feat: expand seed to 50 companies with competitor relationships and macro source

2026-04-14 21:00:19 +00:00
parent 86808465de
commit 8d0526470d
1 changed files with 205 additions and 23 deletions
@@ -1,7 +1,7 @@
 """Seed data for initial tracked watchlist.

 Run against a live database to populate the starter companies, aliases,
-watchlist, and source configurations.
+watchlist, source configurations, macro news source, and competitor relationships.

 Usage:
    python -m services.symbol_registry.seed
@@ -18,19 +18,67 @@ from services.shared.logging import setup_logging

 logger = logging.getLogger("seed")

-# --- Seed Companies ---
-# Diverse mix: mega-cap tech, finance, healthcare, energy, consumer
+# --- Seed Companies (50 diverse large/mega-cap) ---
 COMPANIES = [
+    # Technology
    {"ticker": "AAPL", "legal_name": "Apple Inc.", "exchange": "NASDAQ", "sector": "Technology", "industry": "Consumer Electronics", "market_cap_bucket": "mega"},
    {"ticker": "MSFT", "legal_name": "Microsoft Corporation", "exchange": "NASDAQ", "sector": "Technology", "industry": "Software", "market_cap_bucket": "mega"},
    {"ticker": "NVDA", "legal_name": "NVIDIA Corporation", "exchange": "NASDAQ", "sector": "Technology", "industry": "Semiconductors", "market_cap_bucket": "mega"},
-    {"ticker": "AMZN", "legal_name": "Amazon.com Inc.", "exchange": "NASDAQ", "sector": "Consumer Cyclical", "industry": "Internet Retail", "market_cap_bucket": "mega"},
    {"ticker": "GOOGL", "legal_name": "Alphabet Inc.", "exchange": "NASDAQ", "sector": "Technology", "industry": "Internet Content", "market_cap_bucket": "mega"},
-    {"ticker": "JPM", "legal_name": "JPMorgan Chase & Co.", "exchange": "NYSE", "sector": "Financial Services", "industry": "Banks", "market_cap_bucket": "mega"},
-    {"ticker": "JNJ", "legal_name": "Johnson & Johnson", "exchange": "NYSE", "sector": "Healthcare", "industry": "Drug Manufacturers", "market_cap_bucket": "mega"},
-    {"ticker": "XOM", "legal_name": "Exxon Mobil Corporation", "exchange": "NYSE", "sector": "Energy", "industry": "Oil & Gas Integrated", "market_cap_bucket": "mega"},
-    {"ticker": "TSLA", "legal_name": "Tesla Inc.", "exchange": "NASDAQ", "sector": "Consumer Cyclical", "industry": "Auto Manufacturers", "market_cap_bucket": "large"},
    {"ticker": "META", "legal_name": "Meta Platforms Inc.", "exchange": "NASDAQ", "sector": "Technology", "industry": "Internet Content", "market_cap_bucket": "mega"},
+    {"ticker": "AVGO", "legal_name": "Broadcom Inc.", "exchange": "NASDAQ", "sector": "Technology", "industry": "Semiconductors", "market_cap_bucket": "mega"},
+    {"ticker": "ORCL", "legal_name": "Oracle Corporation", "exchange": "NYSE", "sector": "Technology", "industry": "Software", "market_cap_bucket": "mega"},
+    {"ticker": "CRM", "legal_name": "Salesforce Inc.", "exchange": "NYSE", "sector": "Technology", "industry": "Software", "market_cap_bucket": "large"},
+    {"ticker": "AMD", "legal_name": "Advanced Micro Devices Inc.", "exchange": "NASDAQ", "sector": "Technology", "industry": "Semiconductors", "market_cap_bucket": "large"},
+    {"ticker": "INTC", "legal_name": "Intel Corporation", "exchange": "NASDAQ", "sector": "Technology", "industry": "Semiconductors", "market_cap_bucket": "large"},
+    {"ticker": "CSCO", "legal_name": "Cisco Systems Inc.", "exchange": "NASDAQ", "sector": "Technology", "industry": "Networking", "market_cap_bucket": "large"},
+    {"ticker": "ADBE", "legal_name": "Adobe Inc.", "exchange": "NASDAQ", "sector": "Technology", "industry": "Software", "market_cap_bucket": "large"},
+    # Consumer Cyclical
+    {"ticker": "AMZN", "legal_name": "Amazon.com Inc.", "exchange": "NASDAQ", "sector": "Consumer Cyclical", "industry": "Internet Retail", "market_cap_bucket": "mega"},
+    {"ticker": "TSLA", "legal_name": "Tesla Inc.", "exchange": "NASDAQ", "sector": "Consumer Cyclical", "industry": "Auto Manufacturers", "market_cap_bucket": "large"},
+    {"ticker": "HD", "legal_name": "The Home Depot Inc.", "exchange": "NYSE", "sector": "Consumer Cyclical", "industry": "Home Improvement", "market_cap_bucket": "mega"},
+    {"ticker": "NKE", "legal_name": "Nike Inc.", "exchange": "NYSE", "sector": "Consumer Cyclical", "industry": "Footwear & Accessories", "market_cap_bucket": "large"},
+    {"ticker": "MCD", "legal_name": "McDonald's Corporation", "exchange": "NYSE", "sector": "Consumer Cyclical", "industry": "Restaurants", "market_cap_bucket": "large"},
+    {"ticker": "SBUX", "legal_name": "Starbucks Corporation", "exchange": "NASDAQ", "sector": "Consumer Cyclical", "industry": "Restaurants", "market_cap_bucket": "large"},
+    # Financial Services
+    {"ticker": "JPM", "legal_name": "JPMorgan Chase & Co.", "exchange": "NYSE", "sector": "Financial Services", "industry": "Banks", "market_cap_bucket": "mega"},
+    {"ticker": "V", "legal_name": "Visa Inc.", "exchange": "NYSE", "sector": "Financial Services", "industry": "Credit Services", "market_cap_bucket": "mega"},
+    {"ticker": "MA", "legal_name": "Mastercard Inc.", "exchange": "NYSE", "sector": "Financial Services", "industry": "Credit Services", "market_cap_bucket": "mega"},
+    {"ticker": "BAC", "legal_name": "Bank of America Corporation", "exchange": "NYSE", "sector": "Financial Services", "industry": "Banks", "market_cap_bucket": "mega"},
+    {"ticker": "GS", "legal_name": "Goldman Sachs Group Inc.", "exchange": "NYSE", "sector": "Financial Services", "industry": "Capital Markets", "market_cap_bucket": "large"},
+    {"ticker": "MS", "legal_name": "Morgan Stanley", "exchange": "NYSE", "sector": "Financial Services", "industry": "Capital Markets", "market_cap_bucket": "large"},
+    {"ticker": "BRK.B", "legal_name": "Berkshire Hathaway Inc.", "exchange": "NYSE", "sector": "Financial Services", "industry": "Insurance", "market_cap_bucket": "mega"},
+    # Healthcare
+    {"ticker": "JNJ", "legal_name": "Johnson & Johnson", "exchange": "NYSE", "sector": "Healthcare", "industry": "Drug Manufacturers", "market_cap_bucket": "mega"},
+    {"ticker": "UNH", "legal_name": "UnitedHealth Group Inc.", "exchange": "NYSE", "sector": "Healthcare", "industry": "Health Insurance", "market_cap_bucket": "mega"},
+    {"ticker": "LLY", "legal_name": "Eli Lilly and Company", "exchange": "NYSE", "sector": "Healthcare", "industry": "Drug Manufacturers", "market_cap_bucket": "mega"},
+    {"ticker": "PFE", "legal_name": "Pfizer Inc.", "exchange": "NYSE", "sector": "Healthcare", "industry": "Drug Manufacturers", "market_cap_bucket": "large"},
+    {"ticker": "ABBV", "legal_name": "AbbVie Inc.", "exchange": "NYSE", "sector": "Healthcare", "industry": "Drug Manufacturers", "market_cap_bucket": "mega"},
+    {"ticker": "MRK", "legal_name": "Merck & Co. Inc.", "exchange": "NYSE", "sector": "Healthcare", "industry": "Drug Manufacturers", "market_cap_bucket": "mega"},
+    # Energy
+    {"ticker": "XOM", "legal_name": "Exxon Mobil Corporation", "exchange": "NYSE", "sector": "Energy", "industry": "Oil & Gas Integrated", "market_cap_bucket": "mega"},
+    {"ticker": "CVX", "legal_name": "Chevron Corporation", "exchange": "NYSE", "sector": "Energy", "industry": "Oil & Gas Integrated", "market_cap_bucket": "mega"},
+    {"ticker": "COP", "legal_name": "ConocoPhillips", "exchange": "NYSE", "sector": "Energy", "industry": "Oil & Gas E&P", "market_cap_bucket": "large"},
+    {"ticker": "SLB", "legal_name": "Schlumberger Limited", "exchange": "NYSE", "sector": "Energy", "industry": "Oil & Gas Services", "market_cap_bucket": "large"},
+    # Communication Services
+    {"ticker": "NFLX", "legal_name": "Netflix Inc.", "exchange": "NASDAQ", "sector": "Communication Services", "industry": "Entertainment", "market_cap_bucket": "mega"},
+    {"ticker": "DIS", "legal_name": "The Walt Disney Company", "exchange": "NYSE", "sector": "Communication Services", "industry": "Entertainment", "market_cap_bucket": "large"},
+    {"ticker": "CMCSA", "legal_name": "Comcast Corporation", "exchange": "NASDAQ", "sector": "Communication Services", "industry": "Telecom", "market_cap_bucket": "large"},
+    {"ticker": "T", "legal_name": "AT&T Inc.", "exchange": "NYSE", "sector": "Communication Services", "industry": "Telecom", "market_cap_bucket": "large"},
+    # Industrials
+    {"ticker": "CAT", "legal_name": "Caterpillar Inc.", "exchange": "NYSE", "sector": "Industrials", "industry": "Farm & Heavy Equipment", "market_cap_bucket": "large"},
+    {"ticker": "BA", "legal_name": "The Boeing Company", "exchange": "NYSE", "sector": "Industrials", "industry": "Aerospace & Defense", "market_cap_bucket": "large"},
+    {"ticker": "UPS", "legal_name": "United Parcel Service Inc.", "exchange": "NYSE", "sector": "Industrials", "industry": "Logistics", "market_cap_bucket": "large"},
+    {"ticker": "HON", "legal_name": "Honeywell International Inc.", "exchange": "NASDAQ", "sector": "Industrials", "industry": "Conglomerates", "market_cap_bucket": "large"},
+    # Consumer Defensive
+    {"ticker": "PG", "legal_name": "Procter & Gamble Company", "exchange": "NYSE", "sector": "Consumer Defensive", "industry": "Household Products", "market_cap_bucket": "mega"},
+    {"ticker": "KO", "legal_name": "The Coca-Cola Company", "exchange": "NYSE", "sector": "Consumer Defensive", "industry": "Beverages", "market_cap_bucket": "mega"},
+    {"ticker": "PEP", "legal_name": "PepsiCo Inc.", "exchange": "NASDAQ", "sector": "Consumer Defensive", "industry": "Beverages", "market_cap_bucket": "mega"},
+    {"ticker": "WMT", "legal_name": "Walmart Inc.", "exchange": "NYSE", "sector": "Consumer Defensive", "industry": "Discount Stores", "market_cap_bucket": "mega"},
+    {"ticker": "COST", "legal_name": "Costco Wholesale Corporation", "exchange": "NASDAQ", "sector": "Consumer Defensive", "industry": "Discount Stores", "market_cap_bucket": "mega"},
+    # Real Estate / Utilities
+    {"ticker": "AMT", "legal_name": "American Tower Corporation", "exchange": "NYSE", "sector": "Real Estate", "industry": "REIT - Specialty", "market_cap_bucket": "large"},
+    {"ticker": "NEE", "legal_name": "NextEra Energy Inc.", "exchange": "NYSE", "sector": "Utilities", "industry": "Utilities - Renewable", "market_cap_bucket": "large"},
 ]

 # --- Aliases ---
@@ -40,18 +88,102 @@ ALIASES = {
    "NVDA": [("NVIDIA", "brand"), ("GeForce", "product"), ("CUDA", "product")],
    "AMZN": [("Amazon", "brand"), ("AWS", "product"), ("Prime", "product")],
    "GOOGL": [("Google", "brand"), ("Alphabet", "legal_name"), ("YouTube", "product")],
+    "META": [("Facebook", "brand"), ("Instagram", "product"), ("WhatsApp", "product")],
    "JPM": [("JPMorgan", "brand"), ("Chase", "brand")],
    "JNJ": [("J&J", "brand")],
    "XOM": [("Exxon", "brand"), ("ExxonMobil", "brand")],
    "TSLA": [("Tesla", "brand")],
-    "META": [("Facebook", "brand"), ("Instagram", "product"), ("WhatsApp", "product")],
+    "NFLX": [("Netflix", "brand")],
+    "DIS": [("Disney", "brand"), ("Disney+", "product")],
+    "V": [("Visa", "brand")],
+    "MA": [("Mastercard", "brand")],
+    "KO": [("Coca-Cola", "brand"), ("Coke", "brand")],
+    "PEP": [("Pepsi", "brand"), ("PepsiCo", "brand")],
+    "BA": [("Boeing", "brand")],
+    "WMT": [("Walmart", "brand")],
+    "COST": [("Costco", "brand")],
+    "CRM": [("Salesforce", "brand")],
+    "ORCL": [("Oracle", "brand")],
+    "ADBE": [("Adobe", "brand"), ("Photoshop", "product")],
+    "AMD": [("AMD", "brand"), ("Ryzen", "product")],
+    "INTC": [("Intel", "brand")],
+    "BAC": [("Bank of America", "brand"), ("BofA", "brand")],
+    "GS": [("Goldman Sachs", "brand"), ("Goldman", "brand")],
+    "UNH": [("UnitedHealth", "brand"), ("Optum", "product")],
+    "LLY": [("Eli Lilly", "brand"), ("Lilly", "brand")],
+    "PFE": [("Pfizer", "brand")],
+    "CVX": [("Chevron", "brand")],
+    "PG": [("P&G", "brand"), ("Procter & Gamble", "brand")],
+    "HD": [("Home Depot", "brand")],
+    "NKE": [("Nike", "brand")],
+    "MCD": [("McDonald's", "brand")],
+    "SBUX": [("Starbucks", "brand")],
 }

-# --- Source configs per company ---
-# Polygon.io for market data and news (matches PolygonMarketAdapter and PolygonNewsAdapter)
-# SEC EDGAR for filings (matches SECEdgarAdapter)
-# Alpaca for paper trading (matches AlpacaBrokerAdapter)
+# --- Competitor Relationships ---
+# (ticker_a, ticker_b, relationship_type, strength)
+COMPETITOR_RELATIONSHIPS = [
+    # Tech ecosystem rivals
+    ("AAPL", "MSFT", "direct_rival", 0.75),
+    ("AAPL", "GOOGL", "overlapping_products", 0.60),
+    ("AAPL", "META", "overlapping_products", 0.40),
+    ("GOOGL", "META", "direct_rival", 0.85),
+    ("MSFT", "GOOGL", "overlapping_products", 0.70),
+    ("MSFT", "AMZN", "overlapping_products", 0.65),
+    ("MSFT", "ORCL", "direct_rival", 0.60),
+    ("MSFT", "CRM", "overlapping_products", 0.55),
+    ("MSFT", "ADBE", "overlapping_products", 0.40),
+    ("CRM", "ORCL", "direct_rival", 0.70),
+    ("CRM", "ADBE", "overlapping_products", 0.45),
+    # Semiconductors
+    ("NVDA", "AMD", "direct_rival", 0.80),
+    ("NVDA", "INTC", "direct_rival", 0.65),
+    ("NVDA", "AVGO", "same_sector", 0.50),
+    ("AMD", "INTC", "direct_rival", 0.85),
+    ("INTC", "AVGO", "same_sector", 0.40),
+    # Supply chain: chips → tech
+    ("NVDA", "AAPL", "supply_chain_adjacent", 0.50),
+    ("NVDA", "MSFT", "supply_chain_adjacent", 0.60),
+    ("NVDA", "TSLA", "supply_chain_adjacent", 0.45),
+    ("NVDA", "META", "supply_chain_adjacent", 0.50),
+    ("AVGO", "AAPL", "supply_chain_adjacent", 0.55),
+    # Cloud rivals
+    ("AMZN", "GOOGL", "overlapping_products", 0.55),
+    # Financial services
+    ("JPM", "BAC", "direct_rival", 0.80),
+    ("JPM", "GS", "overlapping_products", 0.60),
+    ("GS", "MS", "direct_rival", 0.85),
+    ("V", "MA", "direct_rival", 0.90),
+    # Healthcare / pharma
+    ("JNJ", "PFE", "direct_rival", 0.65),
+    ("JNJ", "ABBV", "direct_rival", 0.60),
+    ("JNJ", "MRK", "direct_rival", 0.60),
+    ("LLY", "PFE", "direct_rival", 0.70),
+    ("LLY", "ABBV", "direct_rival", 0.65),
+    ("LLY", "MRK", "direct_rival", 0.65),
+    ("PFE", "MRK", "direct_rival", 0.75),
+    ("PFE", "ABBV", "direct_rival", 0.70),
+    ("ABBV", "MRK", "direct_rival", 0.70),
+    # Energy
+    ("XOM", "CVX", "direct_rival", 0.85),
+    ("XOM", "COP", "same_sector", 0.55),
+    ("CVX", "COP", "same_sector", 0.55),
+    # Entertainment / streaming
+    ("NFLX", "DIS", "direct_rival", 0.75),
+    ("NFLX", "AMZN", "overlapping_products", 0.50),
+    # Telecom
+    ("CMCSA", "T", "direct_rival", 0.70),
+    # Consumer: beverages
+    ("KO", "PEP", "direct_rival", 0.90),
+    # Consumer: restaurants
+    ("MCD", "SBUX", "same_sector", 0.45),
+    # Consumer: retail
+    ("WMT", "COST", "direct_rival", 0.70),
+    ("WMT", "AMZN", "overlapping_products", 0.60),
+    ("COST", "AMZN", "overlapping_products", 0.40),
+]

+# --- Source configs per company ---
 SOURCES_PER_COMPANY = [
    {
        "source_type": "market_api",
@@ -85,7 +217,6 @@ SOURCES_PER_COMPANY = [
    },
 ]

-# Broker source — one per account, not per company
 BROKER_SOURCE = {
    "source_type": "broker",
    "source_name": "Alpaca Paper",
@@ -96,10 +227,24 @@ BROKER_SOURCE = {
    },
 }

+# Macro news source (global, not company-specific)
+MACRO_NEWS_SOURCE = {
+    "source_type": "macro_news",
+    "source_name": "Polygon Global News",
+    "credibility_score": 0.7,
+    "config": {
+        "url": "https://api.polygon.io/v2/reference/news",
+        "params": {"order": "desc"},
+        "results_key": "results",
+        "provider": "polygon",
+        "limit": 50,
+    },
+}
+

 async def seed(pool: asyncpg.Pool) -> None:
    """Insert seed data. Uses upsert for companies, skips existing aliases/sources."""
-    company_ids = {}
+    company_ids: dict[str, str] = {}

    # Companies — upsert on (ticker, exchange)
    for c in COMPANIES:
@@ -116,8 +261,8 @@ async def seed(pool: asyncpg.Pool) -> None:
            c["ticker"], c["legal_name"], c["exchange"],
            c["sector"], c["industry"], c["market_cap_bucket"],
        )
-        company_ids[row["ticker"]] = row["id"]
-        logger.info(f"Company: {row['ticker']} -> {row['id']}")
+        company_ids[row["ticker"]] = str(row["id"])
+        logger.info("Company: %s -> %s", row["ticker"], row["id"])

    # Aliases
    for ticker, aliases in ALIASES.items():
@@ -135,7 +280,7 @@ async def seed(pool: asyncpg.Pool) -> None:
    # Watchlist
    wl = await pool.fetchrow(
        """INSERT INTO watchlists (name, description)
-           VALUES ('Starter 10', 'Initial tracked watchlist — 10 diverse mega/large-cap symbols')
+           VALUES ('Starter 50', 'Initial tracked watchlist — 50 diverse mega/large-cap symbols')
           ON CONFLICT (name) DO UPDATE SET description = EXCLUDED.description
           RETURNING id""",
    )
@@ -145,9 +290,9 @@ async def seed(pool: asyncpg.Pool) -> None:
            "INSERT INTO watchlist_members (watchlist_id, company_id) VALUES ($1, $2) ON CONFLICT DO NOTHING",
            wl_id, cid,
        )
-    logger.info(f"Watchlist 'Starter 10' -> {wl_id}")
+    logger.info("Watchlist 'Starter 50' -> %s", wl_id)

-    # Sources per company — check for existing before inserting
+    # Sources per company
    for ticker, cid in company_ids.items():
        existing = await pool.fetch(
            "SELECT source_type, source_name FROM sources WHERE company_id = $1",
@@ -158,7 +303,6 @@ async def seed(pool: asyncpg.Pool) -> None:
        for src in SOURCES_PER_COMPANY:
            key = (src["source_type"], src["source_name"])
            if key in existing_set:
-                logger.debug(f"Source {key} already exists for {ticker}, skipping")
                continue
            await pool.execute(
                """INSERT INTO sources (company_id, source_type, source_name, config, credibility_score)
@@ -167,7 +311,7 @@ async def seed(pool: asyncpg.Pool) -> None:
                json.dumps(src["config"]), src["credibility_score"],
            )

-        # Broker source only for the first company (account-level)
+        # Broker source only for the first company
        if ticker == COMPANIES[0]["ticker"]:
            bkey = (BROKER_SOURCE["source_type"], BROKER_SOURCE["source_name"])
            if bkey not in existing_set:
@@ -177,11 +321,49 @@ async def seed(pool: asyncpg.Pool) -> None:
                    cid, BROKER_SOURCE["source_type"], BROKER_SOURCE["source_name"],
                    json.dumps(BROKER_SOURCE["config"]), BROKER_SOURCE["credibility_score"],
                )
+
+        # Macro news source on the first company (global, but needs a company_id FK)
+        if ticker == COMPANIES[0]["ticker"]:
+            mkey = (MACRO_NEWS_SOURCE["source_type"], MACRO_NEWS_SOURCE["source_name"])
+            if mkey not in existing_set:
+                await pool.execute(
+                    """INSERT INTO sources (company_id, source_type, source_name, config, credibility_score)
+                       VALUES ($1, $2, $3, $4::jsonb, $5)""",
+                    cid, MACRO_NEWS_SOURCE["source_type"], MACRO_NEWS_SOURCE["source_name"],
+                    json.dumps(MACRO_NEWS_SOURCE["config"]), MACRO_NEWS_SOURCE["credibility_score"],
+                )
    logger.info("Sources seeded")

+    # Competitor relationships
+    rel_count = 0
+    for ticker_a, ticker_b, rel_type, strength in COMPETITOR_RELATIONSHIPS:
+        cid_a = company_ids.get(ticker_a)
+        cid_b = company_ids.get(ticker_b)
+        if not cid_a or not cid_b:
+            logger.warning("Skipping relationship %s-%s: company not found", ticker_a, ticker_b)
+            continue
+        # Use LEAST/GREATEST ordering for the unique index
+        a_id = min(cid_a, cid_b)
+        b_id = max(cid_a, cid_b)
+        await pool.execute(
+            """INSERT INTO competitor_relationships
+                   (company_a_id, company_b_id, relationship_type, strength, bidirectional, source)
+               VALUES ($1, $2, $3, $4, TRUE, 'manual')
+               ON CONFLICT (LEAST(company_a_id, company_b_id), GREATEST(company_a_id, company_b_id))
+                   WHERE active = TRUE
+               DO UPDATE SET strength = EXCLUDED.strength, relationship_type = EXCLUDED.relationship_type, updated_at = NOW()""",
+            a_id, b_id, rel_type, strength,
+        )
+        rel_count += 1
+    logger.info("Competitor relationships seeded: %d", rel_count)
+
    total = await pool.fetchval("SELECT count(*) FROM companies")
    sources_total = await pool.fetchval("SELECT count(*) FROM sources")
-    logger.info(f"Seed complete: {total} companies, {sources_total} sources, watchlist with {len(company_ids)} members")
+    rels_total = await pool.fetchval("SELECT count(*) FROM competitor_relationships WHERE active = TRUE")
+    logger.info(
+        "Seed complete: %d companies, %d sources, %d competitor relationships, watchlist with %d members",
+        total, sources_total, rels_total, len(company_ids),
+    )


 async def main() -> None: