Upload 2 files

requirements.txt

@@ -0,0 +1,88 @@
+aiohappyeyeballs==2.4.0
+aiohttp==3.10.5
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.4.0
+astor==0.8.1
+attrs==24.2.0
+beautifulsoup4==4.12.3
+certifi==2024.7.4
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+Cython==3.0.11
+decorator==5.1.1
+deprecation==2.1.0
+docx==0.2.4
+Faker==28.1.0
+fastapi==0.112.2
+fire==0.6.0
+fonttools==4.53.1
+frozenlist==1.4.1
+gotrue==2.7.0
+h11==0.14.0
+h2==4.1.0
+hpack==4.0.0
+httpcore==1.0.5
+httpx==0.27.0
+hyperframe==6.0.1
+idna==3.8
+imageio==2.35.1
+imgaug==0.4.0
+kiwisolver==1.4.5
+lazy_loader==0.4
+lmdb==1.5.1
+lxml==5.3.0
+matplotlib==3.9.2
+multidict==6.0.5
+networkx==3.3
+numpy==1.26.4
+opencv-contrib-python==4.10.0.84
+opencv-python==4.10.0.84
+opt-einsum==3.3.0
+optional==0.0.1
+packaging==24.1
+paddleocr==2.8.1
+paddlepaddle==2.6.1
+pandas==2.2.2
+pdf2image==1.17.0
+pillow==10.4.0
+postgrest==0.16.11
+protobuf==5.27.3
+pyclipper==1.3.0.post5
+pydantic==2.8.2
+pydantic_core==2.20.1
+pyparsing==3.1.4
+PyPDF2==3.0.1
+python-dateutil==2.9.0.post0
+python-docx==1.1.2
+python-dotenv==1.0.1
+pytz==2024.1
+PyYAML==6.0.2
+rapidfuzz==3.9.6
+realtime==2.0.2
+regex==2024.7.24
+requests==2.32.3
+scikit-image==0.24.0
+scipy==1.14.1
+setuptools==73.0.1
+shapely==2.0.6
+six==1.16.0
+sniffio==1.3.1
+soupsieve==2.6
+starlette==0.38.2
+storage3==0.7.7
+StrEnum==0.4.15
+supabase==2.7.3
+supafunc==0.5.1
+termcolor==2.4.0
+tifffile==2024.8.24
+tiktoken==0.7.0
+tqdm==4.66.5
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+uvicorn==0.30.6
+websockets==12.0
+yarl==1.9.4

travel_analytics.py

@@ -0,0 +1,130 @@
+from fastapi import FastAPI, HTTPException
+from supabase import create_client, Client
+from typing import List, Dict
+from statistics import mean
+from collections import Counter
+import os
+from datetime import datetime
+import json
+
+app = FastAPI()
+
+# Initialize Supabase client
+url: str = os.getenv('SUPABASE_URL')
+key: str = os.getenv('SUPABASE_KEY')
+supabase: Client = create_client(url, key)
+
+@app.get("/travel-analytics")
+async def get_travel_analytics():
+    try:
+        # Fetch data from Supabase
+        response = supabase.table("receipt_radar_structured_data_duplicate_duplicate").select("metadata, total_cost, brand_category").eq('user_id',"4b7fa719-244e-4ae8-9025-651a9a41e43f").execute()
+        
+        # Extract metadata from the response
+        metadata_list: List[Dict] = [json.loads(row['metadata']) for row in response.data if row['metadata']]
+        total_costs = [float(row['total_cost']) for row in response.data if row.get('total_cost')]
+        print(metadata_list)
+        print(total_costs)
+        # Initialize variables for analytics
+        total_trips = len(metadata_list)
+        trip_durations = []
+        domestic_trips = 0
+        international_trips = 0
+        destination_types = Counter()
+        booking_lead_times = []
+        accommodation_spending = []
+        transport_spending = []
+        activities_spending = []
+        domestic_departure_countries = Counter()
+        international_departure_countries = Counter()
+        domestic_arrival_countries = Counter()
+        international_arrival_countries = Counter()
+        all_dates = []
+        
+        # Process each metadata entry
+        for metadata in metadata_list:
+            # Trip duration
+            if 'check_in_date' in metadata and 'check_out_date' in metadata:
+                print("inside 1st")
+                check_in_date = metadata['check_in_date']
+                check_out_date = metadata['check_out_date']
+                duration = (check_out_date - check_in_date).days
+                trip_durations.append(duration)
+                all_dates.append(check_in_date)
+                all_dates.append(check_out_date)
+            
+            # Domestic vs International
+            if 'departure_country' in metadata and 'arrival_country' in metadata:
+                print("inside 2nd")
+                departure_country = metadata['departure_country']
+                arrival_country = metadata['arrival_country']
+                
+                if departure_country == arrival_country:
+                    print("inside 2nd")
+                    domestic_trips += 1
+                    domestic_departure_countries[departure_country] += 1
+                    domestic_arrival_countries[arrival_country] += 1
+                else:
+                    international_trips += 1
+                    international_departure_countries[departure_country] += 1
+                    international_arrival_countries[arrival_country] += 1
+            
+            # Destination type (simplified)
+            if 'destination_type' in metadata:
+                print("inside 3rd")
+                destination_types[metadata['destination_type']] += 1
+            
+            # Booking lead time
+            if 'date_of_purchase' in metadata and 'departure_date' in metadata:
+                print("inside 4th")
+                lead_time = (datetime.strptime(metadata['departure_date'],"%d-%m-%Y") - datetime.strptime(metadata['date_of_purchase'],"%d-%m-%Y")).days
+                booking_lead_times.append(lead_time)
+            
+            # Spending
+            if 'accommodation_cost' in metadata:
+                accommodation_spending.append(metadata['accommodation_cost'])
+            if 'transport_cost' in metadata:
+                transport_spending.append(metadata['transport_cost'])
+            if 'activities_cost' in metadata:
+                activities_spending.append(metadata['activities_cost'])
+        
+        # Calculate the number of years covered by the data
+        if all_dates:
+            min_date = min(all_dates)
+            max_date = max(all_dates)
+            date_range_years = (max_date - min_date).days / 365.25
+        else:
+            date_range_years = 1  # Default to 1 year if no dates are available
+        
+        # Calculate analytics
+        analytics = {
+            "travel_frequency": {
+                "trips_per_year": total_trips / date_range_years,
+                "average_trip_duration": mean(trip_durations) if trip_durations else None,
+                "domestic_vs_international": f"{domestic_trips}:{international_trips}",
+                "domestic_departure_countries": dict(domestic_departure_countries),
+                "international_departure_countries": dict(international_departure_countries),
+                "domestic_arrival_countries": dict(domestic_arrival_countries),
+                "international_arrival_countries": dict(international_arrival_countries),
+            },
+            "destination_preferences": {
+                "popular_types": dict(destination_types.most_common(5))
+            },
+            "booking_patterns": {
+                "average_lead_time": mean(booking_lead_times) if booking_lead_times else None
+            },
+            "travel_expenditure": {
+                "average_accommodation_cost": mean(accommodation_spending) if accommodation_spending else None,
+                "average_transport_cost": mean(transport_spending) if transport_spending else None,
+                "average_activities_cost": mean(activities_spending) if activities_spending else None
+            }
+        }
+        
+        return analytics
+    
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+# if __name__ == "__main__":
+#     import uvicorn
+#     uvicorn.run(app, host="0.0.0.0", port=8000,reload="--reload")