Anton_wireframe/preprocessor/verify_database.py

#!/usr/bin/env python3
"""
Quick verification script for the database
"""

from models import CompanyTable, FundTable, InvestorTable, SectorTable, get_db_session


def verify_database():
    session = get_db_session()

    print("=" * 60)
    print("🔍 DATABASE VERIFICATION")
    print("=" * 60)

    # Count records
    investor_count = session.query(InvestorTable).count()
    company_count = session.query(CompanyTable).count()
    sector_count = session.query(SectorTable).count()
    fund_count = session.query(FundTable).count()

    print("\n📊 Record Counts:")
    print(f"   Investors: {investor_count:,}")
    print(f"   Companies: {company_count:,}")
    print(f"   Sectors: {sector_count:,}")
    print(f"   Funds: {fund_count:,}")

    # Check relationships
    investors_with_companies = (
        session.query(InvestorTable)
        .filter(InvestorTable.portfolio_companies.any())
        .count()
    )

    investors_with_sectors = (
        session.query(InvestorTable).filter(InvestorTable.sectors.any()).count()
    )

    print("\n🔗 Relationships:")
    print(f"   Investors with portfolio companies: {investors_with_companies:,}")
    print(f"   Investors with sectors: {investors_with_sectors:,}")

    # Sample data quality checks
    investors_with_website = (
        session.query(InvestorTable).filter(InvestorTable.website.isnot(None)).count()
    )

    investors_with_investments = (
        session.query(InvestorTable)
        .filter(
            InvestorTable.number_of_investments.isnot(None),
            InvestorTable.number_of_investments > 0,
        )
        .count()
    )

    print("\n✅ Data Quality:")
    print(
        f"   Investors with website: {investors_with_website:,} ({investors_with_website / investor_count * 100:.1f}%)"
    )
    print(
        f"   Investors with investment count: {investors_with_investments:,} ({investors_with_investments / investor_count * 100:.1f}%)"
    )

    # Check for enrichment readiness
    investors_with_aum = (
        session.query(InvestorTable).filter(InvestorTable.aum.isnot(None)).count()
    )

    investors_with_headquarters = (
        session.query(InvestorTable)
        .filter(InvestorTable.headquarters.isnot(None))
        .count()
    )

    investors_with_thesis = (
        session.query(InvestorTable)
        .filter(InvestorTable.investment_thesis.isnot(None))
        .count()
    )

    print("\n🎯 Enrichment Status:")
    print(f"   Investors with AUM: {investors_with_aum:,}")
    print(f"   Investors with HQ: {investors_with_headquarters:,}")
    print(f"   Investors with thesis: {investors_with_thesis:,}")
    print(f"   Investors with funds: {fund_count:,}")

    if fund_count == 0:
        print("\n⚠️  No funds found - enrichment needed!")

    # Show a random sample
    import random

    sample_investors = session.query(InvestorTable).limit(1000).all()
    sample = random.sample(sample_investors, min(3, len(sample_investors)))

    print("\n📋 Random Sample:")
    for inv in sample:
        print(f"\n   {inv.name}")
        print(f"   Website: {inv.website or 'N/A'}")
        print(f"   Investments: {inv.number_of_investments or 'N/A'}")
        print(f"   Portfolio: {len(inv.portfolio_companies)} companies")
        print(f"   Sectors: {len(inv.sectors)} sectors")
        if inv.funds:
            print(f"   Funds: {len(inv.funds)}")

    session.close()

    print("\n" + "=" * 60)

    if fund_count == 0:
        print("📝 Next step: Run enrichment script")
        print("   python enrich_investors.py enriched_investors.csv")
    else:
        print("✅ Database is enriched and ready!")

    print("=" * 60)


if __name__ == "__main__":
    verify_database()