from pathlib import Path

import matplotlib.pyplot as plt
import pandas as pd

# baca ke variabel 'dataset'
csv_path = Path(__file__).resolve().parents[2] / "retail_raw_reduced.csv"
dataset = pd.read_csv(csv_path)

# buat kolom order_month dari order_date (jika belum ada)
dataset['order_date'] = pd.to_datetime(dataset['order_date'])
dataset['order_month'] = dataset['order_date'].dt.strftime('%Y-%m')

# mengambil informasi top 5 brands berdasarkan quantity
top_brands = (dataset[dataset['order_month'] == '2019-12'].groupby('brand')['quantity']
              .sum()
              .reset_index()
              .sort_values(by='quantity', ascending=False)
              .head(5))

# membuat dataframe baru, filter hanya di bulan Desember 2019 dan hanya top 5 brands
dataset_top5brand_dec = dataset[(dataset['order_month'] == '2019-12') & 
                                (dataset['brand'].isin(top_brands['brand'].to_list()))]

# print top brands
print(top_brands)