Cache data

app.py

@@ -35,24 +35,23 @@ def fetch_data():
             )
     return pd.DataFrame(issues_data)
 
-def save_data(df):
-    df.to_json("issues.json", orient="records", indent=4, index=False)
+# def save_data(df):
+#     df.to_json("issues.json", orient="records", indent=4, index=False)
 
-@st.cache_data
-def load_data():
-    try:
-        df = pd.read_json("issues.json", convert_dates=["Created at", "Closed at", "Last update"], date_unit="ms")
-    except:
-        df = fetch_data()
-        save_data(df)
-    return df
+# @st.cache_data
+# def load_data():
+#     try:
+#         df = pd.read_json("issues.json", convert_dates=["Created at", "Closed at", "Last update"], date_unit="ms")
+#     except:
+#         df = fetch_data()
+#         save_data(df)
+#     return df
 
 
 st.title(f"GitHub Issues Dashboard")
-status = st.status(label="Loading data...", state="running")
-
-df = load_data()
-
+with st.status(label="Loading data...", state="running") as status:
+    df = fetch_data()
+    status.update(label="Data loaded!", state="complete")
 today = datetime.date.today()
 
 # Section 1: Issue activity metrics
@@ -97,9 +96,9 @@ st.subheader("Latest updates 📝")
 col1, col2 = st.columns(2)
 with col1:
     last_update_date = st.date_input("Last updated after:", value=today - datetime.timedelta(days=7), format="DD-MM-YYYY")
-    last_update_date = datetime.datetime.combine(last_update_date, datetime.datetime.min.time())  # Convert to datetime object
+    last_update_date = datetime.datetime.combine(last_update_date, datetime.datetime.min.time())
 with col2:
-    updated_issues = open_issues[open_issues["Last update"] > last_update_date]
+    updated_issues = open_issues[pd.to_datetime(open_issues["Last update"]).dt.tz_localize(None) > pd.to_datetime(last_update_date)]
     st.metric("Results:", updated_issues.shape[0])
 
 st.dataframe(
@@ -118,9 +117,9 @@ st.subheader("Stale issues? 🕸️")
 col1, col2 = st.columns(2)
 with col1:
     not_updated_since = st.date_input("Not updated since:", value=today - datetime.timedelta(days=90), format="DD-MM-YYYY")
-    not_updated_since = datetime.datetime.combine(not_updated_since, datetime.datetime.min.time())  # Convert to datetime object
+    not_updated_since = datetime.datetime.combine(not_updated_since, datetime.datetime.min.time())
 with col2:
-    stale_issues = open_issues[open_issues["Last update"] < not_updated_since]
+    stale_issues = open_issues[pd.to_datetime(open_issues["Last update"]).dt.tz_localize(None) < pd.to_datetime(not_updated_since)]
     st.metric("Results:", stale_issues.shape[0])
 st.dataframe(
     stale_issues[["Issue","Labels", "Repository", "Last update","URL"]].sort_values(by="Last update", ascending=True),
@@ -198,10 +197,10 @@ st.dataframe(
 # st.header("Issue dependencies")
 # ## Map: dependencies between issues. Network of issue mentions.x
 
-status.update(label="Checking for updated data...", state="running")
-updated_data = fetch_data()
-if df.equals(updated_data):
-    status.update(label="Data is up to date!", state="complete")
-else:
-    save_data(updated_data)
-    status.update(label="Refresh for updated data!", state="complete")
+# status.update(label="Checking for updated data...", state="running")
+# updated_data = fetch_data()
+# if df.equals(updated_data):
+#     status.update(label="Data is up to date!", state="complete")
+# else:
+#     save_data(updated_data)
+#     status.update(label="Refresh for updated data!", state="complete")