WLD DeepCoin 단계별 구조 재편 및 설정·문서 통합

로고스/루트 레거시를 제거하고 deepcoin 패키지·scripts 01~05 CLI·docs/reference로 데이터·GT·분석·매칭·운영 단계를 정리했다. config와 .env 기반 설정, trade_anaysis.html 동기화 포함. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-30 22:58:25 +09:00
parent e631a5701f
commit b52d61b777
76 changed files with 11552 additions and 4567 deletions
--- a/deepcoin/data/downloader.py
+++ b/deepcoin/data/downloader.py
@@ -0,0 +1,394 @@
+"""
+WLD 과거 봉을 빗썸 API에서 받아 coins.db에 저장합니다.
+
+- 최초: 최근 N개월 전량 적재
+- 이후: DB 마지막 시각 **이후** 봉만 추가 (증분)
+"""
+
+from __future__ import annotations
+
+import sqlite3
+from datetime import datetime
+
+import pandas as pd
+from dateutil.relativedelta import relativedelta
+
+from config import (
+    BITHUMB_MINUTE_INTERVALS,
+    COIN_NAME,
+    DAILY_INTERVAL_MIN,
+    DB_PATH,
+    DOWNLOAD_BACKFILL_EXTRA_BARS,
+    DOWNLOAD_DAILY_EXTRA_DAYS,
+    DOWNLOAD_INTERVALS,
+    DOWNLOAD_MIN_INCREMENTAL_BARS,
+    DOWNLOAD_MONTHS,
+    DOWNLOAD_MONTHS_1M,
+    INCREMENTAL_OVERLAP_BARS,
+    KR_COINS,
+    SYMBOL,
+)
+from deepcoin.ops.monitor import Monitor
+
+
+def bong_count_for_months(interval_minutes: int, months: int) -> int:
+    """N개월치 봉 개수(여유분 포함)."""
+    days = months * 30
+    if interval_minutes >= DAILY_INTERVAL_MIN:
+        return days + DOWNLOAD_DAILY_EXTRA_DAYS
+    bars_per_day = (24 * 60) // interval_minutes
+    return days * bars_per_day + DOWNLOAD_BACKFILL_EXTRA_BARS
+
+
+def bong_count_since(
+    interval_minutes: int, last_ts: pd.Timestamp, overlap: int = INCREMENTAL_OVERLAP_BARS
+) -> int:
+    """마지막 저장 시각 이후 필요한 API 봉 수(겹침 포함)."""
+    now = pd.Timestamp.now()
+    if last_ts.tzinfo is not None and now.tzinfo is None:
+        last_ts = last_ts.tz_localize(None)
+    delta_min = max(0, (now - last_ts).total_seconds() / 60)
+    bars = int(delta_min / interval_minutes) + overlap + 10
+    return max(bars, DOWNLOAD_MIN_INCREMENTAL_BARS)
+
+
+def months_cutoff(months: int) -> pd.Timestamp:
+    """N개월 전 시각."""
+    return pd.Timestamp(datetime.now() - relativedelta(months=months))
+
+
+def trim_to_recent_months(data: pd.DataFrame, months: int) -> pd.DataFrame:
+    """최근 N개월 구간만 남깁니다."""
+    if data is None or data.empty:
+        return data
+    cutoff = months_cutoff(months)
+    if not isinstance(data.index, pd.DatetimeIndex):
+        data = data.copy()
+        data.index = pd.to_datetime(data.index)
+    return data[data.index >= cutoff].copy()
+
+
+def interval_label(interval: int) -> str:
+    if interval >= 1440:
+        return "일봉(1440)"
+    return f"{interval}분봉"
+
+
+def months_for_interval(interval: int, default_months: int) -> int:
+    """간격별 DB 보관 개월 수 (1분봉은 별도 상한)."""
+    if interval == 1:
+        return DOWNLOAD_MONTHS_1M
+    return default_months
+
+
+def download_jobs() -> list[tuple[int, str]]:
+    labels = {
+        1: "1분",
+        3: "3분",
+        5: "5분",
+        10: "10분",
+        15: "15분",
+        30: "30분",
+        60: "60분(1시간)",
+        240: "240분(4시간)",
+        1440: "1440분(1일)",
+    }
+    jobs = []
+    for iv in DOWNLOAD_INTERVALS:
+        if iv < 1440 and iv not in BITHUMB_MINUTE_INTERVALS:
+            print(f"경고: {iv}분봉은 빗썸 API 미지원 — 건너뜀")
+            continue
+        jobs.append((iv, labels.get(iv, f"{iv}분")))
+    return jobs
+
+
+def ensure_table(cursor, table_name: str) -> None:
+    cursor.execute(
+        f"CREATE TABLE IF NOT EXISTS {table_name} "
+        "(CODE text, NAME text, ymdhms datetime, ymd text, hms text, "
+        "Close REAL, Open REAL, High REAL, Low REAL, Volume REAL)"
+    )
+    cursor.execute(
+        f"CREATE INDEX IF NOT EXISTS {table_name}_idx ON {table_name}(CODE, ymdhms)"
+    )
+
+
+def get_earliest_timestamp(
+    symbol: str, interval: int, db_path: str = DB_PATH
+) -> pd.Timestamp | None:
+    """테이블에 저장된 해당 심볼의 가장 오래된 봉 시각."""
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+    table_name = f"{symbol}_{interval}"
+    ensure_table(cursor, table_name)
+    cursor.execute(
+        f"SELECT MIN(ymdhms) FROM {table_name} WHERE CODE = ?",
+        (symbol,),
+    )
+    row = cursor.fetchone()
+    conn.close()
+    if row and row[0]:
+        return pd.Timestamp(row[0])
+    return None
+
+
+def get_last_timestamp(
+    symbol: str, interval: int, db_path: str = DB_PATH
+) -> pd.Timestamp | None:
+    """테이블에 저장된 해당 심볼의 마지막 봉 시각."""
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+    table_name = f"{symbol}_{interval}"
+    ensure_table(cursor, table_name)
+    cursor.execute(
+        f"SELECT MAX(ymdhms) FROM {table_name} WHERE CODE = ?",
+        (symbol,),
+    )
+    row = cursor.fetchone()
+    conn.close()
+    if row and row[0]:
+        return pd.Timestamp(row[0])
+    return None
+
+
+def get_row_count(symbol: str, interval: int, db_path: str = DB_PATH) -> int:
+    """저장된 봉 개수."""
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+    table_name = f"{symbol}_{interval}"
+    ensure_table(cursor, table_name)
+    cursor.execute(
+        f"SELECT COUNT(*) FROM {table_name} WHERE CODE = ?",
+        (symbol,),
+    )
+    row = cursor.fetchone()
+    conn.close()
+    return int(row[0]) if row else 0
+
+
+def filter_after_last(
+    data: pd.DataFrame, last_ts: pd.Timestamp | None
+) -> pd.DataFrame:
+    """마지막 저장 시각보다 이후(>)인 봉만 반환."""
+    if data is None or data.empty or last_ts is None:
+        return data
+    if not isinstance(data.index, pd.DatetimeIndex):
+        data = data.copy()
+        data.index = pd.to_datetime(data.index)
+    last = pd.Timestamp(last_ts)
+    return data[data.index > last].copy()
+
+
+def prune_before_cutoff(
+    symbol: str, interval: int, months: int, db_path: str = DB_PATH
+) -> int:
+    """N개월보다 오래된 봉 삭제 (DB 용량 유지)."""
+    cutoff = months_cutoff(months).strftime("%Y-%m-%d %H:%M:%S")
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+    table_name = f"{symbol}_{interval}"
+    ensure_table(cursor, table_name)
+    cursor.execute(
+        f"DELETE FROM {table_name} WHERE CODE = ? AND ymdhms < ?",
+        (symbol, cutoff),
+    )
+    deleted = cursor.rowcount
+    conn.commit()
+    cursor.close()
+    conn.close()
+    return deleted
+
+
+def append_data(
+    symbol: str,
+    interval: int,
+    data: pd.DataFrame,
+    last_ts: pd.Timestamp | None = None,
+    db_path: str = DB_PATH,
+) -> tuple[int, int]:
+    """
+    마지막 시각 이후 봉만 INSERT합니다. 기존 데이터는 삭제하지 않습니다.
+
+    Args:
+        last_ts: None이면 전체 data 적재, 있으면 index > last_ts 만 적재
+
+    Returns:
+        (추가된 행 수, 스킵된 행 수)
+    """
+    if data is None or data.empty:
+        return 0, 0
+
+    total = len(data)
+    to_save = data if last_ts is None else filter_after_last(data, last_ts)
+    skipped = total - len(to_save)
+
+    if to_save.empty:
+        return 0, skipped
+
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+    table_name = f"{symbol}_{interval}"
+    ensure_table(cursor, table_name)
+
+    records = []
+    for i in range(len(to_save)):
+        ts = to_save.index[i]
+        if hasattr(ts, "to_pydatetime"):
+            ts = ts.to_pydatetime()
+        ymd = ts.strftime("%Y%m%d")
+        hms = ts.strftime("%H%M%S")
+        ymdhms = ts.strftime("%Y-%m-%d %H:%M:%S")
+        records.append(
+            (
+                symbol,
+                KR_COINS[symbol],
+                ymdhms,
+                ymd,
+                hms,
+                float(to_save["Open"].iloc[i]),
+                float(to_save["High"].iloc[i]),
+                float(to_save["Low"].iloc[i]),
+                float(to_save["Close"].iloc[i]),
+                float(to_save["Volume"].iloc[i]),
+            )
+        )
+
+    cursor.executemany(
+        f"INSERT INTO {table_name} "
+        "(CODE, NAME, ymdhms, ymd, hms, Close, Open, High, Low, Volume) "
+        "VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
+        records,
+    )
+    conn.commit()
+    cursor.close()
+    conn.close()
+    return len(records), skipped
+
+
+def backfill_before_earliest(
+    monitor: Monitor,
+    symbol: str,
+    interval: int,
+    months: int,
+) -> int:
+    """
+    DB 최초 봉보다 오래된 구간을 API로 채웁니다 (1년 적재 시 필요).
+
+    Returns:
+        추가된 행 수.
+    """
+    months = months_for_interval(interval, months)
+    cutoff = months_cutoff(months)
+    earliest = get_earliest_timestamp(symbol, interval)
+    if earliest is None or earliest <= cutoff:
+        return 0
+
+    label = interval_label(interval)
+    # now부터 역순 수집이므로 cutoff까지 닿으려면 N개월 전체 봉 수가 필요
+    target = bong_count_for_months(interval, months)
+
+    print(
+        f"  [백필] {label} — {cutoff.date()} ~ {earliest} "
+        f"(API 역수집 약 {target}봉)"
+    )
+
+    data = monitor.get_coin_more_data(
+        symbol, interval, bong_count=target, verbose=True
+    )
+    if data is None or data.empty:
+        print("  -> 백필 API 데이터 없음")
+        return 0
+
+    if not isinstance(data.index, pd.DatetimeIndex):
+        data.index = pd.to_datetime(data.index)
+    hist = data[(data.index >= cutoff) & (data.index < earliest)].copy()
+    if hist.empty:
+        print("  -> 백필 대상 구간 없음")
+        return 0
+
+    inserted, skipped = append_data(symbol, interval, hist, last_ts=None)
+    print(f"  -> 백필 추가 {inserted}행 (스킵 {skipped})")
+    return inserted
+
+
+def download_symbol(
+    monitor: Monitor,
+    symbol: str,
+    interval: int,
+    months: int,
+) -> None:
+    """한 간격의 봉을 API로 받아 증분·백필 저장합니다."""
+    months = months_for_interval(interval, months)
+    label = interval_label(interval)
+    existing = get_row_count(symbol, interval)
+
+    if existing > 0:
+        backfill_before_earliest(monitor, symbol, interval, months)
+
+    last_ts = get_last_timestamp(symbol, interval)
+
+    if last_ts is None:
+        target = bong_count_for_months(interval, months)
+        mode = "초기 적재"
+    else:
+        target = min(
+            bong_count_since(interval, last_ts),
+            bong_count_for_months(interval, months),
+        )
+        mode = f"증분 (마지막 {last_ts.strftime('%Y-%m-%d %H:%M:%S')} 이후)"
+
+    print(f"\n[{symbol}] {label} — {mode}")
+    print(f"  DB 기존 {existing}행 | API 목표 약 {target}봉")
+
+    data = monitor.get_coin_more_data(
+        symbol, interval, bong_count=target, verbose=True
+    )
+    if data is None or data.empty:
+        print("  -> API 데이터 없음")
+        return
+
+    data = trim_to_recent_months(data, months)
+    if data.empty:
+        print("  -> 최근 N개월 필터 후 데이터 없음")
+        return
+
+    inserted, skipped = append_data(symbol, interval, data, last_ts=last_ts)
+    pruned = prune_before_cutoff(symbol, interval, months)
+
+    new_last = get_last_timestamp(symbol, interval)
+    total = get_row_count(symbol, interval)
+    print(f"  -> API {len(data)}봉 | 추가 {inserted}행 | 스킵(기존) {skipped}행")
+    if pruned > 0:
+        print(f"  -> {months}개월 이전 {pruned}행 정리")
+    if new_last is not None:
+        print(f"  -> DB 합계 {total}행 | {data.index[0]} ~ {new_last}")
+
+
+def download(months: int | None = None) -> None:
+    """
+    WLD 다중 분봉·일봉을 coins.db에 증분 적재합니다.
+
+    간격: config.DOWNLOAD_INTERVALS
+    """
+    months = months or DOWNLOAD_MONTHS
+    monitor = Monitor(cooldown_file=None)
+    jobs = download_jobs()
+
+    intervals_str = ", ".join(str(iv) for iv, _ in jobs)
+    print(f"=== {COIN_NAME} ({SYMBOL}) -> {DB_PATH} (증분 INSERT) ===")
+    print(f"보관 {months}개월 | 간격(분): {intervals_str}")
+    started = datetime.now()
+
+    for interval, desc in jobs:
+        print(f"\n--- {desc} ---")
+        try:
+            download_symbol(monitor, SYMBOL, interval, months)
+        except Exception as e:
+            print(f"오류 interval={interval}: {e}")
+
+    elapsed = datetime.now() - started
+    print(f"\n완료 (소요: {elapsed})")
+
+
+if __name__ == "__main__":
+    download()