version5_adapter_pattern.py

import pandas as pd
import uuid
from utils import XMLAdapter

# ↓↓↓ BUENA PRÁCTICA A LA HORA DE CREAR FUNCIONES ↓↓↓
# →→→ HACER QUE REALICEN POCAS TAREAS POR FUNCIÓN ←←←

# Creando la función 'pipeline'
def pipeline(*steps):
    def wrapper(inputs):
        for step in steps:
            inputs = apply(step, inputs)
        return inputs
    return wrapper

# Formateado y filtrado
def step1(df):
    df.columns = df.columns.str.lower().str.replace(" ", "_")
    df = df[df["payment_method"] == "PayPal"]
    df = df[df["frequency_of_purchases"].isin(["Weekly", "Fortnightly", "bi-weekly"])]
    return df

# Agrupación y rankeo
def step2(df):
    df = df[["customer_id", "category", "purchase_amount_(usd)"]].groupby(["customer_id", "category"]).sum().reset_index()
    df["rank"] = df.groupby("category")["purchase_amount_(usd)"].rank(method="dense", ascending=False)
    df = df[df["rank"] == 1]
    return df

# Convertir el resultado en una lista que por dentro contiene tuplas
def step3(df):
    values = df[["customer_id", "category"]].to_dict()
    customers = [x for x in values["customer_id"].values()]
    categories = [x for x in values["category"].values()]
    result = list(zip(customers, categories))
    return result

def apply(step, values):
    return [step(value) for value in values]

# Cargar los datos
df1 = XMLAdapter("shopping_behavior_2023.csv").get_data()
df2 = XMLAdapter("shopping_behavior_2024.csv").get_data()
df3 = XMLAdapter("shopping_behavior_2025.csv").get_data()

# Procesar todo
p = pipeline(step1, step2, step3)
results = p([df1, df2, df3])

# Escribir cada resultado en un archivo propio
years = ["2023", "2024", "2025"]
for year, result_list in zip(years, results):
    filename = f"result_{year}.txt"
    with open(filename, "w") as f:
        for customer_id, category in result_list:
            f.write(f"{customer_id}, {category}\n")
        print(f"Archivo result_{year}.txt creado con {len(result_list)} registros")