cfc/docs/参考资料/cross_validate.py

"""
交叉验证：提取所有5份PDF的JSON数据，逐模块比较
"""
import sys, os
sys.path.insert(0, r'D:\workspace\cfc\docs\参考资料')
import extract_full_report_v5 as m

BASE = r'D:\workspace\cfc\docs\参考资料'
pdfs = sorted(f for f in os.listdir(BASE) if f.lower().endswith('.pdf'))
print(f'找到 {len(pdfs)} 份PDF\n')

# 提取所有报告
results = {}
for fname in pdfs:
    label = fname.replace('.pdf', '')
    print(f'提取 {label}...')
    results[label] = m.extract_pdf_to_json(os.path.join(BASE, fname))

all_labels = list(results.keys())
print()

# =============================================
# 1. 报告概述
# =============================================
print('=' * 80)
print('1. 报告概述')
print('=' * 80)
overview_fields = ['姓名', '编号', '年龄', '性别', '肠道预测年龄', '肠型',
                   '肠道菌群平衡', '菌群多样性', '有益菌', '有害菌', '核心菌属',
                   '健康总分', '菌群健康', '慢病控制', '营养均衡']
header = f"{'字段':<14}" + "".join(f"{l[:8]:<10}" for l in all_labels)
print(header)
print('-' * len(header))
for field in overview_fields:
    vals = []
    for label in all_labels:
        v = results[label]['报告概述'].get(field, '—')
        vals.append(str(v)[:8])
    print(f"{field:<14}" + "".join(f"{v:<10}" for v in vals))

# =============================================
# 2. 疾病风险评估
# =============================================
print('\n' + '=' * 80)
print('2. 疾病风险评估')
print('=' * 80)
# 收集所有疾病名
all_diseases = set()
for label in all_labels:
    for r in results[label]['疾病风险评估']:
        all_diseases.add(r['名称'])
all_diseases = sorted(all_diseases)
print(f'共 {len(all_diseases)} 个疾病指标')
for d in all_diseases:
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['疾病风险评估'] if r['名称'] == d]
        if found:
            v = found[0].get('数值', found[0].get('状态', '?'))
        else:
            v = '—'
        vals.append(str(v)[:8])
    print(f"  {d:<14}" + "".join(f"{v:<10}" for v in vals))

# =============================================
# 3. 主要营养评估
# =============================================
print('\n' + '=' * 80)
print('3. 主要营养评估')
print('=' * 80)
all_nutri = set()
for label in all_labels:
    for r in results[label]['主要营养评估']:
        all_nutri.add(r['名称'])
for n in sorted(all_nutri):
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['主要营养评估'] if r['名称'] == n]
        vals.append(found[0]['数值'] if found else '—')
    print(f"  {n:<10}" + "".join(f"{v:<8}" for v in vals))

# =============================================
# 4. 氨基酸评估
# =============================================
print('\n' + '=' * 80)
print('4. 氨基酸评估')
print('=' * 80)
all_amino = set()
for label in all_labels:
    for r in results[label]['氨基酸评估']:
        all_amino.add(r['名称'])
for a in sorted(all_amino):
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['氨基酸评估'] if r['名称'] == a]
        vals.append(found[0]['数值'] if found else '—')
    print(f"  {a:<8}" + "".join(f"{v:<8}" for v in vals))

# =============================================
# 5. 维生素评估
# =============================================
print('\n' + '=' * 80)
print('5. 维生素评估')
print('=' * 80)
all_vit = set()
for label in all_labels:
    for r in results[label]['维生素评估']:
        all_vit.add(r['名称'])
for v in sorted(all_vit):
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['维生素评估'] if r['名称'] == v]
        vals.append(found[0]['数值'] if found else '—')
    print(f"  {v:<10}" + "".join(f"{v:<8}" for v in vals))

# =============================================
# 6. 微量元素评估
# =============================================
print('\n' + '=' * 80)
print('6. 微量元素评估')
print('=' * 80)
for t in ['铁', '锌']:
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['微量元素评估'] if r['名称'] == t]
        vals.append(found[0]['数值'] if found else '—')
    print(f"  {t:<8}" + "".join(f"{v:<8}" for v in vals))

# =============================================
# 7. 主要消化道致病菌
# =============================================
print('\n' + '=' * 80)
print('7. 主要消化道致病菌')
print('=' * 80)
all_path = set()
for label in all_labels:
    for r in results[label]['主要消化道致病菌']:
        all_path.add(r['致病菌'])
for p in sorted(all_path):
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['主要消化道致病菌'] if r['致病菌'] == p]
        vals.append(found[0]['丰度'] if found else '—')
    print(f"  {p:<10}" + "".join(f"{v:<8}" for v in vals))

# =============================================
# 8. 肠道屏障及代谢物
# =============================================
print('\n' + '=' * 80)
print('8. 肠道屏障及代谢物')
print('=' * 80)
all_bar = set()
for label in all_labels:
    for r in results[label]['肠道屏障及代谢物']:
        all_bar.add(r['名称'])
for b in sorted(all_bar):
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['肠道屏障及代谢物'] if r['名称'] == b]
        v = found[0].get('数值', found[0].get('评估值', '?')) if found else '—'
        vals.append(v)
    print(f"  {b:<16}" + "".join(f"{v:<8}" for v in vals))

# =============================================
# 9. 短链脂肪酸
# =============================================
print('\n' + '=' * 80)
print('9. 短链脂肪酸')
print('=' * 80)
all_scfa = set()
for label in all_labels:
    for r in results[label]['短链脂肪酸']:
        all_scfa.add(r['名称'])
for s in sorted(all_scfa):
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['短链脂肪酸'] if r['名称'] == s]
        v = found[0].get('数值', found[0].get('评估值', '?')) if found else '—'
        vals.append(v)
    print(f"  {s:<20}" + "".join(f"{v:<8}" for v in vals))

# =============================================
# 10. 神经递质及激素
# =============================================
print('\n' + '=' * 80)
print('10. 神经递质及激素')
print('=' * 80)
all_nt = set()
for label in all_labels:
    for r in results[label]['神经递质及激素']:
        all_nt.add(r['名称'])
for n in sorted(all_nt):
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['神经递质及激素'] if r['名称'] == n]
        v = found[0].get('数值', found[0].get('评估值', '?')) if found else '—'
        vals.append(v)
    print(f"  {n:<20}" + "".join(f"{v:<8}" for v in vals))

# =============================================
# 11. 抗生素风险评估
# =============================================
print('\n' + '=' * 80)
print('11. 抗生素风险评估')
print('=' * 80)
all_abx = set()
for label in all_labels:
    for r in results[label]['抗生素风险评估']:
        all_abx.add(r['名称'])
for a in sorted(all_abx):
    vals = []
    for label in all_labels:
        found = [r for r in results[label]['抗生素风险评估'] if r['名称'] == a]
        vals.append(found[0]['数值'] if found else '—')
    print(f"  {a:<10}" + "".join(f"{v:<8}" for v in vals))

# =============================================
# 12. 个体化食物推荐表
# =============================================
print('\n' + '=' * 80)
print('12. 个体化食物推荐表')
print('=' * 80)
for label in all_labels:
    food = results[label]['个体化食物推荐表']
    print(f"  {label}: {food['条目数']} 条, 格式={food['格式']}")

# =============================================
# 总结
# =============================================
print('\n' + '=' * 80)
print('交叉验证总结')
print('=' * 80)
print(f"共验证 {len(all_labels)} 份报告")
for label in all_labels:
    r = results[label]
    total = 0
    for k in ['疾病风险评估', '主要营养评估', '氨基酸评估', '维生素评估', '微量元素评估',
              '抗生素风险评估', '主要消化道致病菌', '肠道屏障及代谢物', '短链脂肪酸', '神经递质及激素']:
        total += len(r.get(k, []))
    total += r['个体化食物推荐表']['条目数']
    print(f"  {label}: {total} 总指标项")