{
    "key": "pene_rate",
    "name": "目标市场渗透率",
    "numeric_value": 0.20,
    "unit": "%",
    "source_ref": "SRC-003",
    "logic": "甲市场 A/B 渗透率约 60%/40%；乙市场更适合 B 的低部署成本，同时面临 C 替代冲击，且当前教育成本更高，所以基准假设取 20%。",
    "used_in": "TAM"
}

from scripts.report_generator import MarketSizingData, ReportGenerator
data = MarketSizingData(
    market_name="中国某新兴服务市场",
    geography="中国大陆",
    base_year=2026,
    forecast_years=5,
    tam=9.6,
    sam=5.76,
    som=0.288,
    unit="亿元",
    cagr=0.08,
    market_definition={
        "产品/服务": {"in": "目标服务年费", "out": "硬件一次性收入"},
        "地理": {"in": "中国大陆", "out": "港澳台及海外"},
    },
    market_segments=[
        {
            "name": "核心场景 A",
            "base_value": 6.0,
            "growth_rate": 0.10,
            "logic": "由对象数、采用率、年费三项相乘得到，代表最大组成市场。",
        },
        {
            "name": "验证场景 B",
            "base_value": 3.6,
            "growth_rate": 0.05,
            "logic": "由相邻场景 proxy 推导，体量较小但更适合早期验证。",
        },
    ],
    source_cards=[
        {
            "source_id": "SRC-001",
            "provider": "World Bank",
            "dataset_or_title": "Population, total",
            "metric": "SP.POP.TOTL",
            "geography": "China",
            "period": "2024",
            "unit": "people",
            "value_or_path": "1.408B",
            "url_or_endpoint": "https://api.worldbank.org/v2/country/CN/indicator/SP.POP.TOTL",
            "accessed_at": "2026-06-24",
            "transform_note": "换算为亿人后进入 base_pop",
            "used_in": "base_pop",
        },
        {
            "source_id": "SRC-002",
            "provider": "内部筛选逻辑",
            "dataset_or_title": "目标人群筛选假设",
            "metric": "核心人群占比",
            "geography": "中国大陆",
            "period": "基准年",
            "unit": "%",
            "value_or_path": "40%",
            "url_or_endpoint": "logic-only",
            "accessed_at": "2026-06-24",
            "transform_note": "按年龄、收入和使用场景三层筛选。",
            "used_in": "core_pop_pct",
        },
        {
            "source_id": "SRC-003",
            "provider": "Comparable market scan",
            "dataset_or_title": "相邻市场渗透率对比",
            "metric": "penetration benchmark",
            "geography": "中国大陆",
            "period": "latest available",
            "unit": "%",
            "value_or_path": "相邻市场约 40%",
            "url_or_endpoint": "manual research notes",
            "accessed_at": "2026-06-24",
            "transform_note": "因教育成本和替代品冲击下调至 20%。",
            "used_in": "pene_rate",
        },
        {
            "source_id": "SRC-004",
            "provider": "业务机制假设",
            "dataset_or_title": "购买频次假设",
            "metric": "年购买频次",
            "geography": "中国大陆",
            "period": "基准年",
            "unit": "次/年",
            "value_or_path": "12",
            "url_or_endpoint": "logic-only",
            "accessed_at": "2026-06-24",
            "transform_note": "按月度订阅或月度复购处理。",
            "used_in": "freq",
        },
        {
            "source_id": "SRC-005",
            "provider": "公开价格页/价格带",
            "dataset_or_title": "目标服务价格假设",
            "metric": "单次价格",
            "geography": "中国大陆",
            "period": "基准年",
            "unit": "元",
            "value_or_path": "100",
            "url_or_endpoint": "manual pricing notes",
            "accessed_at": "2026-06-24",
            "transform_note": "取公开价格带中位数。",
            "used_in": "price",
        }
    ],
    assumptions=[
        {"key": "base_pop", "name": "基础人口", "numeric_value": 1.0, "unit": "亿人", "source_ref": "SRC-001", "logic": "只计入目标城市人群，按总人口筛选后换算。"},
        {"key": "core_pop_pct", "name": "核心人群占比", "numeric_value": 0.40, "unit": "%", "source_ref": "SRC-002", "logic": "按年龄、收入和场景三层筛选得到。"},
        {"key": "pene_rate", "name": "付费渗透率", "numeric_value": 0.20, "unit": "%", "source_ref": "SRC-003", "logic": "参考相邻市场 40% 渗透率，并因教育成本和替代品冲击折半。"},
        {"key": "freq", "name": "年购买频次", "numeric_value": 12, "unit": "次/年", "source_ref": "SRC-004", "logic": "按月度订阅/复购频率处理。"},
        {"key": "price", "name": "单次价格", "numeric_value": 100, "unit": "元", "source_ref": "SRC-005", "logic": "参考公开价格带的中位数。"},
        {"key": "sam_ratio", "name": "可服务比例", "numeric_value": 0.60, "unit": "%", "logic": "扣除非目标渠道、地域和暂不可服务客户。"},
        {"key": "som_share", "name": "年度可获取份额", "numeric_value": 0.05, "unit": "%", "logic": "按目标进入节奏、销售产能和竞品份额推导。"},
        {"key": "cagr", "name": "年增长率", "numeric_value": 0.08, "unit": "%", "logic": "由用户增长、价格变化和渗透率提升合成。"},
    ],
)
ReportGenerator().generate(data, output_dir="./output", formats=["xlsx", "md"])