# ===================================================================
# MODULE 8, LESSON 6: LEADING AND SCALING DATA SCIENCE
# ===================================================================

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime, timedelta
import warnings
warnings.filterwarnings('ignore')

# Set style
sns.set_style("whitegrid")
np.random.seed(42)

print("="*70)
print("LEADING AND SCALING DATA SCIENCE IN FINANCIAL INSTITUTIONS")
print("="*70)

# ----------------------------------------------------------------
# PART A: DATA SCIENCE STRATEGY MAP
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART A: Data Science Strategy Map")
print("-"*60)

strategy_map = pd.DataFrame({
    'Strategic Objective': [
        'Improve Customer Experience',
        'Reduce Credit Risk',
        'Increase Operational Efficiency',
        'Comply with Regulations'
    ],
    'Data Science Initiative': [
        'Churn prediction, personalisation, next-best-action',
        'Default prediction, stress testing, portfolio optimisation',
        'Process automation, anomaly detection, resource optimisation',
        'Model governance, explainability, fairness testing'
    ],
    'Success Metrics': [
        'NPS increase > 10%, churn reduction > 15%',
        'AUC > 0.80, default reduction > 10%',
        'Cost savings > 20%, efficiency increase > 30%',
        '100% regulatory compliance, zero audit findings'
    ],
    'Timeline': [
        '6-12 months',
        '12-18 months',
        '6-12 months',
        'Ongoing'
    ],
    'Owner': [
        'Head of Customer Analytics',
        'Head of Credit Risk',
        'Head of Operations',
        'Head of Model Governance'
    ]
})

print("Data Science Strategy Map:")
print(strategy_map.to_string(index=False))

# ----------------------------------------------------------------
# PART B: TEAM STRUCTURE AND SCALING
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART B: Team Structure and Scaling")
print("-"*60)

# Define team stages
team_stages = pd.DataFrame({
    'Stage': ['Startup', 'Growth', 'Mature', 'Enterprise'],
    'Team Size': ['3-5', '10-20', '30-50', '50-100+'],
    'Structure': ['Flat', 'Functional', 'Hybrid', 'Matrix'],
    'Key Roles': ['Data Scientists', '+ Engineers', '+ Product Managers', '+ Leaders'],
    'Focus': ['Exploration', 'Delivery', 'Scale', 'Innovation']
})

print("Team Evolution Stages:")
print(team_stages.to_string(index=False))

# Visualise team growth
fig, ax = plt.subplots(figsize=(10, 6))
stages = ['Startup', 'Growth', 'Mature', 'Enterprise']
sizes = [5, 15, 40, 80]
ax.bar(stages, sizes, color=['blue', 'green', 'orange', 'red'], alpha=0.7)
ax.set_xlabel('Stage')
ax.set_ylabel('Team Size')
ax.set_title('Data Science Team Scaling Over Time')
for i, v in enumerate(sizes):
    ax.text(i, v + 2, str(v), ha='center', fontweight='bold')
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.savefig('team_scaling.png', dpi=300, bbox_inches='tight')
plt.show()
print("Team scaling chart saved as 'team_scaling.png'")

# ----------------------------------------------------------------
# PART C: BUDGET ALLOCATION
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART C: Budget Allocation")
print("-"*60)

budget = pd.DataFrame({
    'Category': ['Personnel', 'Technology (Cloud)', 'Data Acquisition', 'Training', 'External Services', 'Other'],
    'Amount ($M)': [5.0, 1.5, 0.5, 0.3, 0.5, 0.2],
    'Percentage': ['62.5%', '18.8%', '6.3%', '3.8%', '6.3%', '2.5%']
})

print("Annual Budget Allocation:")
print(budget.to_string(index=False))

# Visualise
fig, ax = plt.subplots(figsize=(8, 6))
ax.pie(budget['Amount ($M)'], labels=budget['Category'], autopct='%1.1f%%', 
       colors=sns.color_palette('Set3'), startangle=90)
ax.set_title('Data Science Budget Allocation')
plt.tight_layout()
plt.savefig('budget_allocation.png', dpi=300, bbox_inches='tight')
plt.show()
print("Budget allocation chart saved as 'budget_allocation.png'")

# ----------------------------------------------------------------
# PART D: ROI CALCULATION
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART D: ROI Calculation Example")
print("-"*60)

def calculate_roi(investment, annual_benefits, annual_costs, years=3):
    """Calculate ROI for a data science project."""
    net_annual = annual_benefits - annual_costs
    total_benefits = net_annual * years
    roi = (total_benefits - investment) / investment * 100
    return {
        'Investment': investment,
        'Annual Net Benefit': net_annual,
        'Total Benefit (3 years)': total_benefits,
        'ROI (%)': roi
    }

# Example: Fraud Detection
fraud_roi = calculate_roi(
    investment=2_000_000,
    annual_benefits=5_000_000,
    annual_costs=500_000,
    years=3
)

print("Fraud Detection Model ROI:")
for key, value in fraud_roi.items():
    if isinstance(value, int):
        print(f"  {key}: ${value:,.2f}")
    else:
        print(f"  {key}: {value:.2f}%")

# Multiple projects
projects = [
    {'name': 'Fraud Detection', 'investment': 2_000_000, 'benefits': 5_000_000, 'costs': 500_000},
    {'name': 'Churn Prediction', 'investment': 1_500_000, 'benefits': 3_000_000, 'costs': 300_000},
    {'name': 'Portfolio Optimisation', 'investment': 1_000_000, 'benefits': 2_500_000, 'costs': 250_000},
    {'name': 'Credit Scoring', 'investment': 1_200_000, 'benefits': 4_000_000, 'costs': 400_000},
]

roi_results = []
for p in projects:
    roi_data = calculate_roi(p['investment'], p['benefits'], p['costs'])
    roi_results.append({
        'Project': p['name'],
        'Investment ($M)': p['investment'] / 1_000_000,
        'Annual Net Benefit ($M)': roi_data['Annual Net Benefit'] / 1_000_000,
        'ROI (3yrs)': roi_data['ROI (%)']
    })

roi_df = pd.DataFrame(roi_results)
print("\nProject ROI Comparison:")
print(roi_df.to_string(index=False))

# Visualise ROI
fig, ax = plt.subplots(figsize=(10, 6))
bars = ax.bar(roi_df['Project'], roi_df['ROI (3yrs)'], color='green', alpha=0.7)
ax.set_xlabel('Project')
ax.set_ylabel('ROI (%)')
ax.set_title('Project ROI Comparison')
for bar, val in zip(bars, roi_df['ROI (3yrs)']):
    ax.text(bar.get_x() + bar.get_width()/2, bar.get_height() + 10, 
            f'{val:.0f}%', ha='center', va='bottom', fontweight='bold')
ax.axhline(y=200, color='red', linestyle='--', label='Target ROI (200%)')
ax.legend()
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.savefig('roi_comparison.png', dpi=300, bbox_inches='tight')
plt.show()

# ----------------------------------------------------------------
# PART E: CULTURE ASSESSMENT
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART E: Data-Driven Culture Assessment")
print("-"*60)

culture_metrics = {
    'Metric': ['Leadership Commitment', 'Data Literacy', 'Data Accessibility', 
               'Tooling/Infrastructure', 'Talent/Skills', 'Innovation Culture'],
    'Current Score (1-5)': [3, 2, 3, 4, 3, 2],
    'Target Score (1-5)': [5, 4, 5, 5, 4, 5],
    'Gap': [2, 2, 2, 1, 1, 3],
    'Action Plan': [
        'Executive sponsorship program, regular AI updates',
        'Data literacy training for all employees',
        'Self-service analytics platform, data democratisation',
        'Cloud migration, modern tooling',
        'Hiring plan, upskilling programs, retention strategy',
        'Hackathons, innovation labs, partnerships'
    ]
}

culture_df = pd.DataFrame(culture_metrics)
print("Data Culture Assessment:")
print(culture_df.to_string(index=False))

# Radar chart
from math import pi
fig, ax = plt.subplots(figsize=(8, 8), subplot_kw={'projection': 'polar'})

metrics = culture_df['Metric'].tolist()
current = culture_df['Current Score (1-5)'].tolist()
target = culture_df['Target Score (1-5)'].tolist()

N = len(metrics)
angles = [n / float(N) * 2 * pi for n in range(N)]
angles += angles[:1]

current += current[:1]
target += target[:1]

ax.plot(angles, current, 'o-', linewidth=2, label='Current State', color='blue')
ax.fill(angles, current, alpha=0.1, color='blue')
ax.plot(angles, target, 'o-', linewidth=2, label='Target State', color='green', linestyle='--')
ax.fill(angles, target, alpha=0.1, color='green')

ax.set_xticks(angles[:-1])
ax.set_xticklabels(metrics, size=9)
ax.set_ylim(0, 5)
ax.set_yticks([1, 2, 3, 4, 5])
ax.set_yticklabels(['1', '2', '3', '4', '5'], size=8)
ax.legend(loc='upper right', bbox_to_anchor=(1.3, 1.0))
ax.set_title('Data-Driven Culture Assessment', size=14, pad=20)

plt.tight_layout()
plt.savefig('culture_assessment_radar.png', dpi=300, bbox_inches='tight')
plt.show()
print("Culture assessment chart saved as 'culture_assessment_radar.png'")

# ----------------------------------------------------------------
# PART F: TALENT DEVELOPMENT FRAMEWORK
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART F: Talent Development Framework")
print("-"*60)

career_framework = pd.DataFrame({
    'Level': ['Junior', 'Mid-Level', 'Senior', 'Lead', 'Principal', 'Director'],
    'Years Experience': ['0-2', '2-5', '5-8', '8-12', '12-15', '15+'],
    'Key Skills': [
        'Technical basics, SQL, Python', 'ML, statistics, domain knowledge', 
        'Advanced ML, mentoring, project leadership', 'Technical strategy, cross-functional', 
        'Innovation, thought leadership, enterprise impact', 'Executive leadership, vision'
    ],
    'Responsibilities': [
        'Assist with analysis', 'Build models', 'Lead projects',
        'Coach team, set standards', 'Shape strategy', 'Lead function'
    ],
    'Training Focus': [
        'Core skills, coding', 'ML, feature engineering', 'Leadership, communication',
        'Strategic thinking, stakeholder management', 'Innovation, industry trends', 'Executive leadership'
    ]
})

print("Career Development Framework:")
print(career_framework.to_string(index=False))

# ----------------------------------------------------------------
# PART G: LEADERSHIP DEVELOPMENT PLAN
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART G: Leadership Development Plan")
print("-"*60)

leadership_plan = {
    "Quarter 1": {
        "Focus": "Build foundational leadership skills",
        "Activities": [
            "Read 2 leadership books (e.g., 'The First 90 Days', 'Leaders Eat Last')",
            "Attend a leadership training workshop",
            "Find a mentor (senior leader)",
            "Volunteer to lead a small project"
        ]
    },
    "Quarter 2": {
        "Focus": "Develop strategic thinking",
        "Activities": [
            "Learn about business strategy (MBA courses, case studies)",
            "Attend strategy meetings with executives",
            "Lead a strategic initiative",
            "Develop a 3-year roadmap for your area"
        ]
    },
    "Quarter 3": {
        "Focus": "Enhance communication and influence",
        "Activities": [
            "Join Toastmasters or a speaking group",
            "Present to executive audience",
            "Write a blog or article on data science",
            "Build relationships across the organisation"
        ]
    },
    "Quarter 4": {
        "Focus": "Scale impact",
        "Activities": [
            "Mentor a junior team member",
            "Identify opportunities for scaling data science",
            "Drive a cross-functional initiative",
            "Evaluate and improve team processes"
        ]
    }
}

print("Leadership Development Plan (12 months):")
for quarter, details in leadership_plan.items():
    print(f"\n{quarter}:")
    print(f"  Focus: {details['Focus']}")
    print("  Activities:")
    for activity in details['Activities']:
        print(f"    • {activity}")

# ----------------------------------------------------------------
# PART H: SUMMARY AND RECOMMENDATIONS
# ----------------------------------------------------------------

print("\n" + "="*70)
print("PART H: Summary and Recommendations")
print("="*70)

print("""
Leading and Scaling Data Science – Key Takeaways:

1. Mindset Shift: From individual contributor to leader – focus on people, strategy, and outcomes.
2. Building a Function: Start with a pilot, scale across business units, and embed in operations.
3. Strategy: Align data science with business goals; prioritise initiatives.
4. Budgeting: Allocate resources to personnel, technology, and data.
5. Culture: Foster innovation, data literacy, and cross-functional collaboration.
6. ROI: Measure impact; demonstrate value to stakeholders.
7. Talent: Develop career paths; invest in training and mentorship.
8. Governance: Ensure compliance, risk management, and ethical AI.

Recommendations:
  - Start with a clear vision and 3-year roadmap.
  - Secure executive sponsorship early.
  - Build a strong, diverse team with complementary skills.
  - Focus on delivering value quickly; don't over-engineer.
  - Invest in data infrastructure and MLOps.
  - Promote a culture of experimentation and learning.
  - Develop your own leadership capabilities continuously.
  - Stay informed about emerging trends and technologies.
""")

print("="*70)
print("END OF LESSON 6 – MODULE 8")
print("="*70)