Update app.py

app.py

@@ -1,10 +1,11 @@
 import streamlit as st
-import requests
 import pandas as pd
 import altair as alt
 import datetime
 import re
 import os
+import asyncio
+import aiohttp
 
 st.set_page_config(page_title="Congress Stock Trades", layout="wide")
 
@@ -13,15 +14,46 @@ API_KEY = os.getenv("FMP_API_KEY")
 SENATE_BASE_URL = "https://financialmodelingprep.com/api/v4/senate-trading-rss-feed"
 HOUSE_BASE_URL = "https://financialmodelingprep.com/api/v4/senate-disclosure-rss-feed"
 
-def fetch_data(base_url, pages=5):
-    data = []
-    for page in range(pages):
-        url = f"{base_url}?page={page}&apikey={API_KEY}"
-        r = requests.get(url)
-        if r.status_code == 200:
-            data.extend(r.json())
-    return data
+# ---------------------------
+# ASYNC FUNCTIONS FOR FETCHING DATA
+# ---------------------------
+async def fetch_data_page(session, base_url, page):
+    url = f"{base_url}?page={page}&apikey={API_KEY}"
+    try:
+        async with session.get(url) as response:
+            if response.status == 200:
+                return await response.json()
+            else:
+                return []  # Fail gracefully
+    except Exception:
+        return []
+
+async def fetch_all_data_async(base_url, pages=5):
+    async with aiohttp.ClientSession() as session:
+        tasks = [fetch_data_page(session, base_url, page) for page in range(pages)]
+        results = []
+        progress_bar = st.progress(0)
+        completed = 0
+        for coro in asyncio.as_completed(tasks):
+            data = await coro
+            results.extend(data)
+            completed += 1
+            progress_bar.progress(completed / pages)
+        return results
+
+def load_data_async(base_url, pages=5):
+    raw_data = asyncio.run(fetch_all_data_async(base_url, pages))
+    if not raw_data:
+        return pd.DataFrame()
+    df = pd.DataFrame(raw_data)
+    if "transactionDate" in df.columns:
+        df["transactionDate"] = pd.to_datetime(df["transactionDate"], errors="coerce")
+        df.sort_values(by="transactionDate", ascending=False, inplace=True)
+    return df
 
+# ---------------------------
+# HELPER FUNCTION TO PARSE AMOUNT RANGE
+# ---------------------------
 def parse_amount_range(amount_str):
     if not isinstance(amount_str, str):
         return None
@@ -35,21 +67,15 @@ def parse_amount_range(amount_str):
     match = re.match(r"\d+", clean_str)
     return float(match.group()) if match else None
 
-def load_data(base_url):
-    raw_data = fetch_data(base_url, pages=5)
-    if not raw_data:
-        return pd.DataFrame()
-    df = pd.DataFrame(raw_data)
-    if "transactionDate" in df.columns:
-        df["transactionDate"] = pd.to_datetime(df["transactionDate"], errors="coerce")
-        df.sort_values(by="transactionDate", ascending=False, inplace=True)
-    return df
-
+# ---------------------------
+# MAIN APP CODE
+# ---------------------------
 st.sidebar.title("Filters")
 
 with st.sidebar.expander("Parameters", expanded=True):
     start_date = st.date_input("Start transaction date", value=datetime.date(2025, 1, 1))
-    top_n = st.slider("Top N stocks", min_value=1, max_value=20, value=10, help="Select the top N stock by trade amount and volume.")
+    top_n = st.slider("Top N stocks", min_value=1, max_value=20, value=10, 
+                      help="Select the top N stock by trade amount and volume.")
 
 run_button = st.sidebar.button("Run Analysis")
 
@@ -57,32 +83,28 @@ st.title("Congress Trades Analysis")
 st.write("Analyze the latest trades reported by members of Congress. From the Senate and from the House.")
 
 if run_button:
-    senate_data = load_data(SENATE_BASE_URL)
-    house_data = load_data(HOUSE_BASE_URL)
+    # Use asynchronous fetching for both Senate and House
+    senate_data = load_data_async(SENATE_BASE_URL, pages=5)
+    house_data = load_data_async(HOUSE_BASE_URL, pages=5)
 
+    # Process Senate data
     if not senate_data.empty:
-    # Convert 'transactionDate' and 'dateRecieved' to datetime
         senate_data["transactionDate"] = pd.to_datetime(senate_data["transactionDate"], errors="coerce")
         senate_data["dateRecieved"] = pd.to_datetime(senate_data["dateRecieved"], errors="coerce")
-        
-        # Filter where either transactionDate or dateRecieved is on or after start_date
         senate_data = senate_data[
             (senate_data["transactionDate"] >= pd.to_datetime(start_date)) |
             (senate_data["dateRecieved"] >= pd.to_datetime(start_date))
         ]
+    # Process House data
     if not house_data.empty:
-        # house_data = house_data[house_data["transactionDate"] >= pd.to_datetime(start_date)] gives issues
         house_data["transactionDate"] = pd.to_datetime(house_data["transactionDate"], errors="coerce")
         house_data["disclosureDate"] = pd.to_datetime(house_data["disclosureDate"], errors="coerce")
-        
-        # Filter where either transactionDate or disclosureDate is on or after start_date
         house_data = house_data[
             (house_data["transactionDate"] >= pd.to_datetime(start_date)) |
             (house_data["disclosureDate"] >= pd.to_datetime(start_date))
         ]
 
-
-    # Prepare Senate
+    # Prepare chart data for Senate
     senate_chart_data = pd.DataFrame()
     if not senate_data.empty:
         senate_chart_data = pd.DataFrame({
@@ -91,8 +113,7 @@ if run_button:
             "amount": senate_data["amount"].apply(parse_amount_range),
             "chamber": "Senate"
         })
-
-    # Prepare House
+    # Prepare chart data for House
     house_chart_data = pd.DataFrame()
     if not house_data.empty:
         house_chart_data = pd.DataFrame({
@@ -106,14 +127,12 @@ if run_button:
     combined_data.dropna(subset=["amount", "ticker"], inplace=True)
     combined_data = combined_data[combined_data["amount"] > 0]
 
-    # Convert types to "purchase" or "sale"
+    # Standardize trade type
     def standardize_trade_type(t):
         if "sale" in t or "sold" in t or "sell" in t:
             return "sale"
         return "purchase"
-
     combined_data["tradeType"] = combined_data["rawType"].apply(standardize_trade_type)
-
     combined_data["count"] = 1
 
     # Get top N by sum
@@ -135,7 +154,6 @@ if run_button:
             .groupby(["ticker", "chamber", "tradeType"], as_index=False)
             .agg({"amount": "sum", "count": "sum"})
         )
-
         base = alt.Chart(chart_data).encode(
             x=alt.X("ticker:N", axis=alt.Axis(labelAngle=-45)),
             xOffset="chamber:N",
@@ -145,44 +163,31 @@ if run_button:
         bars = base.mark_bar()
         text = base.mark_text(dy=-5, color="black").encode(text=alt.Text("count:Q"))
         chart = alt.layer(bars, text).properties(width=40 * len(top_tickers), height=400)
-
         st.altair_chart(chart, use_container_width=True)
 
-    # Reorder columns for Senate
+    # Reorder Senate columns
     if not senate_data.empty:
-        # The order you specified:
-        # 1) name
-        # 2) disclosure/received date
-        # 3) symbol
-        # 4) purchase/sale
-        # 5) amount
-        # 6) assetDescription
-        # We'll map "office" -> name, "dateRecieved" -> date, "symbol" -> symbol, 
-        # "type" -> purchase/sale, "amount" -> amount, "assetDescription" -> assetDescription
-        # Then we append remaining columns
         desired_order_senate = [
             "office",  # name
             "dateRecieved",  
-            "symbol",        # symbol
-            "type",          # purchase/sale
-            "amount",        # amount
+            "symbol",        
+            "type",          
+            "amount",        
             "assetDescription"
         ]
-        # Create an ordered list of columns that exist
         existing_senate_cols = [c for c in desired_order_senate if c in senate_data.columns]
-        # Append the rest that we didn't list
         remaining_senate_cols = [c for c in senate_data.columns if c not in existing_senate_cols]
         reordered_senate_cols = existing_senate_cols + remaining_senate_cols
         senate_data = senate_data[reordered_senate_cols]
 
-    # Reorder columns for House
+    # Reorder House columns
     if not house_data.empty:
         desired_order_house = [
             "representative",  # name
             "disclosureDate",  
-            "ticker",          # symbol
-            "type",            # purchase/sale
-            "amount",          # amount
+            "ticker",          
+            "type",            
+            "amount",          
             "assetDescription"
         ]
         existing_house_cols = [c for c in desired_order_house if c in house_data.columns]
@@ -191,21 +196,19 @@ if run_button:
         house_data = house_data[reordered_house_cols]
 
     st.subheader("Senate Data")
-    st.write("Latest Transaction in Senate. Please sort the table by **`disclosureDate`** and / or **`dateRecieved`** columns.")
+    st.write("Latest Transaction in Senate. Please sort the table by **`disclosureDate`** and/or **`dateRecieved`** columns.")
     st.dataframe(senate_data, use_container_width=True)
 
     st.subheader("House Data")
-    st.write("Latest Transaction in House. Please sort the table by the **`disclosureDate`** and / or **`transactionDate`** columns. ")
+    st.write("Latest Transaction in House. Please sort the table by **`disclosureDate`** and/or **`transactionDate`** columns.")
     st.dataframe(house_data, use_container_width=True)
-
 else:
     st.write("Set filters and press Run to load data.")
 
-
 hide_streamlit_style = """
 <style>
 #MainMenu {visibility: hidden;}
 footer {visibility: hidden;}
 </style>
 """
-st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+st.markdown(hide_streamlit_style, unsafe_allow_html=True)