Refactor investor and fund schemas to support new check size range

- Removed deprecated `stage_focus` column from `InvestorTable` and `InvestorSchema`. - Updated `FundTable` to change `fund_size` from VARCHAR to INTEGER and added `check_size_lower` and `check_size_upper` columns. - Modified API routes to return investor-fund combinations as separate entries. - Created new `InvestorFundData` schema for combined investor-fund responses. - Implemented LLM parsing for check size range from estimated investment size. - Updated database migration script to reflect schema changes and ensure data integrity. - Removed obsolete verification and test scripts related to the old schema.
2025-10-07 15:24:36 +01:00
parent c0fbbdd917
commit d341cacb9a
12 changed files with 556 additions and 884 deletions
@@ -4,7 +4,11 @@ from db.db import get_db
 from db.models import InvestorTable, SectorTable
 from fastapi import APIRouter, Depends, HTTPException, Query
 from pydantic import BaseModel
-from schemas.router_schemas import InvestmentStage, InvestorData
+from schemas.router_schemas import (
+    InvestmentStage,
+    InvestorData,
+    InvestorFundData,
+)
 from sqlalchemy.orm import Session, selectinload

 router = APIRouter(tags=["Investor Routes"])
@@ -33,34 +37,95 @@ class InvestorUpdate(BaseModel):
    number_of_investments: Optional[int] = None


-@router.get("/investors", response_model=List[InvestorData])
+@router.get("/investors", response_model=List[InvestorFundData])
 def read_investors(db: Session = Depends(get_db)):
-    """Get all investors with their related data"""
+    """Get all investors with their funds as separate entries
+
+    Each investor-fund combination is returned as a separate row.
+    An investor with 3 funds will appear as 3 entries.
+    """
    investors = (
        db.query(InvestorTable)
        .options(
            selectinload(InvestorTable.portfolio_companies),
            selectinload(InvestorTable.team_members),
            selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
        )
        .all()
    )

-    # Transform InvestorTable objects to InvestorData format
-    investor_data_list = []
+    # Transform to InvestorFundData format (one row per investor-fund combination)
+    investor_fund_list = []
    for investor in investors:
-        investor_data = InvestorData(
-            investor=investor,  # This maps to InvestorSchema
-            portfolio_companies=investor.portfolio_companies,
-            team_members=investor.team_members,
-            sectors=investor.sectors,
-        )
-        investor_data_list.append(investor_data)
+        # If investor has funds, create one entry per fund
+        if investor.funds:
+            for fund in investor.funds:
+                investor_fund_data = InvestorFundData(
+                    # Investor fields
+                    investor_id=investor.id,
+                    investor_name=investor.name,
+                    investor_description=investor.description,
+                    investor_website=investor.website,
+                    investor_headquarters=investor.headquarters,
+                    aum=investor.aum,
+                    aum_as_of_date=investor.aum_as_of_date,
+                    aum_source_url=investor.aum_source_url,
+                    investment_thesis=investor.investment_thesis,
+                    portfolio_highlights=investor.portfolio_highlights,
+                    number_of_investments=investor.number_of_investments,
+                    # Fund fields
+                    fund_id=fund.id,
+                    fund_name=fund.fund_name,
+                    fund_size=fund.fund_size,
+                    fund_size_source_url=fund.fund_size_source_url,
+                    check_size_lower=fund.check_size_lower,
+                    check_size_upper=fund.check_size_upper,
+                    geographic_focus=fund.geographic_focus,
+                    investment_stage_focus=fund.investment_stage_focus,
+                    sector_focus=fund.sector_focus,
+                    # Related data (same for all funds of this investor)
+                    portfolio_companies=investor.portfolio_companies,
+                    team_members=investor.team_members,
+                    sectors=investor.sectors,
+                )
+                investor_fund_list.append(investor_fund_data)
+        else:
+            # If no funds, create one entry with null fund fields
+            investor_fund_data = InvestorFundData(
+                # Investor fields
+                investor_id=investor.id,
+                investor_name=investor.name,
+                investor_description=investor.description,
+                investor_website=investor.website,
+                investor_headquarters=investor.headquarters,
+                aum=investor.aum,
+                aum_as_of_date=investor.aum_as_of_date,
+                aum_source_url=investor.aum_source_url,
+                investment_thesis=investor.investment_thesis,
+                portfolio_highlights=investor.portfolio_highlights,
+                number_of_investments=investor.number_of_investments,
+                # Fund fields (null)
+                fund_id=None,
+                fund_name=None,
+                fund_size=None,
+                fund_size_source_url=None,
+                check_size_lower=None,
+                check_size_upper=None,
+                geographic_focus=None,
+                investment_stage_focus=None,
+                sector_focus=None,
+                # Related data
+                portfolio_companies=investor.portfolio_companies,
+                team_members=investor.team_members,
+                sectors=investor.sectors,
+            )
+            investor_fund_list.append(investor_fund_data)

-    return investor_data_list
+    return investor_fund_list


-@router.get("/investors/filter", response_model=List[InvestorData])
+@router.get("/investors/filter", response_model=List[InvestorFundData])
 def filter_investors(
    stage: Optional[InvestmentStage] = Query(
        None, description="Filter by investment stage"
@@ -75,13 +140,18 @@ def filter_investors(
    max_aum: Optional[int] = Query(None, description="Maximum AUM"),
    db: Session = Depends(get_db),
 ):
-    """Filter investors based on various criteria"""
+    """Filter investors based on various criteria
+
+    Returns investor-fund combinations as separate rows.
+    An investor with 3 funds will appear as 3 entries.
+    """

    # Start with base query
    query = db.query(InvestorTable).options(
        selectinload(InvestorTable.portfolio_companies),
        selectinload(InvestorTable.team_members),
        selectinload(InvestorTable.sectors),
+        selectinload(InvestorTable.funds),
    )

    # Apply filters
@@ -111,29 +181,86 @@ def filter_investors(

    investors = query.all()

-    # Transform to InvestorData format
-    investor_data_list = []
+    # Transform to InvestorFundData format (one row per investor-fund combination)
+    investor_fund_list = []
    for investor in investors:
-        investor_data = InvestorData(
-            investor=investor,
-            portfolio_companies=investor.portfolio_companies,
-            team_members=investor.team_members,
-            sectors=investor.sectors,
-        )
-        investor_data_list.append(investor_data)
+        # If investor has funds, create one entry per fund
+        if investor.funds:
+            for fund in investor.funds:
+                investor_fund_data = InvestorFundData(
+                    # Investor fields
+                    investor_id=investor.id,
+                    investor_name=investor.name,
+                    investor_description=investor.description,
+                    investor_website=investor.website,
+                    investor_headquarters=investor.headquarters,
+                    aum=investor.aum,
+                    aum_as_of_date=investor.aum_as_of_date,
+                    aum_source_url=investor.aum_source_url,
+                    investment_thesis=investor.investment_thesis,
+                    portfolio_highlights=investor.portfolio_highlights,
+                    number_of_investments=investor.number_of_investments,
+                    # Fund fields
+                    fund_id=fund.id,
+                    fund_name=fund.fund_name,
+                    fund_size=fund.fund_size,
+                    fund_size_source_url=fund.fund_size_source_url,
+                    check_size_lower=fund.check_size_lower,
+                    check_size_upper=fund.check_size_upper,
+                    geographic_focus=fund.geographic_focus,
+                    investment_stage_focus=fund.investment_stage_focus,
+                    sector_focus=fund.sector_focus,
+                    # Related data
+                    portfolio_companies=investor.portfolio_companies,
+                    team_members=investor.team_members,
+                    sectors=investor.sectors,
+                )
+                investor_fund_list.append(investor_fund_data)
+        else:
+            # If no funds, create one entry with null fund fields
+            investor_fund_data = InvestorFundData(
+                # Investor fields
+                investor_id=investor.id,
+                investor_name=investor.name,
+                investor_description=investor.description,
+                investor_website=investor.website,
+                investor_headquarters=investor.headquarters,
+                aum=investor.aum,
+                aum_as_of_date=investor.aum_as_of_date,
+                aum_source_url=investor.aum_source_url,
+                investment_thesis=investor.investment_thesis,
+                portfolio_highlights=investor.portfolio_highlights,
+                number_of_investments=investor.number_of_investments,
+                # Fund fields (null)
+                fund_id=None,
+                fund_name=None,
+                fund_size=None,
+                fund_size_source_url=None,
+                check_size_lower=None,
+                check_size_upper=None,
+                geographic_focus=None,
+                investment_stage_focus=None,
+                sector_focus=None,
+                # Related data
+                portfolio_companies=investor.portfolio_companies,
+                team_members=investor.team_members,
+                sectors=investor.sectors,
+            )
+            investor_fund_list.append(investor_fund_data)

-    return investor_data_list
+    return investor_fund_list


@router.get("/investors/{investor_id}", response_model=InvestorData)
 def read_investor(investor_id: int, db: Session = Depends(get_db)):
-    """Get a specific investor by ID"""
+    """Get a specific investor by ID with all their funds"""
    investor = (
        db.query(InvestorTable)
        .options(
            selectinload(InvestorTable.portfolio_companies),
            selectinload(InvestorTable.team_members),
            selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
        )
        .filter(InvestorTable.id == investor_id)
        .first()
@@ -142,12 +269,13 @@ def read_investor(investor_id: int, db: Session = Depends(get_db)):
    if not investor:
        raise HTTPException(status_code=404, detail="Investor not found")

-    # Transform to InvestorData format
+    # Transform to InvestorData format (includes funds array)
    return InvestorData(
        investor=investor,
        portfolio_companies=investor.portfolio_companies,
        team_members=investor.team_members,
        sectors=investor.sectors,
+        funds=investor.funds,
    )


@@ -166,6 +294,7 @@ def create_investor(investor: InvestorCreate, db: Session = Depends(get_db)):
            selectinload(InvestorTable.portfolio_companies),
            selectinload(InvestorTable.team_members),
            selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
        )
        .filter(InvestorTable.id == db_investor.id)
        .first()
@@ -177,6 +306,7 @@ def create_investor(investor: InvestorCreate, db: Session = Depends(get_db)):
        portfolio_companies=investor_with_relations.portfolio_companies,
        team_members=investor_with_relations.team_members,
        sectors=investor_with_relations.sectors,
+        funds=investor_with_relations.funds,
    )


@@ -205,6 +335,7 @@ def update_investor(
            selectinload(InvestorTable.portfolio_companies),
            selectinload(InvestorTable.team_members),
            selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
        )
        .filter(InvestorTable.id == investor_id)
        .first()
@@ -216,6 +347,7 @@ def update_investor(
        portfolio_companies=investor_with_relations.portfolio_companies,
        team_members=investor_with_relations.team_members,
        sectors=investor_with_relations.sectors,
+        funds=investor_with_relations.funds,
    )


@@ -233,13 +365,16 @@ def delete_investor(investor_id: int, db: Session = Depends(get_db)):
    return {"message": "Investor deleted successfully"}


-@router.get("/investors/{investor_id}/similar", response_model=List[InvestorData])
+@router.get("/investors/{investor_id}/similar", response_model=List[InvestorFundData])
 def find_similar_investors(
    investor_id: int,
    limit: int = Query(10, description="Maximum number of similar investors to return"),
    db: Session = Depends(get_db),
 ):
-    """Find investors similar to a given investor based on characteristics"""
+    """Find investors similar to a given investor based on characteristics
+
+    Returns investor-fund combinations as separate rows.
+    """

    # Get the target investor
    target_investor = (
@@ -248,6 +383,7 @@ def find_similar_investors(
            selectinload(InvestorTable.portfolio_companies),
            selectinload(InvestorTable.team_members),
            selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
        )
        .filter(InvestorTable.id == investor_id)
        .first()
@@ -266,6 +402,7 @@ def find_similar_investors(
            selectinload(InvestorTable.portfolio_companies),
            selectinload(InvestorTable.team_members),
            selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
        )
        .filter(InvestorTable.id != investor_id)
        .all()
@@ -338,13 +475,71 @@ def find_similar_investors(
    scored_investors.sort(key=lambda x: x[0], reverse=True)
    similar_investors = [inv for score, inv in scored_investors[:limit]]

-    # Transform to InvestorData format
-    return [
-        InvestorData(
-            investor=inv,
-            portfolio_companies=inv.portfolio_companies,
-            team_members=inv.team_members,
-            sectors=inv.sectors,
-        )
-        for inv in similar_investors
-    ]
+    # Transform to InvestorFundData format (one row per investor-fund combination)
+    investor_fund_list = []
+    for investor in similar_investors:
+        # If investor has funds, create one entry per fund
+        if investor.funds:
+            for fund in investor.funds:
+                investor_fund_data = InvestorFundData(
+                    # Investor fields
+                    investor_id=investor.id,
+                    investor_name=investor.name,
+                    investor_description=investor.description,
+                    investor_website=investor.website,
+                    investor_headquarters=investor.headquarters,
+                    aum=investor.aum,
+                    aum_as_of_date=investor.aum_as_of_date,
+                    aum_source_url=investor.aum_source_url,
+                    investment_thesis=investor.investment_thesis,
+                    portfolio_highlights=investor.portfolio_highlights,
+                    number_of_investments=investor.number_of_investments,
+                    # Fund fields
+                    fund_id=fund.id,
+                    fund_name=fund.fund_name,
+                    fund_size=fund.fund_size,
+                    fund_size_source_url=fund.fund_size_source_url,
+                    check_size_lower=fund.check_size_lower,
+                    check_size_upper=fund.check_size_upper,
+                    geographic_focus=fund.geographic_focus,
+                    investment_stage_focus=fund.investment_stage_focus,
+                    sector_focus=fund.sector_focus,
+                    # Related data
+                    portfolio_companies=investor.portfolio_companies,
+                    team_members=investor.team_members,
+                    sectors=investor.sectors,
+                )
+                investor_fund_list.append(investor_fund_data)
+        else:
+            # If no funds, create one entry with null fund fields
+            investor_fund_data = InvestorFundData(
+                # Investor fields
+                investor_id=investor.id,
+                investor_name=investor.name,
+                investor_description=investor.description,
+                investor_website=investor.website,
+                investor_headquarters=investor.headquarters,
+                aum=investor.aum,
+                aum_as_of_date=investor.aum_as_of_date,
+                aum_source_url=investor.aum_source_url,
+                investment_thesis=investor.investment_thesis,
+                portfolio_highlights=investor.portfolio_highlights,
+                number_of_investments=investor.number_of_investments,
+                # Fund fields (null)
+                fund_id=None,
+                fund_name=None,
+                fund_size=None,
+                fund_size_source_url=None,
+                check_size_lower=None,
+                check_size_upper=None,
+                geographic_focus=None,
+                investment_stage_focus=None,
+                sector_focus=None,
+                # Related data
+                portfolio_companies=investor.portfolio_companies,
+                team_members=investor.team_members,
+                sectors=investor.sectors,
+            )
+            investor_fund_list.append(investor_fund_data)
+
+    return investor_fund_list