def blasphemy_ccp_cochange_by_dev_num_group(repo_file_quality_per_year,
repo_file_blasphemy_per_year):
"""
Note that repo_file_quality_per_year uses bug hit ratio and not ccp.
For change analysis it doesn't matter.
:param repo_file_quality_per_year:
:return:
"""
key = 'repo_name'
control_variables = ['dev_num_group']
repo_file_quality_per_year_df = build_repo_per_year_df(
repo_file_quality_per_year,
key=key,
control_variables=control_variables)
repo_file_blasphemy_per_year_df = build_repo_per_year_df(
repo_file_blasphemy_per_year,
key=key,
control_variables=control_variables)
per_year_df = pd.merge(repo_file_quality_per_year_df,
repo_file_blasphemy_per_year_df,
on=[key, 'year'] + control_variables)
cochange_analysis_by_value(per_year_df,
first_metric='corrective_commits_ratio',
second_metric='blasphemy_hit_rates',
first_the_higher_the_better=False,
second_the_higher_the_better=False,
first_sig_threshold=0.1,
second_sig_threshold=0.01,
fixed_variable='dev_num_group',
fixed_values=['small', 'medium', 'large'],
key=key,
control_variables=control_variables)
def onboarding_ccp_cochange(repo_file_quality_per_year,
repo_file_onboarding_per_year):
"""
Note that repo_file_quality_per_year uses bug hit ratio and not ccp.
For change analysis it doesn't matter.
:param repo_file_quality_per_year:
:return:
"""
key = 'repo_name'
repo_file_quality_per_year_df = build_repo_per_year_df(
repo_file_quality_per_year, key=key)
repo_file_onboarding_per_year_df = build_repo_per_year_df(
repo_file_onboarding_per_year, key=key)
repo_file_onboarding_per_year_df = repo_file_onboarding_per_year_df[
repo_file_onboarding_per_year_df.comming_developers > 9]
per_year_df = pd.merge(repo_file_quality_per_year_df,
repo_file_onboarding_per_year_df,
on=[key, 'year'])
per_year_df['ccp'] = per_year_df.corrective_commits_ratio.map(
lambda x: ccp_estimator.estimate_positives(x))
cochange_analysis(per_year_df,
first_metric='ccp',
second_metric='comming_involved_developers_ratio',
first_the_higher_the_better=False,
second_the_higher_the_better=True,
first_sig_threshold=0.1,
second_sig_threshold=0.1,
key=key)
def blasphemy_ccp_cochange(repo_file_quality_per_year,
repo_file_blasphemy_per_year):
"""
Note that repo_file_quality_per_year uses bug hit ratio and not ccp.
For change analysis it doesn't matter.
:param repo_file_quality_per_year:
:return:
"""
key = 'repo_name'
repo_file_quality_per_year_df = build_repo_per_year_df(
repo_file_quality_per_year, key=key)
repo_file_blasphemy_per_year_df = build_repo_per_year_df(
repo_file_blasphemy_per_year, key=key)
per_year_df = pd.merge(repo_file_quality_per_year_df,
repo_file_blasphemy_per_year_df,
on=[key, 'year'])
cochange_analysis(per_year_df,
first_metric='corrective_commits_ratio',
second_metric='blasphemy_hit_rates',
first_the_higher_the_better=False,
second_the_higher_the_better=False,
first_sig_threshold=0.1,
second_sig_threshold=0.01,
key=key)
def churn_ccp_cochange_by_age(repo_file_quality_per_year,
repo_file_churn_per_year):
"""
Note that repo_file_quality_per_year uses bug hit ratio and not ccp.
For change analysis it doesn't matter.
:param repo_file_quality_per_year:
:return:
"""
key = 'repo_name'
control_variables = ['age_group']
repo_file_quality_per_year_df = build_repo_per_year_df(
repo_file_quality_per_year,
key=key,
control_variables=control_variables)
repo_file_churn_per_year_df = build_repo_per_year_df(
repo_file_churn_per_year, key=key, control_variables=control_variables)
repo_file_churn_per_year_df = repo_file_churn_per_year_df[(
repo_file_churn_per_year_df.base_year_developers > 9)]
per_year_df = pd.merge(repo_file_quality_per_year_df,
repo_file_churn_per_year_df,
on=[key, 'year'] + control_variables)
per_year_df['ccp'] = per_year_df.corrective_commits_ratio.map(
lambda x: ccp_estimator.estimate_positives(x))
cochange_analysis_by_value(per_year_df,
first_metric='ccp',
second_metric='continuing_developers_ratio',
first_the_higher_the_better=False,
second_the_higher_the_better=True,
first_sig_threshold=0.1,
second_sig_threshold=0.1,
fixed_variable='age_group',
fixed_values=['old', 'medium', 'young'],
key=key,
control_variables=control_variables)
def onboarding_ccp_cochange_by_lang(repo_file_quality_per_year,
repo_file_onboarding_per_year):
"""
Note that repo_file_quality_per_year uses bug hit ratio and not ccp.
For change analysis it doesn't matter.
:param repo_file_quality_per_year:
:return:
"""
key = 'repo_name'
fixed_variable = 'language'
control_variables = [fixed_variable]
repo_file_quality_per_year_df = build_repo_per_year_df(
repo_file_quality_per_year,
key=key,
control_variables=control_variables)
repo_file_churn_per_year_df = build_repo_per_year_df(
repo_file_onboarding_per_year,
key=key,
control_variables=control_variables)
repo_file_churn_per_year_df = repo_file_churn_per_year_df[
(repo_file_churn_per_year_df.comming_developers > 9)
& (repo_file_churn_per_year_df.language.isin(lang_name))]
per_year_df = pd.merge(repo_file_quality_per_year_df,
repo_file_churn_per_year_df,
on=[key, 'year'] + control_variables)
per_year_df['ccp'] = per_year_df.corrective_commits_ratio.map(
lambda x: ccp_estimator.estimate_positives(x))
cochange_analysis_by_value(
per_year_df,
first_metric='ccp',
second_metric='comming_involved_developers_ratio',
first_the_higher_the_better=False,
second_the_higher_the_better=True,
first_sig_threshold=0.1,
second_sig_threshold=0.1,
fixed_variable=fixed_variable,
fixed_values=lang_name,
key=key,
control_variables=control_variables)
def coupling_ccp_cochange(repo_file_quality_per_year,
repo_file_coupling_per_year):
"""
Note that repo_file_quality_per_year uses bug hit ratio and not ccp.
For change analysis it doesn't matter.
:param repo_file_quality_per_year:
:return:
"""
key = 'repo_name'
repo_file_quality_per_year_df = build_repo_per_year_df(
repo_file_quality_per_year, key=key)
repo_file_coupling_per_year_df = build_repo_per_year_df(
repo_file_coupling_per_year, key=key)
per_year_df = pd.merge(repo_file_quality_per_year_df,
repo_file_coupling_per_year_df,
on=[key, 'year'])
repos = get_valid_repos()
per_year_df = pd.merge(per_year_df, repos, on=[key])
cochange_analysis(per_year_df,
first_metric='corrective_commits_ratio',
second_metric='avg_capped_files',
first_the_higher_the_better=False,
second_the_higher_the_better=False,
first_sig_threshold=0.1,
second_sig_threshold=1,
key=key)
cochange_with_control(per_year_df,
first_metric='corrective_commits_ratio',
second_metric='avg_capped_files',
first_the_higher_the_better=False,
second_the_higher_the_better=False,
first_sig_threshold=0.1,
second_sig_threshold=1,
key=key)
def blasphemy_ccp_cochange_by_lang(repo_file_quality_per_year,
repo_file_blasphemy_per_year):
"""
Note that repo_file_quality_per_year uses bug hit ratio and not ccp.
For change analysis it doesn't matter.
:param repo_file_quality_per_year:
:return:
"""
key = 'repo_name'
control_variables = ['language']
#import pdb; pdb.set_trace()
repo_file_quality_per_year_df = build_repo_per_year_df(
repo_file_quality_per_year,
key=key,
control_variables=control_variables)
repo_file_blasphemy_per_year_df = build_repo_per_year_df(
repo_file_blasphemy_per_year,
key=key,
control_variables=control_variables)
repo_file_blasphemy_per_year_df = repo_file_blasphemy_per_year_df[(
repo_file_blasphemy_per_year_df.language.isin(lang_name))]
per_year_df = pd.merge(repo_file_quality_per_year_df,
repo_file_blasphemy_per_year_df,
on=[key, 'year'] + control_variables)
cochange_analysis_by_value(per_year_df,
first_metric='corrective_commits_ratio',
second_metric='blasphemy_hit_rates',
first_the_higher_the_better=False,
second_the_higher_the_better=False,
first_sig_threshold=0.1,
second_sig_threshold=0.01,
fixed_variable='language',
fixed_values=lang_name,
key=key,
control_variables=control_variables)
def run_blasphemy_stability():
key = 'repo_name'
repo_file_blasphemy_per_year = os.path.join(
DATA_PATH, 'ccp_by_quality_terms_by_repo_per_year.csv')
repo_file_blasphemy_per_year_df = build_repo_per_year_df(
repo_file_blasphemy_per_year, key=key)
print(
analyze_stability(repo_file_blasphemy_per_year_df,
key=key,
metric_name='blasphemy_hit_rates',
time_column='year',
minimal_time=EARLIEST_ANALYZED_YEAR,
control_variables=[],
min_cnt_column='commits',
min_cnt_threshold=200))