def repository(path):
# build an example repository object and try some things out
ignore_dirs = [
'docs/*',
'tests/*',
'Data/*'
]
r = Repository(path)
# is it bare?
print('\nRepo bare?')
print(r.is_bare())
print('\n')
# get the commit history
ch = r.commit_history('HEAD', limit=None, include_globs=['*.py'], ignore_globs=ignore_dirs)
print(ch.head(5))
# get the list of committers
print('\nCommiters:')
print(''.join([str(x) + '\n' for x in set(ch['committer'].values)]))
print('\n')
# print out everyone's contributions
attr = ch.reindex(columns=['committer', 'lines', 'insertions', 'deletions']).groupby(['committer'])
attr = attr.agg({
'lines': np.sum,
'insertions': np.sum,
'deletions': np.sum
})
print(attr)
# get the file change history
fh = r.file_change_history('HEAD', limit=None, ignore_globs=ignore_dirs)
fh['ext'] = fh['filename'].map(lambda x: x.split('.')[-1])
print(fh.head(50))
# print out unique extensions
print('\nExtensions Found:')
print(''.join([str(x) + '\n' for x in set(fh['ext'].values)]))
print('\n')
# agg by extension
etns = fh.reindex(columns=['ext', 'insertions', 'deletions']).groupby(['ext'])
etns = etns.agg({
'insertions': np.sum,
'deletions': np.sum
})
print(etns)
def repository(path):
# build an example repository object and try some things out
ignore_dirs = [
'docs/*',
'tests/*',
'Data/*'
]
r = Repository(path)
# is it bare?
print('\nRepo bare?')
print(r.is_bare())
print('\n')
# get the commit history
ch = r.commit_history('HEAD', limit=None, include_globs=['*.py'], ignore_globs=ignore_dirs)
print(ch.head(5))
# get the list of committers
print('\nCommiters:')
print(''.join([str(x) + '\n' for x in set(ch['committer'].values)]))
print('\n')
# print out everyone's contributions
attr = ch.reindex(columns=['committer', 'lines', 'insertions', 'deletions']).groupby(['committer'])
attr = attr.agg({
'lines': np.sum,
'insertions': np.sum,
'deletions': np.sum
})
print(attr)
# get the file change history
fh = r.file_change_history('HEAD', limit=None, ignore_globs=ignore_dirs)
fh['ext'] = fh['filename'].map(lambda x: x.split('.')[-1])
print(fh.head(50))
# print out unique extensions
print('\nExtensions Found:')
print(''.join([str(x) + '\n' for x in set(fh['ext'].values)]))
print('\n')
# agg by extension
etns = fh.reindex(columns=['ext', 'insertions', 'deletions']).groupby(['ext'])
etns = etns.agg({
'insertions': np.sum,
'deletions': np.sum
})
print(etns)
from gitpandas import Repository
import numpy as np
import lifelines
import matplotlib.pyplot as plt
import pandas as pd
plt.style.use('ggplot')
__author__ = 'willmcginnis'
if __name__ == '__main__':
threshold = 100
repo = Repository(working_dir='git://github.com/scikit-learn/scikit-learn.git', verbose=True)
fch = repo.file_change_history(limit=None, extensions=['py'])
fch['file_owner'] = ''
fch['refactor'] = 0
fch['timestamp'] = fch.index.astype(np.int64) // (24 * 3600 * 10**9)
fch['observed'] = False
fch = fch.reindex()
fch = fch.reset_index()
# add in the file owner and whether or not each item is a refactor
for idx, row in fch.iterrows():
fch.set_value(idx, 'file_owner', repo.file_owner(row.rev, row.filename))
if abs(row.insertions - row.deletions) > threshold:
fch.set_value(idx, 'refactor', 1)
else:
fch.set_value(idx, 'refactor', 0)
# add in the time since column
class TestLocalProperties(unittest.TestCase):
"""
"""
def setUp(self):
"""
:return:
"""
project_dir = str(os.path.dirname(
os.path.abspath(__file__))) + os.sep + 'repos'
repo_dir = str(os.path.dirname(os.path.abspath(
__file__))) + os.sep + 'repos' + os.sep + 'repository1'
if os.path.exists(project_dir):
shutil.rmtree(project_dir)
os.makedirs(project_dir)
if not os.path.exists(repo_dir):
os.makedirs(repo_dir)
# create an empty repo (but not bare)
grepo = git.Repo.init(repo_dir)
# add a file
with open(repo_dir + os.sep + 'README.md', 'w') as f:
f.write('Sample README for a sample project\n')
# commit it
grepo.git.add('README.md')
grepo.git.commit(m='first commit')
# now add some other files:
for idx in range(5):
with open(repo_dir + os.sep + 'file_%d.py' % (idx, ), 'w') as f:
f.write('import sys\nimport os\n')
time.sleep(2.0)
grepo.git.add(all=True)
grepo.git.commit(m='adding file_%d.py' % (idx, ))
self.repo = Repository(working_dir=repo_dir, verbose=True)
def tearDown(self):
self.repo.__del__()
project_dir = str(os.path.dirname(
os.path.abspath(__file__))) + os.sep + 'repos'
shutil.rmtree(project_dir)
def test_repo_name(self):
self.assertEqual(self.repo._repo_name(), 'repository1')
def test_branches(self):
branches = list(self.repo.branches()['branch'].values)
self.assertIn('master', branches)
def test_tags(self):
tags = list(self.repo.tags()['tag'].values)
self.assertEqual(len(tags), 0)
def test_is_bare(self):
self.assertFalse(self.repo.is_bare())
def test_commit_history(self):
ch = self.repo.commit_history(branch='master')
self.assertEqual(ch.shape[0], 6)
ch2 = self.repo.commit_history(branch='master', extensions=['py'])
self.assertEqual(ch2.shape[0], 5)
ch3 = self.repo.commit_history(branch='master', limit=3)
self.assertEqual(ch3.shape[0], 3)
ch4 = self.repo.commit_history(branch='master', days=5)
self.assertEqual(ch4.shape[0], 6)
fch = self.repo.file_change_history(branch='master')
self.assertEqual(fch.shape[0], 6)
fch2 = self.repo.file_change_history(branch='master',
extensions=['py'])
self.assertEqual(fch2.shape[0], 5)
fch3 = self.repo.file_change_history(branch='master', limit=3)
self.assertEqual(fch3.shape[0], 3)
fcr = self.repo.file_change_rates(branch='master')
self.assertEqual(fcr.shape[0], 6)
self.assertEqual(fcr['unique_committers'].sum(), 6)
self.assertEqual(fcr['net_change'].sum(), 11)
# we know this repo doesnt have coverage
self.assertFalse(self.repo.has_coverage())
# we know this repo only has one committer
self.assertEqual(
self.repo.bus_factor(by='repository')['bus factor'].values[0], 1)
# lets do some blaming
blame = self.repo.blame(extensions=['py'])
self.assertEqual(blame['loc'].sum(), 10)
self.assertEqual(blame.shape[0], 1)
cblame = self.repo.cumulative_blame()
self.assertEqual(cblame.shape[0], 6)
self.assertEqual(cblame[cblame.columns.values[0]].sum(), 36)
revs = self.repo.revs(num_datapoints=2)
self.assertEqual(revs.shape[0], 2)
revs = self.repo.revs(limit=2)
self.assertEqual(revs.shape[0], 2)
revs = self.repo.revs()
self.assertEqual(revs.shape[0], 6)
from gitpandas import Repository
import numpy as np
import lifelines
import matplotlib.pyplot as plt
__author__ = 'willmcginnis'
if __name__ == '__main__':
threshold = 5
repo = Repository(
working_dir='git://github.com/CamDavidsonPilon/lifelines.git')
fch = repo.file_change_history(limit=None, extensions=['py'])
fch['file_owner'] = ''
fch['refactor'] = 0
fch['timestamp'] = fch.index.astype(np.int64) // (24 * 3600 * 10**9)
fch['observed'] = False
fch = fch.reindex()
fch = fch.reset_index()
# add in the file owner and whether or not each item is a refactor
for idx, row in fch.iterrows():
fch.set_value(idx, 'file_owner',
repo.file_owner(row.rev, row.filename))
if abs(row.insertions - row.deletions) > threshold:
fch.set_value(idx, 'refactor', 1)
else:
fch.set_value(idx, 'refactor', 0)
# add in the time since column
fch['time_until_refactor'] = 0
from gitpandas import Repository
import numpy as np
import lifelines
import matplotlib.pyplot as plt
plt.style.use('ggplot')
__author__ = 'willmcginnis'
if __name__ == '__main__':
threshold = 100
repo = Repository(
working_dir='git://github.com/scikit-learn/scikit-learn.git',
verbose=True)
fch = repo.file_change_history(limit=None, include_globs=['*.py'])
fch['file_owner'] = ''
fch['refactor'] = 0
fch['timestamp'] = fch.index.astype(np.int64) // (24 * 3600 * 10**9)
fch['observed'] = False
fch = fch.reindex()
fch = fch.reset_index()
# add in the file owner and whether or not each item is a refactor
for idx, row in fch.iterrows():
fch.set_value(idx, 'file_owner',
repo.file_owner(row.rev, row.filename))
if abs(row.insertions - row.deletions) > threshold:
fch.set_value(idx, 'refactor', 1)
else:
fch.set_value(idx, 'refactor', 0)
class TestLocalProperties(unittest.TestCase):
"""
"""
def setUp(self):
"""
:return:
"""
project_dir = str(os.path.dirname(os.path.abspath(__file__))) + os.sep + 'repos'
repo_dir = str(os.path.dirname(os.path.abspath(__file__))) + os.sep + 'repos' + os.sep + 'repository1'
if os.path.exists(project_dir):
shutil.rmtree(project_dir)
os.makedirs(project_dir)
if not os.path.exists(repo_dir):
os.makedirs(repo_dir)
# create an empty repo (but not bare)
grepo = git.Repo.init(repo_dir)
# add a file
with open(repo_dir + os.sep + 'README.md', 'w') as f:
f.write('Sample README for a sample project\n')
# commit it
grepo.git.add('README.md')
grepo.git.commit(m='first commit')
# now add some other files:
for idx in range(5):
with open(repo_dir + os.sep + 'file_%d.py' % (idx, ), 'w') as f:
f.write('import sys\nimport os\n')
time.sleep(2.0)
grepo.git.add(all=True)
grepo.git.commit(m='adding file_%d.py' % (idx, ))
self.repo = Repository(working_dir=repo_dir, verbose=True)
def tearDown(self):
self.repo.__del__()
project_dir = str(os.path.dirname(os.path.abspath(__file__))) + os.sep + 'repos'
shutil.rmtree(project_dir)
def test_repo_name(self):
self.assertEqual(self.repo.repo_name, 'repository1')
def test_branches(self):
branches = list(self.repo.branches()['branch'].values)
self.assertIn('master', branches)
def test_tags(self):
tags = list(self.repo.tags()['tag'].values)
self.assertEqual(len(tags), 0)
def test_is_bare(self):
self.assertFalse(self.repo.is_bare())
def test_commit_history(self):
ch = self.repo.commit_history(branch='master')
self.assertEqual(ch.shape[0], 6)
ch2 = self.repo.commit_history(branch='master', extensions=['py'])
self.assertEqual(ch2.shape[0], 5)
ch3 = self.repo.commit_history(branch='master', limit=3)
self.assertEqual(ch3.shape[0], 3)
ch4 = self.repo.commit_history(branch='master', days=5)
self.assertEqual(ch4.shape[0], 6)
fch = self.repo.file_change_history(branch='master')
self.assertEqual(fch.shape[0], 6)
fch2 = self.repo.file_change_history(branch='master', extensions=['py'])
self.assertEqual(fch2.shape[0], 5)
fch3 = self.repo.file_change_history(branch='master', limit=3)
self.assertEqual(fch3.shape[0], 3)
fcr = self.repo.file_change_rates(branch='master')
self.assertEqual(fcr.shape[0], 6)
self.assertEqual(fcr['unique_committers'].sum(), 6)
self.assertEqual(fcr['net_change'].sum(), 11)
# we know this repo doesnt have coverage
self.assertFalse(self.repo.has_coverage())
# we know this repo only has one committer
self.assertEqual(self.repo.bus_factor(by='repository')['bus factor'].values[0], 1)
# lets do some blaming
blame = self.repo.blame(extensions=['py'])
self.assertEqual(blame['loc'].sum(), 10)
self.assertEqual(blame.shape[0], 1)
cblame = self.repo.cumulative_blame()
self.assertEqual(cblame.shape[0], 6)
self.assertEqual(cblame[cblame.columns.values[0]].sum(), 36)
revs = self.repo.revs(num_datapoints=2)
self.assertEqual(revs.shape[0], 2)
revs = self.repo.revs(limit=2)
self.assertEqual(revs.shape[0], 2)
revs = self.repo.revs()
self.assertEqual(revs.shape[0], 6)
from gitpandas import Repository
import numpy as np
import lifelines
import matplotlib.pyplot as plt
threshold = 20
repo = Repository(working_dir='git://github.com/ogr3/race-management-system.git', verbose=True)
fch = repo.file_change_history(limit=100000, extensions=['py', 'pyx', 'h', 'c', 'cpp', 'java', 'xml'])
fch['file_owner'] = ''
fch['refactor'] = 0
fch['timestamp'] = fch.index.astype(np.int64) // (24 * 3600 * 10**9)
fch['observed'] = False
fch = fch.reindex()
fch = fch.reset_index()
# add in the file owner and whether or not each item is a refactor
for idx, row in fch.iterrows():
fch.set_value(idx, 'file_owner', repo.file_owner(row.rev, row.filename, committer=True))
if abs(row.insertions - row.deletions) > threshold:
fch.set_value(idx, 'refactor', 1)
else:
fch.set_value(idx, 'refactor', 0)
# add in the time since column
fch['time_until_refactor'] = 0
for idx, row in fch.iterrows():
ts = None
chunk = fch[(fch['timestamp'] > row.timestamp) & (fch['refactor'] == 1) & (fch['filename'] == row.filename)]
if chunk.shape[0] > 0:
ts = chunk['timestamp'].min()
fch.set_value(idx, 'observed', True)
from gitpandas import Repository
import numpy as np
import lifelines
import matplotlib.pyplot as plt
plt.style.use('ggplot')
__author__ = 'willmcginnis'
if __name__ == '__main__':
threshold = 100
repo = Repository(working_dir='git://github.com/scikit-learn/scikit-learn.git', verbose=True)
fch = repo.file_change_history(limit=None, include_globs=['*.py'])
fch['file_owner'] = ''
fch['refactor'] = 0
fch['timestamp'] = fch.index.astype(np.int64) // (24 * 3600 * 10**9)
fch['observed'] = False
fch = fch.reindex()
fch = fch.reset_index()
# add in the file owner and whether or not each item is a refactor
for idx, row in fch.iterrows():
fch.set_value(idx, 'file_owner', repo.file_owner(row.rev, row.filename))
if abs(row.insertions - row.deletions) > threshold:
fch.set_value(idx, 'refactor', 1)
else:
fch.set_value(idx, 'refactor', 0)
# add in the time since column
fch['time_until_refactor'] = 0
