We Keep Coding

Repeated Categorical X-Axis Labels in Matplotlib

I have a simple question: why are my x-axis labels repeated?
Here's an MWE: X-Axis Labels MWE
a = { # DATA -- 'CATEGORY': (VALUE, ERROR)
'Cats': (1, 0.105),
'Dogs': (2, 0.023),
'Pigs': (2.6, 0.134)
}
compositions = list(a.keys()) # MAKE INTO LIST
a_vals = [i[0] for i in a.values()] # EXTRACT VALUES
a_errors = [i[1] for i in a.values()] # EXTRACT ERRORS
fig = plt.figure(figsize=(8, 6)) # DICTATE FIGURE SIZE
bax = brokenaxes(ylims=((0,1.5), (1.7, 3)), hspace = 0.05) # BREAK AXES
bax.plot(compositions, a_vals, marker = 'o') # PLOT DATA
for i in range(0, len(a_errors)): # PLOT ALL ERROR BARS
bax.errorbar(i, a_vals[i], yerr = a_errors[i], capsize = 5, fmt = 'red') # FORMAT ERROR BAR
Here's stuff I tried:
Manually setting x-axis tick marks using xticks
Converting strings to floats using np.asarray(x, float)
Reducing # ticks using pyplot.locator_params(nbins=3)

You can use bax.locator_params(axis='x', nbins=len(compositions)) to reduce the number of x-ticks so that it matches the length of compositions.
More on locator_params() method, which controls the behavior of major tick locators:
https://matplotlib.org/stable/api/_as_gen/matplotlib.axes.Axes.locator_params.html
import matplotlib.pyplot as plt
from brokenaxes import brokenaxes
a = { # DATA -- 'CATEGORY': (VALUE, ERROR)
'Cats': (1, 0.105),
'Dogs': (2, 0.023),
'Pigs': (2.6, 0.134)
}
compositions = list(a.keys()) # MAKE INTO LIST
a_vals = [i[0] for i in a.values()] # EXTRACT VALUES
a_errors = [i[1] for i in a.values()] # EXTRACT ERRORS
fig = plt.figure(figsize=(8, 6)) # DICTATE FIGURE SIZE
bax = brokenaxes(ylims=((0, 1.5), (1.7, 3)), hspace=0.05) # BREAK AXES
bax.plot(compositions, a_vals, marker='o') # PLOT DATA
for i in range(0, len(a_errors)): # PLOT ALL ERROR BARS
bax.errorbar(i, a_vals[i], yerr=a_errors[i], capsize=5, fmt='red') # FORMAT ERROR BAR
bax.locator_params(axis='x', nbins=len(compositions))
plt.show()
Result:

How do I plot a categorical bar chart with different classes for each category in Matplotlib?

I was trying to reproduce this plot with Matplotlib:
So, by looking at the documentation, I found out that the closest thing is a grouped bar chart. The problem is that I have a different number of "bars" for each category (subject, illumination, ...) compared to the example provided by matplotlib that instead only has 2 classes (M, F) for each category (G1, G2, G3, ...). I don't know exactly from where to start, does anyone here has any clue? I think in this case the trick they made to specify bars location:
x = np.arange(len(labels)) # the label locations
width = 0.35 # the width of the bars
fig, ax = plt.subplots()
rects1 = ax.bar(x - width/2, men_means, width, label='Men')
rects2 = ax.bar(x + width/2, women_means, width, label='Women')
does not work at all as in the second class (for example) there is a different number of bars. It would be awesome if anyone could give me an idea. Thank you in advance!

Supposing the data resides in a dataframe, the bars can be generated by looping through the categories:
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
# first create some test data, similar in structure to the question's
categories = ['Subject', 'Illumination', 'Location', 'Daytime']
df = pd.DataFrame(columns=['Category', 'Class', 'Value'])
for cat in categories:
for _ in range(np.random.randint(2, 7)):
df = df.append({'Category': cat,
'Class': "".join(np.random.choice([*'tuvwxyz'], 10)),
'Value': np.random.uniform(10, 17)}, ignore_index=True)
fig, ax = plt.subplots()
start = 0 # position for first label
gap = 1 # gap between labels
labels = [] # list for all the labels
label_pos = np.array([]) # list for all the label positions
# loop through the categories of the dataframe
# provide a list of colors (at least as long as the expected number of categories)
for (cat, df_cat), color in zip(df.groupby('Category', sort=False), ['navy', 'orange'] * len(df)):
num_in_cat = len(df_cat)
# add a text for the category, using "axes coordinates" for the y-axis
ax.text(start + num_in_cat / 2, 0.95, cat, ha='center', va='top', transform=ax.get_xaxis_transform())
# positions for the labels of the current category
this_label_pos = np.arange(start, start + num_in_cat)
# create bars at the desired positions
ax.bar(this_label_pos, df_cat['Value'], color=color)
# store labels and their positions
labels += df_cat['Class'].to_list()
label_pos = np.append(label_pos, this_label_pos)
start += num_in_cat + gap
# set the positions for the labels
ax.set_xticks(label_pos)
# set the labels
ax.set_xticklabels(labels, rotation=30)
# optionally set a new lower position for the y-axis
ax.set_ylim(ymin=9)
# optionally reduce the margin left and right
ax.margins(x=0.01)
plt.tight_layout()
plt.show()

Prevent Matplotlib Legend from smushing h-padding on vertical subplots?

I have a script where I am plotting several variables in a grid of 5x1. I have noticed that when I have data that makes my legend shorter, the subplots themselves have an acceptable height and horizontal padding. When I have data that makes my legend bigger (vertically) the subplots are squashed leaving extra horizontal padding between the plots.
Is there a way to prevent this? To separate the legend assignment from the axes object and draw each plot independent of legend spacing?
Below is a minimal reproducible example to show what I mean:
#!/usr/bin/env python3
from pathlib import Path
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
def plotter(df, var_cols):
dfa = df.query("accepted == 'accepted'")
dfr = df.query("accepted != 'accepted'")
colors = {v: c for v, c in zip(['accepted', 'rejected', 'rerun'],
['darkgreen', 'firebrick', 'steelblue'])}
fig, axes = plt.subplots(nrows=len(var_cols), sharex=True)
for var, ax in zip(var_cols, axes):
for k, d in dfr.groupby('accepted'):
ax.scatter(d.iteration, d[var], label=k, alpha=0.8, c=d.accepted.map(colors))
ax.plot(dfa.iteration, dfa[var], '-o', label='accepted', color=colors['accepted'])
# Grab 3rd axes because I want the legend to be towards the center
handles, labels = axes[2].get_legend_handles_labels()
# Sort legend labels to put 'accepted' on top
labels, handles = zip(*sorted(zip(labels, handles), key=lambda t: t[0]))
axes[2].legend(handles, labels, markerscale=1.2, bbox_to_anchor=(1, 0.5))
fig.tight_layout()
def main():
states = {1: 'accepted', 2: 'rejected', 3: 'rerun'}
np.random.seed(666)
dat1 = pd.DataFrame({
'iteration': [0, 1, 2],
'accepted': ['accepted']*3,
'h_cap': [10.1, 6.5, 12.2],
'h_stor': [500, 410, 0],
'h_mark': [10, 6, 1],
'bid': [500, 100, 50],
'npv': [2.278, 2.6, 2.85]
})
dat2 = pd.DataFrame({
'iteration': range(10),
'accepted': [states[num] for num in np.random.randint(1, 4, size=10)],
'h_cap': np.random.rand(10),
'h_stor': np.random.rand(10),
'h_mark': np.random.rand(10),
'bid': np.random.rand(10),
'npv': np.random.rand(10)
})
var_cols = ['h_cap', 'h_stor', 'h_mark', 'bid', 'npv']
plotter(dat1, var_cols)
plt.savefig(Path('~/Desktop/nonsmushed.png').expanduser())
plotter(dat2, var_cols)
plt.savefig(Path('~/Desktop/smushed.png').expanduser())
if __name__ == '__main__':
main()
nonsmushed.png
smushed.png

Because your legend "belongs" to axes[2], tight_layout() adjusts the spacing so that the adjacent axes don't cover the legend.
I think the simplest solution would be to create a "figure-level" legend (fig.legend()), but the problem with that is that tight_layout() doesn't account for that legend, and you will have to adjust the right margin by hand (there might be a way to calculate it automatically if needed, but that might get messy)
(...)
labels, handles = zip(*sorted(zip(labels, handles), key=lambda t: t[0]))
fig.legend(handles, labels, markerscale=1.2, bbox_to_anchor=(1, 0.5))
fig.tight_layout()
fig.subplots_adjust(right=0.75) # adjust value as needed

Plotting a pie-chart in matplotlib at a specific angle with the fracs on the wedges

I am plotting a piechart with matplotlib using the following code:
ax = axes([0.1, 0.1, 0.6, 0.6])
labels = 'Twice Daily', 'Daily', '3-4 times per week', 'Once per week','Occasionally'
fracs = [20,50,10,10,10]
explode=(0, 0, 0, 0,0.1)
patches, texts, autotexts = ax.pie(fracs, labels=labels, explode = explode,
autopct='%1.1f%%', shadow =True)
proptease = fm.FontProperties()
proptease.set_size('xx-small')
setp(autotexts, fontproperties=proptease)
setp(texts, fontproperties=proptease)
rcParams['legend.fontsize'] = 7.0
savefig("pie1")
This produces the following piechart.
However, I want to start the pie-chart with the first wedge on top, the only solution I could find for this was using this code
However on using this as below,
from pylab import *
from matplotlib import font_manager as fm
from matplotlib.transforms import Affine2D
from matplotlib.patches import Circle, Wedge, Polygon
import numpy as np
fig = plt.figure()
ax = fig.add_subplot(111)
labels = 'Twice Daily', 'Daily', '3-4 times per week', 'Once per week','Occasionally'
fracs = [20,50,10,10,10]
wedges, plt_labels = ax.pie(fracs, labels=labels)
ax.axis('equal')
starting_angle = 90
rotation = Affine2D().rotate(np.radians(starting_angle))
for wedge, label in zip(wedges, plt_labels):
label.set_position(rotation.transform(label.get_position()))
if label._x > 0:
label.set_horizontalalignment('left')
else:
label.set_horizontalalignment('right')
wedge._path = wedge._path.transformed(rotation)
plt.savefig("pie2")
This produces the following pie chart
However, this does not print the fracs on the wedges as in the earlier pie chart. I have tried a few different things, but I am not able to preserve the fracs. How can I start the first wedge at noon and display the fracs on the wedges as well??

Ordinarily I wouldn't recommend changing the source of a tool, but it's hacky to fix this outside and easy inside. So here's what I'd do if you needed this to work Right Now(tm), and sometimes you do..
In the file matplotlib/axes.py, change the declaration of the pie function to
def pie(self, x, explode=None, labels=None, colors=None,
autopct=None, pctdistance=0.6, shadow=False,
labeldistance=1.1, start_angle=None):
i.e. simply add start_angle=None to the end of the arguments.
Then add the five lines bracketed by "# addition".
for frac, label, expl in cbook.safezip(x,labels, explode):
x, y = center
theta2 = theta1 + frac
thetam = 2*math.pi*0.5*(theta1+theta2)
# addition begins here
if start_angle is not None and i == 0:
dtheta = (thetam - start_angle)/(2*math.pi)
theta1 -= dtheta
theta2 -= dtheta
thetam = start_angle
# addition ends here
x += expl*math.cos(thetam)
y += expl*math.sin(thetam)
Then if start_angle is None, nothing happens, but if start_angle has a value, then that's the location that the first slice (in this case the 20%) is centred on. For example,
patches, texts, autotexts = ax.pie(fracs, labels=labels, explode = explode,
autopct='%1.1f%%', shadow =True, start_angle=0.75*pi)
produces
Note that in general you should avoid doing this, patching the source I mean, but there are times in the past when I've been on deadline and simply wanted something Now(tm), so there you go..

How to plot a grouped bar chart from multiple datasets

I am going through Think Stats and I would like to compare multiple data sets visually. I can see from the book examples that it is possible to generate an interleaved bar graph with a different color for each data set by using a module provided by the book author, how to obtain the same result in pyplot?

Call the bar function multiple times, one for each series. You can control the left position of the bars using the left parameter, and you can use this to prevent overlap.
Entirely untested code:
pyplot.bar( numpy.arange(10) * 2, data1, color = 'red' )
pyplot.bar( numpy.arange(10) * 2 + 1, data2, color = 'red' )
Data2 will be drawn shifted over the right compared to where data one will be drawn.

Matplotlib's example code for interleaved bar charts works nicely for arbitrary real-valued x coordinates (as mentioned by #db42).
However, if your x coordinates are categorical values (like in the case of dictionaries in the linked question), the conversion from categorical x coordinates to real x coordinates is cumbersome and unnecessary.
You can plot two dictionaries side-by-side directly using matplotlib's api. The trick for plotting two bar charts with an offset to each other is to set align=edge and a positive width (+width) for plotting one bar chart, whereas a negative width (-width) for plotting the other one.
The example code modified for plotting two dictionaries looks like the following then:
"""
========
Barchart
========
A bar plot with errorbars and height labels on individual bars
"""
import matplotlib.pyplot as plt
# Uncomment the following line if you use ipython notebook
# %matplotlib inline
width = 0.35 # the width of the bars
men_means = {'G1': 20, 'G2': 35, 'G3': 30, 'G4': 35, 'G5': 27}
men_std = {'G1': 2, 'G2': 3, 'G3': 4, 'G4': 1, 'G5': 2}
rects1 = plt.bar(men_means.keys(), men_means.values(), -width, align='edge',
yerr=men_std.values(), color='r', label='Men')
women_means = {'G1': 25, 'G2': 32, 'G3': 34, 'G4': 20, 'G5': 25}
women_std = {'G1': 3, 'G2': 5, 'G3': 2, 'G4': 3, 'G5': 3}
rects2 = plt.bar(women_means.keys(), women_means.values(), +width, align='edge',
yerr=women_std.values(), color='y', label='Women')
# add some text for labels, title and axes ticks
plt.xlabel('Groups')
plt.ylabel('Scores')
plt.title('Scores by group and gender')
plt.legend()
def autolabel(rects):
"""
Attach a text label above each bar displaying its height
"""
for rect in rects:
height = rect.get_height()
plt.text(rect.get_x() + rect.get_width()/2., 1.05*height,
'%d' % int(height),
ha='center', va='bottom')
autolabel(rects1)
autolabel(rects2)
plt.show()
The result:

I came across this problem a while ago and created a wrapper function that takes a 2D array and automatically creates a multi-barchart from it:
The code:
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import operator as o
import numpy as np
dpoints = np.array([['rosetta', '1mfq', 9.97],
['rosetta', '1gid', 27.31],
['rosetta', '1y26', 5.77],
['rnacomposer', '1mfq', 5.55],
['rnacomposer', '1gid', 37.74],
['rnacomposer', '1y26', 5.77],
['random', '1mfq', 10.32],
['random', '1gid', 31.46],
['random', '1y26', 18.16]])
fig = plt.figure()
ax = fig.add_subplot(111)
def barplot(ax, dpoints):
'''
Create a barchart for data across different categories with
multiple conditions for each category.
#param ax: The plotting axes from matplotlib.
#param dpoints: The data set as an (n, 3) numpy array
'''
# Aggregate the conditions and the categories according to their
# mean values
conditions = [(c, np.mean(dpoints[dpoints[:,0] == c][:,2].astype(float)))
for c in np.unique(dpoints[:,0])]
categories = [(c, np.mean(dpoints[dpoints[:,1] == c][:,2].astype(float)))
for c in np.unique(dpoints[:,1])]
# sort the conditions, categories and data so that the bars in
# the plot will be ordered by category and condition
conditions = [c[0] for c in sorted(conditions, key=o.itemgetter(1))]
categories = [c[0] for c in sorted(categories, key=o.itemgetter(1))]
dpoints = np.array(sorted(dpoints, key=lambda x: categories.index(x[1])))
# the space between each set of bars
space = 0.3
n = len(conditions)
width = (1 - space) / (len(conditions))
# Create a set of bars at each position
for i,cond in enumerate(conditions):
indeces = range(1, len(categories)+1)
vals = dpoints[dpoints[:,0] == cond][:,2].astype(np.float)
pos = [j - (1 - space) / 2. + i * width for j in indeces]
ax.bar(pos, vals, width=width, label=cond,
color=cm.Accent(float(i) / n))
# Set the x-axis tick labels to be equal to the categories
ax.set_xticks(indeces)
ax.set_xticklabels(categories)
plt.setp(plt.xticks()[1], rotation=90)
# Add the axis labels
ax.set_ylabel("RMSD")
ax.set_xlabel("Structure")
# Add a legend
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles[::-1], labels[::-1], loc='upper left')
barplot(ax, dpoints)
plt.show()
If you're interested in what this function does and the logic behind it, here's a (shamelessly self-promoting) link to the blog post describing it.