Document repo analytics

.github/analytics/README.md

@@ -0,0 +1,18 @@
+# Repo Analytics
+
+To run the repo analytics follow the steps below:
+
+1. You must have a Github token, if you don't have one you can create one by following [this guide](https://docs.github.com/en/enterprise-server@3.4/authentication/keeping-your-account-and-data-secure/creating-a-personal-access-token).
+2. Install the requirements:
+
+```bash
+pip install -r .github/analytics/requirements.txt
+```
+3. Run the analytics:
+
+```bash
+GITHUB_TOKEN=<token> \
+python .github/analytics/get_repo_metrics.py \
+  --repo-owner google \
+  --repo-name flax
+```

.github/analytics/get_repo_metrics.py

@@ -17,6 +17,7 @@
 from datetime import datetime
 from pathlib import Path
 from typing import Callable, List
+from absl import app, flags
 
 import pandas as pd
 import requests
@@ -300,10 +301,14 @@ def _process_issues(df: pd.DataFrame) -> pd.Series:
 #-----------------------------------------------------------------------------
 # main
 #-----------------------------------------------------------------------------
-def main(
-    repo_owner: str = 'google',
-    repo_name: str = 'flax',
-):
+FLAGS = flags.FLAGS
+flags.DEFINE_string('repo_owner', 'google', 'User name or organization')
+flags.DEFINE_string('repo_name', 'flax', 'Name of the repository')
+
+def main(_):
+  repo_owner: str = FLAGS.repo_owner
+  repo_name: str = FLAGS.repo_name
+
   # Download issue data
   issues = GithubGrabber(
     '.github/analytics/issue_activity_since_date.gql',
@@ -407,4 +412,4 @@ def main(
   plt.show()
 
 if __name__ == '__main__':
-  main()
+  app.run(main)

.github/analytics/requirements.txt

@@ -0,0 +1,4 @@
+pandas
+absl-py
+requests
+matplotlib

setup.py

@@ -53,7 +53,6 @@
     "tensorflow_datasets",
     "tensorflow",
     "torch",
-    "pandas", # get_repo_metrics script
 ]
 
 __version__ = None