repeated y axis ticks in violinplot

Question

I want to plot the distribution with violinplot of a set of values between 1 and 800, I have used this code. I am very new to this.

import matplotlib.pyplot as plt
from matplotlib import ticker as mticker
import seaborn as sns
import numpy as np

log_data = [[np.log10(d) for d in row] for row in [data['count']]]
print(log_data)

fig, ax = plt.subplots()
sns.violinplot(data=log_data, ax=ax)

plt.show()

Why do I have three 10^0s?

This is my data: [ 8, 7, 5, 1, 2, 6, 5, 1, 2, 31, 9, 40, 9, 53, 4, 8, 3, 1, 46, 2, 18, 4, 17, 26, 17, 2, 19, 14, 2, 16, 35, 42, 22, 2, 19, 13, 59, 11, 69, 33, 2, 2, 24, 86, 16, 11, 7, 5, 18, 22, 1, 2, 16, 28, 3, 2, 12, 16, 1, 8, 1, 2, 5, 4, 9, 1, 1, 5, 1, 4, 5, 2, 11, 25, 6, 45, 64, 6, 2, 63, 26, 2, 3, 8, 3, 16, 8, 2, 2, 99, 2, 51, 43, 5, 53, 10, 19, 20, 6, 9, 1, 4, 1, 19, 4, 2, 3, 2, 77, 4, 7, 3, 2, 1, 81, 15, 50, 22, 58, 21, 10, 1, 18, 8, 1, 35, 2, 32, 18, 12, 11, 7, 5, 27, 29, 1, 2, 5, 1, 2, 3, 3, 1, 45, 22, 1, 12, 2, 21, 4, 1, 19, 27, 23, 3, 1, 21, 1, 124, 13, 17, 1, 18, 33, 23, 3, 6, 2, 8, 3, 1, 228, 28, 1, 1, 122, 868, 47, 2, 1, 9, 108, 10, 1, 5, 40, 43, 5, 2, 137, 9, 11, 19, 19, 11, 21, 8, 1, 6, 2, 3, 3, 26, 42, 14, 1, 14, 15, 3, 30, 17, 5, 17, 3, 38, 11, 54, 3, 1, 1, 3, 3, 7, 3, 1, 1, 5, 9, 1, 5, 4, 7, 35, 8, 10, 6, 6, 5, 3, 28, 2, 2, 5, 13, 6, 2, 4, 3, 2, 7, 52, 31, 1, 7, 7, 216, 4, 13, 6, 14, 4, 4, 5, 102, 3, 15, 4, 12, 48, 5, 9, 3, 10, 35, 36, 2, 10, 2, 55, 15, 17, 2, 19, 14, 14, 15, 5, 4, 11, 1, 1, 18, 4, 63, 63, 22, 37, 2, 22, 8, 22, 8, 20, 104, 3, 2, 6, 11, 20, 1, 3, 78, 2, 1, 52, 33, 2, 4, 9, 1, 27, 9, 4, 4, 2, 9, 9, 2, 24, 137, 12, 2, 2, 1, 6, 11, 8, 1, 20, 23, 75, 5, 1, 14, 3, 31, 15, 4, 2, 26, 50, 9, 75, 42, 14, 4, 1, 2, 9, 34, 25, 37, 53, 122, 28, 52, 22, 1, 109, 1, 1, 11, 1, 15, 2, 9, 32, 23, 5, 6, 3, 2, 51, 9, 12, 10, 7, 5, 2, 1, 311, 41, 1, 6, 13, 2, 5, 18, 105, 13, 17, 3, 9, 48, 2, 15, 18, 16, 77, 13, 3, 2, 2, 8, 1, 3, 4, 93, 23, 169, 1, 24, 2, 1, 8, 36, 1, 1, 1, 6, 3, 1, 25, 1, 2, 59, 2, 3, 3, 1, 8, 2, 1, 6, 15, 1, 7, 29, 4, 4, 8, 22, 5, 80, 16, 3, 147, 23, 6, 16, 1, 8, 530]

Using the set_yscale

ax.set_yscale('log')

sns.violinplot(data=first_issues_count, ax=ax)

Answer 1

A logscale option for the violinplot is on the roadmap for seaborn 0.12. Meanwhile, you can calculate the violinplot using the log10 of the _data and some formatting tricks, similar to Violin Plot troubles in Python on log scale.

The example code below shows how the formatting tricks could be adapted for your situation. For comparison, a sns.boxenplot is added, which doesn't have problems with a real log scale.

import matplotlib.pyplot as plt
from matplotlib.ticker import StrMethodFormatter
import seaborn as sns
import numpy as np

data = np.array([8, 7, 5, 1, 2, 6, 5, 1, 2, 31, 9, 40, 9, 53, 4, 8, 3, 1, 46, 2, 18, 4, 17, 26, 17, 2, 19, 14, 2, 16, 35, 42, 22, 2, 19, 13, 59, 11, 69, 33, 2, 2, 24, 86, 16, 11, 7, 5, 18, 22, 1, 2, 16, 28, 3, 2, 12, 16, 1, 8, 1, 2, 5, 4, 9, 1, 1, 5, 1, 4, 5, 2, 11, 25, 6, 45, 64, 6, 2, 63, 26, 2, 3, 8, 3, 16, 8, 2, 2, 99, 2, 51, 43, 5, 53, 10, 19, 20, 6, 9, 1, 4, 1, 19, 4, 2, 3, 2, 77, 4, 7, 3, 2, 1, 81, 15, 50, 22, 58, 21, 10, 1, 18, 8, 1, 35, 2, 32, 18, 12, 11, 7, 5, 27, 29, 1, 2, 5, 1, 2, 3, 3, 1, 45, 22, 1, 12, 2, 21, 4, 1, 19, 27, 23, 3, 1, 21, 1, 124, 13, 17, 1, 18, 33, 23, 3, 6, 2, 8, 3, 1, 228, 28, 1, 1, 122, 868, 47, 2, 1, 9, 108, 10, 1, 5, 40, 43, 5, 2, 137, 9, 11, 19, 19, 11, 21, 8, 1, 6, 2, 3, 3, 26, 42, 14, 1, 14, 15, 3, 30, 17, 5, 17, 3, 38, 11, 54, 3, 1, 1, 3, 3, 7, 3, 1, 1, 5, 9, 1, 5, 4, 7, 35, 8, 10, 6, 6, 5, 3, 28, 2, 2, 5, 13, 6, 2, 4, 3, 2, 7, 52, 31, 1, 7, 7, 216, 4, 13, 6, 14, 4, 4, 5, 102, 3, 15, 4, 12, 48, 5, 9, 3, 10, 35, 36, 2, 10, 2, 55, 15, 17, 2, 19, 14, 14, 15, 5, 4, 11, 1, 1, 18, 4, 63, 63, 22, 37, 2, 22, 8, 22, 8, 20, 104, 3, 2, 6, 11, 20, 1, 3, 78, 2, 1, 52, 33, 2, 4, 9, 1, 27, 9, 4, 4, 2, 9, 9, 2, 24, 137, 12, 2, 2, 1, 6, 11, 8, 1, 20, 23, 75, 5, 1, 14, 3, 31, 15, 4, 2, 26, 50, 9, 75, 42, 14, 4, 1, 2, 9, 34, 25, 37, 53, 122, 28, 52, 22, 1, 109, 1, 1, 11, 1, 15, 2, 9, 32, 23, 5, 6, 3, 2, 51, 9, 12, 10, 7, 5, 2, 1, 311, 41, 1, 6, 13, 2, 5, 18, 105, 13, 17, 3, 9, 48, 2, 15, 18, 16, 77, 13, 3, 2, 2, 8, 1, 3, 4, 93, 23, 169, 1, 24, 2, 1, 8, 36, 1, 1, 1, 6, 3, 1, 25, 1, 2, 59, 2, 3, 3, 1, 8, 2, 1, 6, 15, 1, 7, 29, 4, 4, 8, 22, 5, 80, 16, 3, 147, 23, 6, 16, 1, 8, 530])

sns.set_style('ticks')
fig, (ax1, ax2) = plt.subplots(ncols=2, figsize=(16, 8))

sns.violinplot(y=np.log10(data), ax=ax1)
major_ticks = np.arange(np.floor(np.log10(data).min()), np.log10(data).max() + 1)
ax1.yaxis.set_ticks(major_ticks, minor=False)
ax1.yaxis.set_ticks([np.log10(x) for p in major_ticks for x in np.linspace(10 ** p, 10 ** (p + 1), 10)], minor=True)
ax1.yaxis.set_major_formatter(StrMethodFormatter("$10^{{{x:.0f}}}$"))

ax2.set_yscale('log')
sns.boxenplot(y=data, ax=ax2)
ymin, ymax = ax1.get_ylim()
ax2.set_ylim(10**ymin, 10**ymax)

plt.tight_layout()
plt.show()