407 lines
13 KiB
Python
407 lines
13 KiB
Python
"""
|
||
Skill B: Quant (量化研究员)
|
||
============================
|
||
职能：行情分析、资金流计算、异常检测
|
||
|
||
输入：ETF 代码列表
|
||
输出：Market_Data_JSON (资金流评分、技术指标、异常信号)
|
||
"""
|
||
|
||
import sys
|
||
from pathlib import Path
|
||
sys.path.insert(0, str(Path(__file__).parent.parent))
|
||
|
||
from core.config import config, llm_call
|
||
import akshare as ak
|
||
import pandas as pd
|
||
import numpy as np
|
||
from datetime import datetime, timedelta
|
||
from typing import Dict, List, Optional, Tuple
|
||
import warnings
|
||
warnings.filterwarnings('ignore')
|
||
|
||
|
||
class QuantAnalyzer:
|
||
"""量化分析器 - 负责 ETF 行情数据获取和资金流分析"""
|
||
|
||
def __init__(self):
|
||
self.cache = {} # 简单缓存机制
|
||
|
||
def get_etf_realtime_data(self, etf_code: str) -> Optional[Dict]:
|
||
"""
|
||
获取 ETF 实时行情数据
|
||
|
||
Args:
|
||
etf_code: ETF 代码（如 "512980"）
|
||
|
||
Returns:
|
||
实时行情字典
|
||
"""
|
||
try:
|
||
# 使用 akshare 获取实时行情
|
||
df = ak.fund_etf_spot_em()
|
||
|
||
# 查找目标 ETF
|
||
etf_data = df[df['代码'] == etf_code]
|
||
|
||
if etf_data.empty:
|
||
print(f"[Quant] 未找到 ETF: {etf_code}")
|
||
return None
|
||
|
||
row = etf_data.iloc[0]
|
||
|
||
return {
|
||
"code": etf_code,
|
||
"name": row['名称'],
|
||
"price": float(row['最新价']),
|
||
"change_pct": float(row['涨跌幅']),
|
||
"volume": float(row['成交量']),
|
||
"amount": float(row['成交额']),
|
||
"turnover_rate": float(row.get('换手率', 0)),
|
||
"timestamp": datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||
}
|
||
|
||
except Exception as e:
|
||
print(f"[Quant] 获取实时数据失败 {etf_code}: {e}")
|
||
return None
|
||
|
||
def get_etf_historical_data(
|
||
self,
|
||
etf_code: str,
|
||
days: int = 20
|
||
) -> Optional[pd.DataFrame]:
|
||
"""
|
||
获取 ETF 历史行情数据
|
||
|
||
Args:
|
||
etf_code: ETF 代码
|
||
days: 获取天数（默认20个交易日）
|
||
|
||
Returns:
|
||
历史行情 DataFrame
|
||
"""
|
||
try:
|
||
# 计算日期范围
|
||
end_date = datetime.now().strftime("%Y%m%d")
|
||
start_date = (datetime.now() - timedelta(days=days*2)).strftime("%Y%m%d")
|
||
|
||
# 获取历史数据
|
||
df = ak.fund_etf_hist_em(
|
||
symbol=etf_code,
|
||
period="daily",
|
||
start_date=start_date,
|
||
end_date=end_date,
|
||
adjust="qfq"
|
||
)
|
||
|
||
if df is None or df.empty:
|
||
print(f"[Quant] 无历史数据: {etf_code}")
|
||
return None
|
||
|
||
# 重命名列
|
||
df.rename(columns={
|
||
'日期': 'date',
|
||
'开盘': 'open',
|
||
'收盘': 'close',
|
||
'最高': 'high',
|
||
'最低': 'low',
|
||
'成交量': 'volume',
|
||
'成交额': 'amount',
|
||
'涨跌幅': 'change_pct',
|
||
'换手率': 'turnover_rate'
|
||
}, inplace=True)
|
||
|
||
return df.tail(days)
|
||
|
||
except Exception as e:
|
||
print(f"[Quant] 获取历史数据失败 {etf_code}: {e}")
|
||
return None
|
||
|
||
def calculate_fund_flow_score(
|
||
self,
|
||
etf_code: str,
|
||
window: int = 5
|
||
) -> Dict:
|
||
"""
|
||
计算资金流向评分
|
||
|
||
核心逻辑：
|
||
1. 成交额放量 (amount_surge)
|
||
2. 换手率提升 (turnover_boost)
|
||
3. 价格与成交量背离检测
|
||
|
||
Args:
|
||
etf_code: ETF 代码
|
||
window: 计算窗口（天数）
|
||
|
||
Returns:
|
||
资金流评分字典
|
||
"""
|
||
df = self.get_etf_historical_data(etf_code, days=window*2)
|
||
|
||
if df is None or len(df) < window:
|
||
return {
|
||
"code": etf_code,
|
||
"flow_score": 0,
|
||
"amount_surge": 0,
|
||
"turnover_boost": 0,
|
||
"divergence_signal": False,
|
||
"status": "insufficient_data"
|
||
}
|
||
|
||
# 近期数据 vs 历史基准
|
||
recent = df.tail(window)
|
||
baseline = df.head(window)
|
||
|
||
# 1. 成交额放量评分 (0-50)
|
||
recent_avg_amount = recent['amount'].mean()
|
||
baseline_avg_amount = baseline['amount'].mean()
|
||
|
||
if baseline_avg_amount > 0:
|
||
amount_ratio = recent_avg_amount / baseline_avg_amount
|
||
amount_surge_score = min((amount_ratio - 1) * 50, 50)
|
||
else:
|
||
amount_surge_score = 0
|
||
|
||
# 2. 换手率提升评分 (0-30)
|
||
recent_avg_turnover = recent['turnover_rate'].mean()
|
||
baseline_avg_turnover = baseline['turnover_rate'].mean()
|
||
|
||
if baseline_avg_turnover > 0:
|
||
turnover_ratio = recent_avg_turnover / baseline_avg_turnover
|
||
turnover_boost_score = min((turnover_ratio - 1) * 30, 30)
|
||
else:
|
||
turnover_boost_score = 0
|
||
|
||
# 3. 价格与成交量背离检测 (奖励分 +20)
|
||
recent_price_change = recent['close'].iloc[-1] / recent['close'].iloc[0] - 1
|
||
recent_volume_change = recent['volume'].iloc[-1] / recent['volume'].iloc[0] - 1
|
||
|
||
# 价跌量增 = 可能见底信号
|
||
divergence_signal = (recent_price_change < -0.02 and recent_volume_change > 0.3)
|
||
divergence_bonus = 20 if divergence_signal else 0
|
||
|
||
# 总分计算 (0-100)
|
||
total_score = max(0, min(100,
|
||
amount_surge_score + turnover_boost_score + divergence_bonus
|
||
))
|
||
|
||
return {
|
||
"code": etf_code,
|
||
"flow_score": round(total_score, 2),
|
||
"amount_surge": round(amount_surge_score, 2),
|
||
"turnover_boost": round(turnover_boost_score, 2),
|
||
"divergence_signal": divergence_signal,
|
||
"recent_avg_amount": round(recent_avg_amount / 1e8, 2), # 单位：亿
|
||
"baseline_avg_amount": round(baseline_avg_amount / 1e8, 2),
|
||
"status": "success"
|
||
}
|
||
|
||
def detect_anomaly(
|
||
self,
|
||
etf_code: str,
|
||
sigma: float = 2.0
|
||
) -> Dict:
|
||
"""
|
||
异常检测 - 识别异常放量或暴涨暴跌
|
||
|
||
Args:
|
||
etf_code: ETF 代码
|
||
sigma: 标准差倍数（默认2倍）
|
||
|
||
Returns:
|
||
异常信号字典
|
||
"""
|
||
df = self.get_etf_historical_data(etf_code, days=30)
|
||
|
||
if df is None or len(df) < 10:
|
||
return {"code": etf_code, "has_anomaly": False, "reason": "insufficient_data"}
|
||
|
||
# 计算统计基准
|
||
mean_amount = df['amount'].mean()
|
||
std_amount = df['amount'].std()
|
||
mean_change = df['change_pct'].mean()
|
||
std_change = df['change_pct'].std()
|
||
|
||
# 最新数据
|
||
latest = df.iloc[-1]
|
||
|
||
anomaly_signals = []
|
||
|
||
# 成交额异常
|
||
if latest['amount'] > mean_amount + sigma * std_amount:
|
||
anomaly_signals.append("volume_surge")
|
||
|
||
# 涨跌幅异常
|
||
if abs(latest['change_pct']) > abs(mean_change) + sigma * std_change:
|
||
if latest['change_pct'] > 0:
|
||
anomaly_signals.append("price_spike")
|
||
else:
|
||
anomaly_signals.append("price_crash")
|
||
|
||
return {
|
||
"code": etf_code,
|
||
"has_anomaly": len(anomaly_signals) > 0,
|
||
"signals": anomaly_signals,
|
||
"latest_amount": round(latest['amount'] / 1e8, 2),
|
||
"latest_change_pct": round(latest['change_pct'], 2),
|
||
"threshold_amount": round((mean_amount + sigma * std_amount) / 1e8, 2),
|
||
"threshold_change": round(abs(mean_change) + sigma * std_change, 2)
|
||
}
|
||
|
||
def batch_analyze(
|
||
self,
|
||
etf_codes: List[str]
|
||
) -> Dict[str, Dict]:
|
||
"""
|
||
批量分析 ETF
|
||
|
||
Args:
|
||
etf_codes: ETF 代码列表
|
||
|
||
Returns:
|
||
分析结果字典 {code: result}
|
||
"""
|
||
results = {}
|
||
|
||
print(f"[Quant] 开始批量分析 {len(etf_codes)} 个 ETF...")
|
||
|
||
for code in etf_codes:
|
||
print(f"[Quant] 分析 {code}...")
|
||
|
||
# 资金流评分
|
||
flow_result = self.calculate_fund_flow_score(code)
|
||
|
||
# 异常检测
|
||
anomaly_result = self.detect_anomaly(code)
|
||
|
||
# 实时行情
|
||
realtime_data = self.get_etf_realtime_data(code)
|
||
|
||
results[code] = {
|
||
"flow_analysis": flow_result,
|
||
"anomaly_detection": anomaly_result,
|
||
"realtime": realtime_data,
|
||
"timestamp": datetime.now().isoformat()
|
||
}
|
||
|
||
print(f"[Quant] 批量分析完成")
|
||
return results
|
||
|
||
def generate_market_report(
|
||
self,
|
||
analysis_results: Dict[str, Dict]
|
||
) -> Dict:
|
||
"""
|
||
生成市场数据报告（供其他 Agent 使用）
|
||
|
||
Args:
|
||
analysis_results: batch_analyze 的输出
|
||
|
||
Returns:
|
||
标准化的 Market_Data_JSON
|
||
"""
|
||
report = {
|
||
"timestamp": datetime.now().isoformat(),
|
||
"total_analyzed": len(analysis_results),
|
||
"etf_scores": {},
|
||
"top_flow_etfs": [],
|
||
"anomaly_alerts": []
|
||
}
|
||
|
||
# 提取评分
|
||
for code, result in analysis_results.items():
|
||
flow_score = result.get("flow_analysis", {}).get("flow_score", 0)
|
||
report["etf_scores"][code] = flow_score
|
||
|
||
# 异常提醒
|
||
if result.get("anomaly_detection", {}).get("has_anomaly"):
|
||
report["anomaly_alerts"].append({
|
||
"code": code,
|
||
"signals": result["anomaly_detection"]["signals"]
|
||
})
|
||
|
||
# 排序 Top 资金流 ETF
|
||
sorted_etfs = sorted(
|
||
report["etf_scores"].items(),
|
||
key=lambda x: x[1],
|
||
reverse=True
|
||
)
|
||
report["top_flow_etfs"] = [
|
||
{"code": code, "score": score}
|
||
for code, score in sorted_etfs[:5]
|
||
]
|
||
|
||
return report
|
||
|
||
|
||
# ==================== 工具函数 ====================
|
||
|
||
def get_all_etf_codes_from_asset_map() -> List[str]:
|
||
"""从 asset_map.json 提取所有 ETF 代码"""
|
||
import json
|
||
from pathlib import Path
|
||
|
||
asset_map_path = Path("core") / "asset_map.json"
|
||
|
||
if not asset_map_path.exists():
|
||
print("[Quant] 未找到 asset_map.json")
|
||
return []
|
||
|
||
with open(asset_map_path, 'r', encoding='utf-8') as f:
|
||
asset_map = json.load(f)
|
||
|
||
etf_codes = set()
|
||
for sector_data in asset_map.get("sectors", {}).values():
|
||
etf_codes.update(sector_data.get("etfs", []))
|
||
|
||
return list(etf_codes)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
print("=" * 50)
|
||
print("Skill B: Quant 量化研究员测试")
|
||
print("=" * 50)
|
||
|
||
# 创建分析器实例
|
||
quant = QuantAnalyzer()
|
||
|
||
# 测试单个 ETF
|
||
test_code = "512480" # 半导体 ETF
|
||
print(f"\n测试 ETF: {test_code}")
|
||
|
||
# 1. 获取实时数据
|
||
print("\n1. 实时行情:")
|
||
realtime = quant.get_etf_realtime_data(test_code)
|
||
if realtime:
|
||
print(f" {realtime['name']}: ¥{realtime['price']}, 涨跌幅: {realtime['change_pct']}%")
|
||
|
||
# 2. 资金流评分
|
||
print("\n2. 资金流分析:")
|
||
flow = quant.calculate_fund_flow_score(test_code)
|
||
print(f" 资金流评分: {flow['flow_score']}")
|
||
print(f" 成交额放量: {flow['amount_surge']}")
|
||
print(f" 换手率提升: {flow['turnover_boost']}")
|
||
|
||
# 3. 异常检测
|
||
print("\n3. 异常检测:")
|
||
anomaly = quant.detect_anomaly(test_code)
|
||
print(f" 发现异常: {anomaly['has_anomaly']}")
|
||
if anomaly['has_anomaly']:
|
||
print(f" 异常信号: {anomaly['signals']}")
|
||
|
||
# 4. 批量分析（测试少量 ETF）
|
||
print("\n4. 批量分析测试:")
|
||
test_codes = ["512480", "515980", "159928"] # 半导体、AI、消费
|
||
batch_results = quant.batch_analyze(test_codes)
|
||
|
||
# 5. 生成报告
|
||
report = quant.generate_market_report(batch_results)
|
||
print(f"\n5. 市场报告:")
|
||
print(f" 分析数量: {report['total_analyzed']}")
|
||
print(f" Top 资金流 ETF:")
|
||
for item in report['top_flow_etfs']:
|
||
print(f" {item['code']}: {item['score']:.2f}")
|
||
|
||
print("\n✅ Quant 模块测试完成")
|