make_hist.py

# Run inside https://github.com/mayeut/manylinux-timeline
#
# Example nox file for those too lazy to set up a venv:
#
# import nox
#
# @nox.session(reuse_venv=True)
# def run(session):
#     session.install("hist[plot]", "pandas")
#     session.run("python", "make_hist.py")

from hist import Hist
import pandas as pd
import matplotlib.pyplot as plt
from pathlib import Path
import numpy as np


def ver_to_int(version):
    major, minor = version.split(".")
    minor = minor.split("b")[0].split("-")[0]
    return (int(major) % 2000) * 100 + int(minor)


data = []

for file_path in Path("consumer_data/2021/10").glob("*.csv"):
    data.append(
        pd.read_csv(
            file_path,
            converters={
                "python_version": str,
                "pip_version": ver_to_int,
                "glibc_version": ver_to_int,
            },
        )
    )

df = pd.concat(data).reset_index()

glib_ml = pd.cut(
    df["glibc_version"],
    bins=(0, 200, 205, 212, 217, 1000),
    labels=("0", "1", "2010", "2014", "2_24"),
)
pip_ml = pd.cut(
    df["pip_version"],
    bins=(0, 801, 1900, 1903, 2003, 3000),
    labels=("0", "1", "2010", "2014", "2_24"),
)
codes = np.min([glib_ml.cat.codes, pip_ml.cat.codes], axis=0)

all_ml = pd.Series(codes, dtype="category")
all_ml.cat.categories = ("0", "1", "2010", "2014", "2_24")
df["policy"] = all_ml
df["max_policy"] = glib_ml

h = Hist.from_columns(
    df,
    ("cpu", "python_version", "pip_version", "policy", "max_policy"),
    weight="num_downloads",
)

fig, axs = plt.subplots(2, 3, figsize=(12, 8))
for i, py in enumerate(["2.7", "3.6", "3.7", "3.8", "3.9", "3.10"]):
    ax = axs.flatten()[i]
    ph = h.project("python_version", "pip_version")[py, :]
    ph.plot_pie(ax=ax, normalize=True, autopct="%1.0f%%", pctdistance=0.8)
    ax.set_title(f"Python {py} {int(ph.sum()) // 1000000:,} M")


fig.suptitle("October 2021 all manylinux")
plt.tight_layout()
plt.savefig("pip_versions.png")

fig, axs = plt.subplots(2, 3, figsize=(12, 8))
for i, py in enumerate(["2.7", "3.6", "3.7", "3.8", "3.9", "3.10"]):
    ax = axs.flatten()[i]
    ph = h.project("python_version", "policy")[py, :]
    ph.plot_pie(ax=ax, normalize=True, autopct="%1.0f%%", pctdistance=0.8)
    ax.set_title(f"Python {py} {int(ph.sum()) // 1000000:,} M")

fig.suptitle("October 2021 all manylinux")
plt.savefig("manylinux_versions.png")

fig, axs = plt.subplots(2, 3, figsize=(12, 8))
for i, py in enumerate(["2.7", "3.6", "3.7", "3.8", "3.9", "3.10"]):
    ax = axs.flatten()[i]
    ph = h.project("python_version", "max_policy")[py, :]
    ph.plot_pie(ax=ax, normalize=True, autopct="%1.0f%%", pctdistance=0.8)
    ax.set_title(f"Python {py} {int(ph.sum()) // 1000000:,} M")

fig.suptitle("October 2021 max supported manylinux")
plt.savefig("manylinux_max.png")