iciv-predictor 0.1.0__tar.gz

iciv_predictor-0.1.0/PKG-INFO

@@ -0,0 +1,181 @@
+Metadata-Version: 2.4
+Name: iciv-predictor
+Version: 0.1.0
+Summary: ICIV股票预测竞赛SDK - 用于开发和测试交易策略
+Author-email: ICIV Lab <iciv@example.com>
+License: MIT
+Project-URL: Homepage, https://stock.w3drop.com
+Project-URL: Documentation, https://stock.w3drop.com/docs
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pandas>=1.5.0
+Requires-Dist: numpy>=1.21.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+
+# ICIV Stock Predictor SDK
+
+股票预测竞赛SDK，用于开发和测试交易策略。
+
+## 安装
+
+```bash
+pip install iciv-predictor
+```
+
+或从源码安装：
+
+```bash
+git clone https://github.com/your-repo/iciv-predictor-sdk.git
+cd iciv-predictor-sdk
+pip install -e .
+```
+
+## 快速开始
+
+### 1. 创建预测器
+
+```python
+from iciv_predictor import BasePredictor, PredictionOutput
+import numpy as np
+
+class MyPredictor(BasePredictor):
+    def __init__(self, df, predict_steps=48):
+        super().__init__(df, predict_steps)
+        # 初始化你的参数
+        self.short_ma = 12
+        self.long_ma = 48
+    
+    def predict_step(self, current_idx):
+        """
+        预测当前时间点
+        
+        Args:
+            current_idx: 当前索引，只能使用历史数据 df[:current_idx+1]
+        
+        Returns:
+            PredictionOutput 或 None
+        """
+        if current_idx < self.long_ma:
+            return None
+        
+        # 获取历史收盘价
+        closes = self.get_close_prices(current_idx)
+        
+        # 计算均线
+        short_avg = closes[-self.short_ma:].mean()
+        long_avg = closes[-self.long_ma:].mean()
+        
+        # 判断方向
+        if short_avg > long_avg:
+            direction = 1   # 看涨，买入
+        elif short_avg < long_avg:
+            direction = -1  # 看跌，卖出
+        else:
+            direction = 0   # 持有
+        
+        return PredictionOutput(
+            predict_from_idx=current_idx,
+            predicted_prices=np.zeros(self.predict_steps),
+            predicted_returns=np.zeros(self.predict_steps),
+            confidence=0.6,
+            direction=direction
+        )
+```
+
+### 2. 本地测试
+
+```bash
+iciv-test my_predictor.py --data 000021_SZ.csv
+```
+
+或使用Python：
+
+```python
+from iciv_predictor import Backtester
+import pandas as pd
+
+# 加载数据
+df = pd.read_csv('000021_SZ.csv')
+df['trade_time'] = pd.to_datetime(df['datetime'])
+
+# 创建预测器
+predictor = MyPredictor(df)
+
+# 运行回测
+backtester = Backtester()
+result = backtester.run(df, predictor)
+
+print(f"收益率: {result.total_return:.2f}%")
+print(f"最大回撤: {result.max_drawdown:.2f}%")
+print(f"交易次数: {result.total_trades}")
+```
+
+### 3. 提交到平台
+
+测试通过后，将你的 `.py` 文件提交到 https://stock.w3drop.com
+
+## API 参考
+
+### BasePredictor
+
+基类，所有预测器必须继承此类。
+
+**方法**:
+
+| 方法 | 说明 |
+|------|------|
+| `__init__(df, predict_steps=48)` | 初始化，predict_steps为预测步长 |
+| `predict_step(current_idx)` | **必须实现**，返回PredictionOutput |
+| `get_historical_data(idx)` | 获取历史DataFrame |
+| `get_close_prices(idx)` | 获取历史收盘价数组 |
+| `get_returns(idx)` | 获取历史收益率数组 |
+
+### PredictionOutput
+
+预测输出结构。
+
+**字段**:
+
+| 字段 | 类型 | 说明 |
+|------|------|------|
+| `predict_from_idx` | int | 预测起始索引 |
+| `predicted_prices` | np.ndarray | 预测价格序列 |
+| `predicted_returns` | np.ndarray | 预测收益率序列 |
+| `confidence` | float | 置信度 (0-1) |
+| `direction` | int | **交易信号**: 1=买入, -1=卖出, 0=持有 |
+
+## 回测规则
+
+1. **预测频率**: 每48步（约4小时）预测一次
+2. **测试集**: 使用后20%数据
+3. **交易逻辑**:
+   - direction=1 且无持仓 → 买入
+   - direction=-1 且有持仓 → 卖出
+4. **手续费**: 买卖各万分之三
+5. **强制平仓**: 测试期结束时平仓
+
+## 注意事项
+
+⚠️ **禁止使用未来数据**！`predict_step(idx)` 只能访问 `idx` 及之前的数据。
+
+```python
+# ✅ 正确
+closes = self.get_close_prices(current_idx)
+
+# ❌ 错误 - 访问了未来数据
+future = self.df['close'].iloc[current_idx + 10]
+```
+
+## License
+
+MIT

iciv_predictor-0.1.0/README.md

@@ -0,0 +1,157 @@
+# ICIV Stock Predictor SDK
+
+股票预测竞赛SDK，用于开发和测试交易策略。
+
+## 安装
+
+```bash
+pip install iciv-predictor
+```
+
+或从源码安装：
+
+```bash
+git clone https://github.com/your-repo/iciv-predictor-sdk.git
+cd iciv-predictor-sdk
+pip install -e .
+```
+
+## 快速开始
+
+### 1. 创建预测器
+
+```python
+from iciv_predictor import BasePredictor, PredictionOutput
+import numpy as np
+
+class MyPredictor(BasePredictor):
+    def __init__(self, df, predict_steps=48):
+        super().__init__(df, predict_steps)
+        # 初始化你的参数
+        self.short_ma = 12
+        self.long_ma = 48
+    
+    def predict_step(self, current_idx):
+        """
+        预测当前时间点
+        
+        Args:
+            current_idx: 当前索引，只能使用历史数据 df[:current_idx+1]
+        
+        Returns:
+            PredictionOutput 或 None
+        """
+        if current_idx < self.long_ma:
+            return None
+        
+        # 获取历史收盘价
+        closes = self.get_close_prices(current_idx)
+        
+        # 计算均线
+        short_avg = closes[-self.short_ma:].mean()
+        long_avg = closes[-self.long_ma:].mean()
+        
+        # 判断方向
+        if short_avg > long_avg:
+            direction = 1   # 看涨，买入
+        elif short_avg < long_avg:
+            direction = -1  # 看跌，卖出
+        else:
+            direction = 0   # 持有
+        
+        return PredictionOutput(
+            predict_from_idx=current_idx,
+            predicted_prices=np.zeros(self.predict_steps),
+            predicted_returns=np.zeros(self.predict_steps),
+            confidence=0.6,
+            direction=direction
+        )
+```
+
+### 2. 本地测试
+
+```bash
+iciv-test my_predictor.py --data 000021_SZ.csv
+```
+
+或使用Python：
+
+```python
+from iciv_predictor import Backtester
+import pandas as pd
+
+# 加载数据
+df = pd.read_csv('000021_SZ.csv')
+df['trade_time'] = pd.to_datetime(df['datetime'])
+
+# 创建预测器
+predictor = MyPredictor(df)
+
+# 运行回测
+backtester = Backtester()
+result = backtester.run(df, predictor)
+
+print(f"收益率: {result.total_return:.2f}%")
+print(f"最大回撤: {result.max_drawdown:.2f}%")
+print(f"交易次数: {result.total_trades}")
+```
+
+### 3. 提交到平台
+
+测试通过后，将你的 `.py` 文件提交到 https://stock.w3drop.com
+
+## API 参考
+
+### BasePredictor
+
+基类，所有预测器必须继承此类。
+
+**方法**:
+
+| 方法 | 说明 |
+|------|------|
+| `__init__(df, predict_steps=48)` | 初始化，predict_steps为预测步长 |
+| `predict_step(current_idx)` | **必须实现**，返回PredictionOutput |
+| `get_historical_data(idx)` | 获取历史DataFrame |
+| `get_close_prices(idx)` | 获取历史收盘价数组 |
+| `get_returns(idx)` | 获取历史收益率数组 |
+
+### PredictionOutput
+
+预测输出结构。
+
+**字段**:
+
+| 字段 | 类型 | 说明 |
+|------|------|------|
+| `predict_from_idx` | int | 预测起始索引 |
+| `predicted_prices` | np.ndarray | 预测价格序列 |
+| `predicted_returns` | np.ndarray | 预测收益率序列 |
+| `confidence` | float | 置信度 (0-1) |
+| `direction` | int | **交易信号**: 1=买入, -1=卖出, 0=持有 |
+
+## 回测规则
+
+1. **预测频率**: 每48步（约4小时）预测一次
+2. **测试集**: 使用后20%数据
+3. **交易逻辑**:
+   - direction=1 且无持仓 → 买入
+   - direction=-1 且有持仓 → 卖出
+4. **手续费**: 买卖各万分之三
+5. **强制平仓**: 测试期结束时平仓
+
+## 注意事项
+
+⚠️ **禁止使用未来数据**！`predict_step(idx)` 只能访问 `idx` 及之前的数据。
+
+```python
+# ✅ 正确
+closes = self.get_close_prices(current_idx)
+
+# ❌ 错误 - 访问了未来数据
+future = self.df['close'].iloc[current_idx + 10]
+```
+
+## License
+
+MIT

iciv_predictor-0.1.0/iciv_predictor/__init__.py

@@ -0,0 +1,18 @@
+"""
+ICIV Stock Predictor SDK
+股票预测竞赛SDK - 用于开发和测试交易策略
+"""
+
+__version__ = "0.1.0"
+__author__ = "ICIV Lab"
+
+from .predictor import BasePredictor, PredictionOutput
+from .backtest import Backtester, BacktestConfig, BacktestResult
+
+__all__ = [
+    'BasePredictor', 
+    'PredictionOutput',
+    'Backtester',
+    'BacktestConfig',
+    'BacktestResult'
+]

iciv_predictor-0.1.0/iciv_predictor/backtest.py

@@ -0,0 +1,173 @@
+"""
+回测引擎 - 模拟服务器回测逻辑
+"""
+from dataclasses import dataclass, field
+from typing import List, Optional
+from datetime import datetime
+import numpy as np
+import pandas as pd
+
+
+@dataclass
+class TradeRecord:
+    """交易记录"""
+    trade_time: datetime
+    trade_type: str  # 'BUY' or 'SELL'
+    price: float
+    shares: int
+    amount: float
+    fee: float
+    capital_after: float
+
+
+@dataclass
+class BacktestResult:
+    """回测结果"""
+    initial_capital: float
+    final_capital: float
+    total_return: float  # 收益率 %
+    max_drawdown: float  # 最大回撤 %
+    win_rate: float  # 胜率 %
+    total_trades: int
+    trade_records: List[TradeRecord]
+
+
+@dataclass
+class BacktestConfig:
+    """回测配置"""
+    initial_capital: float = 1000000.0  # 初始资金 100万
+    buy_fee_rate: float = 0.0003  # 买入费率 万三
+    sell_fee_rate: float = 0.0003  # 卖出费率 万三
+
+
+class Backtester:
+    """
+    回测引擎 - 完全匹配服务器逻辑
+    
+    特点:
+    - 每48步预测一次（约4小时）
+    - direction=1 买入, direction=-1 卖出
+    - 测试结束强制平仓
+    """
+    
+    def __init__(self, config: BacktestConfig = None):
+        self.config = config or BacktestConfig()
+    
+    def run(self, df: pd.DataFrame, predictor) -> BacktestResult:
+        """
+        运行回测
+        
+        Args:
+            df: K线数据 (需包含 trade_time, close 列)
+            predictor: 预测器实例
+        
+        Returns:
+            BacktestResult
+        """
+        capital = self.config.initial_capital
+        position = 0
+        trades = []
+        equity_curve = [capital]
+        
+        predict_steps = predictor.predict_steps
+        total_len = len(df)
+        
+        # 每48步预测一次
+        for idx in range(0, total_len - predict_steps, predict_steps):
+            output = predictor.predict_step(idx)
+            
+            if output is None:
+                continue
+            
+            direction = output.direction
+            price = df['close'].iloc[idx]
+            trade_time = df['trade_time'].iloc[idx]
+            
+            # 买入
+            if direction == 1 and position == 0:
+                shares = int(capital * 0.99 / price / 100) * 100
+                if shares >= 100:
+                    amount = shares * price
+                    fee = amount * self.config.buy_fee_rate
+                    capital -= (amount + fee)
+                    position = shares
+                    trades.append(TradeRecord(
+                        trade_time=trade_time,
+                        trade_type='BUY',
+                        price=price,
+                        shares=shares,
+                        amount=amount,
+                        fee=fee,
+                        capital_after=capital
+                    ))
+            
+            # 卖出
+            elif direction == -1 and position > 0:
+                amount = position * price
+                fee = amount * self.config.sell_fee_rate
+                capital += (amount - fee)
+                trades.append(TradeRecord(
+                    trade_time=trade_time,
+                    trade_type='SELL',
+                    price=price,
+                    shares=position,
+                    amount=amount,
+                    fee=fee,
+                    capital_after=capital
+                ))
+                position = 0
+            
+            # 记录权益
+            equity = capital + position * price
+            equity_curve.append(equity)
+        
+        # 强制平仓
+        if position > 0:
+            price = df['close'].iloc[-1]
+            trade_time = df['trade_time'].iloc[-1]
+            amount = position * price
+            fee = amount * self.config.sell_fee_rate
+            capital += (amount - fee)
+            trades.append(TradeRecord(
+                trade_time=trade_time,
+                trade_type='SELL',
+                price=price,
+                shares=position,
+                amount=amount,
+                fee=fee,
+                capital_after=capital
+            ))
+        
+        # 计算指标
+        initial = self.config.initial_capital
+        total_return = (capital - initial) / initial * 100
+        
+        # 最大回撤
+        max_drawdown = 0.0
+        peak = equity_curve[0]
+        for eq in equity_curve:
+            if eq > peak:
+                peak = eq
+            dd = (peak - eq) / peak * 100
+            if dd > max_drawdown:
+                max_drawdown = dd
+        
+        # 胜率
+        wins = 0
+        pairs = 0
+        for i in range(0, len(trades) - 1, 2):
+            if trades[i].trade_type == 'BUY' and trades[i+1].trade_type == 'SELL':
+                pairs += 1
+                if trades[i+1].price > trades[i].price:
+                    wins += 1
+        win_rate = (wins / pairs * 100) if pairs > 0 else 0
+        
+        return BacktestResult(
+            initial_capital=initial,
+            final_capital=capital,
+            total_return=total_return,
+            max_drawdown=max_drawdown,
+            win_rate=win_rate,
+            total_trades=len(trades),
+            trade_records=trades
+        )

iciv_predictor-0.1.0/iciv_predictor/cli.py

@@ -0,0 +1,111 @@
+"""
+命令行工具 - 本地测试策略
+"""
+import argparse
+import sys
+import os
+import importlib.util
+import pandas as pd
+
+from .predictor import BasePredictor
+from .backtest import Backtester, BacktestConfig
+
+
+def load_predictor_class(filepath):
+    """从文件加载预测器类"""
+    spec = importlib.util.spec_from_file_location("strategy", filepath)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    
+    # 查找继承BasePredictor的类
+    for name in dir(module):
+        obj = getattr(module, name)
+        if isinstance(obj, type) and issubclass(obj, BasePredictor) and obj is not BasePredictor:
+            return obj
+    
+    raise ValueError("未找到继承BasePredictor的类")
+
+
+def main():
+    parser = argparse.ArgumentParser(description='ICIV策略本地测试工具')
+    parser.add_argument('strategy', help='策略文件路径 (.py)')
+    parser.add_argument('--data', '-d', default='000021_SZ.csv', help='数据文件路径')
+    parser.add_argument('--capital', '-c', type=float, default=1000000, help='初始资金')
+    parser.add_argument('--test-ratio', '-t', type=float, default=0.2, help='测试集比例')
+    
+    args = parser.parse_args()
+    
+    # 检查文件
+    if not os.path.exists(args.strategy):
+        print(f"❌ 策略文件不存在: {args.strategy}")
+        sys.exit(1)
+    
+    if not os.path.exists(args.data):
+        print(f"❌ 数据文件不存在: {args.data}")
+        sys.exit(1)
+    
+    print(f"\n{'='*60}")
+    print(f"📊 ICIV 策略测试")
+    print(f"{'='*60}")
+    print(f"策略文件: {args.strategy}")
+    print(f"数据文件: {args.data}")
+    print(f"初始资金: ¥{args.capital:,.0f}")
+    print(f"{'='*60}\n")
+    
+    # 加载数据
+    try:
+        df = pd.read_csv(args.data)
+        if 'datetime' in df.columns:
+            df = df.rename(columns={'datetime': 'trade_time'})
+        df['trade_time'] = pd.to_datetime(df['trade_time'])
+        print(f"✓ 数据加载: {len(df)} 条记录")
+    except Exception as e:
+        print(f"❌ 数据加载失败: {e}")
+        sys.exit(1)
+    
+    # 加载策略
+    try:
+        predictor_class = load_predictor_class(args.strategy)
+        print(f"✓ 策略加载: {predictor_class.__name__}")
+    except Exception as e:
+        print(f"❌ 策略加载失败: {e}")
+        sys.exit(1)
+    
+    # 分割数据
+    test_start = int(len(df) * (1 - args.test_ratio))
+    test_df = df.iloc[test_start:].reset_index(drop=True)
+    print(f"✓ 测试集: {len(test_df)} 条 (从索引 {test_start} 开始)")
+    
+    # 创建预测器和回测器
+    try:
+        predictor = predictor_class(test_df)
+        config = BacktestConfig(initial_capital=args.capital)
+        backtester = Backtester(config)
+        
+        print(f"\n🔄 运行回测...")
+        result = backtester.run(test_df, predictor)
+        
+        print(f"\n{'='*60}")
+        print(f"📈 回测结果")
+        print(f"{'='*60}")
+        print(f"  初始资金: ¥{result.initial_capital:,.0f}")
+        print(f"  最终资金: ¥{result.final_capital:,.2f}")
+        print(f"  收益率:   {result.total_return:+.2f}%")
+        print(f"  最大回撤: {result.max_drawdown:.2f}%")
+        print(f"  胜率:     {result.win_rate:.1f}%")
+        print(f"  交易次数: {result.total_trades}")
+        
+        if result.trade_records:
+            print(f"\n📋 交易记录:")
+            for t in result.trade_records[-6:]:
+                print(f"  {t.trade_time} {t.trade_type:5s} ¥{t.price:.2f} x {t.shares}")
+        
+    except Exception as e:
+        print(f"❌ 回测失败: {e}")
+        import traceback
+        traceback.print_exc()
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

iciv_predictor-0.1.0/iciv_predictor/predictor.py

@@ -0,0 +1,159 @@
+"""
+ICIV Stock Predictor SDK
+用户需要继承 BasePredictor 类实现自己的预测算法
+"""
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from typing import Optional, List
+import numpy as np
+import pandas as pd
+
+
+@dataclass
+class PredictionOutput:
+    """预测输出结构"""
+    # 预测起始索引 (当前时间点)
+    predict_from_idx: int
+    
+    # 预测的价格序列 (长度 = predict_steps)
+    predicted_prices: np.ndarray
+    
+    # 预测的收益率序列 (百分比)
+    predicted_returns: np.ndarray
+    
+    # 置信度 (0-1)
+    confidence: float = 0.5
+    
+    # 方向判断: 1=看涨, -1=看跌, 0=中性
+    direction: int = 0
+
+
+class BasePredictor(ABC):
+    """
+    预测器基类 - 用户需要继承此类实现自己的预测算法
+    
+    使用示例:
+    ```python
+    class MyPredictor(BasePredictor):
+        def __init__(self, df: pd.DataFrame, predict_steps: int = 48):
+            super().__init__(df, predict_steps)
+            # 自定义初始化...
+        
+        def predict_step(self, current_idx: int) -> Optional[PredictionOutput]:
+            # 实现预测逻辑...
+            return PredictionOutput(...)
+    ```
+    """
+    
+    def __init__(self, df: pd.DataFrame, predict_steps: int = 48):
+        """
+        初始化预测器
+        
+        Args:
+            df: K线数据 DataFrame, 包含以下列:
+                - trade_time: 交易时间
+                - open: 开盘价
+                - high: 最高价
+                - low: 最低价
+                - close: 收盘价
+                - volume: 成交量
+                - amount: 成交额
+            predict_steps: 预测步数 (默认48步, 即4小时)
+        """
+        self.df = df.copy()
+        self.predict_steps = predict_steps
+        
+        # 确保数据按时间排序
+        if 'trade_time' in self.df.columns:
+            self.df = self.df.sort_values('trade_time').reset_index(drop=True)
+        
+        # 计算收益率
+        self.df['return'] = self.df['close'].pct_change() * 100
+        
+        # 数据总长度
+        self.total_len = len(self.df)
+    
+    @abstractmethod
+    def predict_step(self, current_idx: int) -> Optional[PredictionOutput]:
+        """
+        对当前时间点进行预测
+        
+        Args:
+            current_idx: 当前时间点索引 (只能使用 df[:current_idx+1] 的数据)
+        
+        Returns:
+            PredictionOutput 或 None (如果无法预测)
+            
+        注意:
+            - 不要使用未来数据! 只能使用 current_idx 及之前的数据
+            - direction 字段用于生成交易信号
+        """
+        pass
+    
+    def get_historical_data(self, current_idx: int) -> pd.DataFrame:
+        """获取历史数据 (截至 current_idx)"""
+        return self.df.iloc[:current_idx + 1].copy()
+    
+    def get_close_prices(self, current_idx: int) -> np.ndarray:
+        """获取历史收盘价"""
+        return self.df['close'].iloc[:current_idx + 1].values
+    
+    def get_returns(self, current_idx: int) -> np.ndarray:
+        """获取历史收益率"""
+        return self.df['return'].iloc[:current_idx + 1].values
+
+
+# ==================== 示例预测器 ====================
+
+class SimpleMovingAveragePredictor(BasePredictor):
+    """
+    简单移动平均预测器 (示例)
+    """
+    
+    def __init__(self, df: pd.DataFrame, predict_steps: int = 48, 
+                 short_window: int = 12, long_window: int = 48):
+        super().__init__(df, predict_steps)
+        self.short_window = short_window
+        self.long_window = long_window
+    
+    def predict_step(self, current_idx: int) -> Optional[PredictionOutput]:
+        if current_idx < self.long_window:
+            return None
+        
+        closes = self.get_close_prices(current_idx)
+        current_price = closes[-1]
+        
+        # 计算移动平均
+        short_ma = closes[-self.short_window:].mean()
+        long_ma = closes[-self.long_window:].mean()
+        
+        # 判断方向
+        if short_ma > long_ma * 1.01:  # 短期均线高于长期均线 1%
+            direction = 1  # 看涨
+        elif short_ma < long_ma * 0.99:
+            direction = -1  # 看跌
+        else:
+            direction = 0
+        
+        # 简单预测: 假设价格按趋势变化
+        avg_return = self.df['return'].iloc[current_idx - self.short_window:current_idx + 1].mean()
+        predicted_returns = np.full(self.predict_steps, avg_return)
+        
+        # 计算预测价格
+        predicted_prices = np.zeros(self.predict_steps)
+        price = current_price
+        for i in range(self.predict_steps):
+            price = price * (1 + predicted_returns[i] / 100)
+            predicted_prices[i] = price
+        
+        # 置信度基于均线差距
+        ma_diff = abs(short_ma - long_ma) / long_ma
+        confidence = min(0.9, 0.3 + ma_diff * 10)
+        
+        return PredictionOutput(
+            predict_from_idx=current_idx,
+            predicted_prices=predicted_prices,
+            predicted_returns=predicted_returns,
+            confidence=confidence,
+            direction=direction
+        )

iciv_predictor-0.1.0/iciv_predictor.egg-info/PKG-INFO

@@ -0,0 +1,181 @@
+Metadata-Version: 2.4
+Name: iciv-predictor
+Version: 0.1.0
+Summary: ICIV股票预测竞赛SDK - 用于开发和测试交易策略
+Author-email: ICIV Lab <iciv@example.com>
+License: MIT
+Project-URL: Homepage, https://stock.w3drop.com
+Project-URL: Documentation, https://stock.w3drop.com/docs
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pandas>=1.5.0
+Requires-Dist: numpy>=1.21.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+
+# ICIV Stock Predictor SDK
+
+股票预测竞赛SDK，用于开发和测试交易策略。
+
+## 安装
+
+```bash
+pip install iciv-predictor
+```
+
+或从源码安装：
+
+```bash
+git clone https://github.com/your-repo/iciv-predictor-sdk.git
+cd iciv-predictor-sdk
+pip install -e .
+```
+
+## 快速开始
+
+### 1. 创建预测器
+
+```python
+from iciv_predictor import BasePredictor, PredictionOutput
+import numpy as np
+
+class MyPredictor(BasePredictor):
+    def __init__(self, df, predict_steps=48):
+        super().__init__(df, predict_steps)
+        # 初始化你的参数
+        self.short_ma = 12
+        self.long_ma = 48
+    
+    def predict_step(self, current_idx):
+        """
+        预测当前时间点
+        
+        Args:
+            current_idx: 当前索引，只能使用历史数据 df[:current_idx+1]
+        
+        Returns:
+            PredictionOutput 或 None
+        """
+        if current_idx < self.long_ma:
+            return None
+        
+        # 获取历史收盘价
+        closes = self.get_close_prices(current_idx)
+        
+        # 计算均线
+        short_avg = closes[-self.short_ma:].mean()
+        long_avg = closes[-self.long_ma:].mean()
+        
+        # 判断方向
+        if short_avg > long_avg:
+            direction = 1   # 看涨，买入
+        elif short_avg < long_avg:
+            direction = -1  # 看跌，卖出
+        else:
+            direction = 0   # 持有
+        
+        return PredictionOutput(
+            predict_from_idx=current_idx,
+            predicted_prices=np.zeros(self.predict_steps),
+            predicted_returns=np.zeros(self.predict_steps),
+            confidence=0.6,
+            direction=direction
+        )
+```
+
+### 2. 本地测试
+
+```bash
+iciv-test my_predictor.py --data 000021_SZ.csv
+```
+
+或使用Python：
+
+```python
+from iciv_predictor import Backtester
+import pandas as pd
+
+# 加载数据
+df = pd.read_csv('000021_SZ.csv')
+df['trade_time'] = pd.to_datetime(df['datetime'])
+
+# 创建预测器
+predictor = MyPredictor(df)
+
+# 运行回测
+backtester = Backtester()
+result = backtester.run(df, predictor)
+
+print(f"收益率: {result.total_return:.2f}%")
+print(f"最大回撤: {result.max_drawdown:.2f}%")
+print(f"交易次数: {result.total_trades}")
+```
+
+### 3. 提交到平台
+
+测试通过后，将你的 `.py` 文件提交到 https://stock.w3drop.com
+
+## API 参考
+
+### BasePredictor
+
+基类，所有预测器必须继承此类。
+
+**方法**:
+
+| 方法 | 说明 |
+|------|------|
+| `__init__(df, predict_steps=48)` | 初始化，predict_steps为预测步长 |
+| `predict_step(current_idx)` | **必须实现**，返回PredictionOutput |
+| `get_historical_data(idx)` | 获取历史DataFrame |
+| `get_close_prices(idx)` | 获取历史收盘价数组 |
+| `get_returns(idx)` | 获取历史收益率数组 |
+
+### PredictionOutput
+
+预测输出结构。
+
+**字段**:
+
+| 字段 | 类型 | 说明 |
+|------|------|------|
+| `predict_from_idx` | int | 预测起始索引 |
+| `predicted_prices` | np.ndarray | 预测价格序列 |
+| `predicted_returns` | np.ndarray | 预测收益率序列 |
+| `confidence` | float | 置信度 (0-1) |
+| `direction` | int | **交易信号**: 1=买入, -1=卖出, 0=持有 |
+
+## 回测规则
+
+1. **预测频率**: 每48步（约4小时）预测一次
+2. **测试集**: 使用后20%数据
+3. **交易逻辑**:
+   - direction=1 且无持仓 → 买入
+   - direction=-1 且有持仓 → 卖出
+4. **手续费**: 买卖各万分之三
+5. **强制平仓**: 测试期结束时平仓
+
+## 注意事项
+
+⚠️ **禁止使用未来数据**！`predict_step(idx)` 只能访问 `idx` 及之前的数据。
+
+```python
+# ✅ 正确
+closes = self.get_close_prices(current_idx)
+
+# ❌ 错误 - 访问了未来数据
+future = self.df['close'].iloc[current_idx + 10]
+```
+
+## License
+
+MIT

iciv_predictor-0.1.0/iciv_predictor.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+README.md
+pyproject.toml
+iciv_predictor/__init__.py
+iciv_predictor/backtest.py
+iciv_predictor/cli.py
+iciv_predictor/predictor.py
+iciv_predictor.egg-info/PKG-INFO
+iciv_predictor.egg-info/SOURCES.txt
+iciv_predictor.egg-info/dependency_links.txt
+iciv_predictor.egg-info/entry_points.txt
+iciv_predictor.egg-info/requires.txt
+iciv_predictor.egg-info/top_level.txt

iciv_predictor-0.1.0/iciv_predictor.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

iciv_predictor-0.1.0/iciv_predictor.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+iciv-test = iciv_predictor.cli:main

iciv_predictor-0.1.0/iciv_predictor.egg-info/requires.txt

@@ -0,0 +1,6 @@
+pandas>=1.5.0
+numpy>=1.21.0
+
+[dev]
+pytest>=7.0.0
+pytest-cov>=4.0.0

iciv_predictor-0.1.0/iciv_predictor.egg-info/top_level.txt

@@ -0,0 +1 @@
+iciv_predictor

iciv_predictor-0.1.0/pyproject.toml

@@ -0,0 +1,45 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "iciv-predictor"
+version = "0.1.0"
+description = "ICIV股票预测竞赛SDK - 用于开发和测试交易策略"
+readme = "README.md"
+license = {text = "MIT"}
+authors = [
+    {name = "ICIV Lab", email = "iciv@example.com"}
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+requires-python = ">=3.9"
+dependencies = [
+    "pandas>=1.5.0",
+    "numpy>=1.21.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-cov>=4.0.0",
+]
+
+[project.urls]
+Homepage = "https://stock.w3drop.com"
+Documentation = "https://stock.w3drop.com/docs"
+
+[project.scripts]
+iciv-test = "iciv_predictor.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["iciv_predictor*"]

iciv_predictor-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+