backend/modules/home_page.py

import pandas as pd
import os
import sys
src_directory = os.path.abspath(os.path.join(os.path.dirname(__file__), "../..", "backend"))
sys.path.append(src_directory)
from utils import logger

file_path =  "./world_population.csv"

# file_path =  "C:/Users/Vijay/Downloads/world_population.csv"
# data_frame = pd.read_csv(file_path)

def process_data():
    try:
        logger.log("I'm going to read the csv")
        data_frame = pd.read_csv(file_path)
        logger.log("I'm reading the csv")
        return data_frame
    except Exception as e :
        logger.log("I couldn't read the file")
        return f"Unable to read the file {e}"
    
def display_continents(dataframe):
    continents = dataframe['Continent'].unique()
    logger.log("Displaying the list of continents in the data")
    return continents

def display_countries(dataframe):
    countries = dataframe['Country'].values
    logger.log("Displaying the list of countries in the data")
    return countries

def continent_stat(dataframe, attribute="Population", stat_type="highest"):
    try:
        if 'Continent' not in dataframe.columns or attribute not in dataframe.columns:
            return ValueError(f"Dataframe must contain 'Continent' and '{attribute}' columns.")
        
        continent_stats = dataframe.groupby('Continent')[attribute].agg(total_attribute='sum')

        if stat_type == "highest":
            continent = continent_stats.idxmax().item()
            value = continent_stats.max().item()
            logger.log(f"Displaying the continent with the highest {attribute}: {continent} with {attribute} {value}")

        elif stat_type == "lowest":
            continent = continent_stats.idxmin().item()
            value = continent_stats.min().item()
            logger.log(f"Displaying the continent with the lowest {attribute}: {continent} with {attribute} {value}")

        else:
            raise ValueError("Invalid stat_type. Use 'highest' or 'lowest'.")
        
        return {continent: value}
    
    except Exception as e:
        logger.log(f"Error in continent_stat: {str(e)}")
        return {"error": str(e)}

def country_stat(dataframe, attribute : str = "Population", stat_type :str = "highest"):
    try : 
        if stat_type.lower() == "highest":
            index= dataframe[attribute].idxmax()
        elif stat_type.lower() == "lowest":
            index= dataframe[attribute].idxmin()

        country = dataframe['Country'][index]
        requested_attribute = dataframe[attribute][index]
        result = {country:requested_attribute.item()}
        logger.log(f"Displaying the country with {stat_type} {attribute} in the data")
        return result
    except Exception as e:
        return f"Unable to fetch the data. Error {e}"

    

# def list_country_by_continent(dataframe,continent):
#     try:
#         df_countries = dataframe[dataframe['Continent'] == continent]
#         countries= df_countries['Country'].to_list()
#         logger.log("Separated data by continent")
#         return countries
#     except Exception as e:
#         return f"{e}"

# def get_stat_by_continent(df ,continent: str, data_type: str, stat: str , ):

#     if continent.lower() == "NorthAmerica".lower():
#         continent = "North America"
#     if continent.lower() == "SouthAmerica".lower():
#         continent = "South America"

#     valid_stats = ['max', 'min', 'mean' , 'sum' , 'count']
#     if stat not in valid_stats:
#         return f"Invalid stat. Please use one of the following: {valid_stats}."
    
#     continent_population_stats = df.groupby('Continent')[data_type].agg(
#         Maximum='max', Minimum='min', Average = 'mean',Total='sum' , Number_of_Countries = 'count')
    
#     continent_countries = df[df['Continent'] == continent]

#     if continent not in continent_population_stats.index:
#         return f"Continent '{continent}' not found in the data."
    
#     if stat == 'max':
#         population_result = continent_population_stats.loc[continent]['Maximum']
#         country_id = continent_countries.loc[continent_countries[data_type].idxmax()]
#         country_name = country_id['Country']
#         population_value = country_id[data_type]
#         return f"{continent}'s {stat} {data_type} is {int(population_result)}. Country: {country_name} , {data_type} :{population_value}"
#     if stat == 'min':  
#         population_result = continent_population_stats.loc[continent]['Minimum']
#         country_id = continent_countries.loc[continent_countries[data_type].idxmin()]
#         country_name = country_id['Country']
#         population_value = country_id[data_type]
#         return f"{continent}'s {stat} {data_type} is {int(population_result)}. Country: {country_name} , {data_type} :{population_value}"
#     if stat == 'mean':
#         population_result = continent_population_stats.loc[continent]['Average']
#         return f"{continent}'s average {data_type} is {int(population_result)}"
#     if stat == 'sum':
#         population_result = continent_population_stats.loc[continent]['Total']
#         return f"{continent}'s total {data_type} is {int(population_result)}"
#     if stat == 'count' :
#         population_result = continent_population_stats.loc[continent]['Number_of_Countries']
#         return f"Total countries in {continent} is {int(population_result)}"
    
# def get_continent_with_max_value(dataframe, key, value):
#     max_id = dataframe[value].idxmax()
#     value_num = dataframe[value][max_id]
#     value_country = dataframe[key][max_id]
#     return f"{value_country}'s max {value} is {value_num}"