mscs.py

#!/usr/bin/env python3

import requests
import pandas as pd
import matplotlib.pyplot as plt

# Replace these with your own repository details and personal access token
GITHUB_TOKEN = 'hunter42'
REPO_OWNER = 'matrix-org'
REPO_NAME = 'matrix-doc'


# Function to get pull requests with labels and created date from GitHub
def get_pull_requests(repo_owner, repo_name, token):
    url = f'https://api.github.com/repos/{repo_owner}/{repo_name}/pulls'
    headers = {'Authorization': f'token {token}'}
    params = {'state': 'all'}
    pull_requests = []
    page = 1
    
    while True:
        response = requests.get(url, headers=headers, params={**params, 'page': page})
        if response.status_code != 200:
            raise Exception(f"Failed to fetch pull requests: {response.status_code}")
        
        prs = response.json()
        if not prs:
            break
        
        for pr in prs:
            proposal = [True for label in pr['labels'] if label['name'] == 'proposal']
            if not proposal:
                continue
            #labels = [label['name'] for label in pr['labels'] if label['name'] in ['kind:core', 'kind:feature', 'kind:maintenance']]
            #if len(labels) == 0:
            #    labels = ["other"]
            if pr['state'] == 'closed':
                labels = ['merged'] if [True for label in pr['labels'] if label['name'] == 'merged'] else ['closed']
            else:
                labels = ['open']
            created_at = pr['created_at']
            pull_requests.append({'number': pr['number'], 'labels': labels, 'created_at': created_at})
        
        page += 1

    return pull_requests

# Fetch pull requests
pull_requests = get_pull_requests(REPO_OWNER, REPO_NAME, GITHUB_TOKEN)

# Convert the data to a DataFrame
df = pd.DataFrame(pull_requests)
df['created_at'] = pd.to_datetime(df['created_at']).dt.date

# Expand the DataFrame to have one row per label
expanded_rows = []
for index, row in df.iterrows():
    for label in row['labels']:
        expanded_rows.append({'created_at': row['created_at'], 'label': label})

labels_df = pd.DataFrame(expanded_rows)

# Group by date and label to count occurrences
labels_counts = labels_df.groupby(['created_at', 'label']).size().unstack(fill_value=0)

# Compute the cumulative sum
cumulative_counts = labels_counts.cumsum()

# Plot the data as a stacked area graph
plt.figure(figsize=(14, 8))
cumulative_counts.plot.area(ax=plt.gca())
plt.xlabel('Date')
plt.ylabel('Cumulative Number of MSCs')
plt.title('Cumulative Number of MSCs by Kind Over Time')
plt.legend(title='Labels', bbox_to_anchor=(1.05, 1), loc='upper left')
plt.tight_layout()
plt.show()