"""05 | 多因子选股（横截面）
目标：体验"因子"最朴素的样子——按指标排序选股。
数据：akshare 全A快照(含市盈率/市净率等)。
"""
import time
import akshare as ak, pandas as pd

def fetch_spot(retries=6):
    last = None
    for i in range(retries):
        try:
            return ak.stock_zh_a_spot_em()
        except Exception as e:
            last = e; time.sleep(3 + i * 3)
    raise last

try:
    spot = fetch_spot()
    print("全A快照:", spot.shape)
    df = spot.copy()
    pe = pd.to_numeric(df.get("市盈率-动态"), errors="coerce")
    df = df[pe.notna()].copy()
    df["EP"] = 1 / pe[pe.notna()]                 # 盈利收益率(1/PE)
    df["EP_rank"] = df["EP"].rank(pct=True)
    top = df.sort_values("EP_rank", ascending=False).head(20)[
        ["代码", "名称", "最新价", "市盈率-动态", "EP_rank"]]
    print("\n== 按盈利收益率(EP)选出的前20（低估值）==")
    print(top.to_string(index=False))
    top.to_csv("../data/05_top20_EP.csv", index=False, encoding="utf-8-sig")
    print("已存 data/05_top20_EP.csv")
except Exception as e:
    print("取数失败(网络/接口变动):", repr(e)[:200])
    print("可稍后重跑；或先跑 01-04（已缓存，离线可跑）")

# 思考题：
# 1) 单因子排序选股有什么坑？(行业偏差/市值偏差/未来函数)
# 2) 怎么把2个因子合成打分？(标准化后加权，试试 z-score)