Github Stats Api

https://developer.github.com/v3/repos/statistics/

    %%capture
    import uritemplate, requests, pandas, hvplot.pandas; __import__('requests_cache').install_cache('stats')

    stats = "https://api.github.com/repos/{owner}/{repo}/stats/"

    for x in "contributors commit_activity code_frequency".split():
        globals()[x] = uritemplate.URITemplate(stats+x)

    owner, repo = "omnisci/jupyterlab-omnisci".split('/')

    def get(url):
        if requests.get(url).status_code == 202: return __import__('time').sleep(1) or get(url)
        return pandas.DataFrame(requests.get(url).json())

    df = get(contributors.expand(globals()))
    df = df.weeks.apply(pandas.Series).stack().apply(pandas.Series).reset_index(-1, drop=True).join(df.author.apply(pandas.Series))
    df.w = df.w.pipe(pandas.to_datetime, unit='s')
    df = df.set_index(['w', 'login'])

    contributions = df[list('acd')].rename(columns=dict(zip('ad', '+-'), c='commits')).unstack('login')
    contributions.T
w 2018-03-25 2018-04-01 2018-04-08 2018-04-15 2018-04-22 2018-04-29 2018-05-06 2018-05-13 2018-05-20 2018-05-27 ... 2019-08-11 2019-08-18 2019-08-25 2019-09-01 2019-09-08 2019-09-15 2019-09-22 2019-09-29 2019-10-06 2019-10-13
login
+ domoritz 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
gnestor 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
ian-r-rose 42848 507 771 319 551 311 0 0 0 0 ... 0 0 656 149 0 0 0 0 0 0
saulshanabrook 0 0 0 0 410 0 70 456 28 225 ... 1671 0 0 0 0 0 0 0 0 0
tonyfast 0 0 0 0 15 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
commits domoritz 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
gnestor 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
ian-r-rose 14 3 10 5 8 9 0 0 0 0 ... 0 0 5 4 0 0 0 0 0 0
saulshanabrook 0 0 0 0 8 0 1 3 2 7 ... 10 0 0 0 0 0 0 0 0 0
tonyfast 0 0 0 0 1 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
- domoritz 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
gnestor 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
ian-r-rose 42164 17 353 78 111 103 0 0 0 0 ... 0 0 1814 73 0 0 0 0 0 0
saulshanabrook 0 0 0 0 56 0 33 127 28 12 ... 4720 0 0 0 0 0 0 0 0 0
tonyfast 0 0 0 0 1 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0

15 rows × 82 columns

    df = get(commit_activity.expand(globals()))
    df.week = df.week.pipe(pandas.to_datetime, unit='s')
    df = df.set_index('week').days.apply(pandas.Series)
    df.columns = (
        df.index[0]+pandas.to_timedelta(df.columns.map('{} days'.format))
    ).strftime('%A')

    weekly_commits = df
    weekly_commits.T
week 2018-10-21 2018-10-28 2018-11-04 2018-11-11 2018-11-18 2018-11-25 2018-12-02 2018-12-09 2018-12-16 2018-12-23 ... 2019-08-11 2019-08-18 2019-08-25 2019-09-01 2019-09-08 2019-09-15 2019-09-22 2019-09-29 2019-10-06 2019-10-13
Sunday 1 0 0 8 0 1 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
Monday 0 8 9 3 3 3 1 0 13 0 ... 9 0 0 0 0 0 0 0 0 0
Tuesday 0 11 0 4 1 0 0 0 0 0 ... 1 0 0 0 0 0 0 0 0 0
Wednesday 0 0 0 0 0 0 0 2 0 1 ... 0 0 0 0 0 0 0 0 0 0
Thursday 0 0 0 0 0 0 0 0 0 7 ... 0 0 2 0 0 0 0 0 0 0
Friday 4 1 0 0 0 3 0 0 0 0 ... 0 0 3 4 0 0 0 0 0 0
Saturday 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0

7 rows × 52 columns

    df = get(code_frequency.expand(globals()))
    df = df[[1, 2]].rename(columns=dict(zip([1,2], "+-"))).set_index(df[0].pipe(pandas.to_datetime, unit='s').rename('week'))
    code_changes = df; code_changes.T
week 2018-03-25 2018-04-01 2018-04-08 2018-04-15 2018-04-22 2018-04-29 2018-05-06 2018-05-13 2018-05-20 2018-05-27 ... 2019-08-11 2019-08-18 2019-08-25 2019-09-01 2019-09-08 2019-09-15 2019-09-22 2019-09-29 2019-10-06 2019-10-13
+ 42848 507 771 319 976 311 70 456 28 225 ... 1671 0 656 149 0 0 0 0 0 0
- -42164 -17 -353 -78 -168 -103 -33 -127 -28 -12 ... -4720 0 -1814 -73 0 0 0 0 0 0

2 rows × 82 columns

Written on October 13, 2019