Update custom_utils.py

custom_utils.py

@@ -1,6 +1,4 @@
 import os
-from typing import List, Optional
-from pydantic import BaseModel, ValidationError
 from datetime import datetime
 import pandas as pd
 import openai
@@ -13,83 +11,6 @@ import time
 DB_NAME = "airbnb_dataset"
 COLLECTION_NAME = "listings_reviews"
 
-class Host(BaseModel):
-    host_id: str
-    host_url: str
-    host_name: str
-    host_location: str
-    host_about: str
-    host_response_time: Optional[str] = None
-    host_thumbnail_url: str
-    host_picture_url: str
-    host_response_rate: Optional[int] = None
-    host_is_superhost: bool
-    host_has_profile_pic: bool
-    host_identity_verified: bool
-
-class Location(BaseModel):
-    type: str
-    coordinates: List[float]
-    is_location_exact: bool
-
-class Address(BaseModel):
-    street: str
-    government_area: str
-    market: str
-    country: str
-    country_code: str
-    location: Location
-
-class Review(BaseModel):
-    _id: str
-    date: Optional[datetime] = None
-    listing_id: str
-    reviewer_id: str
-    reviewer_name: Optional[str] = None
-    comments: Optional[str] = None
-
-class Listing(BaseModel):
-    _id: int
-    listing_url: str
-    name: str
-    summary: str
-    space: str
-    description: str
-    neighborhood_overview: Optional[str] = None
-    notes: Optional[str] = None
-    transit: Optional[str] = None
-    access: str
-    interaction: Optional[str] = None
-    house_rules: str
-    property_type: str
-    room_type: str
-    bed_type: str
-    minimum_nights: int
-    maximum_nights: int
-    cancellation_policy: str
-    last_scraped: Optional[datetime] = None
-    calendar_last_scraped: Optional[datetime] = None
-    first_review: Optional[datetime] = None
-    last_review: Optional[datetime] = None
-    accommodates: int
-    bedrooms: Optional[float] = 0
-    beds: Optional[float] = 0
-    number_of_reviews: int
-    bathrooms: Optional[float] = 0
-    amenities: List[str]
-    price: int
-    security_deposit: Optional[float] = None
-    cleaning_fee: Optional[float] = None
-    extra_people: int
-    guests_included: int
-    images: dict
-    host: Host
-    address: Address
-    availability: dict
-    review_scores: dict
-    reviews: List[Review]
-    text_embeddings: List[float]
-
 def process_records(data_frame):
     records = data_frame.to_dict(orient='records')
     # Handle potential `NaT` values