Chan/ChanMacro/database.py

"""
database.py — SQLite schema initialization and connection management.
"""

import sqlite3
import os
from pathlib import Path

SCHEMA = """
-- ═══════════════════════════════════════════════
-- L0: Raw data tables
-- ═══════════════════════════════════════════════

CREATE TABLE IF NOT EXISTS ohlcv_daily (
    date TEXT NOT NULL,
    symbol TEXT NOT NULL DEFAULT 'BTC/USDT:USDT',
    open REAL,
    high REAL,
    low REAL,
    close REAL,
    volume REAL,
    ema20 REAL,
    ema60 REAL,
    ema120 REAL,
    atr_14 REAL,
    bb_width REAL,
    adx_14 REAL,
    PRIMARY KEY (date, symbol)
);

CREATE TABLE IF NOT EXISTS breadth_daily (
    date TEXT PRIMARY KEY,
    total_tracked INTEGER DEFAULT 50,
    advance_top50 INTEGER DEFAULT 0,
    decline_top50 INTEGER DEFAULT 0,
    above_ema20_top50 INTEGER DEFAULT 0,
    new_highs_20d_top50 INTEGER DEFAULT 0,
    btc_dominance REAL,
    advance_top20 INTEGER DEFAULT 0,
    advance_top30 INTEGER DEFAULT 0,
    above_ema20_top20 INTEGER DEFAULT 0,
    above_ema20_top30 INTEGER DEFAULT 0,
    new_highs_20d_top20 INTEGER DEFAULT 0,
    new_highs_20d_top30 INTEGER DEFAULT 0,
    fetched_at TEXT DEFAULT (datetime('now'))
);

CREATE TABLE IF NOT EXISTS derivatives (
    date TEXT NOT NULL,
    symbol TEXT NOT NULL DEFAULT 'BTC/USDT:USDT',
    funding_rate REAL,
    open_interest REAL,
    oi_24h_change_pct REAL,
    long_liquidations REAL,
    short_liquidations REAL,
    basis_annualised_pct REAL,
    source TEXT DEFAULT 'binance',
    fetched_at TEXT DEFAULT (datetime('now')),
    PRIMARY KEY (date, symbol)
);

CREATE TABLE IF NOT EXISTS etf_flow (
    date TEXT NOT NULL,
    product TEXT NOT NULL,
    net_flow_million REAL NOT NULL,
    price REAL,
    source TEXT DEFAULT 'farside',
    fetched_at TEXT DEFAULT (datetime('now')),
    PRIMARY KEY (date, product)
);

CREATE TABLE IF NOT EXISTS stablecoin_supply (
    date TEXT NOT NULL,
    token TEXT NOT NULL,
    chain TEXT NOT NULL DEFAULT 'all',
    supply REAL NOT NULL,
    source TEXT DEFAULT 'defillama',
    fetched_at TEXT DEFAULT (datetime('now')),
    PRIMARY KEY (date, token, chain)
);

-- ═══════════════════════════════════════════════
-- L3: Regime history
-- ═══════════════════════════════════════════════

CREATE TABLE IF NOT EXISTS regime_history (
    date TEXT PRIMARY KEY,
    regime TEXT NOT NULL,
    confidence REAL,
    regime_version TEXT NOT NULL DEFAULT 'v1_price_breadth_vol',
    maturity_score REAL DEFAULT 50.0,
    all_scores_json TEXT DEFAULT '{}',
    prior_regime TEXT,
    confirmation_days INTEGER DEFAULT 1,
    created_at TEXT DEFAULT (datetime('now'))
);

-- ═══════════════════════════════════════════════
-- ★ signal_features — THE moat
-- ═══════════════════════════════════════════════

CREATE TABLE IF NOT EXISTS signal_features (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    date TEXT NOT NULL,
    signal_type TEXT NOT NULL,
    signal_version TEXT NOT NULL DEFAULT 'b3_v1',
    symbol TEXT DEFAULT 'BTC/USDT:USDT',

    -- ★★ Version control (most important fields)
    regime_version TEXT NOT NULL DEFAULT 'v1_price_breadth_vol',
    signal_grade TEXT,
    signal_strength REAL,

    -- Market State Vector snapshot
    regime TEXT NOT NULL,
    regime_confidence REAL,
    regime_maturity_score REAL DEFAULT 50.0,
    market_state_hash TEXT,
    state_embedding TEXT DEFAULT '[]',
    breadth_top20 REAL,
    breadth_top30 REAL,
    breadth_top50 REAL,
    breadth_bucket TEXT,
    breadth_divergence REAL,
    oi_state TEXT,
    volatility_regime TEXT,
    price_structure_score REAL,

    -- Chan context (V5+)
    chan_trend_direction TEXT,
    chan_pivot_count INTEGER,
    chan_divergence_type TEXT,

    -- Outcomes
    entry_price REAL,
    result_1d REAL,
    result_3d REAL,
    result_5d REAL,
    result_7d REAL,
    result_14d REAL,
    max_favorable_excursion REAL,
    max_adverse_excursion REAL,
    is_win_7d INTEGER,

    created_at TEXT DEFAULT (datetime('now'))
);

CREATE INDEX IF NOT EXISTS idx_sf_regime ON signal_features(regime);
CREATE INDEX IF NOT EXISTS idx_sf_signal ON signal_features(signal_type);
CREATE INDEX IF NOT EXISTS idx_sf_oi_state ON signal_features(oi_state);
CREATE INDEX IF NOT EXISTS idx_sf_date ON signal_features(date);
CREATE INDEX IF NOT EXISTS idx_sf_state_hash ON signal_features(market_state_hash);
CREATE INDEX IF NOT EXISTS idx_sf_regime_version ON signal_features(regime_version);
CREATE INDEX IF NOT EXISTS idx_sf_signal_version ON signal_features(signal_version);

-- ═══════════════════════════════════════════════
-- Expectancy cache (raw counts, NOT posteriors)
-- ═══════════════════════════════════════════════

CREATE TABLE IF NOT EXISTS expectancy_cache (
    state_hash TEXT NOT NULL,
    signal_type TEXT NOT NULL,
    wins_weighted REAL DEFAULT 0,
    losses_weighted REAL DEFAULT 0,
    sum_return_7d REAL DEFAULT 0,
    sum_return_sq_7d REAL DEFAULT 0,
    effective_samples REAL DEFAULT 0,
    sufficiency TEXT DEFAULT 'INSUFFICIENT',
    updated_at TEXT DEFAULT (datetime('now')),
    PRIMARY KEY (state_hash, signal_type)
);

-- ═══════════════════════════════════════════════
-- Similarity outcome (KNN weight learning, Phase D)
-- ═══════════════════════════════════════════════

CREATE TABLE IF NOT EXISTS similarity_outcome (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    state_a_hash TEXT,
    state_b_hash TEXT,
    distance REAL,
    actual_return_gap REAL,
    dimension_weights_json TEXT DEFAULT '{}',
    created_at TEXT DEFAULT (datetime('now'))
);

-- ═══════════════════════════════════════════════
-- chan_context — Chan theory integration (V1 empty)
-- ═══════════════════════════════════════════════

CREATE TABLE IF NOT EXISTS chan_context (
    date TEXT NOT NULL,
    timeframe TEXT NOT NULL DEFAULT '1d',
    trend_direction TEXT,
    trend_strength REAL,
    pivot_count INTEGER,
    pivot_level TEXT,
    signal_type TEXT,
    signal_strength REAL,
    divergence_type TEXT,
    chan_structure_score REAL,
    alignment_score REAL,
    raw_context_json TEXT DEFAULT '{}',
    PRIMARY KEY (date, timeframe)
);
"""


def init_db(db_path: str = "data/macro.db") -> sqlite3.Connection:
    """Initialize database: create directory and all tables."""
    Path(db_path).parent.mkdir(parents=True, exist_ok=True)
    conn = sqlite3.connect(db_path)
    conn.executescript(SCHEMA)
    conn.commit()
    return conn


def get_connection(db_path: str = "data/macro.db") -> sqlite3.Connection:
    """Get a database connection. Creates tables if first run."""
    if not os.path.exists(db_path):
        return init_db(db_path)
    conn = sqlite3.connect(db_path)
    conn.row_factory = sqlite3.Row
    return conn