how to plot group bars with missing values in Python

Question

I am using the following code to group bar plot in Python as follows.

import matplotlib
import matplotlib.pyplot as plt
import numpy as np


labels = ['G1', 'G2', 'G3', 'G4', 'G5']
men_means = [20, 34, 30, 35, 27]
women_means = [25, 32, 34, 20, 25]

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')

# Add some text for labels, title and custom x-axis tick labels, etc.
ax.set_ylabel('Scores')
ax.set_title('Scores by group and gender')
ax.set_xticks(x)
ax.set_xticklabels(labels)
ax.legend()


def autolabel(rects):
    """Attach a text label above each bar in *rects*, displaying its height."""
    for rect in rects:
        height = rect.get_height()
        ax.annotate('{}'.format(height),
                    xy=(rect.get_x() + rect.get_width() / 2, height),
                    xytext=(0, 3),  # 3 points vertical offset
                    textcoords="offset points",
                    ha='center', va='bottom')


autolabel(rects1)
autolabel(rects2)

fig.tight_layout()

plt.show()

How can I plot the same bar plot with one missing value men_means list as follows.

labels = ['G1', 'G2', 'G3', 'G4', 'G5']
men_means = [20, 34, 30, 35]
women_means = [25, 32, 34, 20, 25]

Here G5 is is absent in men_means

Ajay Verma · Accepted Answer · 2020-09-21 10:14:36Z

One can assign Zero values for men_means at G5 and do the plotting.

However it's not possible to know which index is missing in either of list. I suggest use of Dictionary to map the labels to specific values and then figure out which values it missing and assign it to Zero.

def fix_dict(data):
    labels = ['G1', 'G2', 'G3', 'G4', 'G5']
    for d in set(labels).difference(set(data.keys())):
        data[d] = 0
    return data
dict_men_means = {'G1':20, 'G2': 34, 'G3': 30, 'G4':35}
dict_women_means =  {'G1':25, 'G2': 32, 'G3': 34, 'G4':20, 'G5':25}
mean_means = [v for v in fix_dict(dict_men_means).values()]
women_means = [v for v in fix_dict(dict_women_means).values()]

Including this the code will become

import matplotlib
import matplotlib.pyplot as plt
import numpy as np


labels = ['G1', 'G2', 'G3', 'G4', 'G5']
dict_men_means = {'G1':20, 'G2': 34, 'G3': 30, 'G4':35}
dict_women_means =  {'G1':25, 'G2': 32, 'G3': 34, 'G4':20, 'G5':25}
mean_means = [v for v in fix_dict(dict_men_means).values()]
women_means = [v for v in fix_dict(dict_women_means).values()]

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')

# Add some text for labels, title and custom x-axis tick labels, etc.
ax.set_ylabel('Scores')
ax.set_title('Scores by group and gender')
ax.set_xticks(x)
ax.set_xticklabels(labels)
ax.legend()


def autolabel(rects):
    """Attach a text label above each bar in *rects*, displaying its height."""
    for rect in rects:
        height = rect.get_height()
        ax.annotate('{}'.format(height),
                    xy=(rect.get_x() + rect.get_width() / 2, height),
                    xytext=(0, 3),  # 3 points vertical offset
                    textcoords="offset points",
                    ha='center', va='bottom')


autolabel(rects1)
autolabel(rects2)

fig.tight_layout()

plt.show()

0 is still shown on the top of the bar. Is there anyway we can avoid it to be shown on the top of the bar.

Stupid420 · Accepted Answer · 2020-09-21 12:31:38Z

0

I tried it with if statement in autolabel function as follows.

import matplotlib
import matplotlib.pyplot as plt
import numpy as np


labels = ['G1', 'G2', 'G3', 'G4', 'G5']
men_means = [20, 34, 30, 35, 0]
women_means = [25, 32, 34, 20, 25]

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')

# Add some text for labels, title and custom x-axis tick labels, etc.
ax.set_ylabel('Scores')
ax.set_title('Scores by group and gender')
ax.set_xticks(x)
ax.set_xticklabels(labels)
ax.legend()


def autolabel(rects):
    """Attach a text label above each bar in *rects*, displaying its height."""
    for rect in rects:
        height = rect.get_height()
        
        if height!=0:
            
            ax.annotate('{}'.format(height),
                        xy=(rect.get_x() + rect.get_width() / 2, height),
                        xytext=(0, 3),  # 3 points vertical offset
                        textcoords="offset points",
                        ha='center', va='bottom')


autolabel(rects1)
autolabel(rects2)

fig.tight_layout()

plt.show()

answered Sep 21, 2020 at 12:31

Stupid420

1,4394 gold badges24 silver badges50 bronze badges

1 Comment

Tao Venzke Over a year ago

I like your answer. However, since the value is missing, maybe it´s better to use [20, 34, 30, 35, float('nan')]. Then, instead of check "if height != 0", we can check "if math.isnan(height)"

Collectives™ on Stack Overflow

how to plot group bars with missing values in Python

2 Answers 2

1 Comment

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

1 Comment

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related