ready for deployment of some sort

This commit is contained in:
mjgaughan 2023-11-05 11:11:03 -06:00
parent 3872f65c54
commit fd10bdfa33
2 changed files with 36 additions and 20 deletions

View File

@ -60,7 +60,7 @@ def get_discussion_gql(repo_owner, repo_name):
data_json = json.dumps(data)
headers = {'content-type': 'application/json', 'Accept-Charset': 'UTF-8', 'Authorization': 'bearer ' + key}
r = requests.post(url=url, data=data_json, headers=headers)
print(r.content)
#print(r.content)
return r
def within_time(comment_content, early_cutoff):

54
main.py
View File

@ -11,34 +11,50 @@ def main():
# we should discuss whether we're using the 93 day window that seems to be widely used or if we want a longer window
early_cutoff = dt.datetime(2023,10, 11)
print("Earliest date examined: " + str(early_cutoff))
#placeholder for now
manifest = '../kaylea_dissertation/lifecycle/package_metadata/jupyter-notebook_manifest.yaml'
with open(manifest, 'r') as stream:
largest_object = {}
#manifest = '../kaylea_dissertation/lifecycle/package_metadata/jupyter-notebook_manifest.yaml'
directory='../kaylea_dissertation/lifecycle/package_metadata/'
for filename in os.listdir(directory):
f = os.path.join(directory, filename)
# checking if it is a file
if os.path.isfile(f):
print(f)
get_everything(f, largest_object, early_cutoff)
#remove this and it should just run? for the most part at least I think
break
print(largest_object.keys())
def get_everything(manifest_path, largest_object, early_cutoff):
with open(manifest_path, 'r') as stream:
try:
config = yaml.safe_load(stream)
#below lines will probably need to be refactored as tasks expand
vcs_path = config['Upstream_VCS']
print("------------------")
print(vcs_path)
perceval_obj = pt.main(vcs_path, early_cutoff)
gha_obj = gha.main(vcs_path, early_cutoff)
#print("------------------")
#print(vcs_path)
repo_path = vcs_path[0]
largest_object[repo_path] = {}
largest_object[repo_path]["perceval_obj"] = pt.main(vcs_path, early_cutoff)
largest_object[repo_path]["gha_obj"] = gha.main(vcs_path, early_cutoff)
#these are the two variables in the denominator of the formality measure
print("Age of Project: " + str(perceval_obj['age_of_project']))
print('Contributor Count: ' + str(len(perceval_obj['contributors'])))
print('Collaborator Count: ' + str(len(perceval_obj['collaborators'])))
print('Number of Milestones: ' + str(gha_obj['milestone_count']))
new_mmt = compute_new_mmt(len(perceval_obj['contributors']), len(perceval_obj['collaborators']))
print('New MMT: ' + str(new_mmt))
old_mmt = compute_old_mmt(len(perceval_obj['contributors']), len(perceval_obj['collaborators']))
print('Old MMT: ' + str(old_mmt))
#print("Age of Project: " + str(largest_object[repo_path]["perceval_obj"]['age_of_project']))
#print('Contributor Count: ' + str(len(largest_object[repo_path]["perceval_obj"]['contributors'])))
#print('Collaborator Count: ' + str(len(largest_object[repo_path]["perceval_obj"]['collaborators'])))
#print('Number of Milestones: ' + str(largest_object[repo_path]["gha_obj"]['milestone_count']))
largest_object[repo_path]['new_mmt'] = compute_new_mmt(len(largest_object[repo_path]["perceval_obj"]['contributors']), len(largest_object[repo_path]["perceval_obj"]['collaborators']))
#print('New MMT: ' + str(largest_object[repo_path]['new_mmt']))
largest_object[repo_path]['old_mmt'] = compute_old_mmt(len(largest_object[repo_path]["perceval_obj"]['contributors']), len(largest_object[repo_path]["perceval_obj"]['collaborators']))
#print('Old MMT: ' + str(largest_object[repo_path]['old_mmt']))
#new mmt formality score
new_formality = compute_formality_score(new_mmt, gha_obj['milestone_count'], perceval_obj['age_of_project'])
print(new_formality)
largest_object[repo_path]['new_formality'] = compute_formality_score(largest_object[repo_path]['new_mmt'], largest_object[repo_path]["gha_obj"]['milestone_count'], largest_object[repo_path]["perceval_obj"]['age_of_project'])
print(largest_object[repo_path]['new_formality'])
# testing out beneath:
ghs_obj = ghs.main(vcs_path, early_cutoff)
print(ghs_obj["time_cleaned_comm"])
largest_object[repo_path]['ghs_obj'] = ghs.main(vcs_path, early_cutoff)
#print(ghs_obj["time_cleaned_comm"])
except yaml.YAMLOError as err:
print(err)
print("----------------------")
#this is Yoshi 2 MMT per van Meijel
def compute_new_mmt(contrib_count, collab_count):