Get the insertions and deletions for the last six months

git-stats.sh

#!/bin/bash
# Get the insertions and deletions for the last six months

git log --since 'last 6 months' --shortstat master > stats.log

stats.py

#!/usr/bin/env python

from collections import defaultdict
from pprint import pprint

KEYS = {
     'deletion(-)':    'deletions',
     'deletions(-)':   'deletions',
     'file changed':   'files changed',
     'files changed':  'files changed',
     'insertion(+)':   'insertions',
     'insertions(+)':  'insertions'}

stats = defaultdict(lambda:0)

with open('stats.log', 'r') as f:
    content = f.read()

for line in content.split("\n"):
    line = line.strip()
    shortstats = line.split(',')

    for shortstat in shortstats:
        if shortstat == '':
            continue

        shortstat = shortstat.strip()
        shortstat_list = shortstat.split(' ', 1)
        value, key = shortstat_list
        stats[KEYS[key]] += int(value)

pprint(dict(stats))

This worked nicely but there were some commits which were major outliers (like a two million line json file that was accidentally checked in)

Usage:

./git-stats.sh > stats.log
./stats.py