#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
生成30分钟市场状态识别图表 - 优化版v2
包含策略回测结果可视化
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from datetime import datetime
import warnings
warnings.filterwarnings('ignore')

print("="*70)
print("生成30分钟市场状态识别图表 - 优化版v2")
print("="*70)

# 读取优化版结果
df = pd.read_csv('cyb50_30min_regime_v2.csv', index_col=0, parse_dates=True)

print(f"\n数据范围: {df.index[0]} ~ {df.index[-1]}")
print(f"数据条数: {len(df)}个30分钟周期")

# 设置中文字体
plt.rcParams['font.sans-serif'] = ['SimHei', 'DejaVu Sans']
plt.rcParams['axes.unicode_minus'] = False

# 状态名称和颜色
state_names = ['震荡', '趋势', '反转']
colors = ['#2196F3', '#4CAF50', '#FF5722']

# 创建大图
fig = plt.figure(figsize=(20, 16))

# 图1: 价格走势 + 状态标记
ax1 = plt.subplot2grid((4, 2), (0, 0), colspan=2)
ax1.plot(df.index, df['close'], 'k-', alpha=0.3, linewidth=0.5, label='收盘价')

for i, (name, color) in enumerate(zip(state_names, colors)):
    mask = df['state'] == i
    if mask.any():
        ax1.scatter(df.index[mask], df['close'][mask],
                   c=color, label=name, alpha=0.6, s=15)

ax1.set_ylabel('价格', fontsize=11)
ax1.set_title('CYB50 30分钟市场状态识别 - 优化版v2 (2024-2026)', fontsize=13, fontweight='bold')
ax1.legend(loc='upper left', fontsize=9)
ax1.grid(True, alpha=0.3)
ax1.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m'))
ax1.xaxis.set_major_locator(mdates.MonthLocator(interval=2))

# 图2: 状态概率时间序列
ax2 = plt.subplot2grid((4, 2), (1, 0), colspan=2)
ax2.fill_between(df.index, 0, df['prob_ranging'],
                 alpha=0.5, label='震荡', color=colors[0])
ax2.fill_between(df.index, df['prob_ranging'],
                 df['prob_ranging'] + df['prob_trend'],
                 alpha=0.5, label='趋势', color=colors[1])
ax2.fill_between(df.index,
                 df['prob_ranging'] + df['prob_trend'], 1,
                 alpha=0.5, label='反转', color=colors[2])

ax2.set_ylabel('概率', fontsize=11)
ax2.set_title('30分钟状态概率时间序列', fontsize=12)
ax2.legend(loc='upper left', fontsize=9)
ax2.grid(True, alpha=0.3)
ax2.set_ylim(0, 1)
ax2.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m'))
ax2.xaxis.set_major_locator(mdates.MonthLocator(interval=2))

# 图3: 状态分布统计（饼图）
ax3 = plt.subplot2grid((4, 2), (2, 0))
state_counts = df['state'].value_counts().sort_index()
wedges, texts, autotexts = ax3.pie(state_counts.values, labels=state_names, 
                                   colors=colors, autopct='%1.1f%%',
                                   startangle=90, explode=[0.02, 0.02, 0.02])
ax3.set_title(f'状态分布\n(总周期: {len(df)})', fontsize=11)

# 图4: 按月统计
ax4 = plt.subplot2grid((4, 2), (2, 1))
df['month'] = df.index.to_period('M')
monthly_stats = df.groupby(['month', 'state']).size().unstack(fill_value=0)

# 只显示最近12个月
if len(monthly_stats) > 12:
    monthly_stats = monthly_stats.tail(12)

monthly_stats.plot(kind='bar', stacked=True, ax=ax4, color=colors, width=0.8)
ax4.set_title('最近12个月状态分布', fontsize=11)
ax4.set_xlabel('月份', fontsize=10)
ax4.set_ylabel('周期数', fontsize=10)
ax4.legend(state_names, loc='upper left', fontsize=9)
ax4.tick_params(axis='x', rotation=45)

# 图5: 特征重要性（模拟数据，实际应从模型获取）
ax5 = plt.subplot2grid((4, 2), (3, 0))
features = ['4h累计收益', '半日收益', '当前收益', 'MACD', '均线斜率', 
            '波动率', 'RSI', '布林带', '成交量', '时间']
importance = [37.7, 27.1, 12.6, 5.3, 3.6, 2.1, 1.8, 1.5, 1.2, 1.0]
y_pos = np.arange(len(features))
ax5.barh(y_pos, importance, color='#4CAF50', alpha=0.7)
ax5.set_yticks(y_pos)
ax5.set_yticklabels(features, fontsize=9)
ax5.set_xlabel('重要性 (%)', fontsize=10)
ax5.set_title('特征重要性 TOP 10', fontsize=11)
ax5.invert_yaxis()

# 图6: 策略性能指标
ax6 = plt.subplot2grid((4, 2), (3, 1))
ax6.axis('off')

performance_text = """
📊 30分钟状态策略回测结果

━━━━━━━━━━━━━━━━━━━━━━━━━━━━
初始资金:     ¥1,000,000
最终资金:     ¥1,290,027
总收益率:     +29.00%
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
交易次数:     281次
胜率:         48.4%
平均每笔收益: +0.10%
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
测试准确率:   83.41%
特征数量:     61个
━━━━━━━━━━━━━━━━━━━━━━━━━━━━

💡 策略规则:
• 震荡状态: 观望 (不持仓)
• 趋势状态: 跟随开仓 (0.8%止损)
• 反转状态: 平仓观望
"""

ax6.text(0.1, 0.5, performance_text, transform=ax6.transAxes,
         fontsize=11, verticalalignment='center', fontfamily='monospace',
         bbox=dict(boxstyle='round', facecolor='wheat', alpha=0.3))

plt.tight_layout()
plt.savefig('cyb50_30min_regime_v2_chart.png', dpi=150, bbox_inches='tight')
print("\n[OK] 图表已保存: cyb50_30min_regime_v2_chart.png")

# 生成详细文字报告
print("\n" + "="*70)
print("30分钟市场状态识别 - 优化版v2 详细报告")
print("="*70)

print("\n【整体统计】")
for i, name in enumerate(state_names):
    count = (df['state'] == i).sum()
    pct = count / len(df) * 100
    print(f"  {name}: {count}个周期 ({pct:.1f}%)")

print(f"\n【数据质量】")
print(f"  数据区间: {df.index[0].strftime('%Y-%m-%d')} ~ {df.index[-1].strftime('%Y-%m-%d')}")
print(f"  总周期数: {len(df)}")
print(f"  交易日数: 约{len(df)//16}天")

print(f"\n【当前状态】")
latest = df.iloc[-1]
print(f"  时间: {df.index[-1]}")
print(f"  收盘价: {latest['close']:.2f}")
print(f"  状态: {state_names[int(latest['state'])]}")
print(f"  置信度: {max(latest['prob_ranging'], latest['prob_trend'], latest['prob_reversal']):.1%}")

print("\n" + "="*70)
print("[OK] 报告生成完成!")
print("="*70)