quantvn 0.1.0__tar.gz → 0.1.1__tar.gz

{quantvn-0.1.0/quantvn.egg-info → quantvn-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quantvn
-Version: 0.1.0
+Version: 0.1.1
 Summary: QuantVN API Library for Financial Data Analysis
 Author: quantvn
 Classifier: Development Status :: 3 - Alpha
@@ -16,6 +16,7 @@ License-File: LICENSE
 Requires-Dist: requests
 Requires-Dist: pandas
 Requires-Dist: matplotlib
+Requires-Dist: tqdm
 Dynamic: author
 Dynamic: classifier
 Dynamic: description-content-type

quantvn-0.1.1/quantvn/crypto/data/__init__.py

@@ -0,0 +1,7 @@
+from __future__ import annotations
+
+from .derivatives import get_hist as get_crypto_hist
+
+__all__ = [
+    "get_crypto_hist",
+]

quantvn-0.1.1/quantvn/crypto/data/derivatives.py

@@ -0,0 +1,77 @@
+from __future__ import annotations
+from datetime import datetime, timezone, timedelta
+from pathlib import Path
+import pandas as pd
+from tqdm import tqdm
+
+from quantvn.crypto.data.download import download_monthly, extract_csv
+
+__all__ = ["get_hist"]
+
+def get_hist(
+    symbol: str,
+    interval: str = "1m",
+    cache_dir: str | Path | None = None,
+) -> pd.DataFrame:
+    """
+    Fetch historical monthly data from Binance.
+
+    start/end: str in "YYYY-MM-DD HH:MM:SS" format or datetime, in Vietnam time (UTC+7)
+    Returns DataFrame in format:
+    ["Date","time","Open","High","Low","Close","volume"]
+    """
+    cache_dir = Path(cache_dir or Path.home() / ".cache/quantvn")
+    VN_TZ = timezone(timedelta(hours=7))
+
+    # default start/end
+    start_dt = datetime(2019, 7, 1, tzinfo=VN_TZ)
+    end_dt = datetime(2022, 12, 31, 23, 59, 59, tzinfo=VN_TZ)
+
+    # parse if string
+    if isinstance(start_dt, str):
+        start_dt = datetime.strptime(start_dt, "%Y-%m-%d %H:%M:%S").replace(tzinfo=VN_TZ)
+    if isinstance(end_dt, str):
+        end_dt = datetime.strptime(end_dt, "%Y-%m-%d %H:%M:%S").replace(tzinfo=VN_TZ)
+
+    # generate list of months
+    months = []
+    dt = start_dt.replace(day=1)
+    while dt <= end_dt:
+        months.append(dt.strftime("%Y-%m"))
+        if dt.month == 12:
+            dt = dt.replace(year=dt.year + 1, month=1)
+        else:
+            dt = dt.replace(month=dt.month + 1)
+
+    all_dfs = []
+    for m in tqdm(months, desc=f"Downloading {symbol}", disable=True):
+        try:
+            zip_path = download_monthly(symbol, interval, m, cache_dir)
+            df = extract_csv(zip_path)
+            all_dfs.append(df)
+        except Exception as e:
+            print(f"Skip {symbol} {interval} {m}: {e}")
+
+    if not all_dfs:
+        return pd.DataFrame(columns=["Date","time","Open","High","Low","Close","volume"])
+
+    # concat all months
+    df_all = pd.concat(all_dfs, ignore_index=True)
+    df_all = df_all.drop_duplicates(subset=["t"]).sort_values("t").reset_index(drop=True)
+
+    # convert timestamp t -> Asia/Ho_Chi_Minh
+    df_all["t"] = pd.to_datetime(df_all["t"], unit="ms", errors="coerce", utc=True)
+    df_all = df_all.dropna(subset=["t"])
+    df_all["t"] = df_all["t"].dt.tz_convert(VN_TZ)
+
+    # filter by start/end datetime
+    df_all = df_all[(df_all["t"] >= start_dt) & (df_all["t"] <= end_dt)]
+
+    # rename Volume -> volume
+    df_all.rename(columns={"Volume": "volume"}, inplace=True)
+
+    # tạo cột Date + time
+    df_all["Date"] = df_all["t"].dt.strftime("%Y-%m-%d")
+    df_all["time"] = df_all["t"].dt.strftime("%H:%M:%S")
+
+    return df_all[["Date","time","Open","High","Low","Close","volume"]]

quantvn-0.1.1/quantvn/crypto/data/download.py

@@ -0,0 +1,50 @@
+import zipfile
+from pathlib import Path
+
+import pandas as pd
+import requests
+
+BASE_URL = "https://data.binance.vision/data/spot/monthly/klines/"
+
+def download_monthly(symbol: str, interval: str, month: str, cache_dir: Path) -> Path:
+    """
+    Download a monthly ZIP file for any symbol & interval, return local path.
+    """
+    cache_dir = cache_dir / symbol / interval
+    cache_dir.mkdir(parents=True, exist_ok=True)
+
+    zip_name = f"{symbol}-{interval}-{month}.zip"
+    zip_path = cache_dir / zip_name
+    if zip_path.exists():
+        return zip_path
+
+    url = f"{BASE_URL}{symbol}/{interval}/{zip_name}"
+    resp = requests.get(url, stream=True, timeout=60)
+    if resp.status_code != 200:
+        raise RuntimeError(f"File not found: {url}")
+
+    with open(zip_path, "wb") as f:
+        for chunk in resp.iter_content(1024*1024):
+            f.write(chunk)
+
+    return zip_path
+
+def extract_csv(zip_path: Path) -> pd.DataFrame:
+    """
+    Extract CSV from ZIP and return DataFrame with columns:
+    t, Open, High, Low, Close, Volume
+    """
+    with zipfile.ZipFile(zip_path, "r") as zf:
+        csv_name = zf.namelist()[0]
+        with zf.open(csv_name) as f:
+            df = pd.read_csv(f, header=None)
+
+    df = df.iloc[:, :6]  # keep first 6 cols
+    df.columns = ["t", "Open", "High", "Low", "Close", "Volume"]
+
+    # ensure t is int64 safe
+    df["t"] = pd.to_numeric(df["t"], errors="coerce")
+    df = df.dropna(subset=["t"])
+    df["t"] = df["t"].astype("int64")
+
+    return df

quantvn-0.1.1/quantvn/crypto/metrics/__init__.py

@@ -0,0 +1,4 @@
+from quantvn.crypto.metrics.backtest import Backtest_Crypto
+from quantvn.crypto.metrics.metrics import Metrics
+
+__all__ = ["Metrics", "Backtest_Crypto"]

quantvn-0.1.1/quantvn/crypto/metrics/backtest.py

@@ -0,0 +1,76 @@
+import numpy as np
+import pandas as pd
+
+
+class Backtest_Crypto:
+    def __init__(self, df, pnl_type="after_fees"):
+        if pnl_type not in ["raw", "after_fees"]:
+            raise ValueError("Invalid pnl_type. Choose 'raw' or 'after_fees'.")
+
+        self.df = df.copy()
+        self.pnl_type = pnl_type
+        self.df["datetime"] = pd.to_datetime(self.df["Date"] + " " + self.df["time"])
+        self.df.set_index("datetime", inplace=True)
+        self.df.sort_index(inplace=True)
+
+        # Calculate raw PNL
+        self.df["pnl_raw"] = self.df["Close"].diff().shift(-1) * self.df["position"]
+        self.df["pnl_raw"].fillna(0, inplace=True)
+
+        # Calculate PNL after fees
+        transaction_fee = 2700 / 100000  # VND per contract
+        overnight_fee = 2550 / 100000  # VND per contract per day if held overnight
+
+        self.df["transaction_fee"] = self.df["position"].diff().abs() * transaction_fee
+
+        # Identify overnight holdings
+        self.df["date"] = self.df.index.date
+        self.df["overnight"] = (self.df["position"] > 0) & (
+            self.df["date"] != self.df["date"].shift()
+        )
+        self.df["overnight_fee"] = self.df["overnight"] * overnight_fee
+
+        self.df["total_fee"] = self.df["transaction_fee"].fillna(0) + self.df[
+            "overnight_fee"
+        ].fillna(0)
+        self.df["pnl_after_fees"] = self.df["pnl_raw"] - self.df["total_fee"]
+
+    def PNL(self):
+        """Calculate cumulative PNL based on selected pnl_type."""
+        return self.df[f"pnl_{self.pnl_type}"].cumsum()
+
+    def daily_PNL(self):
+        """Calculate daily PNL based on selected pnl_type."""
+        daily_pnl = (
+            self.df.groupby(self.df.index.date)[f"pnl_{self.pnl_type}"].sum().cumsum()
+        )
+        return daily_pnl
+
+    def daily_PNL_custom(self):
+        """Calculate daily PNL based on selected pnl_type."""
+        daily_pnl = (
+            self.df.groupby(self.df.index.date)[f"pnl_{self.pnl_type}"].sum().cumsum()
+        )
+
+        # Chuyển thành danh sách dictionary [{date, pnl}]
+        result = {str(date): round(pnl, 2) for date, pnl in daily_pnl.items()}
+
+        return result
+
+    def estimate_minimum_capital(self):
+        """Estimate the minimum capital required to run the strategy based on selected PNL type."""
+        self.df["cumulative_pnl"] = (
+            self.df[f"pnl_{self.pnl_type}"].cumsum().shift().fillna(0)
+        )
+        self.df["capital_required"] = (
+            self.df["position"].abs() * self.df["Close"]
+        ) - self.df["cumulative_pnl"]
+
+        return max(self.df["capital_required"].max(), 0)
+
+    def PNL_percentage(self):
+        """Calculate PNL percentage by dividing daily_PNL by estimate_minimum_capital."""
+        min_capital = self.estimate_minimum_capital()
+        if min_capital == 0:
+            return np.nan  # Avoid division by zero
+        return round(self.daily_PNL() / min_capital, 2)

quantvn-0.1.1/quantvn/crypto/metrics/metrics.py

@@ -0,0 +1,67 @@
+import numpy as np
+
+
+class Metrics:
+    def __init__(self, backtest):
+        self.backtest = backtest
+        self.daily_pnl = backtest.daily_PNL().diff().dropna()
+
+    def avg_loss(self):
+        losses = self.daily_pnl[self.daily_pnl < 0]
+        return losses.mean()
+
+    def avg_return(self):
+        return self.daily_pnl.mean()
+
+    def avg_win(self):
+        wins = self.daily_pnl[self.daily_pnl > 0]
+        return wins.mean()
+
+    def max_drawdown(self):
+        cumulative = self.daily_pnl.cumsum()
+        peak = cumulative.cummax()
+        drawdown = cumulative - peak
+        return drawdown.min() / self.backtest.estimate_minimum_capital()
+
+    def win_rate(self):
+        wins = (self.daily_pnl > 0).sum()
+        total = len(self.daily_pnl)
+        return wins / total if total > 0 else 0
+
+    def volatility(self):
+        return self.daily_pnl.std()
+
+    def sharpe(self, risk_free_rate=0.0):
+        return (self.avg_return() - risk_free_rate) / self.volatility() * np.sqrt(365)
+
+    def sortino(self):
+        downside_std = self.daily_pnl[self.daily_pnl < 0].std()
+        return (
+            np.sqrt(252) * self.avg_return() / downside_std
+            if downside_std > 0
+            else np.nan
+        )
+
+    def calmar(self):
+        return (
+            np.sqrt(252) * self.avg_return() / abs(self.max_drawdown())
+            if self.max_drawdown() != 0
+            else np.nan
+        )
+
+    def profit_factor(self):
+        total_gain = self.daily_pnl[self.daily_pnl > 0].sum()
+        total_loss = abs(self.daily_pnl[self.daily_pnl < 0].sum())
+        return total_gain / total_loss if total_loss != 0 else np.nan
+
+    def risk_of_ruin(self):
+        win_rate = self.win_rate()
+        loss_rate = 1 - win_rate
+        return (
+            (loss_rate / win_rate) ** (1 / self.avg_loss())
+            if self.avg_loss() != 0
+            else np.nan
+        )
+
+    def value_at_risk(self, confidence_level=0.05):
+        return self.daily_pnl.quantile(confidence_level)

{quantvn-0.1.0 → quantvn-0.1.1}/quantvn/vn/metrics/backtest.py

@@ -1,11 +1,9 @@
 # ===== Backtest_Stock & helpers (migrated from your “second block”) =====
-import logging
-from abc import abstractmethod
-from typing import TypedDict, List, Dict, Union
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
 
+
 class Backtest_Derivates:
     """
     A class for backtesting derivatives trading strategies.
@@ -131,7 +129,7 @@ class Backtest_Derivates:
         float
             Average pos enter per day
         """
-        return abs(self.df['position'].diff().dropna()).sum()/len(self.daily_PNL())
+        return abs(self.df["position"].diff().dropna()).sum() / len(self.daily_PNL())
 
 
 class Backtest_Stock:
@@ -143,7 +141,9 @@ class Backtest_Stock:
     'position' = số lượng cổ phiếu mong muốn (âm sẽ bị cắt về 0).
     """
 
-    def __init__(self, df: pd.DataFrame, pnl_type: str = "after_fees", min_hold_days: int = 3):
+    def __init__(
+        self, df: pd.DataFrame, pnl_type: str = "after_fees", min_hold_days: int = 3
+    ):
         if pnl_type not in ["raw", "after_fees"]:
             raise ValueError("Invalid pnl_type. Choose 'raw' or 'after_fees'.")
 
@@ -152,7 +152,10 @@ class Backtest_Stock:
 
         # Chuẩn hóa thời gian & index
         self.df = df.copy()
-        self.df["datetime"] = pd.to_datetime(self.df["Date"].astype(str) + " " + self.df["time"].astype(str), errors="coerce")
+        self.df["datetime"] = pd.to_datetime(
+            self.df["Date"].astype(str) + " " + self.df["time"].astype(str),
+            errors="coerce",
+        )
         self.df = self.df.dropna(subset=["datetime"])
         self.df.set_index("datetime", inplace=True)
         self.df.sort_index(inplace=True)
@@ -160,7 +163,12 @@ class Backtest_Stock:
         # Long-only ý định
         self.df["Close"] = pd.to_numeric(self.df["Close"], errors="coerce")
         self.df = self.df.dropna(subset=["Close"])
-        self.df["position_intent"] = pd.to_numeric(self.df["position"], errors="coerce").fillna(0).clip(lower=0).astype(float)
+        self.df["position_intent"] = (
+            pd.to_numeric(self.df["position"], errors="coerce")
+            .fillna(0)
+            .clip(lower=0)
+            .astype(float)
+        )
 
         # Xây effective position tôn trọng min_hold theo SỐ PHIÊN
         eff_pos, trade_qty = self._build_effective_position_with_min_hold(
@@ -173,11 +181,15 @@ class Backtest_Stock:
         self.df["trade_qty"] = trade_qty
 
         # PnL: giữ vị thế từ bar t -> t+1
-        self.df["pnl_raw"] = self.df["Close"].diff().shift(-1).fillna(0) * self.df["effective_position"]
+        self.df["pnl_raw"] = (
+            self.df["Close"].diff().shift(-1).fillna(0) * self.df["effective_position"]
+        )
 
         # Phí giao dịch: 0.1% notional mỗi lần khớp
         fee_rate = 0.001
-        notional_traded = np.abs(self.df["trade_qty"].to_numpy()) * self.df["Close"].to_numpy()
+        notional_traded = (
+            np.abs(self.df["trade_qty"].to_numpy()) * self.df["Close"].to_numpy()
+        )
         self.df["transaction_fee"] = notional_traded * fee_rate
 
         self.df["pnl_after_fees"] = self.df["pnl_raw"] - self.df["transaction_fee"]
@@ -275,7 +287,9 @@ class Backtest_Stock:
     def estimate_minimum_capital(self) -> float:
         # Ước lượng nhu cầu vốn tối thiểu thô: notional giữ - lũy kế PnL tại mỗi thời điểm
         cum_pnl = self.df[f"pnl_{self.pnl_type}"].cumsum().shift().fillna(0.0)
-        capital_required = (self.df["effective_position"].abs() * self.df["Close"]) - cum_pnl
+        capital_required = (
+            self.df["effective_position"].abs() * self.df["Close"]
+        ) - cum_pnl
         return float(max(capital_required.max(), 0.0))
 
     def PNL_percentage(self) -> pd.Series:
@@ -319,5 +333,3 @@ class Backtest_Stock:
         plt.grid(True, alpha=0.3)
         plt.tight_layout()
         plt.show()
-
-

{quantvn-0.1.0 → quantvn-0.1.1/quantvn.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quantvn
-Version: 0.1.0
+Version: 0.1.1
 Summary: QuantVN API Library for Financial Data Analysis
 Author: quantvn
 Classifier: Development Status :: 3 - Alpha
@@ -16,6 +16,7 @@ License-File: LICENSE
 Requires-Dist: requests
 Requires-Dist: pandas
 Requires-Dist: matplotlib
+Requires-Dist: tqdm
 Dynamic: author
 Dynamic: classifier
 Dynamic: description-content-type

{quantvn-0.1.0 → quantvn-0.1.1}/quantvn.egg-info/SOURCES.txt

@@ -10,10 +10,11 @@ quantvn.egg-info/requires.txt
 quantvn.egg-info/top_level.txt
 quantvn/crypto/__init__.py
 quantvn/crypto/data/__init__.py
-quantvn/crypto/data/const.py
-quantvn/crypto/data/core.py
 quantvn/crypto/data/derivatives.py
-quantvn/crypto/data/utils.py
+quantvn/crypto/data/download.py
+quantvn/crypto/metrics/__init__.py
+quantvn/crypto/metrics/backtest.py
+quantvn/crypto/metrics/metrics.py
 quantvn/metrics/__init__.py
 quantvn/metrics/portfolio.py
 quantvn/metrics/single_asset.py

{quantvn-0.1.0 → quantvn-0.1.1}/quantvn.egg-info/requires.txt

@@ -1,3 +1,4 @@
 requests
 pandas
 matplotlib
+tqdm

{quantvn-0.1.0 → quantvn-0.1.1}/setup.py

@@ -2,12 +2,13 @@ from setuptools import find_packages, setup
 
 setup(
     name="quantvn",
-    version="0.1.0",
+    version="0.1.1",
     packages=find_packages(),
     install_requires=[
         "requests",
         "pandas",
-        "matplotlib"
+        "matplotlib",
+        "tqdm",
     ],
     author="quantvn",
     description="QuantVN API Library for Financial Data Analysis",

quantvn-0.1.0/quantvn/crypto/data/__init__.py

@@ -1,31 +0,0 @@
-
-from __future__ import annotations
-
-# Public constants/helpers
-from .const import *  # noqa: F401,F403
-
-# Core helpers (chỉ giữ TA & request)
-from .core import (
-    add_all_ta_features,
-    send_request,
-)
-
-# Crypto (đọc S3)
-from .utils import get_crypto
-
-# Backward-compatibility: giữ get_hist của stocks nếu tồn tại (optional)
-try:
-    from .stocks import get_hist as get_stock_hist  # type: ignore
-    get_hist = get_stock_hist  # alias mặc định
-except Exception:
-    # Không có module stocks trong gói này — bỏ qua
-    pass
-
-__all__ = [
-    # helpers
-    "send_request",
-    # TA features
-    "add_all_ta_features",
-    # crypto
-    "get_crypto",
-]

quantvn-0.1.0/quantvn/crypto/data/const.py

@@ -1,26 +0,0 @@
-
-TRADING_URL = "https://trading.vietcap.com.vn/api/"
-GRAPHQL_URL = "https://trading.vietcap.com.vn/data-mt/graphql"
-CHART_URL = "chart/OHLCChart/gap-chart"
-INTRADAY_URL = "market-watch"
-
-INTERVAL_MAP = {
-    '1m':'ONE_MINUTE','5m':'ONE_MINUTE','15m':'ONE_MINUTE','30m':'ONE_MINUTE',
-    '1H':'ONE_HOUR','1D':'ONE_DAY','1W':'ONE_DAY','1M':'ONE_DAY'
-}
-
-OHLC_COLUMNS = ["t","o","h","l","c","v"]
-OHLC_RENAME = {"t":"time","o":"open","h":"high","l":"low","c":"close","v":"volume"}
-
-INTRADAY_MAP = {'truncTime':'time','matchPrice':'price','matchVol':'volume','matchType':'match_type','id':'id'}
-
-PRICE_DEPTH_URL = f"{TRADING_URL}{INTRADAY_URL}/AccumulatedPriceStepVol/getSymbolData"
-
-PRICE_INFO_MAP = {
-    'ev':'ev','ticker':'symbol',
-    'open_price':'open','ceiling_price':'ceiling','floor_price':'floor','reference_price':'ref_price',
-    'highest_price':'high','lowest_price':'low',
-    'price_change':'price_change','percent_price_change':'price_change_pct',
-    'foreign_total_volume':'foreign_volume','foreign_total_room':'foreign_room','foreign_holding_room':'foreign_holding_room',
-    'average_match_volume2_week':'avg_match_volume_2w',
-}

quantvn-0.1.0/quantvn/crypto/data/core.py

@@ -1,82 +0,0 @@
-
-import time, random, requests
-import pandas as pd
-
-DEFAULT_TIMEOUT = 25
-
-def _ua(source="vietmarket"):
-    return {
-        "User-Agent": f"{source}/1.0 (+https://example.local)",
-        "Accept": "application/json, text/plain, */*",
-        "Origin": "https://example.local",
-        "Referer": "https://example.local/",
-    }
-
-def send_request(url, method="GET", headers=None, params=None, payload=None,
-                 retries=2, backoff=(0.6, 1.2), timeout=DEFAULT_TIMEOUT):
-    h = _ua()
-    if headers:
-        h.update(headers)
-    for attempt in range(retries + 1):
-        try:
-            if method.upper() == "GET":
-                r = requests.get(url, headers=h, params=params, timeout=timeout)
-            else:
-                r = requests.post(url, headers=h, params=params, json=payload, timeout=timeout)
-            r.raise_for_status()
-            if "application/json" in r.headers.get("Content-Type", ""):
-                return r.json()
-            return r.text
-        except Exception:
-            if attempt >= retries:
-                raise
-            time.sleep(random.uniform(*backoff))
-
-def add_all_ta_features(
-    df,
-    open: str = "Open",
-    high: str = "High",
-    low: str = "Low",
-    close: str = "Close",
-    volume: str = "Volume",
-    fillna: bool = True,
-):
-    """
-    Thêm toàn bộ technical indicators từ thư viện `ta` vào DataFrame.
-    Giữ nguyên signature giống `ta.add_all_ta_features` để sử dụng y hệt.
-
-    Parameters
-    ----------
-    df : pandas.DataFrame
-        DataFrame phải có các cột giá/khối lượng tương ứng.
-    open,high,low,close,volume : str
-        Tên cột trong df.
-    fillna : bool
-        Nếu True, sẽ điền các giá trị NaN theo mặc định của thư viện `ta`.
-
-    Returns
-    -------
-    pandas.DataFrame
-        DataFrame đầu vào + các cột TA features.
-    """
-    try:
-        from ta import add_all_ta_features as _ta_add_all_ta_features
-        from ta.utils import dropna as _ta_dropna
-    except Exception as e:
-        raise ImportError(
-            "Thiếu thư viện 'ta'. Hãy cài: pip install ta"
-        ) from e
-
-    # Làm sạch NaN theo chuẩn của 'ta'
-    _df = _ta_dropna(df.copy())
-
-    # Gọi trực tiếp hàm gốc
-    return _ta_add_all_ta_features(
-        _df,
-        open=open,
-        high=high,
-        low=low,
-        close=close,
-        volume=volume,
-        fillna=fillna,
-    )

quantvn-0.1.0/quantvn/crypto/data/derivatives.py

@@ -1,22 +0,0 @@
-
-"""
-ĐÃ THAY THẾ: Module derivatives nay đã được thay bằng hàm `get_crypto` (đọc dữ liệu crypto từ S3).
-Vui lòng chuyển sang: from .crypto import get_crypto
-"""
-from __future__ import annotations
-
-from .utils import get_crypto as _get_crypto
-
-__all__ = ["get_hist"]
-
-def get_hist(symbol: str, frequency: str = "1D", *, days: int | None = None, **kwargs):
-    """
-    [Deprecated] Giả lập API cũ:
-    - Bỏ qua tham số `frequency` của phái sinh; dùng `days` nếu truyền vào.
-    - Gọi sang crypto.get_crypto(...).
-    """
-    if days is None:
-        # Mặc định map frequency sang days đơn giản
-        freq_map = {"1D": 365, "1H": 30, "5M": 7}
-        days = freq_map.get(str(frequency).upper(), None)
-    return _get_crypto(symbol, days=days, **kwargs)

quantvn-0.1.0/quantvn/crypto/data/utils.py

@@ -1,93 +0,0 @@
-# quantvn/crypto/data/utils.py
-from __future__ import annotations
-from typing import Optional, Literal
-import io
-import pandas as pd
-import boto3, requests
-from botocore.exceptions import ClientError, NoCredentialsError
-from botocore.config import Config
-from botocore import UNSIGNED
-
-__all__ = ["get_crypto"]
-
-def get_crypto(
-    symbol: str,
-    days: Optional[int] = None,
-    *,
-    bucket: str = "qco-market",
-    prefix: str = "data-csv",
-    session: Optional[boto3.Session] = None,
-    auth: Literal["auto", "signed", "unsigned"] = "auto",
-) -> pd.DataFrame:
-    """
-    Đọc s3://{bucket}/{prefix}/{symbol}.csv và (tuỳ chọn) lọc N ngày.
-    - auth="auto": thử signed; nếu không có credential → fallback unsigned → fallback HTTP.
-    - auth="signed": chỉ signed (bắt buộc user có credential).
-    - auth="unsigned": luôn truy cập ẩn danh (chỉ dùng khi object public).
-    """
-    key = f"{prefix.rstrip('/')}/{symbol}.csv" if prefix else f"{symbol}.csv"
-    session = session or boto3.Session()
-
-    def _post(df: pd.DataFrame) -> pd.DataFrame:
-        if "datetime" not in df.columns:
-            raise KeyError("CSV phải có cột 'datetime'.")
-        df["datetime"] = pd.to_datetime(df["datetime"], errors="coerce", utc=True)
-        if days is not None:
-            cutoff = pd.Timestamp.utcnow() - pd.Timedelta(days=days)
-            df = df[df["datetime"] >= cutoff].copy()
-        df.attrs["s3_key"] = key
-        return df
-
-    def _read_via_boto(client) -> pd.DataFrame:
-        obj = client.get_object(Bucket=bucket, Key=key)
-        return _post(pd.read_csv(obj["Body"]))
-
-    def _http_fallback(possible_region: Optional[str] = None) -> pd.DataFrame:
-        # S3 virtual-hosted–style URL; requests sẽ tự theo redirect nếu region khác. :contentReference[oaicite:1]{index=1}
-        urls = [
-            f"https://{bucket}.s3.amazonaws.com/{key}",
-        ]
-        if possible_region:
-            urls.insert(0, f"https://{bucket}.s3.{possible_region}.amazonaws.com/{key}")
-        for url in urls:
-            r = requests.get(url, timeout=30)
-            if r.ok:
-                return _post(pd.read_csv(io.BytesIO(r.content)))
-        raise PermissionError(
-            "AccessDenied khi dùng unsigned/HTTP. Hãy bật public-read cho prefix hoặc cung cấp credential/presigned URL."
-        )
-
-    # 1) Chế độ ép unsigned ngay từ đầu
-    if auth == "unsigned":
-        try:
-            s3u = session.client("s3", config=Config(signature_version=UNSIGNED))  # :contentReference[oaicite:2]{index=2}
-            return _read_via_boto(s3u)
-        except ClientError as e:
-            region = e.response.get("ResponseMetadata", {}).get("HTTPHeaders", {}).get("x-amz-bucket-region")
-            return _http_fallback(region)
-
-    # 2) signed hoặc auto (ưu tiên signed)
-    try:
-        s3 = session.client("s3")
-        return _read_via_boto(s3)
-    except NoCredentialsError:
-        if auth == "signed":
-            raise
-        # auto → fallback unsigned
-        try:
-            s3u = session.client("s3", config=Config(signature_version=UNSIGNED))  # :contentReference[oaicite:3]{index=3}
-            return _read_via_boto(s3u)
-        except ClientError as e:
-            region = e.response.get("ResponseMetadata", {}).get("HTTPHeaders", {}).get("x-amz-bucket-region")
-            return _http_fallback(region)
-    except ClientError as e:
-        # Trường hợp sai region → thử lại signed với region thật; nếu vẫn fail → HTTP
-        region = e.response.get("ResponseMetadata", {}).get("HTTPHeaders", {}).get("x-amz-bucket-region")
-        if region:
-            try:
-                s3r = session.client("s3", region_name=region)
-                return _read_via_boto(s3r)
-            except Exception:
-                pass
-        # Cuối cùng: HTTP
-        return _http_fallback(region)