Eurojackpot-Tipp-Generator/scripts/utils/zahlen_umschluesseln.py

#!/usr/bin/env python3
"""
Eurojackpot Zahlen-Umschlüsselung

Fügt neue Spalten z1, z2, z3, z4, z5 hinzu mit umschlüsselten Werten:
1-5 → 1, 6-10 → 2, 11-15 → 3, 16-20 → 4, 21-25 → 5,
26-30 → 6, 31-35 → 7, 36-40 → 8, 41-45 → 9, 46-50 → 10
"""

import pandas as pd

def convert_number_to_group(number):
    """Konvertiert eine Zahl (1-50) in eine Gruppe (1-10)."""
    if 1 <= number <= 5:
        return 1
    elif 6 <= number <= 10:
        return 2
    elif 11 <= number <= 15:
        return 3
    elif 16 <= number <= 20:
        return 4
    elif 21 <= number <= 25:
        return 5
    elif 26 <= number <= 30:
        return 6
    elif 31 <= number <= 35:
        return 7
    elif 36 <= number <= 40:
        return 8
    elif 41 <= number <= 45:
        return 9
    elif 46 <= number <= 50:
        return 10
    else:
        return 0  # Fehlerfall

def process_number_conversion():
    """Führt die Zahlenumschlüsselung durch."""
    
    # Eingabedatei laden
    input_file = "/Users/sebastianfrohlich/Library/Mobile Documents/com~apple~CloudDocs/Jupyter Notebooks/Eurojackpot/data/AlleEurojackpotzahlen.csv"
    
    print("🔢 EUROJACKPOT ZAHLEN-UMSCHLÜSSELUNG")
    print("="*50)
    
    # Daten laden
    print(f"📁 Lade Daten aus: AlleEurojackpotzahlen.csv")
    df = pd.read_csv(input_file, sep=';')
    print(f"✅ {len(df)} Ziehungen geladen")
    
    # Umschlüsselungsschema anzeigen
    print(f"\n📋 UMSCHLÜSSELUNGSSCHEMA:")
    print("="*30)
    ranges = [
        (1, 5, 1), (6, 10, 2), (11, 15, 3), (16, 20, 4), (21, 25, 5),
        (26, 30, 6), (31, 35, 7), (36, 40, 8), (41, 45, 9), (46, 50, 10)
    ]
    
    for start, end, group in ranges:
        print(f"Zahlen {start:2}-{end:2} → Gruppe {group:2}")
    
    # Neue Spalten erstellen
    print(f"\n🔄 Erstelle neue Spalten z1, z2, z3, z4, z5...")
    
    source_columns = ['Z1', 'Z2', 'Z3', 'Z4', 'Z5']
    target_columns = ['z1', 'z2', 'z3', 'z4', 'z5']
    
    for source_col, target_col in zip(source_columns, target_columns):
        df[target_col] = df[source_col].apply(convert_number_to_group)
        print(f"  {source_col} → {target_col} ✅")
    
    # Erste 5 Beispiele anzeigen
    print(f"\n📊 BEISPIEL-UMSCHLÜSSELUNGEN (erste 5 Ziehungen):")
    print("="*60)
    print(f"{'Datum':<12} {'Z1→z1':<8} {'Z2→z2':<8} {'Z3→z3':<8} {'Z4→z4':<8} {'Z5→z5':<8}")
    print("-" * 60)
    
    for i in range(min(5, len(df))):
        row = df.iloc[i]
        datum = row['datum']
        conversions = []
        for source_col, target_col in zip(source_columns, target_columns):
            original = row[source_col]
            converted = row[target_col]
            conversions.append(f"{original:2}→{converted}")
        
        print(f"{datum:<12} {conversions[0]:<8} {conversions[1]:<8} {conversions[2]:<8} {conversions[3]:<8} {conversions[4]:<8}")
    
    # Statistiken der Umschlüsselung
    print(f"\n📈 STATISTIKEN DER UMSCHLÜSSELTEN WERTE:")
    print("="*45)
    
    # Häufigkeit der Gruppen über alle Positionen
    all_converted_values = []
    for target_col in target_columns:
        all_converted_values.extend(df[target_col].tolist())
    
    from collections import Counter
    group_counts = Counter(all_converted_values)
    
    print(f"Verteilung der Gruppen (1-10) über alle Positionen:")
    total_values = len(all_converted_values)
    
    for group in range(1, 11):
        count = group_counts.get(group, 0)
        percentage = (count / total_values) * 100
        original_range = f"{(group-1)*5 + 1}-{group*5}"
        print(f"Gruppe {group:2} ({original_range:5}): {count:4}x ({percentage:5.1f}%)")
    
    # Statistiken pro Position
    print(f"\n📊 VERTEILUNG PRO POSITION:")
    print("="*35)
    
    for i, target_col in enumerate(target_columns, 1):
        position_counts = Counter(df[target_col])
        print(f"\nPosition z{i} ({target_col}):")
        for group in range(1, 11):
            count = position_counts.get(group, 0)
            percentage = (count / len(df)) * 100
            print(f"  Gruppe {group:2}: {count:3}x ({percentage:4.1f}%)")
    
    # Häufigste Kombinationen der umschlüsselten Werte
    print(f"\n🎯 HÄUFIGSTE KOMBINATIONEN (umschlüsselt):")
    print("="*45)
    
    # Kombinationen als Strings erstellen
    df['kombination_umschluesselt'] = df.apply(
        lambda row: f"{row['z1']}-{row['z2']}-{row['z3']}-{row['z4']}-{row['z5']}", axis=1
    )
    
    combination_counts = Counter(df['kombination_umschluesselt'])
    
    print(f"Top 15 Kombinationen (z1-z2-z3-z4-z5):")
    for i, (combination, count) in enumerate(combination_counts.most_common(15), 1):
        percentage = (count / len(df)) * 100
        print(f"{i:2}. {combination:15} {count:3}x ({percentage:4.1f}%)")
    
    # Muster-Analyse
    print(f"\n🔍 MUSTER-ANALYSE:")
    print("="*25)
    
    # Aufsteigende Kombinationen
    ascending_count = 0
    descending_count = 0
    
    for _, row in df.iterrows():
        values = [row[col] for col in target_columns]
        if values == sorted(values):
            ascending_count += 1
        elif values == sorted(values, reverse=True):
            descending_count += 1
    
    print(f"Aufsteigende Kombinationen: {ascending_count} ({(ascending_count/len(df)*100):.1f}%)")
    print(f"Absteigende Kombinationen: {descending_count} ({(descending_count/len(df)*100):.1f}%)")
    
    # Gleiche Werte
    same_values_stats = {}
    for num_same in range(2, 6):
        count = 0
        for _, row in df.iterrows():
            values = [row[col] for col in target_columns]
            value_counts = Counter(values)
            if max(value_counts.values()) >= num_same:
                count += 1
        same_values_stats[num_same] = count
        print(f"Mindestens {num_same} gleiche Werte: {count} ({(count/len(df)*100):.1f}%)")
    
    # Bereiche der umschlüsselten Werte
    print(f"\n📋 BEREICHSANALYSE (umschlüsselt):")
    print("="*35)
    
    # Niedrig (1-3), Mittel (4-7), Hoch (8-10)
    for i, target_col in enumerate(target_columns, 1):
        low_count = sum(1 for val in df[target_col] if 1 <= val <= 3)
        mid_count = sum(1 for val in df[target_col] if 4 <= val <= 7)
        high_count = sum(1 for val in df[target_col] if 8 <= val <= 10)
        
        low_pct = (low_count / len(df)) * 100
        mid_pct = (mid_count / len(df)) * 100
        high_pct = (high_count / len(df)) * 100
        
        print(f"z{i}: Niedrig(1-3)={low_pct:4.1f}% | Mittel(4-7)={mid_pct:4.1f}% | Hoch(8-10)={high_pct:4.1f}%")
    
    # Ausgabedatei speichern
    output_file = "/Users/sebastianfrohlich/Library/Mobile Documents/com~apple~CloudDocs/Jupyter Notebooks/Eurojackpot/AlleEurojackpotzahlen_umschluesselt.csv"
    
    print(f"\n💾 DATEI SPEICHERN:")
    print("="*25)
    
    # Spalten neu ordnen (Original + neue Spalten)
    column_order = ['tag', 'datum', 'Z1', 'Z2', 'Z3', 'Z4', 'Z5', 'z1', 'z2', 'z3', 'z4', 'z5', 'SZ1', 'SZ2', 'kombination_umschluesselt']
    
    # Prüfen welche Spalten existieren
    available_columns = [col for col in column_order if col in df.columns]
    df_output = df[available_columns]
    
    df_output.to_csv(output_file, sep=';', index=False)
    print(f"✅ Umschlüsselte Daten gespeichert: AlleEurojackpotzahlen_umschluesselt.csv")
    print(f"📊 Anzahl Spalten: {len(df_output.columns)}")
    print(f"📈 Anzahl Zeilen: {len(df_output)}")
    
    print(f"\n🔍 NEUE SPALTEN:")
    for col in ['z1', 'z2', 'z3', 'z4', 'z5', 'kombination_umschluesselt']:
        if col in df_output.columns:
            print(f"  ✅ {col}")
    
    return df_output

if __name__ == "__main__":
    result_df = process_number_conversion()