Measures quantity of git changes, both summarized and over time

git_log_quantity_per_person.py

#!/usr/bin/env python

import pandas as pd
import sys

goodext = ('java')

removalfactor = 2.0 # Paraphrasing Tolstoy: "nothing can improve a piece of software as much as code removal".
commitfactor  = 0.1 # A commit is only as good as it's content.

def score(adds, removes, commits):
 return adds + removes*removalfactor + commits*commitfactor

def printflatstats(peopledata):
 print('name\tadds\tremoves\tcommits')
 for person, changedata in peopledata.items():
  print('%s\t%6.i\t%6.i\t%4.i' % (person, changedata['adds'], changedata['removes'], changedata['commits']))

def createdatetable(peopledata, dates):
 table = []
 headers = ['dates'] + list(peopledata.keys())
 table += [headers]
 for date in reversed(dates):
  datefmt = '%s-%s-%s' % (date.date[:4], date.date[4:6], date.date[6:])
  row = [datefmt]
  for person in peopledata.keys():
   changedata = date.peopledata.get(person)
   if changedata:
    row += [score(changedata['adds'], changedata['removes'], changedata['commits'])]
   else:
    row += [0.0]
  table += [row]
 return table

def transpose(table):
 return zip(*table)

def combinemonths(table):
 df = pd.DataFrame({c[0]:c[1:] for c in zip(*table)})
 df.dates = [d[:7]+'-01' for d in df.dates]
 df.dates = pd.to_datetime(df.dates)
 df = df.groupby('dates').sum()
 return df

def printdatestats(peopledata, dates):
 table = createdatetable(peopledata, dates)
 table = combinemonths(table)
 persons = table.iloc[-13:, :].sum() # last year-ish
 persons = persons.sort_values().index[::-1]
 table = table[persons]
 s = table.reset_index().to_csv(index=False, sep='\t')
 print(s)

class CommitDate:
 def __init__(self, date):
  self.date = date
  self.peopledata = {}

def addcommit(peopledata, person):
 if not peopledata.get(person):
  peopledata[person] = {'adds':0, 'removes':0, 'commits':1}
 else:
  peopledata[person]['commits'] += 1

def cat(inf):
 global goodext
 peopledata = {}
 dates = []
 import signal
 signal.signal(signal.SIGINT, signal.SIG_IGN)
 try:
  linecnt = 0
  goodfile = False
  for line in inf:
   line = line.strip()
   if line.startswith('Author:'):
    goodfile = False
    person = line.partition(' ')[2].partition('<')[0].strip()
   if line.startswith('Date:'):
    goodfile = False
    dateline = line.split()
    #print(dateline)
    month, day, year = dateline[2], dateline[3], dateline[5]
    #print(month)
    month = ('Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec').index(month) + 1
    day = int(day)
    year = int(year)
    date = '%.4i%.2i%.2i' % (year, month, day)
    if len(dates) <= 0 or dates[-1].date != date:
     dates.append(CommitDate(date))
    addcommit(peopledata, person)
    addcommit(dates[-1].peopledata, person)
   if line.startswith('+++ ') or line.startswith('--- '):
    if line.endswith('/dev/null'):
     continue
    ext = line.rsplit('.', 1)[-1].lower()
    goodfile = (ext in goodext)
    #if not goodfile:
    # print('Not counting extension', ext)
   if not goodfile:
    continue
   elif line[:1] == '+':
    peopledata[person]['adds'] += 1
    dates[-1].peopledata[person]['adds'] += 1
   elif line[:1] == '-':
    peopledata[person]['removes'] += 1
    dates[-1].peopledata[person]['removes'] += 1
   else:
    continue
   linecnt += 1
   if linecnt % 10000 == 0:
    print('.', file=sys.stderr)
 except KeyboardInterrupt:
  pass
 return peopledata, dates

if __name__=='__main__':
 import codecs
 sys.stdin = codecs.getreader('utf8')(sys.stdin.detach(), errors='ignore')
 peopledata, dates = cat(sys.stdin)
 print()
 print()
 printflatstats(peopledata)
 print()
 printdatestats(peopledata, dates)