"""Focus on the key SKU master columns we care about."""
from pathlib import Path
import pandas as pd

p = Path(__file__).parent / "SifrarnikArtikala.xlsx"
df = pd.read_excel(p, sheet_name="SifrarnikArtikala")
print(f"shape: {df.shape}")

key_cols = [
    "Šifra", "Naziv artikla/usluge", "Status",
    "Proizvođač", "Dobavljač",
    "VPC", "MPC",
    "Dev.cj.", "Dev.MPC",
    "Planska devizna VPC",
    "Uvozna dev. cijena",
    "NabCj",
    "Minimalna količina narudžbe (MOQ)",
    "Pakiranje komada Karton", "Pakiranje komada Paleta",
    "Kategorija", "Kategorije artikala",
]
sub = df[[c for c in key_cols if c in df.columns]]
print("\nfirst 8 rows of key cols:")
print(sub.head(8).to_string())
print("\n6 random rows:")
print(sub.sample(6, random_state=2).to_string())

# Stats on Dobavljač + NabCj
print("\n=== Stats ===")
print(f"  Šifra unique: {df['Šifra'].nunique()}")
print(f"  Dobavljač unique: {df['Dobavljač'].nunique()}")
print(f"  Status counts:\n{df['Status'].value_counts().head()}")
print(f"  rows with NabCj>0: {(df['NabCj']>0).sum()}")
print(f"  rows with VPC>0:   {(df['VPC']>0).sum()}")
print(f"  rows with MPC>0:   {(df['MPC']>0).sum()}")
print(f"  NabCj describe:\n{df[df['NabCj']>0]['NabCj'].describe()}")
print(f"  VPC   describe:\n{df[df['VPC']>0]['VPC'].describe()}")

# Distinct suppliers count
print(f"\n  Distinct suppliers (top 10 by frequency):")
print(df["Dobavljač"].value_counts().head(10).to_string())