analizer.py

import pandas as pd

ruta_archivo = r"Punto_nuevo_CRM.xlsx"
nombre_hoja = "Result 1"


def extraer_data(nombre_hoja):
    df = pd.read_excel(ruta_archivo, sheet_name=nombre_hoja)
    return df

def main():
    with open('output.csv', 'w') as f:
        print('INICIO DE PROCESO')
        print('_______________________________________________________')
        df = extraer_data(nombre_hoja)
        deptos = df['depto'].unique()
        deptos = [d for d in deptos if d not in ('Guatemala', 'Nicaragua', 'Costa Rica', 'Honduras')]
        years = df['dm_y'].unique()

        results = {
          f'{key}': {
              f'{depto}': None
              for depto in deptos
          }
          for key in years
        }

        for index, row in df.iterrows():
            if row['dm_m'] == 1 and row['categoria'] in ('PYME', 'Internet') and 'internet' in row['producto'].lower():
                year = str(row['dm_y'])
                depto = row['depto']
                if results[year][depto] is not None:
                    if row['Mensual'] > results[year][depto]['Mensual']:
                        results[year][depto] = row
                    elif row['Mensual'] == results[year][depto]['Mensual'] and row['velocidad'] > results[year][depto]['velocidad']:
                        results[year][depto] = row
                else:
                    results[year][depto] = row
        # print(results)

        for year in results:
            for depto in results[year]:
                if results[year][depto] is not None:
                    line = results[year][depto]
                    f.write(f"{year},{depto},{line['Mensual']},{line['velocidad']}\n")

if __name__ == '__main__':
    main()