services/population.py

import os
import sys

src_directory=os.path.abspath(os.path.join(os.path.dirname(__file__),"../..","pydantic"))
sys.path.append(src_directory)



import pandas as pd
from new.utils.logger import logger
from fastapi import HTTPException
from new.models.schemas import ContinentPopulationResponse, CountryPopulation

file_path = "D:/pandas/world_population (1).csv"

# Load the CSV file
try:
    countries_df = pd.read_csv(file_path)
    countries_df["Population"] = pd.to_numeric(countries_df["Population"], errors="coerce")
    countries_df["Area"] = pd.to_numeric(countries_df["Area"], errors="coerce")
    logger.info("CSV file loaded successfully.")
except Exception as e:
    logger.error(f"Error loading CSV: {e}")
    raise RuntimeError("Failed to load CSV file.")

def get_continent_population(continent_name: str) -> ContinentPopulationResponse:
    try:
        logger.info(f"Fetching data for continent: {continent_name}")
        continent_group = countries_df[countries_df["Continent"] == continent_name].dropna(subset=["Population", "Area"])
        
        if continent_group.empty:
            raise HTTPException(status_code=404, detail="Continent not found.")

        total_population = int(continent_group["Population"].sum())
        total_area = int(continent_group["Area"].sum())
        if total_area == 0:
            raise HTTPException(status_code=400, detail="Total area is zero.")

        max_row = continent_group.loc[continent_group["Population"].idxmax()]
        min_row = continent_group.loc[continent_group["Population"].idxmin()]
        avg_population = int(continent_group["Population"].mean())

        return ContinentPopulationResponse(
            continent=continent_name,
            total_population=total_population,
            total_area=total_area,
            continent_population_density=total_population / total_area,
            max_population=CountryPopulation(
                country=max_row["Country"], population=int(max_row["Population"])
            ),
            min_population=CountryPopulation(
                country=min_row["Country"], population=int(min_row["Population"])
            ),
            avg_population=avg_population
        )
    except HTTPException as http_err:
        logger.error(f"HTTP exception: {http_err.detail}")
        raise http_err
    except Exception as e:
        logger.error(f"Unexpected error: {e}")
        raise HTTPException(status_code=500, detail="Internal server error.")