Cloud usage

import sys
from pathlib import Path

import pandas as pd
import plotly.express as px
import yaml

sys.path.insert(0, str(Path("_scripts/cloud").resolve()))
from filters import drop_clusters, drop_hubs

DATA = Path("_data")
meta = yaml.safe_load((DATA / "release_metadata.yml").read_text())

df_unique = pd.read_csv(DATA / "maus-unique-by-cluster.csv")
df_unique["date"] = pd.to_datetime(df_unique["date"])
df_unique = drop_clusters(df_unique)
df_unique = df_unique[df_unique["unique_users"] > 0]

df_hub = pd.read_csv(DATA / "maus-by-hub.csv")
df_hub["date"] = pd.to_datetime(df_hub["date"])
df_hub = drop_clusters(df_hub)
df_hub = drop_hubs(df_hub)
df_hub = df_hub.dropna(subset=["users"])
df_hub = df_hub[df_hub["users"] > 0]

n_clusters = df_unique["cluster"].nunique()
n_hubs = df_hub.groupby(["cluster", "hub"]).ngroups
last_updated = meta["publishedAt"].strftime("%Y-%m-%d %H:%M UTC")

order = (
    df_unique.groupby("cluster")["unique_users"].mean()
    .sort_values(ascending=False).index.tolist()
)
fig = px.area(
    df_unique.sort_values("date"),
    x="date", y="unique_users", color="cluster",
    category_orders={"cluster": order},
    title="Unique monthly users across all 2i2c clusters",
    labels={"unique_users": "users"},
)
fig.show()

hubs_per = (
    df_hub.groupby(["cluster", "date"])["hub"].nunique()
    .reset_index(name="hubs")
)
order_hubs = (
    hubs_per.groupby("cluster")["hubs"].max()
    .sort_values(ascending=False).index.tolist()
)
fig = px.area(
    hubs_per,
    x="date", y="hubs", color="cluster",
    category_orders={"cluster": order_hubs},
    title="Number of active hubs by cluster",
)
fig.show()