Python script for plotting how many codepoints each Unicode version has assigned

plot_unicode_history.py

from datetime import date

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

data = [
    # (version number, date, number of codepoints assigned)
    ("1.0.0", date(1991, 10, 1),   7161, ( 5 ,   0)),
    ("1.0.1", date(1992,  6, 1),  28359, ( 5 ,  -8)),
    ("1.1"  , date(1993,  6, 1),  34223, (-6 ,   5)),
    ("2.0"  , date(1996,  6, 1),  38950, (-7 ,   5)),
    ("2.1"  , date(1998,  5, 1),  38952, (-7 , -15)),
    ("3.0"  , date(1999,  9, 1),  49259, ( 5 ,   0)),
    ("3.1"  , date(2001,  3, 1),  94205, (-7 ,   5)),
    ("3.2"  , date(2002,  3, 1),  95221, (-7 , -15)),
    ("4.0"  , date(2003,  4, 1),  96447, (-7 ,   5)),
    ("4.1"  , date(2005,  3, 1),  97720, (-7 , -15)),
    ("5.0"  , date(2006,  6, 1),  99089, (-7 ,   5)),
    ("5.1"  , date(2008,  4, 1), 100713, (-7 , -15)),
    ("5.2"  , date(2009, 10, 1), 107361, (-9 ,   5)),
    ("6.0"  , date(2010, 10, 1), 109449, (-7 , -15)),
    ("6.1"  , date(2012,  1, 1), 110181, (-9 ,   5)),
    ("6.2"  , date(2012,  9, 1), 110182, (-7 , -15)),
    ("6.3"  , date(2013,  9, 1), 110187, (-9 ,   5)),
    ("7.0"  , date(2014,  6, 1), 113021, ( 5 ,  -6)),
    ("8.0"  , date(2015,  6, 1), 120737, (-15,   5)),
    ("9.0"  , date(2016,  6, 1), 128237, ( 5 ,  -7)),
    ("10.0" , date(2017,  6, 1), 136755, (-16,   5)),
    ("11.0" , date(2018,  6, 1), 137439, (-7 , -12)),
]

versions = np.array([datum[0] for datum in data])
release_dates = np.array([datum[1] for datum in data])
num_assigned_codepoints = np.array([datum[2] for datum in data])
label_offsets = [datum[3] for datum in data]

fig, ax = plt.subplots()

plt.title("Unicode through the ages")
plt.xlabel("Release date")
plt.ylabel("Number of assigned codepoints")
plt.xlim(date(1990, 1, 1), date(2020, 1, 1))
plt.ylim(0, 150000)

ax.get_yaxis().set_major_formatter(
    matplotlib.ticker.FuncFormatter(lambda x, _: format(int(x), ",")))

ax.plot(release_dates, num_assigned_codepoints,
        color="blue",
        linestyle="--",
        linewidth=2.0)
ax.plot(release_dates, num_assigned_codepoints,
        color="red",
        marker="o",
        linewidth=0,
        fillstyle="full",
        markeredgewidth=0.01)

for i, txt in enumerate(versions):
    ax.annotate(txt, (release_dates[i], num_assigned_codepoints[i]),
                xytext=label_offsets[i],
                textcoords="offset points")

plt.savefig("unicode-history.svg", bbox_inches="tight")
plt.savefig("unicode-history.png", bbox_inches="tight")

Output: