circlify code:

[ctb]

ref #48

tax_df = pd.read_csv('examples/tax/test.tax-mg.summarized.csv')

tax_df2 = tax_df[tax_df['rank'] == 'species']
tax_df2['name'] = tax_df2['lineage'].apply(lambda x: x.split(';')[-1])

fractions = list(tax_df2['fraction'].tolist())
names = list(tax_df2['name'].tolist())

# compute circle positions
circles = circlify.circlify(
    fractions,
    show_enclosure=False,
    target_enclosure=circlify.Circle(x=0, y=0, r=1)
)

# reverse the order of the circles to match the order of data
circles = circles[::-1]

# Create just a figure and only one subplot
fig, ax = plt.subplots(figsize=(10, 10))

# Title
#ax.set_title('Basic circular packing')

# Remove axes
ax.axis('off')

# Find axis boundaries
lim = max(
    max(
        abs(circle.x) + circle.r,
        abs(circle.y) + circle.r,
    )
    for circle in circles
)
plt.xlim(-lim, lim)
plt.ylim(-lim, lim)

# list of labels
labels = names[::-1]
# print circles
for circle, label in zip(circles, labels):
    x, y, r = circle
    ax.add_patch(plt.Circle((x, y), r, alpha=0.2, linewidth=2))
    plt.annotate(
        label,
        (x, y),
        va='center',
        ha='center'
    )

plt.savefig('/tmp/circles1.png')

produces:

[ctb]

hierarchical:

#data = [{'id': 'World', 'datum': 6964195249, 'children': [
#    {'id': "North America", 'datum': 450448697,
#               'children': [
#                   {'id': "United States", 'datum': 308865000},
#                   {'id': "Mexico", 'datum': 107550697},
#                   {'id': "Canada", 'datum': 34033000}
#               ]},

from collections import defaultdict

rank_a = 3
rank_b = 6

dd = {}
totals = defaultdict(float)
for lineage, fraction in tax_df2[['lineage', 'fraction']].itertuples(index=False, name=None):
    print(lineage, fraction)
    top_rank = lineage.split(';')[:rank_a][-1]
    bot_rank = lineage.split(';')[:rank_b][-1]
    ddd = dd.get(top_rank, [])
    totals[top_rank] += fraction
    sub_d = dict(id=bot_rank.split(';')[-1], datum=fraction)
    ddd.append(sub_d)
    dd[top_rank] = ddd

dd2 = []
for k, v in dd.items():
    total = totals.get(k)
    dd = dict(id=k, datum=total, children=v)
    dd2.append(dd)

world = [ dict(name='all', datum=sum(totals.values()), children=dd2) ]
world

# import the circlify library
import circlify

# Compute circle positions thanks to the circlify() function
circles = circlify.circlify(
    world,
    show_enclosure=False,
    target_enclosure=circlify.Circle(x=0, y=0, r=1)
)

# import libraries
import circlify
import matplotlib.pyplot as plt

# Create just a figure and only one subplot
fig, ax = plt.subplots(figsize=(14, 14))

# Title
#ax.set_title('Repartition of the world population')

# Remove axes
ax.axis('off')

# Find axis boundaries
lim = max(
    max(
        abs(circle.x) + circle.r,
        abs(circle.y) + circle.r,
    )
    for circle in circles
)
plt.xlim(-lim, lim)
plt.ylim(-lim, lim)

# Print circle the highest level (continents):
for circle in circles:
    if circle.level != 2:
        continue
    x, y, r = circle
    ax.add_patch(plt.Circle((x, y), r, alpha=0.5,
                 linewidth=2, color="lightblue"))

# Print circle and labels for the highest level:
for circle in circles:
    if circle.level != 3:
        continue
    x, y, r = circle
    label = circle.ex["id"]
    ax.add_patch(plt.Circle((x, y), r, alpha=0.5,
                 linewidth=2, color="#69b3a2"))
    plt.annotate(label, (x, y), ha='center', color="white")

# Print labels for the continents
for circle in circles:
    if circle.level != 2:
        continue
    x, y, r = circle
    label = circle.ex["id"]
    plt.annotate(label, (x, y), va='center', ha='center', bbox=dict(
        facecolor='white', edgecolor='black', boxstyle='round', pad=.5))

plt.legend()

produces: