scripts/utils/analyze_dataset.py

import pandas as pd
import sys

# Cesta k datasetu
dataset_path = 'data/processed/url_dataset_cleaned.csv'

try:
    # Načítanie datasetu
    df = pd.read_csv(dataset_path)
    
    # Analýza labelov
    print("=" * 50)
    print("ANALÝZA DATASETU")
    print("=" * 50)
    print(f"\nCelkový počet záznamov: {len(df)}")
    print(f"\nRozdělenie labelov:")
    print("-" * 50)
    
    label_counts = df['label'].value_counts().sort_index()
    
    for label, count in label_counts.items():
        percentage = (count / len(df)) * 100
        print(f"Label {label}: {count} záznamov ({percentage:.2f}%)")
    
    print("-" * 50)
    print(f"\nPomer label 0 / label 1: {label_counts.get(0, 0) / label_counts.get(1, 1):.2f}")
    
    # Kontrola chýbajúcich hodnôt
    missing = df['label'].isna().sum()
    if missing > 0:
        print(f"\nChýbajúce labely: {missing}")
    
    print("\n" + "=" * 50)
    
except FileNotFoundError:
    print(f"Súbor '{dataset_path}' nebol nájdený")
    print(f"Aktuálny adresár: {sys.path[0]}")
except KeyError:
    print("Stĺpec 'label' neexistuje v datasete")
    print(f"Dostupné stĺpce: {list(df.columns)}") # type: ignore
except Exception as e:
    print(f"Chyba: {e}")