restructure backend to be standalone for deployment

.env.schema

@@ -1,2 +1 @@
-CHROMEDRIVER_PATH=/opt/homebrew/bin/chromedriver # replace with path to your chromedriver install
-DATABASE_URL="postgresql://user:password@postgresserver/db" # replace with your DB credentials
+CHROMEDRIVER_PATH=/opt/homebrew/bin/chromedriver # replace with path to your chromedriver install

README.md

@@ -82,5 +82,5 @@ python -m main
 To start the backend API from the root directory, run:
 
 ```bash
-python -m uvicorn backend.app:app --reload
+python -m uvicorn app:app --reload
 ```

backend/.env.schema

@@ -0,0 +1 @@
+DATABASE_URL="postgresql://user:password@postgresserver/db" # replace with your DB credentials

backend/app.py

@@ -1,13 +1,8 @@
 from fastapi import FastAPI
 
-from backend.database import engine, Base
-from backend.routers import predict
-from backend.routers import analysis
-from backend.db_models import Building, Unit
-
-
-Base.metadata.drop_all(bind=engine,tables=[Unit.__table__, Building.__table__])
-Base.metadata.create_all(engine)
+from database import engine, Base
+from routers import predict
+from routers import analysis
 
 app = FastAPI()
 

backend/constants.py

@@ -0,0 +1,116 @@
+from enum import Enum
+
+class TableHeaders(Enum):
+    BUILDING = 'Building'
+    NEIGHBOURHOOD = 'Neighbourhood'
+    ADDRESS = 'Address'
+    CITY = 'City'
+    LISTING = 'Listing'
+    BED = 'Bed'
+    BATH = 'Bath'
+    SQFT = 'SqFt'
+    PRICE = 'Price'
+    UNIT_AMENITIES = 'Unit Amenities'
+    BUILDING_AMENITIES =  'Building Amenities'
+    PETS = 'Pets'
+    LAT = 'Latitude'
+    LON = 'Longitude'
+    DATE = 'Date'
+
+class UnitAmenities(Enum):
+    BALCONY = 'Balcony'
+    IN_UNIT_LAUNDRY = 'In Unit Laundry'
+    AIR_CONDITIONING = 'Air Conditioning' 
+    HIGH_CEILINGS = 'High Ceilings'
+    FURNISHED = 'Furnished'
+    HARDWOOD_FLOOR = 'Hardwood Floor'
+
+class BuildingAmenities(Enum):
+    CONTROLLED_ACCESS = 'Controlled Access'
+    FITNESS_CENTER = 'Fitness Center'
+    SWIMMING_POOL = 'Swimming Pool'
+    ROOF_DECK = 'Roof Deck'
+    STORAGE = 'Storage'
+    RESIDENTS_LOUNGE = 'Residents Lounge'
+    OUTDOOR_SPACE = 'Outdoor Space'
+
+
+UnitAmenitiesDict = {
+    UnitAmenities.BALCONY.value: 0,
+    UnitAmenities.IN_UNIT_LAUNDRY.value: 0,
+    UnitAmenities.AIR_CONDITIONING.value: 0,
+    UnitAmenities.HIGH_CEILINGS.value: 0,
+    UnitAmenities.FURNISHED.value: 0,
+    UnitAmenities.HARDWOOD_FLOOR.value: 0
+}
+
+BuildingAmenitiesDict = {
+    BuildingAmenities.CONTROLLED_ACCESS.value: 0,
+    BuildingAmenities.FITNESS_CENTER.value: 0,
+    BuildingAmenities.SWIMMING_POOL.value: 0,
+    BuildingAmenities.ROOF_DECK.value: 0,
+    BuildingAmenities.STORAGE.value: 0,
+    BuildingAmenities.RESIDENTS_LOUNGE.value: 0,
+    BuildingAmenities.OUTDOOR_SPACE.value: 0
+}
+
+locations = [
+    {
+        'location': 'Downtown Core',
+        'bounding_box': {
+            'southwest': {'lon': '-79.398', 'lat': '43.643'},
+            'northeast': {'lon': '-79.3762', 'lat': '43.66'}
+        }
+    },
+    {
+        'location': 'Midtown',
+        'bounding_box': {
+            'southwest': {'lon': '-79.4165', 'lat': '43.67'},
+            'northeast': {'lon': '-79.388', 'lat': '43.7'}
+        }
+    },
+    {
+        'location': 'West End',
+        'bounding_box': {
+            'southwest': {'lon': '-79.449', 'lat': '43.628'},
+            'northeast': {'lon': '-79.402', 'lat': '43.65'}
+        }
+    },
+    {
+        'location': 'East End',
+        'bounding_box': {
+            'southwest': {'lon': '-79.36', 'lat': '43.65'},
+            'northeast': {'lon': '-79.315', 'lat': '43.685'}
+        }
+    },
+    {
+        'location': 'North Toronto',
+        'bounding_box': {
+            'southwest': {'lon': '-79.425', 'lat': '43.7'},
+            'northeast': {'lon': '-79.383', 'lat': '43.73'}
+        }
+    },
+    {
+        'location': 'University Area',
+        'bounding_box': {
+            'southwest': {'lon': '-79.4042', 'lat': '43.6572'},
+            'northeast': {'lon': '-79.39', 'lat': '43.6675'}
+        }
+    },
+    {
+        'location': 'Scarborough',
+        'bounding_box': {
+            'southwest': {'lon': '-79.21498455469643', 'lat': '43.74522758306715'},
+            'northeast': {'lon': '-79.17281544530357', 'lat': '43.78977241693285'}
+        }
+    },
+    {
+        'location': 'Etobicoke',
+        'bounding_box': {
+            'southwest': {'lon': '-79.57890339741783', 'lat': '43.6379061704074'},
+            'northeast': {'lon': '-79.53609660258218', 'lat': '43.682093829592596'}
+        }
+    }
+]
+
+table_columns = [table_header.value for table_header in TableHeaders]

backend/db_models.py

@@ -1,11 +1,13 @@
-from backend.database import Base
+from database import Base
 from sqlalchemy import Boolean, Column, ForeignKey, Integer, String, Float, DateTime
 from sqlalchemy.orm import relationship
 from datetime import datetime
 
+
 class Unit(Base):
     __tablename__ = "units"
-    id = Column(Integer, primary_key=True, index=True, autoincrement=True, unique=True)
+    id = Column(Integer, primary_key=True, index=True,
+                autoincrement=True, unique=True)
     building_id = Column(Integer, ForeignKey("buildings.id"))
     bed = Column(Integer, index=True)
     bath = Column(Float)
@@ -21,9 +23,11 @@ class Unit(Base):
 
     building = relationship("Building", back_populates="units")
 
+
 class Building(Base):
     __tablename__ = "buildings"
-    id = Column(Integer, primary_key=True, index=True, autoincrement=True, unique=True)
+    id = Column(Integer, primary_key=True, index=True,
+                autoincrement=True, unique=True)
     name = Column(String, index=True)
     address = Column(String, index=True)
     city = Column(String, index=True)
@@ -37,6 +41,5 @@ class Building(Base):
     storage = Column(Boolean, default=False)
     swimming_pool = Column(Boolean, default=False)
     pets = Column(Boolean, default=False)
-    
+
     units = relationship("Unit", back_populates="building")
-

backend/dependencies.py

@@ -1,8 +1,9 @@
-from backend.database import SessionLocal
+from database import SessionLocal
+
 
 def get_db():
     db = SessionLocal()
     try:
-        return db
+        yield db
     finally:
         db.close()

backend/pydantic_schemas/Analysis.py

@@ -0,0 +1,30 @@
+from pydantic import BaseModel
+from datetime import datetime
+
+class AddListing(BaseModel):
+    building: str
+    neighbourhood: str
+    address: str
+    city: str
+    listing: str
+    bed: int
+    bath: float
+    sqft: float
+    price: float
+    pets: float
+    latitude: float
+    longitude: float
+    date: datetime
+    controlled_access: bool
+    fitness_center: bool
+    outdoor_space: bool
+    residents_lounge: bool
+    roof_deck: bool
+    storage: bool
+    swimming_pool: bool
+    air_conditioning: bool
+    balcony: bool
+    furnished: bool
+    hardwood_floor: bool
+    high_ceilings: bool
+    in_unit_laundry: bool

backend/pydantic_schemas/Building.py

@@ -1,5 +1,6 @@
 from pydantic import BaseModel
-from backend.pydantic_schemas.Unit import Unit
+from pydantic_schemas.Unit import Unit
+
 
 class BuildingBase(BaseModel):
     name: str
@@ -16,9 +17,11 @@ class BuildingBase(BaseModel):
     storage: bool = False
     swimming_pool: bool = False
 
+
 class BuildingCreate(BuildingBase):
     pass
 
+
 class Building(BuildingBase):
     id: int
     units: list[Unit]

backend/requirements.txt

@@ -0,0 +1,19 @@
+annotated-types==0.6.0
+anyio==4.2.0
+click==8.1.7
+fastapi==0.108.0
+h11==0.14.0
+httptools==0.6.1
+idna==3.6
+pydantic==2.5.3
+pydantic_core==2.14.6
+python-dotenv==1.0.0
+PyYAML==6.0.1
+sniffio==1.3.0
+SQLAlchemy==2.0.25
+starlette==0.32.0.post1
+typing_extensions==4.9.0
+uvicorn==0.25.0
+uvloop==0.19.0
+watchfiles==0.21.0
+websockets==12.0

backend/routers/analysis.py

@@ -1,4 +1,9 @@
-from fastapi import APIRouter
+from fastapi import APIRouter, Depends, HTTPException
+import pandas as pd
+from sqlalchemy.orm import Session
+from services.create import add_listing_data_to_db
+from dependencies import get_db
+from pydantic_schemas.Analysis import AddListing
 
 router = APIRouter(
     prefix="/analysis",
@@ -10,3 +15,15 @@
 @router.get("")
 def get_analysis():
     return {"data": {}}
+
+
+@router.post("", status_code=201)
+def add_listings(request: list[AddListing], db: Session = Depends(get_db)):
+    df = pd.DataFrame([obj.dict() for obj in request])
+    df.columns = df.columns.str.replace('_', ' ').str.title()
+    df = df.rename(columns={'Sqft': 'SqFt'})
+    try:
+        add_listing_data_to_db(db, df)
+        return {"message": "Database updated successfully"}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Database error occurred")

backend/routers/predict.py

@@ -1,7 +1,7 @@
 from fastapi import APIRouter
-from model.model import get_model
+import joblib
 import numpy
-from backend.pydantic_schemas import Predict
+from pydantic_schemas import Predict
 
 router = APIRouter(
     prefix="/predict",
@@ -12,7 +12,7 @@
 
 @router.post("")
 def get_prediction(request: Predict.PredictRequestBody):
-    model = get_model()
+    model = joblib.load("model.joblib")
     input = numpy.array(
         [
             request.bed,

backend/scripts/seed.py

@@ -1,5 +1,5 @@
-from backend.database import engine, Base, SessionLocal
-from backend.db_models import Building, Unit
+from database import engine, Base, SessionLocal
+from db_models import Building, Unit
 
 # Create a session
 session = SessionLocal()

backend/services/create.py

@@ -2,12 +2,11 @@
 from sqlalchemy.orm import Session
 
 from constants import TableHeaders, UnitAmenities, BuildingAmenities
-from backend.db_models import Building, Unit
-from backend.dependencies import get_db
-from backend.services.search import get_building_units_by_timestamp, get_building_by_lat_lon
-from data.data_cleaner import get_cleaned_df
+from db_models import Building, Unit
+from dependencies import get_db
+from services.search import get_building_units_by_timestamp, get_building_by_lat_lon
+from services.delete import delete_units_by_timestamp
 
-from .delete import delete_units_by_timestamp
 
 
 def row_to_building(row, db: Session) -> Building:
@@ -54,18 +53,22 @@ def add_listing_data_to_db(db: Session, df: pd.DataFrame):
             subset=[TableHeaders.LAT.value, TableHeaders.LON.value], keep='first').apply(row_to_building, args=(db,), axis=1).dropna()
         create_buildings(db, buildings)
         # Now add all Unit objects associated with each building
-        building_groups = df.groupby([TableHeaders.LAT.value, TableHeaders.LON.value])
+        building_groups = df.groupby(
+            [TableHeaders.LAT.value, TableHeaders.LON.value])
         for (lat, lon), building_df in building_groups:
             building = get_building_by_lat_lon(db, lat=lat, lon=lon)
             timestamp = building_df[TableHeaders.DATE.value].iloc[0]
-            existing_units = get_building_units_by_timestamp(db, building.id, building_df[TableHeaders.DATE.value].iloc[0]).first()
+            existing_units = get_building_units_by_timestamp(
+                db, building.id, building_df[TableHeaders.DATE.value].iloc[0]).first()
             if existing_units is not None:
-                print(f"Units for building {building.id} for timestamp {timestamp} already exist")
+                print(
+                    f"Units for building {building.id} for timestamp {timestamp} already exist")
                 continue
             units = building_df.apply(row_to_unit, args=(building.id,), axis=1)
-            create_units(db, units)
+            create_units(db, units, building.id)
     except Exception as e:
-        print(f"An error occurred while adding listing data to the database: {e}")
+        print(
+            f"An error occurred while adding listing data to the database, rolling back entries")
         # Delete all units for the current date timestamp
         timestamp = df[TableHeaders.DATE.value].iloc[0]
         delete_units_by_timestamp(db=db, timestamp=timestamp)
@@ -78,9 +81,7 @@ def create_buildings(db: Session, buildings: list[Building]):
     print(f"Created buildings in db")
 
 
-
-def create_units(db: Session, units: list[Unit]):
-    building_id = units[0].building_id
+def create_units(db: Session, units: pd.DataFrame, building_id: int):
     db.bulk_save_objects(units)
     db.commit()
     print(f"Created units in db for building with id {building_id}")

backend/services/delete.py

@@ -1,10 +1,12 @@
 from sqlalchemy.orm import Session
 from datetime import datetime
 
-from backend.db_models import Unit
+from db_models import Unit
+
 
 def delete_units_by_timestamp(db: Session, timestamp: datetime):
     try:
+        print("Deleting units by timestamp", timestamp)
         db.query(Unit).filter(Unit.timestamp == timestamp).delete()
         db.commit()
     except Exception as e: