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 +1,230 @@
{
"role": "dimension",
"time": {
"range": null,
"column": null,
"has_gaps": null,
"granularity": "unknown"
},
"grain": [
"service_point_id"
],
"table": "data-ge.water_meter_info",
"columns": [
{
"name": "supply_office",
"dtype": "string",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "非空11 个枚举值GE 约束)",
"enumish": true,
"null_rate": 0.0,
"top_values": [],
"semantic_type": "dimension",
"distinct_count": 11,
"distinct_ratio": 0.03666666666666667,
"pk_candidate_score": 0.05,
"metric_candidate_score": 0.0
},
{
"name": "station",
"dtype": "string",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "非空36 个枚举值GE 约束)",
"enumish": true,
"null_rate": 0.0,
"top_values": [],
"semantic_type": "dimension",
"distinct_count": 36,
"distinct_ratio": 0.12,
"pk_candidate_score": 0.1,
"metric_candidate_score": 0.0
},
{
"name": "district",
"dtype": "string",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "非空13 个枚举值GE 约束)",
"enumish": true,
"null_rate": 0.0,
"top_values": [],
"semantic_type": "dimension",
"distinct_count": 13,
"distinct_ratio": 0.043333333333333335,
"pk_candidate_score": 0.05,
"metric_candidate_score": 0.0
},
{
"name": "meter_diameter",
"dtype": "string",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "非空8 个枚举值GE 约束)",
"enumish": true,
"null_rate": 0.0,
"top_values": [],
"semantic_type": "dimension",
"distinct_count": 8,
"distinct_ratio": 0.02666666666666667,
"pk_candidate_score": 0.03,
"metric_candidate_score": 0.0
},
{
"name": "meter_status",
"dtype": "string",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "非空;单一取值(\"有效\"",
"enumish": true,
"null_rate": 0.0,
"top_values": [],
"semantic_type": "dimension",
"distinct_count": 1,
"distinct_ratio": 0.0033333333333333335,
"pk_candidate_score": 0.0,
"metric_candidate_score": 0.0
},
{
"name": "meter_subtype",
"dtype": "string",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "非空9 个枚举值GE 约束)",
"enumish": true,
"null_rate": 0.0,
"top_values": [],
"semantic_type": "dimension",
"distinct_count": 9,
"distinct_ratio": 0.03,
"pk_candidate_score": 0.03,
"metric_candidate_score": 0.0
},
{
"name": "meter_type",
"dtype": "string",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "非空5 个枚举值GE 约束)",
"enumish": true,
"null_rate": 0.0,
"top_values": [],
"semantic_type": "dimension",
"distinct_count": 5,
"distinct_ratio": 0.016666666666666666,
"pk_candidate_score": 0.02,
"metric_candidate_score": 0.0
},
{
"name": "installation_position",
"dtype": "string",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "非空4 个枚举值GE 约束)",
"enumish": true,
"null_rate": 0.0,
"top_values": [],
"semantic_type": "dimension",
"distinct_count": 4,
"distinct_ratio": 0.013333333333333334,
"pk_candidate_score": 0.02,
"metric_candidate_score": 0.0
},
{
"name": "service_point_id",
"dtype": "unknown",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "命名指示标识列;未提供唯一性或非空验证",
"enumish": null,
"null_rate": null,
"top_values": [],
"semantic_type": "id",
"distinct_count": null,
"distinct_ratio": null,
"pk_candidate_score": 0.6,
"metric_candidate_score": 0.05
},
{
"name": "account_id",
"dtype": "unknown",
"stats": {
"max": null,
"min": null,
"std": null,
"mean": null,
"skewness": null
},
"comment": "命名指示账户标识;未提供唯一性或非空验证",
"enumish": null,
"null_rate": null,
"top_values": [],
"semantic_type": "id",
"distinct_count": null,
"distinct_ratio": null,
"pk_candidate_score": 0.5,
"metric_candidate_score": 0.05
}
],
"quality": {
"warning_hints": [
"以下列未设置非空校验service_point_id, account_id空值情况未知",
"未识别到时间列"
],
"failed_expectations": []
},
"row_count": 300,
"fk_candidates": [],
"confidence_notes": [
"role 判定为 dimension表内列均为枚举/分类或ID未发现数值型度量或时间列34/34 期望均为分类枚举/非空与去重比例。",
"grain 猜测为 service_point_id仅依据命名启发式缺少唯一性与非空度量佐证置信度较低。",
"未识别时间列:列名与期望均未涉及日期/时间,也无最小/最大时间范围可推断。"
],
"primary_key_candidates": []
}