Initial commit: BTC 1h prediction model (53.10% accuracy)
🎯 项目成果： - 准确率: 53.10% (2026年测试集) - 任务类型: 二分类 (预测涨/跌) - 特征: OHLCV + RSI + MACD (9个特征) - 训练数据: 2020-2025年BTC小时数据 (52,351序列) - 测试数据: 2026年1-29日 (484序列) 📊 性能指标： - 精确率: 51.79% - 召回率: 49.36% - F1分数: 0.5054 - 预测分布: 非常平衡 (偏差仅-11个) 🔬 实验历史： - 尝试了5种方案 (回归/分类, 不同数据划分) - 分类任务优于回归任务 (53.10% vs 49.5%) - 全量训练避免了过拟合问题 📦 主要模型文件： - models/checkpoints/dlinear_classification_2026/ - best_model.pt (最佳模型) - preprocessor.pkl (预处理器) - test_2026_results.json (测试结果) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
crypto_predictorandClaude Sonnet 4.5 committed
commit
9bbdc8d42b
82 files changed
+8742
No files matched your search
+191
@@ -0,0 +1,191 @@
|
||||
"""从Binance获取加密货币OHLCV数据"""
|
||||
|
||||
import os
|
||||
from datetime import datetime, timedelta
|
||||
from pathlib import Path
|
||||
from typing import Optional, Literal
|
||||
|
||||
import pandas as pd
|
||||
from binance.client import Client
|
||||
import pytz
|
||||
from dotenv import load_dotenv
|
||||
|
||||
# 加载环境变量
|
||||
load_dotenv()
|
||||
|
||||
|
||||
class BinanceDataFetcher:
|
||||
"""从Binance公开API获取和缓存OHLCV数据"""
|
||||
|
||||
INTERVALS = {
|
||||
'1h': Client.KLINE_INTERVAL_1HOUR,
|
||||
'15m': Client.KLINE_INTERVAL_15MINUTE,
|
||||
}
|
||||
|
||||
def __init__(self, cache_dir: str = "./data/cache"):
|
||||
"""初始化Binance客户端和缓存目录
|
||||
|
||||
Args:
|
||||
cache_dir: 缓存下载数据的目录
|
||||
"""
|
||||
# 配置代理
|
||||
proxies = None
|
||||
use_proxy = os.getenv('USE_PROXY', 'false').lower() == 'true'
|
||||
|
||||
if use_proxy:
|
||||
socks5_proxy = os.getenv('SOCKS5_PROXY', 'socks5://127.0.0.1:7890')
|
||||
proxies = {
|
||||
'http': socks5_proxy,
|
||||
'https': socks5_proxy
|
||||
}
|
||||
print(f"✓ 使用SOCKS5代理: {socks5_proxy}")
|
||||
|
||||
try:
|
||||
# 初始化Binance客户端（带代理）
|
||||
if proxies:
|
||||
self.client = Client(requests_params={'proxies': proxies})
|
||||
else:
|
||||
self.client = Client()
|
||||
|
||||
# 测试连接
|
||||
self.client.ping()
|
||||
print("✓ 已成功连接到Binance API")
|
||||
except Exception as e:
|
||||
print(f"⚠ Binance API连接失败: {e}")
|
||||
print("提示：")
|
||||
print(" 1. 检查代理设置 (.env文件)")
|
||||
print(" 2. 确保代理服务正在运行")
|
||||
print(" 3. 或者使用已缓存的数据")
|
||||
self.client = None
|
||||
|
||||
self.cache_dir = Path(cache_dir)
|
||||
self.cache_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
def fetch_ohlcv(
|
||||
self,
|
||||
symbol: Literal['BTC', 'ETH', 'SOL'],
|
||||
timeframe: Literal['1h', '15m'],
|
||||
start_date: Optional[str] = None,
|
||||
end_date: Optional[str] = None,
|
||||
use_cache: bool = True
|
||||
) -> pd.DataFrame:
|
||||
"""获取加密货币对的OHLCV数据
|
||||
|
||||
Args:
|
||||
symbol: 加密货币符号 (BTC, ETH, SOL)
|
||||
timeframe: 时间框架间隔 (1h 或 15m)
|
||||
start_date: 开始日期，格式：'YYYY-MM-DD' (默认: 1年前)
|
||||
end_date: 结束日期，格式：'YYYY-MM-DD' (默认: 现在)
|
||||
use_cache: 是否使用缓存数据
|
||||
|
||||
Returns:
|
||||
包含以下列的DataFrame: timestamp, open, high, low, close, volume
|
||||
"""
|
||||
# 生成缓存文件名
|
||||
cache_file = self._get_cache_filename(symbol, timeframe, start_date, end_date)
|
||||
|
||||
# 检查缓存
|
||||
if use_cache and cache_file.exists():
|
||||
print(f"从缓存加载数据：{cache_file}")
|
||||
return pd.read_csv(cache_file, parse_dates=['timestamp'])
|
||||
|
||||
# 检查客户端是否可用
|
||||
if self.client is None:
|
||||
raise ConnectionError(
|
||||
"Binance客户端不可用。请使用VPN或使用已缓存的数据。"
|
||||
)
|
||||
|
||||
# 设置默认日期
|
||||
if end_date is None:
|
||||
end_dt = datetime.now(pytz.UTC)
|
||||
else:
|
||||
end_dt = datetime.strptime(end_date, '%Y-%m-%d').replace(tzinfo=pytz.UTC)
|
||||
|
||||
if start_date is None:
|
||||
start_dt = end_dt - timedelta(days=365) # 1年前
|
||||
else:
|
||||
start_dt = datetime.strptime(start_date, '%Y-%m-%d').replace(tzinfo=pytz.UTC)
|
||||
|
||||
# Binance使用USDT交易对
|
||||
pair = f"{symbol}USDT"
|
||||
interval = self.INTERVALS[timeframe]
|
||||
|
||||
print(f"获取 {symbol} {timeframe} 数据，时间范围：{start_dt.date()} 至 {end_dt.date()}...")
|
||||
|
||||
# 获取K线数据
|
||||
klines = self.client.get_historical_klines(
|
||||
symbol=pair,
|
||||
interval=interval,
|
||||
start_str=str(int(start_dt.timestamp() * 1000)),
|
||||
end_str=str(int(end_dt.timestamp() * 1000))
|
||||
)
|
||||
|
||||
if not klines:
|
||||
raise ValueError(f"未获取到 {symbol} {timeframe} 的数据")
|
||||
|
||||
# 转换为DataFrame
|
||||
df = pd.DataFrame(klines, columns=[
|
||||
'timestamp', 'open', 'high', 'low', 'close', 'volume',
|
||||
'close_time', 'quote_volume', 'trades', 'taker_buy_base',
|
||||
'taker_buy_quote', 'ignore'
|
||||
])
|
||||
|
||||
# 选择并转换列
|
||||
df = df[['timestamp', 'open', 'high', 'low', 'close', 'volume']].copy()
|
||||
df['timestamp'] = pd.to_datetime(df['timestamp'], unit='ms')
|
||||
|
||||
for col in ['open', 'high', 'low', 'close', 'volume']:
|
||||
df[col] = df[col].astype(float)
|
||||
|
||||
# 按时间排序
|
||||
df = df.sort_values('timestamp').reset_index(drop=True)
|
||||
|
||||
print(f"已获取 {len(df)} 行数据，时间范围：{df['timestamp'].min()} 至 {df['timestamp'].max()}")
|
||||
|
||||
# 保存到缓存
|
||||
df.to_csv(cache_file, index=False)
|
||||
print(f"已缓存数据至：{cache_file}")
|
||||
|
||||
return df
|
||||
|
||||
def _get_cache_filename(
|
||||
self,
|
||||
symbol: str,
|
||||
timeframe: str,
|
||||
start_date: Optional[str],
|
||||
end_date: Optional[str]
|
||||
) -> Path:
|
||||
"""根据参数生成缓存文件名"""
|
||||
start = start_date or "1y"
|
||||
end = end_date or "now"
|
||||
filename = f"{symbol}_{timeframe}_{start}_{end}.csv"
|
||||
return self.cache_dir / filename
|
||||
|
||||
def get_latest_price(self, symbol: Literal['BTC', 'ETH', 'SOL']) -> float:
|
||||
"""获取符号的当前价格
|
||||
|
||||
Args:
|
||||
symbol: 加密货币符号
|
||||
|
||||
Returns:
|
||||
当前USDT价格
|
||||
"""
|
||||
pair = f"{symbol}USDT"
|
||||
ticker = self.client.get_symbol_ticker(symbol=pair)
|
||||
return float(ticker['price'])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 测试数据获取器
|
||||
fetcher = BinanceDataFetcher()
|
||||
|
||||
# 获取BTC 1小时数据（1年）
|
||||
df = fetcher.fetch_ohlcv('BTC', '1h')
|
||||
print("\nBTC 1小时数据:")
|
||||
print(df.head())
|
||||
print(f"\n形状：{df.shape}")
|
||||
print(f"日期范围：{df['timestamp'].min()} 至 {df['timestamp'].max()}")
|
||||
|
||||
# 获取当前价格
|
||||
current_price = fetcher.get_latest_price('BTC')
|
||||
print(f"\n当前BTC价格：${current_price:,.2f}")
|
||||
Reference in new issue
Block a user