How to plot a contingency table (heatmap) in python using seaborn and matplotlib ?

Examples of how to plot a contingency table in python using seaborn and matplotlib:

Create a contingency table

Lets create an array:

import numpy as np

data = np.array(([78,18,4],[14,98,5],[21,12,82]))

print(data)

returns

[[78 18  4]
 [14 98  5]
 [21 12 82]]

Plot a contingency table

import seaborn as sns; sns.set()
import matplotlib.pyplot as plt

fig = plt.figure(num=None, figsize=(8, 6), dpi=80, facecolor='w', edgecolor='k')

plt.clf()

ax = fig.add_subplot(111)

ax.set_aspect(1)

res = sns.heatmap(data, annot=True, fmt='.2f', cmap="YlGnBu", vmin=0.0, vmax=100.0)

plt.title('How to plot a coningency table with python \n using matplotlib and seaborn ?',fontsize=12)

plt.savefig("plot_contingency_table_seaborn_matplotlib_01.png", bbox_inches='tight', dpi=100)

plt.show()

Add axis labels

fig = plt.figure(num=None, figsize=(8, 6), dpi=80, facecolor='w', edgecolor='k')

plt.clf()

ax = fig.add_subplot(111)

ax.set_aspect(1)

res = sns.heatmap(data, annot=True, fmt='.2f', cmap="YlGnBu", vmin=0.0, vmax=100.0)

plt.title('How to plot a coningency table with python \n using matplotlib and seaborn ?',fontsize=12)

plt.xticks([i+0.5 for i in range(data.shape[0])], ['A1', 'B1', 'C1'])
plt.xticks(rotation=0)

plt.yticks([i+0.5 for i in range(data.shape[1])], ['A2', 'B2', 'C2'])
plt.yticks(rotation=0)

plt.savefig("plot_contingency_table_seaborn_matplotlib_02.png", bbox_inches='tight', dpi=100)

plt.show()

Add annotations

fig = plt.figure(num=None, figsize=(8, 6), dpi=80, facecolor='w', edgecolor='k')

plt.clf()

ax = fig.add_subplot(111)

ax.set_aspect(1)

annot_m = np.empty(data.shape,dtype='<U16')
for i in range(data.shape[0]):
    for j in range(data.shape[0]):
        annot_m[i,j] = 'Score: {}'.format(data[i,j])

res = sns.heatmap(data, annot=annot_m, fmt="", cmap="YlGnBu", vmin=0.0, vmax=100.0)

plt.title('How to plot a coningency table with python \n using matplotlib and seaborn ?',fontsize=12)

plt.xticks([i+0.5 for i in range(data.shape[0])], ['A1', 'B1', 'C1'])
plt.xticks(rotation=0)

plt.yticks([i+0.5 for i in range(data.shape[1])], ['A2', 'B2', 'C2'])
plt.yticks(rotation=0)

plt.yticks(rotation=0)

plt.savefig("plot_contingency_table_seaborn_matplotlib_03.png", bbox_inches='tight', dpi=100)

plt.show()

References

• What is the difference between a Confusion Matrix and Contingency Table?
• How do I create character arrays in numpy?
• How to Add Text plus Value in Python Seaborn Heatmap
• seaborn.heatmap
• Data type objects (dtype)
• numpy.empty