Update app.py

app.py

@@ -10,13 +10,15 @@ from cachetools import TTLCache, cached
 from datetime import datetime, timedelta
 from datasets import Dataset
 import os
+from functools import lru_cache
+import pandas as pd
+from toolz import frequencies
 
-token = os.getenv("HUGGINGFACE_TOKEN")
+token = os.environ["HUGGINGFACE_TOKEN"]
 assert token
 librarian_bot_avatar = "https://aeiljuispo.cloudimg.io/v7/https://s3.amazonaws.com/moonup/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg?w=200&h=200&f=face"
 
 
-@cached(cache=TTLCache(maxsize=1000, ttl=timedelta(minutes=10), timer=datetime.now))
 def get_hub_community_activity(user: str) -> List[Any]:
     all_data = []
     for i in range(1, 2000, 100):
@@ -59,11 +61,11 @@ def update_data():
     data = [parse_pr_data(d) for d in data]
     update_df = pl.DataFrame(data)
     df = pl.concat([previous_df, update_df]).unique()
-    Dataset(df.to_arrow()).push_to_hub("librarian-bot/stats", token=token)
+    if len(df) != len(previous_df):
+        Dataset(df.to_arrow()).push_to_hub("librarian-bot/stats", token=token)
     return df
 
 
-
 # def get_pr_status():
 #     df = update_data()
 #     df = df.filter(pl.col("isPullRequest") is True)
@@ -71,12 +73,26 @@ def update_data():
 #     # return frequencies(x["status"] for x in pr_data)
 
 
+@lru_cache(maxsize=512)
+def get_pr_status(user: str):
+    all_data = get_hub_community_activity(user)
+    pr_data = (
+        x["discussionData"] for x in all_data if x["discussionData"]["isPullRequest"]
+    )
+    return frequencies(x["status"] for x in pr_data)
+
+
 def create_pie():
-    df = update_data()
-    df = df.filter(pl.col("isPullRequest") is True)
-    df = df["status"].value_counts().to_pandas()
-    fig = px.pie(df, values="counts", names="status", template="seaborn")
-    return gr.Plot(fig)
+    frequencies = get_pr_status("librarian-bot")
+    df = pd.DataFrame({"status": frequencies.keys(), "number": frequencies.values()})
+    return px.pie(df, values="number", names="status", template="seaborn")
+
+
+# def create_pie():
+#     df = update_data()
+#     df = df.filter(pl.col("isPullRequest") is True)
+#     df = df["status"].value_counts().to_pandas()
+#     return px.pie(df, values="counts", names="status", template="seaborn")
 
 
 def group_status_by_pr_number():
@@ -102,7 +118,8 @@ def plot_over_time():
     df = df.to_pandas().set_index("createdAt").cumsum()
     return px.line(df, x=df.index, y=[c for c in df.columns if c != "sum"])
 
-df = update_data()
+
+create_pie()
 
 with gr.Blocks() as demo:
     # frequencies = get_pr_status("librarian-bot")
@@ -114,7 +131,7 @@ with gr.Blocks() as demo:
             "The below pie chart shows the percentage of pull requests made by"
             " librarian bot that are open, closed or merged"
         )
-        create_pie()
+        gr.Plot(create_pie())
     with gr.Column():
         gr.Markdown("Pull requests opened, closed and merged over time (cumulative)")
         gr.Plot(plot_over_time())