Run pre-commit manually

Author: yuvipanda

deployer/dev_commands/__init__.py

@@ -9,12 +9,12 @@
 import deployer.dev_commands.exec.infra_components  # noqa: F401
 import deployer.dev_commands.exec.promql  # noqa: F401
 import deployer.dev_commands.generate.billing.cost_table  # noqa: F401
-import deployer.dev_commands.generate.mau  # noqa: F401
 import deployer.dev_commands.generate.cryptnono_config  # noqa: F401
 import deployer.dev_commands.generate.dedicated_cluster.aws  # noqa: F401
 import deployer.dev_commands.generate.dedicated_cluster.gcp  # noqa: F401
 import deployer.dev_commands.generate.hub_asset.cluster_entry  # noqa: F401
 import deployer.dev_commands.generate.hub_asset.hub_files  # noqa: F401
+import deployer.dev_commands.generate.mau  # noqa: F401
 import deployer.dev_commands.generate.placeholders  # noqa: F401
 import deployer.dev_commands.generate.resource_allocation.daemonset_requests  # noqa: F401
 import deployer.dev_commands.generate.resource_allocation.generate_choices  # noqa: F401

deployer/dev_commands/generate/mau.py

@@ -1,22 +1,22 @@
+import calendar
+import csv
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
 from typing import Annotated, Optional
 
+import requests
+import typer
 from rich import progress
-from rich.table import Table
 from rich.live import Live
-from deployer.cli_app import generate_app
-import typer
-import csv
-import calendar
-import requests
-from pathlib import Path
-from datetime import datetime, timedelta, timezone
+from rich.table import Table
 from yarl import URL
+
+from deployer.cli_app import generate_app
 from deployer.infra_components.cluster import Cluster
 
 # Usernames to ignore when calculating MAU
-USERNAMES_TO_IGNORE = set([
+USERNAMES_TO_IGNORE = {
     "deployment-service-check",
-
     # 2i2c staff GitHub IDs
     "agoose77",
     "choldgraf",
@@ -27,7 +27,6 @@
     "jnywong",
     "yuvipanda",
     "jmunroe",
-
     # 2i2c staff google ids
     "ahollands@2i2c.org",
     "choldgraf@2i2c.org",
@@ -37,14 +36,19 @@
     "hcampbell@2i2c.org",
     "jwong@2i2c.org",
     "yuvipanda@2i2c.org",
-    "jmunroe@2i2c.org"
-])
+    "jmunroe@2i2c.org",
+}
+
 
 @generate_app.command()
 def mau(
     month: str = typer.Argument(help="Month to generate MAU data for"),
-    cluster_name: Optional[str] = typer.Option(None, help="Restrict to just one cluster"),
-    csv_file: Annotated[Path | None, typer.Option(help="Output data to csv file at this path")] = None
+    cluster_name: Optional[str] = typer.Option(
+        None, help="Restrict to just one cluster"
+    ),
+    csv_file: Annotated[
+        Path | None, typer.Option(help="Output data to csv file at this path")
+    ] = None,
 ):
     """
     Generate MAU for all (or some) clusters for a given month
@@ -67,13 +71,21 @@ def mau(
         dates_progress = progress_bar.add_task("Days")
 
         for cluster in clusters:
-            progress_bar.update(clusters_progress, description=f"Processing {cluster.spec['name']}", advance=1)
-            promql_api = URL(f"{cluster.get_external_prometheus_url()}/api/v1/query_range")
+            progress_bar.update(
+                clusters_progress,
+                description=f"Processing {cluster.spec['name']}",
+                advance=1,
+            )
+            promql_api = URL(
+                f"{cluster.get_external_prometheus_url()}/api/v1/query_range"
+            )
 
             time_parts = month.split("-", 2)
 
             # Explicitly construct the datetime as UTC, so we get standardized MAU for all our clusters
-            start_date = datetime(int(time_parts[0]), int(time_parts[1]), 1, tzinfo=timezone.utc)
+            start_date = datetime(
+                int(time_parts[0]), int(time_parts[1]), 1, tzinfo=timezone.utc
+            )
 
             # Get all pods that start with jupyter-.*, and treat them as user servers.
             # We could join with kube_pod_labels for a more accurate version of this.
@@ -98,12 +110,16 @@ def mau(
                 start_time = start_date + timedelta(days=i)
                 end_time = start_time + timedelta(days=1) - timedelta(seconds=1)
 
-                progress_bar.update(dates_progress, completed=i, description=f"Processing {start_time.strftime('%Y-%m-%d')}")
+                progress_bar.update(
+                    dates_progress,
+                    completed=i,
+                    description=f"Processing {start_time.strftime('%Y-%m-%d')}",
+                )
                 params = {
                     "query": query,
                     "start": int(start_time.timestamp()),
                     "end": int(end_time.timestamp()),
-                    "step": "1m"
+                    "step": "1m",
                 }
 
                 query_api = promql_api.with_query(params)
@@ -113,16 +129,18 @@ def mau(
 
                 result = resp.json()["data"]["result"]
                 for row in result:
-                    username = row['metric']['annotation_hub_jupyter_org_username']
+                    username = row["metric"]["annotation_hub_jupyter_org_username"]
 
                     if username in USERNAMES_TO_IGNORE:
                         continue
 
                     # Since "step" is 1m, each value that is present indicates this pod was present
                     # for that minute. So the total number of values present indicates how long the
                     # user was active.
-                    minutes_active = len(row['values'])
-                    user_activity[username] = user_activity.get(username, 0) + minutes_active
+                    minutes_active = len(row["values"])
+                    user_activity[username] = (
+                        user_activity.get(username, 0) + minutes_active
+                    )
             cluster_activity[cluster.spec["name"]] = len(user_activity)
 
             table.add_row(cluster.spec["name"], str(len(user_activity)))
@@ -132,4 +150,4 @@ def mau(
             writer = csv.writer(f)
             writer.writerow(("cluster_name", "mau"))
             for name, active_users in cluster_activity.items():
-                writer.writerow((name, str(active_users)))
+                writer.writerow((name, str(active_users)))