Done some major changes

Dockerfile

@@ -1,18 +1,11 @@
-# Use an official Python runtime as a parent image
 FROM python:3.11-slim
 
-# Set the working directory in the container
 WORKDIR /code
 
-# Copy the requirements file into the container at /code
 COPY ./requirements.txt /code/requirements.txt
 
-# Install any needed packages specified in requirements.txt
 RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
 
-# Copy the rest of the application's code into the container at /code
 COPY . /code/
 
-# Tell uvicorn to run on all available network interfaces (0.0.0.0)
-# and on the port Hugging Face Spaces expects (7860).
 CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -1,24 +1,21 @@
 from fastapi import FastAPI, HTTPException, Query
 from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
 import requests
 import pandas as pd
-from datetime import datetime
+from datetime import datetime, date
 import google.generativeai as genai
 import os
+import json
 from dotenv import load_dotenv
+from sheets_client import add_subscriber_to_sheet
+import random
 
 load_dotenv()
 app = FastAPI()
 
 origins = ["*"]
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=origins,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
+app.add_middleware(CORSMiddleware, allow_origins=origins, allow_credentials=True, allow_methods=["*"], allow_headers=["*"])
 
 FLIGHT_API_KEY = os.getenv("FLIGHT_API_KEY")
 GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
@@ -35,6 +32,15 @@ AUSTRALIAN_CITY_CODES = {
     "Hobart": "HBA", "Darwin": "DRW"
 }
 
+class NewsletterPayload(BaseModel):
+    email: str
+    favDestinations: list[str] = []
+    travelOrigin: str = ""
+    dob: str = ""
+
+class ChatPayload(BaseModel):
+    message: str
+
 def fetch_flight_data(api_key, departure_airport, arrival_airport, date_str):
     url = f"https://api.flightapi.io/onewaytrip/{api_key}/{departure_airport}/{arrival_airport}/{date_str}/1/0/0/Economy/AUD"
     try:
@@ -45,38 +51,21 @@ def fetch_flight_data(api_key, departure_airport, arrival_airport, date_str):
         print(f"Error fetching flight data: {e}")
         return None
 
-def parse_and_process_data(data, origin_code, dest_code, search_date):
-    if not data or 'itineraries' not in data:
+def parse_and_process_data(data):
+    if not data or 'itineraries' not in data or not data.get('itineraries'):
         return pd.DataFrame()
-
     carriers = {c['id']: c for c in data.get('carriers', [])}
-    places = {p['id']: p['name'] for p in data.get('places', [])}
-
     flight_options = []
-    
-    if not data.get('itineraries'):
-        return pd.DataFrame()
-
     for i, itinerary in enumerate(data.get('itineraries', [])):
-        if not itinerary.get('pricing_options'):
-            continue
-        
-        price_info = itinerary['pricing_options'][0].get('price', {})
+        price_info = itinerary.get('pricing_options', [{}])[0].get('price', {})
         price = price_info.get('amount')
-
-        if not itinerary.get('leg_ids'):
-            continue
-            
-        leg_id = itinerary['leg_ids'][0]
+        leg_id = itinerary.get('leg_ids', [None])[0]
         leg = next((l for l in data.get('legs', []) if l['id'] == leg_id), None)
-        
-        if not leg or not price:
+        if not all([price, leg]):
             continue
-            
         marketing_carrier_id = leg.get('marketing_carrier_ids', [None])[0]
         carrier_info = carriers.get(marketing_carrier_id, {})
         airline_name = carrier_info.get('name', "Unknown Airline")
-        
         flight_number = "N/A"
         if leg.get('segment_ids'):
             segment_id = leg['segment_ids'][0]
@@ -85,119 +74,105 @@ def parse_and_process_data(data, origin_code, dest_code, search_date):
                 carrier_code = carrier_info.get('code', "XX")
                 flight_num_part = segment.get('marketing_flight_number', leg['id'][:3])
                 flight_number = f"{carrier_code}{flight_num_part}"
-
         flight_options.append({
-            "id": i,
-            "airline": airline_name,
-            "flight": flight_number,
+            "id": i, "airline": airline_name, "flight": flight_number,
             "departure": pd.to_datetime(leg['departure']).strftime('%H:%M'),
-            "arrival": pd.to_datetime(leg['arrival']).strftime('%H:%M'),
-            "price": price
+            "arrival": pd.to_datetime(leg['arrival']).strftime('%H:%M'), "price": price
         })
-
-    if not flight_options:
-        return pd.DataFrame()
-        
-    df = pd.DataFrame(flight_options)
-    return df.sort_values(by="price").reset_index(drop=True)
-
-def get_ai_insights(df, origin, destination, date):
-    if df.empty:
-        return "No flight data was available to analyze."
-    
-    if not GEMINI_API_KEY:
-        return "**AI Analysis Skipped:** Gemini API key not configured on the backend."
-
-    summary_df = df.head(10)
-    data_summary = f"""
-    Flight Price Data Summary:
-    - Route: {origin} to {destination}
-    - Date: {date}
-    - Number of flights found: {len(df)}
-    - Cheapest flight: AUD {df['price'].min()} on {df.loc[df['price'].idxmin(), 'airline']}
-    - Average price of top 10 cheapest: AUD {summary_df['price'].mean():.2f}
-    """
-    
-    prompt = f"""
-    You are a market analyst for a chain of Australian hostels. Your goal is to provide a brief, actionable report based on flight data.
-
-    **Data Provided:**
-    {data_summary}
-
-    **Your Task:**
-    Provide a bullet-point summary in Markdown format for a hostel manager. The tone should be concise and professional. Focus on:
-    - **Top Insight:** What is the single most important takeaway? (e.g., "The route is highly competitive today, driving prices down.")
-    - **Price Trends:** Is it a good day to travel for budget-conscious guests? What is the cheapest price found?
-    - **Key Airlines:** Which 1-2 airlines are dominating the budget-friendly options?
-    - **Actionable Advice:** Give one concrete recommendation. (e.g., "Target marketing efforts towards customers arriving on Rex or Jetstar flights.")
-    """
-
+    return pd.DataFrame(flight_options).sort_values(by="price").reset_index(drop=True)
+
+def get_dashboard_ai_analysis(df, origin, destination, date_str):
+    if not GEMINI_API_KEY or df.empty:
+        return "AI analysis could not be performed due to a configuration issue or lack of data."
+    cheapest_flight = df.iloc[0]
+    data_summary = f"""Context: Flight search from {origin} to {destination} for {date_str}. Total flights: {len(df)}. Price Range: ${df['price'].min():.2f} to ${df['price'].max():.2f}. Cheapest: {cheapest_flight['airline']} for ${cheapest_flight['price']:.2f}."""
+    prompt = f"You are a sharp, concise market analyst for 'Aussie Backpacker Flow'. Based on the following summary, provide actionable insights in markdown bullet points: {data_summary}. Focus on: a one-sentence market snapshot, top budget carriers, demand interpretation, and one specific marketing tip for a hostel manager."
     try:
         model = genai.GenerativeModel('gemini-1.5-flash-latest')
         response = model.generate_content(prompt)
-        report_header = f"Based on the data for **{origin} to {destination}** on **{date}**, here are the key insights:"
+        report_header = f"Based on the data for **{origin} to {destination}** on **{date_str}**, here are the key insights:"
         return f"{report_header}\n\n{response.text}"
     except Exception as e:
-        return f"Could not generate AI insights. Error: {e}"
-
-@app.get("/")
-def read_root():
-    return {
-        "message": "Welcome to the Airline Demand Analyzer API!",
-        "status": "ok",
-        "endpoints": {
-            "analyze_demand": "/api/analyze-demand?origin=<city>&destination=<city>&date=YYYY-MM-DD"
-        }
-    }
-
-@app.get("/api/analyze-demand")
-def analyze_demand(
-    origin: str = Query(..., description="Origin city name, e.g., Sydney"),
-    destination: str = Query(..., description="Destination city name, e.g., Melbourne"),
-    date: str = Query(..., description="Departure date in YYYY-MM-DD format")
-):
-    if not FLIGHT_API_KEY:
-        raise HTTPException(status_code=500, detail="Flight API key not configured on the server.")
-
+        return f"An error occurred during AI analysis: {e}"
+
+def generate_mock_heatmap_data():
+    airports = list(AUSTRALIAN_CITY_CODES.keys())
+    routes = []
+    for _ in range(10):
+        from_city, to_city = random.sample(airports, 2)
+        price = random.randint(70, 400)
+        status = 'green' if price < 150 else 'yellow' if price < 280 else 'red'
+        routes.append({"from": from_city, "to": to_city, "status": status, "price": f"${price}"})
+    return routes
+
+def generate_mock_topmovers_data():
+    routes = ["SYD → MEL", "BNE → CNS", "MEL → ADL", "SYD → CBR", "SYD → OOL"]
+    cities = ["Gold Coast (OOL)", "Cairns (CNS)", "Sydney (SYD)"]
+    price_drops = [{"route": r, "airline": random.choice(["Jetstar", "Rex", "Virgin"]), "drop": f"{random.randint(15, 35)}%", "price": f"${random.randint(70, 120)}"} for r in random.sample(routes, 5)]
+    high_demand = [{"city": c, "flights": random.randint(30, 120), "change": f"+{random.randint(8, 25)}%"} for c in cities]
+    return {"priceDrops": price_drops, "highDemand": high_demand}
+
+@app.post("/api/newsletter")
+def handle_newsletter(payload: NewsletterPayload):
+    success, message = add_subscriber_to_sheet(
+        email=payload.email,
+        fav_destinations=payload.favDestinations,
+        origin=payload.travelOrigin,
+        dob=payload.dob
+    )
+    if not success:
+        raise HTTPException(status_code=400, detail=message)
+    return {"message": message}
+
+@app.get("/api/dashboard-data")
+def get_dashboard_data(origin: str, destination: str, date: str):
     origin_code = AUSTRALIAN_CITY_CODES.get(origin)
     dest_code = AUSTRALIAN_CITY_CODES.get(destination)
-
     if not origin_code or not dest_code:
-        raise HTTPException(status_code=400, detail="Invalid origin or destination city name.")
-
+        raise HTTPException(status_code=400, detail="Invalid city name provided.")
     raw_data = fetch_flight_data(FLIGHT_API_KEY, origin_code, dest_code, date)
-    if not raw_data:
-        raise HTTPException(status_code=404, detail="No flight data found for the specified route and date.")
-
-    flight_df = parse_and_process_data(raw_data, origin_code, dest_code, date)
+    flight_df = parse_and_process_data(raw_data)
     if flight_df.empty:
-         raise HTTPException(status_code=404, detail="No flight options could be parsed for this route.")
-
-    ai_report = get_ai_insights(flight_df, origin, destination, date)
-
+        raise HTTPException(status_code=404, detail=f"No live flight data could be found for {origin} to {destination} on {date}. Please try another route or date.")
+    ai_report = get_dashboard_ai_analysis(flight_df, origin, destination, date)
     cheapest_flight_row = flight_df.loc[flight_df['price'].idxmin()]
-    insight_cards = {
-        "cheapestFlight": {
-            "price": cheapest_flight_row['price'],
-            "airline": cheapest_flight_row['airline'],
-            "flightNumber": cheapest_flight_row['flight']
-        },
-        "busiestAirline": {
-            "name": flight_df['airline'].mode()[0],
-            "flightCount": len(flight_df)
+    dashboard_payload = {
+        "airfareHeatmap": generate_mock_heatmap_data(),
+        "topMovers": generate_mock_topmovers_data(),
+        "insightCards": {
+            "cheapestFlight": {"price": cheapest_flight_row['price'], "airline": cheapest_flight_row['airline'], "flightNumber": cheapest_flight_row['flight']},
+            "busiestAirline": {"name": flight_df['airline'].mode()[0], "flightCount": len(flight_df)},
+            "bestDeal": {"name": cheapest_flight_row['airline'], "savings": "Top Value"}
         },
-        "bestDeal": {
-            "name": cheapest_flight_row['airline'],
-            "savings": "Top Value"
-        }
-    }
-
-    chart_data = flight_df.groupby('airline')['price'].min().reset_index()
-    chart_data.rename(columns={'airline': 'name', 'price': 'price'}, inplace=True)
-
-    return {
-        "insightCards": insight_cards,
         "aiAnalystReport": ai_report,
-        "flightPriceChart": chart_data.to_dict('records'),
+        "flightPriceChart": flight_df.groupby('airline')['price'].min().reset_index().rename(columns={'airline': 'name'}).to_dict('records'),
         "flightDataTable": flight_df.to_dict('records')
-    }
+    }
+    return dashboard_payload
+
+@app.post("/api/chat")
+def handle_chat(payload: ChatPayload):
+    user_message = payload.message
+    if not GEMINI_API_KEY:
+        return {"reply": "Chatbot is disabled. Backend needs a Gemini API key."}
+    try:
+        model = genai.GenerativeModel('gemini-1.5-flash-latest')
+        intent_prompt = f"From the user's message, extract origin city, destination city, and a date (today is {date.today().strftime('%Y-%m-%d')}). Respond ONLY with a valid JSON object. Keys: 'origin', 'destination', 'date'. Missing values should be null. Message: '{user_message}'"
+        response = model.generate_content(intent_prompt)
+        json_str = response.text.strip().replace("```json", "").replace("```", "")
+        params = json.loads(json_str)
+        if not all(params.get(k) for k in ['origin', 'destination', 'date']):
+            return {"reply": "I can help with that! To give you the best info, I need the origin city, destination city, and the date you're interested in."}
+        origin_code = next((code for name, code in AUSTRALIAN_CITY_CODES.items() if name.lower() in params['origin'].lower()), None)
+        dest_code = next((code for name, code in AUSTRALIAN_CITY_CODES.items() if name.lower() in params['destination'].lower()), None)
+        if not origin_code or not dest_code:
+            return {"reply": "Sorry, I couldn't recognise those city names. Please use major Australian cities."}
+        raw_data = fetch_flight_data(FLIGHT_API_KEY, origin_code, dest_code, params['date'])
+        flight_df = parse_and_process_data(raw_data)
+        if flight_df.empty:
+            return {"reply": f"I couldn't find any flights from {params['origin']} to {params['destination']} on {params['date']}."}
+        summary_prompt = f"You are a helpful travel assistant. Based on this flight data, write a short, conversational summary of the cheapest option, and maybe one other good one. Data: {flight_df.head(3).to_markdown()}"
+        summary_response = model.generate_content(summary_prompt)
+        return {"reply": summary_response.text}
+    except Exception as e:
+        return {"reply": f"I had a little trouble with that. My apologies. Error: {e}"}

requirements.txt

@@ -3,4 +3,6 @@ uvicorn[standard]
 python-dotenv
 requests
 pandas
-google-generativeai
+google-generativeai
+gspread
+oauth2client

sheets_client.py

@@ -0,0 +1,52 @@
+import gspread
+from oauth2client.service_account import ServiceAccountCredentials
+import os
+from datetime import datetime
+
+SCOPE = [
+    "https://www.googleapis.com/auth/spreadsheets",
+    "https://www.googleapis.com/auth/drive.file"
+]
+
+def get_sheet():
+    try:
+        # We'll use the content of the credentials file passed as a secret
+        creds_json = os.getenv("GOOGLE_CREDENTIALS_JSON")
+        if not creds_json:
+            print("Error: GOOGLE_CREDENTIALS_JSON secret not set.")
+            return None
+            
+        creds_dict = json.loads(creds_json)
+        creds = ServiceAccountCredentials.from_json_keyfile_dict(creds_dict, SCOPE)
+        client = gspread.authorize(creds)
+        sheet_id = os.getenv("GOOGLE_SHEET_ID")
+        if not sheet_id:
+            print("Error: GOOGLE_SHEET_ID secret not set.")
+            return None
+        sheet = client.open_by_key(sheet_id).sheet1
+        return sheet
+    except Exception as e:
+        print(f"Error connecting to Google Sheets: {e}")
+        return None
+
+def add_subscriber_to_sheet(email: str, fav_destinations: list, origin: str, dob: str):
+    sheet = get_sheet()
+    if sheet is None:
+        return False, "Could not connect to the subscribers sheet."
+    
+    try:
+        all_values = sheet.get_all_values()
+        if not all_values or all_values[0] != ["timestamp", "email", "favorite_destinations", "usual_origin", "dob"]:
+             sheet.insert_row(["timestamp", "email", "favorite_destinations", "usual_origin", "dob"], 1)
+
+        timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        destinations_str = ", ".join(fav_destinations)
+        
+        email_list = sheet.col_values(2)
+        if email in email_list:
+             return False, "This email is already subscribed."
+
+        sheet.append_row([timestamp, email, destinations_str, origin, dob])
+        return True, "Successfully subscribed!"
+    except Exception as e:
+        return False, f"An error occurred: {e}"