#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
分层分析：区分"下跌趋势低波"与其他市场状态后，各指标的真实表现
"""
import sys, io
if sys.platform == 'win32':
    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
    sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8')

import pandas as pd
import numpy as np
import warnings
warnings.filterwarnings('ignore')

df = pd.read_csv(
    'D:/work/project/cyb50-quant/cat-fly/t1/t1_trades_with_environment_20260327_141655.csv',
    encoding='utf-8-sig'
)
cols = [
    '交易方向','开仓时间','平仓时间','开仓价格','平仓价格','仓位',
    '盈亏金额','盈亏百分比','退出原因','持仓周期数','持仓小时数',
    'T1调整','原平仓时间','原平仓价格','原盈亏','盈亏变化',
    '入场信号','开仓市值','平仓时资金','市场状态',
    '趋势短期','趋势中期','趋势强度','波动率分位','波动率水平',
    '成交量分位','布林带位置','布林带区域','RSI分位','RSI区域',
    '1日动量','入场价格'
]
df.columns = cols
df['开仓时间'] = pd.to_datetime(df['开仓时间'])
df['年份'] = df['开仓时间'].dt.year
df['盈利'] = df['盈亏金额'] > 0

# ── 核心分层 ──────────────────────────────────────────────
death_zone = df['市场状态'] == '下跌趋势低波'
good_zone  = ~death_zone

dz = df[death_zone]    # 死亡区：下跌趋势低波
gz = df[good_zone]     # 其余环境

SEP = '=' * 70

def show(title):
    print(f'\n{SEP}')
    print(f'  {title}')
    print(SEP)

def breakdown(sub, name):
    n = len(sub)
    wr = sub['盈利'].mean() if n > 0 else 0
    avg = sub['盈亏金额'].mean() if n > 0 else 0
    total = sub['盈亏金额'].sum()
    print(f'  {name}: {n}笔 | 胜率{wr:.1%} | 均盈亏{avg:+,.0f}元 | 总盈亏{total:+,.0f}元')

# ── 总览 ─────────────────────────────────────────────────
show('总览：下跌趋势低波 vs 其余环境')
breakdown(df,  '全部')
breakdown(dz,  '下跌趋势低波 (死亡区)')
breakdown(gz,  '其余市场状态 (非死亡区)')
print()
print('  年份分布:')
for y in sorted(df['年份'].unique()):
    total_y = len(df[df['年份'] == y])
    dz_y    = len(dz[dz['年份'] == y])
    pct     = dz_y / total_y if total_y > 0 else 0
    gz_sub  = df[(df['年份'] == y) & good_zone]
    gz_wr   = gz_sub['盈利'].mean() if len(gz_sub) > 0 else 0
    print(f'  {y}年: 死亡区占比{pct:.1%}({dz_y}/{total_y}笔) | 非死亡区胜率{gz_wr:.1%}({len(gz_sub)}笔)')

# ── 在死亡区内，各指标表现 ───────────────────────────────
show('死亡区内各指标表现（理解为何之前的规则误导）')

for col in ['波动率水平', 'RSI区域', 'T1调整']:
    print(f'\n  [{col}] 在死亡区:')
    for val in dz[col].dropna().unique():
        sub = dz[dz[col] == val]
        if len(sub) < 3:
            continue
        wr = sub['盈利'].mean()
        avg = sub['盈亏金额'].mean()
        print(f'    {val}: {len(sub)}笔, 胜率{wr:.1%}, 均盈亏{avg:+,.0f}元')

# ── 在非死亡区，各指标真实表现 ───────────────────────────
show('非死亡区内各指标表现（剔除死亡区噪音后的真实信号）')

for col in ['波动率水平', 'RSI区域', 'T1调整', '市场状态']:
    print(f'\n  [{col}] 在非死亡区:')
    results = []
    for val in gz[col].dropna().unique():
        sub = gz[gz[col] == val]
        if len(sub) < 5:
            continue
        wr  = sub['盈利'].mean()
        avg = sub['盈亏金额'].mean()
        results.append((val, len(sub), wr, avg))
    results.sort(key=lambda x: x[2], reverse=True)
    for val, n, wr, avg in results:
        print(f'    {val}: {n}笔, 胜率{wr:.1%}, 均盈亏{avg:+,.0f}元')

# ── 非死亡区内 波动率分位 精确阈值 ─────────────────────
show('非死亡区内 波动率分位 阈值扫描')
valid = gz[gz['波动率分位'].notna()].copy()
thresholds = [0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
print(f'\n  波动率分位区间  笔数  胜率  均盈亏')
bins = [(0, 0.3), (0.3, 0.5), (0.5, 0.7), (0.7, 0.85), (0.85, 1.01)]
for lo, hi in bins:
    sub = valid[(valid['波动率分位'] >= lo) & (valid['波动率分位'] < hi)]
    if len(sub) < 3:
        continue
    wr  = sub['盈利'].mean()
    avg = sub['盈亏金额'].mean()
    print(f'  [{lo:.2f}, {hi:.2f}): {len(sub):>4}笔  {wr:.1%}  {avg:>+8,.0f}元')

# ── 非死亡区内 RSI分位 精确阈值 ────────────────────────
show('非死亡区内 RSI分位 阈值扫描')
valid2 = gz[gz['RSI分位'].notna()].copy()
print(f'\n  RSI分位区间      笔数  胜率  均盈亏')
bins2 = [(0, 0.05), (0.05, 0.1), (0.1, 0.2), (0.2, 0.35), (0.35, 0.6), (0.6, 1.01)]
for lo, hi in bins2:
    sub = valid2[(valid2['RSI分位'] >= lo) & (valid2['RSI分位'] < hi)]
    if len(sub) < 3:
        continue
    wr  = sub['盈利'].mean()
    avg = sub['盈亏金额'].mean()
    print(f'  [{lo:.2f}, {hi:.2f}): {len(sub):>4}笔  {wr:.1%}  {avg:>+8,.0f}元')

# ── 非死亡区内 双指标组合 ────────────────────────────────
show('非死亡区内 双指标组合（市场状态 × 波动率水平）')
combos = []
for ms in gz['市场状态'].dropna().unique():
    for vl in gz['波动率水平'].dropna().unique():
        sub = gz[(gz['市场状态'] == ms) & (gz['波动率水平'] == vl)]
        if len(sub) < 5:
            continue
        wr  = sub['盈利'].mean()
        avg = sub['盈亏金额'].mean()
        combos.append((f'{ms} × {vl}', len(sub), wr, avg))
combos.sort(key=lambda x: x[2], reverse=True)
print(f'\n  {"组合":<25} 笔数  胜率     均盈亏')
for cond, n, wr, avg in combos[:15]:
    print(f'  {cond:<25} {n:>4}  {wr:.1%}  {avg:>+8,.0f}元')

# ── 非死亡区内 RSI × 波动率 ────────────────────────────
show('非死亡区内 RSI区域 × 波动率水平 组合')
combos2 = []
for rs in gz['RSI区域'].dropna().unique():
    for vl in gz['波动率水平'].dropna().unique():
        sub = gz[(gz['RSI区域'] == rs) & (gz['波动率水平'] == vl)]
        if len(sub) < 5:
            continue
        wr  = sub['盈利'].mean()
        avg = sub['盈亏金额'].mean()
        combos2.append((f'{rs} × {vl}', len(sub), wr, avg))
combos2.sort(key=lambda x: x[2], reverse=True)
print(f'\n  {"组合":<28} 笔数  胜率     均盈亏')
for cond, n, wr, avg in combos2[:15]:
    print(f'  {cond:<28} {n:>4}  {wr:.1%}  {avg:>+8,.0f}元')

# ── 非死亡区内 趋势强度 分段 ─────────────────────────────
show('非死亡区内 趋势强度 分段')
valid3 = gz[gz['趋势强度'].notna()].copy()
bins3 = [(0, 1.0), (1.0, 1.5), (1.5, 2.5), (2.5, 4.0), (4.0, 10)]
print(f'\n  趋势强度区间     笔数  胜率  均盈亏')
for lo, hi in bins3:
    sub = valid3[(valid3['趋势强度'] >= lo) & (valid3['趋势强度'] < hi)]
    if len(sub) < 3:
        continue
    wr  = sub['盈利'].mean()
    avg = sub['盈亏金额'].mean()
    print(f'  [{lo:.1f}, {hi:.1f}): {len(sub):>4}笔  {wr:.1%}  {avg:>+8,.0f}元')

# ── 验证：用"仅排除死亡区"作为过滤，各年表现 ─────────────
show('仅排除死亡区后的各年绩效（最简化规则的效果）')
for y in sorted(df['年份'].unique()):
    all_y  = df[df['年份'] == y]
    keep_y = gz[gz['年份'] == y]
    drop_y = dz[dz['年份'] == y]
    kn, kwr, ktotal = len(keep_y), keep_y['盈利'].mean() if len(keep_y) else 0, keep_y['盈亏金额'].sum()
    dn = len(drop_y)
    print(f'  {y}年: 保留{kn}笔 胜率{kwr:.1%} {ktotal:+,.0f}元 | 过滤{dn}笔')

print()
print(SEP)
print('  结论摘要')
print(SEP)
print()
print('  "下跌趋势低波"是唯一应该被完全排除的市场状态。')
print('  在此之外的所有环境，包括极高波动、RSI超卖，策略依然有效甚至更好。')
print()
print('  非死亡区内的辅助加分指标（待从上方组合数据中提炼）:')
print('  详见上方各维度组合分析结果。')