demo数据

This commit is contained in:
zhaoawd
2025-11-14 00:58:00 +08:00
parent 7eb3c059a1
commit a72ca3593e
13 changed files with 2733 additions and 0 deletions

View File

@ -0,0 +1,415 @@
{
"role": "dimension",
"time": {
"range": null,
"column": null,
"has_gaps": null,
"granularity": "unknown"
},
"grain": [
"account_id",
"service_point_id"
],
"table": "data-ge.water_meter_info",
"columns": [
{
"name": "supply_office",
"dtype": "string",
"stats": {},
"comment": "供水管理所名称,枚举值",
"enumish": true,
"null_rate": 0.0,
"top_values": [
{
"pct": null,
"value": "宝山供水管理所"
},
{
"pct": null,
"value": "黄浦供水管理所"
},
{
"pct": null,
"value": "青东供水管理所"
},
{
"pct": null,
"value": "虹口供水管理所"
},
{
"pct": null,
"value": "闸北供水管理所"
},
{
"pct": null,
"value": "松北供水管理所"
},
{
"pct": null,
"value": "杨浦供水管理所"
},
{
"pct": null,
"value": "长宁供水管理所"
},
{
"pct": null,
"value": "闵行供水管理所"
},
{
"pct": null,
"value": "徐汇供水管理所"
},
{
"pct": null,
"value": "普陀供水管理所"
}
],
"semantic_type": "dimension",
"distinct_count": 11,
"distinct_ratio": 0.03666666666666667,
"pk_candidate_score": 0.11,
"metric_candidate_score": 0.0
},
{
"name": "station",
"dtype": "string",
"stats": {},
"comment": "站点名称,枚举值",
"enumish": true,
"null_rate": 0.0,
"top_values": [
{
"pct": null,
"value": "新闸站"
},
{
"pct": null,
"value": "宝杨站"
},
{
"pct": null,
"value": "江川站"
},
{
"pct": null,
"value": "长江站"
},
{
"pct": null,
"value": "市光站"
},
{
"pct": null,
"value": "徐泾站"
},
{
"pct": null,
"value": "真北站"
},
{
"pct": null,
"value": "半淞园站"
},
{
"pct": null,
"value": "芙蓉江站"
},
{
"pct": null,
"value": "密云站"
}
],
"semantic_type": "dimension",
"distinct_count": 36,
"distinct_ratio": 0.12,
"pk_candidate_score": 0.36,
"metric_candidate_score": 0.0
},
{
"name": "district",
"dtype": "string",
"stats": {},
"comment": "行政区划名称,枚举值",
"enumish": true,
"null_rate": 0.0,
"top_values": [
{
"pct": null,
"value": "普陀区"
},
{
"pct": null,
"value": "闵行区"
},
{
"pct": null,
"value": "嘉定区"
},
{
"pct": null,
"value": "杨浦区"
},
{
"pct": null,
"value": "徐汇区"
},
{
"pct": null,
"value": "黄浦区"
},
{
"pct": null,
"value": "松江区"
},
{
"pct": null,
"value": "长宁区"
},
{
"pct": null,
"value": "青浦区"
},
{
"pct": null,
"value": "虹口区"
}
],
"semantic_type": "dimension",
"distinct_count": 13,
"distinct_ratio": 0.043333333333333335,
"pk_candidate_score": 0.13,
"metric_candidate_score": 0.0
},
{
"name": "meter_diameter",
"dtype": "string",
"stats": {},
"comment": "水表直径规格,枚举值",
"enumish": true,
"null_rate": 0.0,
"top_values": [
{
"pct": null,
"value": "20mm"
},
{
"pct": null,
"value": "15mm"
},
{
"pct": null,
"value": "25mm"
},
{
"pct": null,
"value": "40mm"
},
{
"pct": null,
"value": "150mm"
},
{
"pct": null,
"value": "100mm"
},
{
"pct": null,
"value": "80mm"
},
{
"pct": null,
"value": "50mm"
}
],
"semantic_type": "dimension",
"distinct_count": 8,
"distinct_ratio": 0.02666666666666667,
"pk_candidate_score": 0.08,
"metric_candidate_score": 0.0
},
{
"name": "meter_status",
"dtype": "string",
"stats": {},
"comment": "水表状态,枚举值",
"enumish": true,
"null_rate": 0.0,
"top_values": [
{
"pct": null,
"value": "有效"
}
],
"semantic_type": "dimension",
"distinct_count": 1,
"distinct_ratio": 0.0033333333333333335,
"pk_candidate_score": 0.01,
"metric_candidate_score": 0.0
},
{
"name": "meter_subtype",
"dtype": "string",
"stats": {},
"comment": "水表子类型,枚举值",
"enumish": true,
"null_rate": 0.0,
"top_values": [
{
"pct": null,
"value": "旋翼半液封式"
},
{
"pct": null,
"value": "超声波式"
},
{
"pct": null,
"value": "旋翼湿式(指针式)"
},
{
"pct": null,
"value": "旋翼湿式(数字指针式)"
},
{
"pct": null,
"value": "电磁式"
},
{
"pct": null,
"value": "无直管段要求超声波式"
},
{
"pct": null,
"value": "无直管段要求电磁式"
},
{
"pct": null,
"value": "垂直螺翼干式"
},
{
"pct": null,
"value": "机械容积式"
}
],
"semantic_type": "dimension",
"distinct_count": 9,
"distinct_ratio": 0.03,
"pk_candidate_score": 0.09,
"metric_candidate_score": 0.0
},
{
"name": "meter_type",
"dtype": "string",
"stats": {},
"comment": "水表类型,枚举值",
"enumish": true,
"null_rate": 0.0,
"top_values": [
{
"pct": null,
"value": "容积式机械水表"
},
{
"pct": null,
"value": "速度式机械水表"
},
{
"pct": null,
"value": "电磁式远传水表"
},
{
"pct": null,
"value": "速度式机电远传水表"
},
{
"pct": null,
"value": "超声波式远传水表"
}
],
"semantic_type": "dimension",
"distinct_count": 5,
"distinct_ratio": 0.016666666666666666,
"pk_candidate_score": 0.05,
"metric_candidate_score": 0.0
},
{
"name": "installation_position",
"dtype": "string",
"stats": {},
"comment": "安装位置,枚举值",
"enumish": true,
"null_rate": 0.0,
"top_values": [
{
"pct": null,
"value": "嵌墙表"
},
{
"pct": null,
"value": "管道井表"
},
{
"pct": null,
"value": "地下表"
},
{
"pct": null,
"value": "龙头表"
}
],
"semantic_type": "dimension",
"distinct_count": 4,
"distinct_ratio": 0.013333333333333334,
"pk_candidate_score": 0.04,
"metric_candidate_score": 0.0
},
{
"name": "account_id",
"dtype": "string",
"stats": {},
"comment": "账户ID",
"enumish": false,
"null_rate": null,
"top_values": [],
"semantic_type": "id",
"distinct_count": null,
"distinct_ratio": null,
"pk_candidate_score": 0.95,
"metric_candidate_score": 0.0
},
{
"name": "service_point_id",
"dtype": "string",
"stats": {},
"comment": "服务点ID",
"enumish": false,
"null_rate": null,
"top_values": [],
"semantic_type": "id",
"distinct_count": null,
"distinct_ratio": null,
"pk_candidate_score": 0.95,
"metric_candidate_score": 0.0
}
],
"quality": {
"warning_hints": [],
"failed_expectations": []
},
"row_count": 300,
"fk_candidates": [],
"confidence_notes": [
"role判定为dimension因所有列均为枚举或ID类型无metric列",
"grain依据account_id和service_point_id为唯一标识推测",
"未发现时间列因此time字段为null"
],
"primary_key_candidates": [
[
"account_id"
],
[
"service_point_id"
]
]
}