Clean up files. Add more validation on FE and BE

.gitignore

@@ -1,3 +1,3 @@
 .venv
 .vscode
-.python-version
+.python-version

backend/src/airbnb_model.py

@@ -1,17 +1,19 @@
-from pydantic import BaseModel, root_validator
+from pydantic import BaseModel, root_validator, conlist
 from typing import List, Literal
 
 class Options(BaseModel):
     min_price: int = None
     max_price: int = None
-    airbnb_room_type: List[Literal['Entire home/apt', 'Private room', 'Shared room', 'Hotel room']]
+    airbnb_room_type: conlist(Literal['Entire home/apt', 'Private room', 'Shared room', 'Hotel room'], min_items=1)
     activity_preference: List [Literal["entertainment", "food", "leisure", "transportation", "shop", "tourism"]]
 
     @root_validator
     def check_prices(cls, values):
         min_price, max_price = values.get('min_price'), values.get('max_price')
         if min_price > max_price:
             raise ValueError('max_price should be bigger than min_price.')
+        if max_price > 20000:
+            raise ValueError('Too expensive! No airbnbs above $20000 CAD. Lower max_price.')
         return values
 
 # Doesn't seem to do validation. TODO: might wanna look into it more.

backend/src/airbnb_service.py

@@ -13,8 +13,7 @@ def compute_airbnb(user_preference: Options) -> pd.DataFrame:
 
     # Filter with room type
     # ['Entire home/apt', 'Private room', 'Shared room', 'Hotel room']
-    if len(airbnb_room_type)>0:
-        df = df[df['room_type'].isin(airbnb_room_type)] 
+    df = df[df['room_type'].isin(airbnb_room_type)] 
 
     # Filter with price range
     if min_price is not None and max_price is not None:

data-analysis/airbnb/airbnb_cleaning.py

@@ -1,6 +1,5 @@
 #%%
 import pandas as pd
-from shapely.geometry import Point, Polygon
 
 airbnb = pd.read_csv('airbnb_listings.csv.gz')
 
@@ -14,10 +13,9 @@ def d_to_price(d_price):
 # Data cleaning - only using the data we need
 airbnb = airbnb[['name', 'listing_url','neighbourhood', 'latitude', 'longitude', 'price', 'room_type', 'review_scores_rating']] 
 airbnb['price'] = airbnb['price'].apply(lambda x: d_to_price(x))
-# airbnb = airbnb.sort_values(by=['price']) #min = 0, max = 20000
+airbnb = airbnb.sort_values(by=['price']) #min = 0, max = 20000
 
 # Export to a cleaned csv file
 airbnb.to_csv("cleaned_airbnb_data.csv", index=False)
 
-
 # %%

data-analysis/airbnb/airbnb_intersection.py

@@ -1,7 +1,6 @@
 import pandas as pd
-import sys
 import geopandas as gpd
-from shapely.geometry import Point, Polygon
+from shapely.geometry import Point
 import shapely
 
 def count_overlapping_features(gdf: gpd.GeoDataFrame):
@@ -21,7 +20,7 @@ def count_overlapping_features(gdf: gpd.GeoDataFrame):
 
 def amentiy_intersections(amenity: str):
     #  1) get all amenity intersection points(coordinates) -> return only with points with intersection counts bigger than average count
-    amen = pd.read_csv(amenity)
+    amen = pd.read_csv(f'cleaned_data/{amenity}')
     gdamen = gpd.GeoDataFrame(amen, geometry=gpd.points_from_xy(amen.lon, amen.lat), crs='epsg:4326')
     gdamen = gdamen.to_crs("EPSG:32634")
     gdamen['geometry'] = gdamen.buffer(300, 3)

data-analysis/airbnb/airbnb_filtering.py → data-analysis/airbnb/airbnb_scoring.py

@@ -1,68 +1,44 @@
 #%%
 import pandas as pd
-import sys
-import geopandas as gpd
-from shapely.geometry import Point, Polygon
-import shapely
 import airbnb_intersection as inters
-
-def filtering(min_price, max_price, room_type):
-    airbnb = pd.read_csv('airbnb_score.csv')
-    # "Entire home/apt"
-    # "Hotel room"
-    # "Private room"
-    # "Shared room"
-
-    # pr = [0, 200]
-    # rt1 = ["Entire home/apt", "Hotel room"]
-    # rt2 = ["Private room"]
-    # rt3 = ["Entire home/apt", "Private room", "Shared room"]
-
-    # at1 = ["food"]
-    # at2 = ["transportation", "attraction"]
-
-    # filter price range
-    price_filtered = airbnb[(airbnb['price'] >= float(min_price)) & (airbnb['price'] <= float(max_price))]
-    # filter room type
-    return airbnb
 
 # # cleaned_entertainment.csv
-# airbnb = pd.read_csv('cleaned_airbnb_data.csv')
+# airbnb = pd.read_csv('cleaned_data/cleaned_airbnb_data.csv')
 # amen_intersection, name = inters.amentiy_intersections('cleaned_entertainment.csv')
 # intersection_airbnb = inters.intersection_score(airbnb, amen_intersection, name)
 # intersection_airbnb.to_csv('airbnb_' + name[0] +'.csv', index=False) # -> airbnb_e.csv with entertainment
 
 # # cleaned_food.csv
 # # airbnb = intersection_airbnb
-# airbnb = pd.read_csv('airbnb_e.csv')
+# airbnb = pd.read_csv('intermediate_scores/airbnb_e.csv')
 # amen_intersection, name = inters.amentiy_intersections('cleaned_food.csv')
 # intersection_airbnb = inters.intersection_score(airbnb, amen_intersection, name)
 # intersection_airbnb.to_csv('airbnb_e' + name[0] +'.csv', index=False) # -> airbnb_ef.csv with entertainment,food
 
 # # cleaned_leisure.csv
 # # airbnb = intersection_airbnb
-# airbnb = pd.read_csv('airbnb_ef.csv')
+# airbnb = pd.read_csv('intermediate_scores/airbnb_ef.csv')
 # amen_intersection, name = inters.amentiy_intersections('cleaned_leisure.csv')
 # intersection_airbnb = inters.intersection_score(airbnb, amen_intersection, name)
 # intersection_airbnb.to_csv('airbnb_ef' + name[0] +'.csv', index=False) # -> airbnb_food.csv with entertainment,food,leisure
 
 # # cleaned_transportation.csv
 # # airbnb = intersection_airbnb
-# airbnb = pd.read_csv('airbnb_efl.csv')
+# airbnb = pd.read_csv('intermediate_scores/airbnb_efl.csv')
 # amen_intersection, name = inters.amentiy_intersections('cleaned_transportation.csv')
 # intersection_airbnb = inters.intersection_score(airbnb, amen_intersection, name)
 # intersection_airbnb.to_csv('airbnb_efl' + name[0] +'.csv', index=False) # -> airbnb_food.csv with entertainment,food,leisure,transportation
 
 # # cleaned_shop.csv
 # # airbnb = intersection_airbnb
-# airbnb = pd.read_csv('airbnb_eflt.csv')
+# airbnb = pd.read_csv('intermediate_scores/airbnb_eflt.csv')
 # amen_intersection, name = inters.amentiy_intersections('cleaned_shop.csv')
 # intersection_airbnb = inters.intersection_score(airbnb, amen_intersection, name)
 # intersection_airbnb.to_csv('airbnb_eflt' + name[0] +'.csv', index=False) # -> airbnb_food.csv with entertainment,food,leisure,transportation,shop
 
 # cleaned_tourism.csv
 # airbnb = intersection_airbnb
-# airbnb = pd.read_csv('airbnb_eflts.csv')
+# airbnb = pd.read_csv('intermediate_scores/airbnb_eflts.csv')
 # amen_intersection, name = inters.amentiy_intersections('cleaned_tourism.csv')
 # intersection_airbnb = inters.intersection_score(airbnb, amen_intersection, name)
 # intersection_airbnb.to_csv('airbnb_score.csv', index=False) # -> airbnb_food.csv with entertainment,food,leisure,transportation,shop,tourism