def project(path):
p = ProjectDirectory(working_dir=path)
# get the commit history
ch = p.commit_history(
'master',
limit=None,
include_globs=['*.py'],
ignore_globs=['lib/*', 'docs/*', 'test/*', 'tests/*', 'tests_t/*'],
days=7)
print(ch.head)
# 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', 'net'
]).groupby(['committer'])
attr = attr.agg({
'lines': np.sum,
'insertions': np.sum,
'deletions': np.sum,
'net': np.sum
})
print(attr)
def get_repo_details(repo_name):
settings = get_settings()
project_dir = settings.get('project_dir', os.getcwd())
extensions = settings.get('extensions', None)
ignore_dir = settings.get('ignore_dir', None)
repos = ProjectDirectory(working_dir=project_dir)
out = []
for repo in repos.repos:
if repo._repo_name() == repo_name:
df = repo.file_detail(extensions=extensions, ignore_dir=ignore_dir)
df = df.reset_index(level=2)
df = df.sort_values(by=['loc'], ascending=False)
df.reset_index(inplace=True)
for idx in range(df.shape[0]):
out.append({
'file_name':
df.loc[idx, 'file'],
'loc':
df.loc[idx, 'loc'],
'owner':
df.loc[idx, 'file_owner'],
'extension':
df.loc[idx, 'ext'],
'last_edit':
df.loc[idx, 'last_edit_date'].strftime('%H:%M %d-%m-%Y'),
'clean_file_name':
df.loc[idx, 'file'].replace('/', '-')
})
return out
def get_file_change_rates():
settings = get_settings()
project_dir = settings.get('project_dir', os.getcwd())
extensions = settings.get('extensions', None)
ignore_dir = settings.get('ignore_dir', None)
repo = ProjectDirectory(working_dir=project_dir)
cb = repo.file_change_rates(extensions=extensions,
ignore_dir=ignore_dir,
coverage=True,
days=7)
cb.reset_index(level=0, inplace=True)
data = json.loads(cb.to_json(orient='records'))
output = {'data': []}
for blob in data:
row = [
blob.get(x, None) for x in [
'index', 'repository', 'unique_committers',
'net_rate_of_change', 'edit_rate', 'total_lines', 'coverage'
]
]
row = [round(x, 2) if isinstance(x, float) else x for x in row]
output['data'].append(row)
return output
def week_leader_board(n=5):
settings = get_settings()
project_dir = settings.get('project_dir', os.getcwd())
extensions = settings.get('extensions', None)
ignore_dir = settings.get('ignore_dir', None)
repo = ProjectDirectory(working_dir=project_dir)
ch = repo.commit_history(branch='master',
extensions=extensions,
ignore_dir=ignore_dir,
limit=None,
days=21)
metric = 'net'
print(ch)
leader_board = {
'top_committers': [],
'top_repositories': [],
'top_extensions': []
}
committers = ch.groupby(['committer']).agg({metric: np.sum})
committers.reset_index(inplace=True)
committers = committers.sort_values(by=[metric], ascending=False)
leader_board['top_committers'] = [{
'label': x[0],
'net': int(x[1]),
'rank': idx + 1
} for idx, x in enumerate(committers.values.tolist()[:n])]
repos = ch.groupby(['repository']).agg({metric: np.sum})
repos.reset_index(inplace=True)
repos = repos.sort_values(by=[metric], ascending=False)
leader_board['top_repositories'] = [{
'label': x[0],
'net': int(x[1]),
'rank': idx + 1
} for idx, x in enumerate(repos.values.tolist()[:n])]
if extensions is not None:
ext_ranks = []
for ext in extensions:
ch = repo.commit_history(branch='master',
extensions=[ext],
ignore_dir=ignore_dir,
days=21)
ext_ranks.append((ch[metric].sum(), ext))
ext_ranks = sorted(ext_ranks, key=lambda x: x[0], reverse=True)[:n]
leader_board['top_extensions'] = [{
'label': x[1],
'net': int(x[0]),
'rank': idx + 1
} for idx, x in enumerate(ext_ranks)]
return leader_board
def get_punchcard():
settings = get_settings()
project_dir = settings.get('project_dir', os.getcwd())
extensions = settings.get('extensions', None)
ignore_dir = settings.get('ignore_dir', None)
repo = ProjectDirectory(working_dir=project_dir)
pc = repo.punchcard(branch='master',
extensions=extensions,
ignore_dir=ignore_dir)
data_set = []
for idx in range(pc.shape[0]):
data_set.append([
pc.loc[idx, 'day_of_week'], pc.loc[idx, 'hour_of_day'],
pc.loc[idx, 'net']
])
return data_set
def cumulative_blame(by, file_stub):
settings = get_settings()
project_dir = settings.get('project_dir', os.getcwd())
extensions = settings.get('extensions', None)
ignore_dir = settings.get('ignore_dir', None)
repo = ProjectDirectory(working_dir=project_dir)
print(extensions)
print(ignore_dir)
print(by)
cb = repo.cumulative_blame(branch='master',
extensions=extensions,
ignore_dir=ignore_dir,
by=by,
num_datapoints=100,
skip=None,
limit=None)
cb = cb[~cb.index.duplicated()]
t = json.loads(cb.to_json(orient='columns'))
d3_data = []
for committer in t.keys():
blob = dict()
blob['key'] = committer
blob['values'] = []
for data_point in t[committer].keys():
blob['values'].append(
[int(float(data_point)), t[committer][data_point]])
blob['values'] = sorted(blob['values'], key=lambda x: x[0])
d3_data.append(blob)
# dump the data to disk
filename = get_file_prefix() + file_stub
json.dump(
d3_data,
open(
str(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) +
os.sep + 'static' + os.sep + 'data' + os.sep + filename, 'w'),
indent=4)
return True
import os
from gitpandas import ProjectDirectory
from definitions import GIT_PANDAS_DIR
__author__ = 'willmcginnis'
if __name__ == '__main__':
g = ProjectDirectory(working_dir=GIT_PANDAS_DIR)
b = g.file_detail(include_globs=['*.py'], ignore_globs=['lib/*', 'docs/*'])
print(b.head(25))
def setUp(self):
"""
:return:
"""
project_dir = str(os.path.dirname(
os.path.abspath(__file__))) + os.sep + 'repos'
repo1_dir = str(os.path.dirname(os.path.abspath(
__file__))) + os.sep + 'repos' + os.sep + 'repository1'
repo2_dir = str(os.path.dirname(os.path.abspath(
__file__))) + os.sep + 'repos' + os.sep + 'repository2'
if os.path.exists(project_dir):
shutil.rmtree(project_dir)
os.makedirs(project_dir)
if not os.path.exists(repo1_dir):
os.makedirs(repo1_dir)
if not os.path.exists(repo2_dir):
os.makedirs(repo2_dir)
# create an empty repo (but not bare)
grepo1 = git.Repo.init(repo1_dir)
grepo2 = git.Repo.init(repo2_dir)
# add a file
with open(repo1_dir + os.sep + 'README.md', 'w') as f:
f.write('Sample README for a sample python project\n')
# add a file
with open(repo2_dir + os.sep + 'README.md', 'w') as f:
f.write('Sample README for a sample js project\n')
# commit them
grepo1.git.add('README.md')
grepo1.git.commit(m='first commit')
grepo2.git.add('README.md')
grepo2.git.commit(m='first commit')
# now add some other files:
for idx in range(5):
with open(repo1_dir + os.sep + 'file_%d.py' % (idx, ), 'w') as f:
f.write('import sys\nimport os\n')
time.sleep(2.0)
grepo1.git.add(all=True)
grepo1.git.commit(m=' "adding file_%d.py"' % (idx, ))
# now add some other files:
for idx in range(5):
with open(repo2_dir + os.sep + 'file_%d.js' % (idx, ), 'w') as f:
f.write('document.write("hello world!");\n')
time.sleep(2.0)
grepo2.git.add(all=True)
grepo2.git.commit(m=' "adding file_%d.js"' % (idx, ))
self.projectd_1 = ProjectDirectory(working_dir=[repo1_dir, repo2_dir],
verbose=True)
self.projectd_2 = ProjectDirectory(working_dir=project_dir,
verbose=True)
def setUp(self):
self.projectd = ProjectDirectory(
working_dir=['git://github.com/wdm0006/git-pandas.git'],
verbose=True)
"""
"""
from gitpandas.utilities.plotting import plot_punchcard
from gitpandas import ProjectDirectory
repo = ProjectDirectory(working_dir=[
'git://github.com/wdm0006/git-pandas.git',
'git://github.com/wdm0006/categorical_encoding.git',
'git://github.com/wdm0006/sklearn-extensions.git',
'git://github.com/wdm0006/pygeohash.git',
'git://github.com/wdm0006/petersburg.git',
'git://github.com/wdm0006/incomprehensible.git',
],
verbose=True)
by = None
punchcard = repo.punchcard(branch='master',
extensions=['py'],
by=by,
normalize=2500)
plot_punchcard(punchcard, metric='lines', title='punchcard', by=by)
from gitpandas.utilities.plotting import plot_cumulative_blame
from gitpandas import ProjectDirectory
g = ProjectDirectory(working_dir=['git://github.com/rhiever/tpot.git'])
blame = g.cumulative_blame(branch='master',
extensions=['py', 'html', 'sql', 'md'],
by='committer',
limit=None,
skip=None)
plot_cumulative_blame(blame)
"""
"""
from gitpandas.utilities.plotting import plot_punchcard
from gitpandas import ProjectDirectory
g = ProjectDirectory(working_dir=[...], verbose=True)
by = None
punchcard = g.punchcard(branch='master',
include_globs=['*.py'],
by=by,
normalize=2500)
plot_punchcard(punchcard, metric='lines', title='punchcard', by=by)
def get_repo_names():
settings = get_settings()
project_dir = settings.get('project_dir', os.getcwd())
repos = ProjectDirectory(working_dir=project_dir)
repo_names = [str(x._repo_name()) for x in repos.repos]
return repo_names
""" """ from gitpandas.utilities.plotting import plot_punchcard from gitpandas import ProjectDirectory from definitions import GIT_PANDAS_DIR g = ProjectDirectory(working_dir=[str(GIT_PANDAS_DIR)], verbose=True) by = None punchcard = g.punchcard(branch='master', include_globs=['*.py'], by=by, normalize=2500) plot_punchcard(punchcard, metric='lines', title='punchcard', by=by)
import os
from gitpandas import ProjectDirectory
__author__ = 'willmcginnis'
if __name__ == '__main__':
g = ProjectDirectory(working_dir=os.path.abspath('../..'))
b = g.blame(extensions=['py'], ignore_dir=['lib', 'docs'])
info = g.repo_information()
print(info)
print(b)
def setup_repos_object():
settings = get_settings()
project_dir = settings.get('project_dir', os.getcwd())
extensions = settings.get('extensions', None)
ignore_dir = settings.get('ignore_dir', None)
repo = ProjectDirectory(working_dir=project_dir)
from gitpandas.utilities.plotting import plot_cumulative_blame
from gitpandas import GitHubProfile, ProjectDirectory
__author__ = 'willmcginnis'
if __name__ == '__main__':
#g = GitHubProfile(username='******', ignore_forks=True, verbose=True)
g = ProjectDirectory(
working_dir=
'/Users/willmcginnis/Documents/Helton/projects/webapps/salesproph')
blame = g.cumulative_blame(branch='master',
extensions=['py', 'html', 'sql', 'md'],
by='project',
ignore_dir=['docs'],
limit=None,
skip=None)
plot_cumulative_blame(blame)
