German Tank Problem/ Panzer III variation

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

# Known total production of Panzer III tanks
total_production = 5774

# Monthly production data (approximation, replace with actual data if available)
# Assuming production started in January 1939 and ended in December 1943
months = pd.date_range(start='1939-01-01', end='1943-12-31', freq='M')
monthly_production = np.random.poisson(lam=total_production/len(months), size=len(months))

# Adjust monthly production to ensure the total matches the known production number
monthly_production = np.round(monthly_production * (total_production / monthly_production.sum())).astype(int)

monthly_data = {
    'Month': months,
    'Production': monthly_production
}

variant_data = {
    'Variant': ['Ausf. E', 'Ausf. F', 'Ausf. G', 'Ausf. H', 'Ausf. J'],
    'Units': [1200, 1300, 1800, 2000, 2000]  # Example units, adjust based on actual data
}

# Adjust variant units to match the total production
variant_total = sum(variant_data['Units'])
variant_data['Units'] = np.round(np.array(variant_data['Units']) * (total_production / variant_total)).astype(int)

# Create DataFrames
df_monthly = pd.DataFrame(monthly_data)
df_variant = pd.DataFrame(variant_data)

# Calculate proportion of each variant
variant_total = df_variant['Units'].sum()
df_variant['Proportion'] = df_variant['Units'] / variant_total

# Adjust for shortages (example shortage factors)
shortage_factors = {
    'manpower': 0.15,  # 15% reduction
    'material': 0.10   # 10% reduction for specific variants
}

# Adjust monthly production for shortages
df_monthly['Production_Adjusted'] = df_monthly['Production'] * (1 - shortage_factors['manpower'])

# Adjust variant production for material shortages
df_variant['Units_Adjusted'] = df_variant['Units'] * (1 - shortage_factors['material'])

# Output results
print("\nAdjusted Monthly Production:")
print(df_monthly)

print("\nAdjusted Variant Production:")
print(df_variant)

# Example of serial number analysis
serial_numbers = np.arange(101, 5875)  # Example serial numbers (replace with actual data if available)
highest_serial_number = serial_numbers[-1]
print(f"Highest Serial Number: {highest_serial_number}")

# Estimate total production based on highest serial number
estimated_total_production = highest_serial_number + 1  # +1 if considering the last number observed
print(f"Estimated Total Production (based on serial numbers): {estimated_total_production} tanks")

# Estimate total production for each variant (assuming the same proportion)
df_variant['Estimated_Units'] = df_variant['Proportion'] * estimated_total_production
print("\nEstimated Variant Production:")
print(df_variant)

# Plotting Monthly Production
plt.figure(figsize=(16, 8))

# Plot Aggregated Data
plt.subplot(1, 2, 1)
sns.lineplot(x='Month', y='Production', data=df_monthly, marker='o', label='Original Production')
sns.lineplot(x='Month', y='Production_Adjusted', data=df_monthly, marker='o', color='red', linestyle='--', label='Adjusted Production')
plt.title('Monthly Production of Panzer III Tanks (1939-1943)')
plt.xlabel('Month')
plt.ylabel('Production')
plt.xticks(rotation=45)
plt.grid(True)
plt.legend()

# Plot Variant Production
plt.subplot(1, 2, 2)
sns.barplot(x='Variant', y='Units', data=df_variant, color='blue', label='Original Units')
sns.barplot(x='Variant', y='Units_Adjusted', data=df_variant, color='red', alpha=0.5, label='Adjusted Units')
plt.title('Production by Variant')
plt.xlabel('Variant')
plt.ylabel('Units')
plt.legend()

plt.tight_layout()
plt.show()