValues))) # evenly spaced colors
fig, ax = plt.subplots(1, 1)
for i in range(1, len(Data)):
ax.plot(Data[0][1:], Data[i][1:], color=rgba[inverse_order[i-1]])
# Data[0][1:] is x, Data[i][1:] is y, and the color associated with Data[i-1][0]
cbar = fig.colorbar(mpl.cm.ScalarMappable(cmap=mpl.colors.ListedColormap(rgba)), orientation='vertical',
ticks=np.linspace(0, 1, len(rgba) * 2 + 1)[1::2])
cbar.set_ticklabels(headValues[order])
plt.show()
Alternatively, the colors can be assigned using their position in the colormap, but without creating
cmap = mpl.cm.get_cmap('rainbow')
norm = plt.Normalize(headValues.min(), headValues.max())
fig, ax = plt.subplots(1, 1)
for i in range(1, len(Data)):
ax.plot(Data[0][1:], Data[i][1:], color=cmap(norm(Data[i][0])))
cbar = fig.colorbar(mpl.cm.ScalarMappable(cmap=cmap, norm=norm))
To get ticks for each of the 'headValues', these ticks can be set explicitly. As putting a label for each tick will result in overlapping text, labels that are too close to other labels can be replaced by an empty string:
headValues.sort()
cbar2 = fig.colorbar(mpl.cm.ScalarMappable(cmap=cmap, norm=norm), ticks=headValues)
cbar2.set_ticklabels([val if val < next - 0.007 else '' for val, next in zip(headValues[:-1], headValues[1:])]
+ [headValues[-1]])
At the left the result of the first approach (colors in segments), at the right the alternative colorbars (color depending on value):
Currently, I'm working on an introductory paper on data manipulation and such; however... the CSV I'm working on has some things I wish to do a scatter graph on!
I want a scatter graph to show me the volume sold on certain items as well as their average price, differentiating all data according to their region (Through colours I assume).
So what I want is to know if I can add the region column as a quantitative value
or if there's a way to make this possible...
It's my first time using Python and I'm confused way too often
I'm not sure if this is what you mean, but here is some working code, assuming you have data in the format of [(country, volume, price), ...]. If not, you can change the inputs to the scatter method as needed.
import random
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
n_countries = 50
# get the data into "countries", for example
countries = ...
# in this example: countries is [('BS', 21, 25), ('WZ', 98, 25), ...]
df = pd.DataFrame(countries)
# arbitrary method to get a color
def get_color(i, max_i):
cmap = matplotlib.cm.get_cmap('Spectral')
return cmap(i/max_i)
# get the figure and axis - make a larger figure to fit more points
# add labels for metric names
def get_fig_ax():
fig = plt.figure(figsize=(14,14))
ax = fig.add_subplot(1, 1, 1)
ax.set_xlabel('volume')
ax.set_ylabel('price')
return fig, ax
# switch around the assignments depending on your data
def get_x_y_labels():
x = df[1]
y = df[2]
labels = df[0]
return x, y, labels
offset = 1 # offset just so annotations aren't on top of points
x, y, labels = get_x_y_labels()
fig, ax = get_fig_ax()
# add a point and annotation for each of the labels/regions
for i, region in enumerate(labels):
ax.annotate(region, (x[i] + offset, y[i] + offset))
# note that you must use "label" for "legend" to work
ax.scatter(x[i], y[i], color=get_color(i, len(x)), label=region)
# Add the legend just outside of the plot.
# The .1, 0 at the end will put it outside
ax.legend(loc='upper right', bbox_to_anchor=(1, 1, .1, 0))
plt.show()
I'm creating a table in matplotlib, but the table headers are long strings, and the table values are numbers with only a few digits. This leaves me with two bad options: either my table is much wider than necessary, or my headers overlap. To fix this, I'd like to rotate the table headings (possibly up to 90 degrees). In other words, I want to do this in python
Here's my simplified code right now:
import matplotlib, numpy
import matplotlib.pyplot as plt
data=numpy.array([[1, 2],[3,4]])
headings=['long heading 1', 'long heading 2']
fig=plt.figure(figsize=(5,2))
ax=fig.add_subplot(111, frameon=False, xticks=[], yticks=[])
the_table = plt.table(cellText=data, rowLabels=headings, colLabels=headings, colWidths=[0.3]*data.shape[1], loc='center') #0.3 for second image, 0.03 for first
#the_table.auto_set_font_size(False) #comment out for second image
#the_table.set_fontsize(10) #comment out for second image
the_table.scale(1, 1.6)
plt.show()
This produces either the squished image, or the super-wide image (both shown below). In my actual code, the table is ~30 x 30, so the cells can't be very wide. Does anybody know how to rotate the column titles to fix this spacing issue?
I figured it out. It's not pretty, but it works. I added two annotations for each column - the text, and a line to separate it from the next column header. I had to define some parameters that apply to the table and the fancy labels (width, height, col_width), and some parameters to make the fancy labels line up correctly. This solution worked fine on my 30x30 table.
import matplotlib, numpy
import matplotlib.pyplot as plt
width=5
height=3
col_width=.075
data=numpy.array([[1, 2,5],[3,4,7],[7,9,5]])
headings=['long heading 1', 'long heading 2', 'longish 3']
fig=plt.figure(figsize=(width,height))
ax=fig.add_subplot(111, frameon=False, xticks=[], yticks=[])
the_table = plt.table(cellText=data, rowLabels=headings,
colWidths=[col_width]*data.shape[1], loc='center') #remove colLabels
the_table.auto_set_font_size(False)
the_table.set_fontsize(10)
the_table.scale(1, 1.6)
#custom heading titles - new portion
hoffset=0.42 #find this number from trial and error
voffset=0.66 #find this number from trial and error
line_fac=0.98 #controls the length of the dividing line
count=0
for string in headings:
ax.annotate(' '+string, xy=(hoffset+count*col_width,voffset),
xycoords='axes fraction', ha='left', va='bottom',
rotation=45, size=10)
#add a dividing line
ax.annotate('', xy=(hoffset+(count+0.5)*col_width,voffset),
xytext=(hoffset+(count+0.5)*col_width+line_fac/width,voffset+line_fac/height),
xycoords='axes fraction', arrowprops={'arrowstyle':'-'})
count+=1
plt.show()
I just found an other solution:
for cell in table._cells:
if cell[0] ==0:
table._cells[cell].get_text().set_rotation(90)
The first loop is for going through all cells, the second is for picking the first row/header.
if cell[1] =- -1
this would selecte the the first column, which you might want to rotate, too.
Then you can rotate the cell text by e.g. 90 °.
The following worked for me.
create the table
fig = plt.figure( figsize=(pageWidthInInches, pageHeightInInches) )
panel = plotUtils.createPanelSameSizeAsFig(fig)
tablePanel = panel.table(
cellText=cellText
# ,rowLabels=rowLabels
# ,colLabels=colLabels
#,loc='center' # center table in panel, title is in center
#,loc='bottom' # center table in panel does not work well
,loc='best'
#,rowColours=aedwip,
#,colColourslist=aedwip
,cellColours= cellColors
)
# get rid of bar chart axis and box
panel.get_xaxis().set_visible(False)
panel.get_yaxis().set_visible(False)
tablePanel.scale(1, 1.5)
plt.box(on=None)
panel.set_title(title)
Now add the col header. Note my table did not have row labels, you may have to tweak the startX position
tcell = table._cells[(0, 0)]
cellWidth = tcell.get_width()
startX = tcell.get_x() - cellWidth
y = 0.99 #0.98 #0.975 #0.96 #1
headings = sampleDF.columns
for i in range(len(headings)):
heading = headings[i]
x = startX + i * cellWidth
panel.text(x, y, heading, horizontalalignment="left",
verticalalignment="baseline", rotation=45, fontsize=4)
The alignment of a text box can be specified with the horizontalalignment (ha) and verticalalignment (va) arguments, e.g.
import matplotlib.pyplot as plt
fig, ax = plt.subplots(figsize=(8,5))
plt.subplots_adjust(right=0.5)
txt = "Test:\nthis is some text\ninside a bounding box."
fig.text(0.7, 0.5, txt, ha='left', va='center')
Which produces:
Is there anyway to keep the same bounding-box (bbox) alignment, while changing the alignment of the text within that bounding-box? e.g. for the text to be centered in the bounding-box.
(Obviously in this situation I could just replace the bounding-box, but in more complicated cases I'd like to change the text alignment independently.)
The exact bbox depends on the renderer of your specific backend. The following example preserves the x position of the text bbox. It is a bit trickier to exactly preserve both x and y:
import matplotlib
import matplotlib.pyplot as plt
def get_bbox(txt):
renderer = matplotlib.backend_bases.RendererBase()
return txt.get_window_extent(renderer)
fig, ax = plt.subplots(figsize=(8,5))
plt.subplots_adjust(right=0.5)
txt = "Test:\nthis is some text\ninside a bounding box."
text_inst = fig.text(0.7, 0.5, txt, ha='left', va='center')
bbox = get_bbox(text_inst)
bbox_fig = bbox.transformed(fig.transFigure.inverted())
print "original bbox (figure system)\t:", bbox.transformed(fig.transFigure.inverted())
# adjust horizontal alignment
text_inst.set_ha('right')
bbox_new = get_bbox(text_inst)
bbox_new_fig = bbox_new.transformed(fig.transFigure.inverted())
print "aligned bbox\t\t\t:", bbox_new_fig
# shift back manually
offset = bbox_fig.x0 - bbox_new_fig.x0
text_inst.set_x(bbox_fig.x0 + offset)
bbox_shifted = get_bbox(text_inst)
print "shifted bbox\t\t\t:", bbox_shifted.transformed(fig.transFigure.inverted())
plt.show()
I am trying to replicate the following image in matplotlib and it seems barh is my only option. Though it appears that you can't stack barh graphs so I don't know what to do
If you know of a better python library to draw this kind of thing, please let me know.
This is all I could come up with as a start:
import matplotlib.pyplot as plt; plt.rcdefaults()
import numpy as np
import matplotlib.pyplot as plt
people = ('A','B','C','D','E','F','G','H')
y_pos = np.arange(len(people))
bottomdata = 3 + 10 * np.random.rand(len(people))
topdata = 3 + 10 * np.random.rand(len(people))
fig = plt.figure(figsize=(10,8))
ax = fig.add_subplot(111)
ax.barh(y_pos, bottomdata,color='r',align='center')
ax.barh(y_pos, topdata,color='g',align='center')
ax.set_yticks(y_pos)
ax.set_yticklabels(people)
ax.set_xlabel('Distance')
plt.show()
I would then have to add labels individually using ax.text which would be tedious. Ideally I would like to just specify the width of the part to be inserted then it updates the center of that section with a string of my choosing. The labels on the outside (e.g. 3800) I can add myself later, it is mainly the labeling over the bar section itself and creating this stacked method in a nice way I'm having problems with. Can you even specify a 'distance' i.e. span of color in any way?
Edit 2: for more heterogeneous data. (I've left the above method since I find it more usual to work with the same number of records per series)
Answering the two parts of the question:
a) barh returns a container of handles to all the patches that it drew. You can use the coordinates of the patches to aid the text positions.
b) Following these two answers to the question that I noted before (see Horizontal stacked bar chart in Matplotlib), you can stack bar graphs horizontally by setting the 'left' input.
and additionally c) handling data that is less uniform in shape.
Below is one way you could handle data that is less uniform in shape is simply to process each segment independently.
import numpy as np
import matplotlib.pyplot as plt
# some labels for each row
people = ('A','B','C','D','E','F','G','H')
r = len(people)
# how many data points overall (average of 3 per person)
n = r * 3
# which person does each segment belong to?
rows = np.random.randint(0, r, (n,))
# how wide is the segment?
widths = np.random.randint(3,12, n,)
# what label to put on the segment (xrange in py2.7, range for py3)
labels = range(n)
colors ='rgbwmc'
patch_handles = []
fig = plt.figure(figsize=(10,8))
ax = fig.add_subplot(111)
left = np.zeros(r,)
row_counts = np.zeros(r,)
for (r, w, l) in zip(rows, widths, labels):
print r, w, l
patch_handles.append(ax.barh(r, w, align='center', left=left[r],
color=colors[int(row_counts[r]) % len(colors)]))
left[r] += w
row_counts[r] += 1
# we know there is only one patch but could enumerate if expanded
patch = patch_handles[-1][0]
bl = patch.get_xy()
x = 0.5*patch.get_width() + bl[0]
y = 0.5*patch.get_height() + bl[1]
ax.text(x, y, "%d%%" % (l), ha='center',va='center')
y_pos = np.arange(8)
ax.set_yticks(y_pos)
ax.set_yticklabels(people)
ax.set_xlabel('Distance')
plt.show()
Which produces a graph like this , with a different number of segments present in each series.
Note that this is not particularly efficient since each segment used an individual call to ax.barh. There may be more efficient methods (e.g. by padding a matrix with zero-width segments or nan values) but this likely to be problem-specific and is a distinct question.
Edit: updated to answer both parts of the question.
import numpy as np
import matplotlib.pyplot as plt
people = ('A','B','C','D','E','F','G','H')
segments = 4
# generate some multi-dimensional data & arbitrary labels
data = 3 + 10* np.random.rand(segments, len(people))
percentages = (np.random.randint(5,20, (len(people), segments)))
y_pos = np.arange(len(people))
fig = plt.figure(figsize=(10,8))
ax = fig.add_subplot(111)
colors ='rgbwmc'
patch_handles = []
left = np.zeros(len(people)) # left alignment of data starts at zero
for i, d in enumerate(data):
patch_handles.append(ax.barh(y_pos, d,
color=colors[i%len(colors)], align='center',
left=left))
# accumulate the left-hand offsets
left += d
# go through all of the bar segments and annotate
for j in range(len(patch_handles)):
for i, patch in enumerate(patch_handles[j].get_children()):
bl = patch.get_xy()
x = 0.5*patch.get_width() + bl[0]
y = 0.5*patch.get_height() + bl[1]
ax.text(x,y, "%d%%" % (percentages[i,j]), ha='center')
ax.set_yticks(y_pos)
ax.set_yticklabels(people)
ax.set_xlabel('Distance')
plt.show()
You can achieve a result along these lines (note: the percentages I used have nothing to do with the bar widths, as the relationship in the example seems unclear):
See Horizontal stacked bar chart in Matplotlib for some ideas on stacking horizontal bar plots.
Imports and Test DataFrame
Tested in python 3.10, pandas 1.4.2, matplotlib 3.5.1, seaborn 0.11.2
For vertical stacked bars see Stacked Bar Chart with Centered Labels
import pandas as pd
import numpy as np
# create sample data as shown in the OP
np.random.seed(365)
people = ('A','B','C','D','E','F','G','H')
bottomdata = 3 + 10 * np.random.rand(len(people))
topdata = 3 + 10 * np.random.rand(len(people))
# create the dataframe
df = pd.DataFrame({'Female': bottomdata, 'Male': topdata}, index=people)
# display(df)
Female Male
A 12.41 7.42
B 9.42 4.10
C 9.85 7.38
D 8.89 10.53
E 8.44 5.92
F 6.68 11.86
G 10.67 12.97
H 6.05 7.87
Updated with matplotlib v3.4.2
Use matplotlib.pyplot.bar_label
See How to add value labels on a bar chart for additional details and examples with .bar_label.
labels = [f'{v.get_width():.2f}%' if v.get_width() > 0 else '' for v in c ] for python < 3.8, without the assignment expression (:=).
Plotted using pandas.DataFrame.plot with kind='barh'
ax = df.plot(kind='barh', stacked=True, figsize=(8, 6))
for c in ax.containers:
# customize the label to account for cases when there might not be a bar section
labels = [f'{w:.2f}%' if (w := v.get_width()) > 0 else '' for v in c ]
# set the bar label
ax.bar_label(c, labels=labels, label_type='center')
# uncomment and use the next line if there are no nan or 0 length sections; just use fmt to add a % (the previous two lines of code are not needed, in this case)
# ax.bar_label(c, fmt='%.2f%%', label_type='center')
# move the legend
ax.legend(bbox_to_anchor=(1.025, 1), loc='upper left', borderaxespad=0.)
# add labels
ax.set_ylabel("People", fontsize=18)
ax.set_xlabel("Percent", fontsize=18)
plt.show()
Using seaborn
sns.barplot does not have an option for stacked bar plots, however, sns.histplot and sns.displot can be used to create horizontal stacked bars.
seaborn typically requires the dataframe to be in a long, instead of wide, format, so use pandas.DataFrame.melt to reshape the dataframe.
Reshape dataframe
# convert the dataframe to a long form
df = df.reset_index()
df = df.rename(columns={'index': 'People'})
dfm = df.melt(id_vars='People', var_name='Gender', value_name='Percent')
# display(dfm)
People Gender Percent
0 A Female 12.414557
1 B Female 9.416027
2 C Female 9.846105
3 D Female 8.885621
4 E Female 8.438872
5 F Female 6.680709
6 G Female 10.666258
7 H Female 6.050124
8 A Male 7.420860
9 B Male 4.104433
10 C Male 7.383738
11 D Male 10.526158
12 E Male 5.916262
13 F Male 11.857227
14 G Male 12.966913
15 H Male 7.865684
sns.histplot: axes-level plot
fig, axe = plt.subplots(figsize=(8, 6))
sns.histplot(data=dfm, y='People', hue='Gender', discrete=True, weights='Percent', multiple='stack', ax=axe)
# iterate through each set of containers
for c in axe.containers:
# add bar annotations
axe.bar_label(c, fmt='%.2f%%', label_type='center')
axe.set_xlabel('Percent')
plt.show()
sns.displot: figure-level plot
g = sns.displot(data=dfm, y='People', hue='Gender', discrete=True, weights='Percent', multiple='stack', height=6)
# iterate through each facet / supbplot
for axe in g.axes.flat:
# iteate through each set of containers
for c in axe.containers:
# add the bar annotations
axe.bar_label(c, fmt='%.2f%%', label_type='center')
axe.set_xlabel('Percent')
plt.show()
Original Answer - before matplotlib v3.4.2
The easiest way to plot a horizontal or vertical stacked bar, is to load the data into a pandas.DataFrame
This will plot, and annotate correctly, even when all categories ('People'), don't have all segments (e.g. some value is 0 or NaN)
Once the data is in the dataframe:
It's easier to manipulate and analyze
It can be plotted with the matplotlib engine, using:
pandas.DataFrame.plot.barh
label_text = f'{width}' for annotations
pandas.DataFrame.plot.bar
label_text = f'{height}' for annotations
SO: Vertical Stacked Bar Chart with Centered Labels
These methods return a matplotlib.axes.Axes or a numpy.ndarray of them.
Using the .patches method unpacks a list of matplotlib.patches.Rectangle objects, one for each of the sections of the stacked bar.
Each .Rectangle has methods for extracting the various values that define the rectangle.
Each .Rectangle is in order from left the right, and bottom to top, so all the .Rectangle objects, for each level, appear in order, when iterating through .patches.
The labels are made using an f-string, label_text = f'{width:.2f}%', so any additional text can be added as needed.
Plot and Annotate
Plotting the bar, is 1 line, the remainder is annotating the rectangles
# plot the dataframe with 1 line
ax = df.plot.barh(stacked=True, figsize=(8, 6))
# .patches is everything inside of the chart
for rect in ax.patches:
# Find where everything is located
height = rect.get_height()
width = rect.get_width()
x = rect.get_x()
y = rect.get_y()
# The height of the bar is the data value and can be used as the label
label_text = f'{width:.2f}%' # f'{width:.2f}' to format decimal values
# ax.text(x, y, text)
label_x = x + width / 2
label_y = y + height / 2
# only plot labels greater than given width
if width > 0:
ax.text(label_x, label_y, label_text, ha='center', va='center', fontsize=8)
# move the legend
ax.legend(bbox_to_anchor=(1.05, 1), loc='upper left', borderaxespad=0.)
# add labels
ax.set_ylabel("People", fontsize=18)
ax.set_xlabel("Percent", fontsize=18)
plt.show()
Example with Missing Segment
# set one of the dataframe values to 0
df.iloc[4, 1] = 0
Note the annotations are all in the correct location from df.
For this case, the above answers work perfectly. The issue I had, and didn't find a plug-and-play solution online, was that I often have to plot stacked bars in multi-subplot figures, with many values, which tend to have very non-homogenous amplitudes.
(Note: I work usually with pandas dataframes, and matplotlib. I couldn't make the bar_label() method of matplotlib to work all the times.)
So, I just give a kind of ad-hoc, but easily generalizable solution. In this example, I was working with single-row dataframes (for power-exchange monitoring purposes per hour), so, my dataframe (df) had just one row.
(I provide an example figure to show how this can be useful in very densely-packed plots)
[enter image description here][1]
[1]: https://i.stack.imgur.com/9akd8.png
'''
This implementation produces a stacked, horizontal bar plot.
df --> pandas dataframe. Columns are used as the iterator, and only the firs value of each column is used.
waterfall--> bool: if True, apart from the stack-direction, also a perpendicular offset is added.
cyclic_offset_x --> list (of any length) or None: loop through these values to use as x-offset pixels.
cyclic_offset_y --> list (of any length) or None: loop through these values to use as y-offset pixels.
ax --> matplotlib Axes, or None: if None, creates a new axis and figure.
'''
def magic_stacked_bar(df, waterfall=False, cyclic_offset_x=None, cyclic_offset_y=None, ax=None):
if isinstance(cyclic_offset_x, type(None)):
cyclic_offset_x = [0, 0]
if isinstance(cyclic_offset_y, type(None)):
cyclic_offset_y = [0, 0]
ax0 = ax
if isinstance(ax, type(None)):
fig, ax = plt.subplots()
fig.set_size_inches(19, 10)
cycler = 0;
prev = 0 # summation variable to make it stacked
for c in df.columns:
if waterfall:
y = c ; label = "" # bidirectional stack
else:
y = 0; label = c # unidirectional stack
ax.barh(y=y, width=df[c].values[0], height=1, left=prev, label = label)
prev += df[c].values[0] # add to sum-stack
offset_x = cyclic_offset_x[divmod(cycler, len(cyclic_offset_x))[1]]
offset_y = cyclic_offset_y[divmod(cycler, len(cyclic_offset_y))[1]]
ax.annotate(text="{}".format(int(df[c].values[0])), xy=(prev - df[c].values / 2, y),
xytext=(offset_x, offset_y), textcoords='offset pixels',
ha='center', va='top', fontsize=8,
arrowprops=dict(facecolor='black', shrink=0.01, width=0.3, headwidth=0.3),
bbox=dict(boxstyle='round', facecolor='grey', alpha=0.5))
cycler += 1
if not waterfall:
ax.legend() # if waterfall, the index annotates the columns. If
# waterfall ==False, the legend annotates the columns
if isinstance(ax0, type(None)):
ax.set_title("Voi la")
ax.set_xlabel("UltraWatts")
plt.show()
else:
return ax
''' (Sometimes, it is more tedious and requires some custom functions to make the labels look alright.
'''
A, B = 80,80
n_units = df.shape[1]
cyclic_offset_x = -A*np.cos(2*np.pi / (2*n_units) *np.arange(n_units))
cyclic_offset_y = B*np.sin(2*np.pi / (2*n_units) * np.arange(n_units)) + B/2