235 lines
8.2 KiB
JSON
235 lines
8.2 KiB
JSON
[
|
||
{
|
||
"id": "snpt_water_meter_top_supply_office",
|
||
"desc": "统计各供水管理所下辖水表数量并排序",
|
||
"type": "topn",
|
||
"title": "供水管理所水表数量排行",
|
||
"examples": [
|
||
"列出水表最多的前10个供水管理所",
|
||
"各供水所水表数量排名"
|
||
],
|
||
"variables": [
|
||
{
|
||
"name": "top_n",
|
||
"type": "int",
|
||
"default": 10
|
||
}
|
||
],
|
||
"dialect_sql": {
|
||
"mysql": "SELECT supply_office AS dim_value, COUNT(*) AS metric_value FROM `data-ge.water_meter_info` GROUP BY supply_office ORDER BY metric_value DESC LIMIT {{top_n}}"
|
||
},
|
||
"applicability": {
|
||
"constraints": {
|
||
"notes": [],
|
||
"fk_join_available": false,
|
||
"dim_cardinality_hint": 11
|
||
},
|
||
"time_column": "nullable",
|
||
"required_columns": [
|
||
"supply_office"
|
||
]
|
||
},
|
||
"business_caliber": "按供水管理所维度聚合水表总数，粒度=供水管理所"
|
||
},
|
||
{
|
||
"id": "snpt_water_meter_top_station",
|
||
"desc": "统计各个站点下辖水表数量并排序",
|
||
"type": "topn",
|
||
"title": "站点水表数量排行",
|
||
"examples": [
|
||
"列出水表最多的前10个站点",
|
||
"各站点水表数量排名"
|
||
],
|
||
"variables": [
|
||
{
|
||
"name": "top_n",
|
||
"type": "int",
|
||
"default": 10
|
||
}
|
||
],
|
||
"dialect_sql": {
|
||
"mysql": "SELECT station AS dim_value, COUNT(*) AS metric_value FROM `data-ge.water_meter_info` GROUP BY station ORDER BY metric_value DESC LIMIT {{top_n}}"
|
||
},
|
||
"applicability": {
|
||
"constraints": {
|
||
"notes": [
|
||
"高基数维度建议LIMIT<=50"
|
||
],
|
||
"fk_join_available": false,
|
||
"dim_cardinality_hint": 36
|
||
},
|
||
"time_column": "nullable",
|
||
"required_columns": [
|
||
"station"
|
||
]
|
||
},
|
||
"business_caliber": "按站点维度聚合水表总数，粒度=站点"
|
||
},
|
||
{
|
||
"id": "snpt_water_meter_top_district",
|
||
"desc": "统计各区水表数量并排序",
|
||
"type": "topn",
|
||
"title": "区域水表数量排行",
|
||
"examples": [
|
||
"列出各区水表数量排名",
|
||
"哪个区的水表最多？"
|
||
],
|
||
"variables": [
|
||
{
|
||
"name": "top_n",
|
||
"type": "int",
|
||
"default": 10
|
||
}
|
||
],
|
||
"dialect_sql": {
|
||
"mysql": "SELECT district AS dim_value, COUNT(*) AS metric_value FROM `data-ge.water_meter_info` GROUP BY district ORDER BY metric_value DESC LIMIT {{top_n}}"
|
||
},
|
||
"applicability": {
|
||
"constraints": {
|
||
"notes": [],
|
||
"fk_join_available": false,
|
||
"dim_cardinality_hint": 13
|
||
},
|
||
"time_column": "nullable",
|
||
"required_columns": [
|
||
"district"
|
||
]
|
||
},
|
||
"business_caliber": "按行政区划维度聚合水表总数，粒度=区"
|
||
},
|
||
{
|
||
"id": "snpt_water_meter_share_by_type",
|
||
"desc": "计算各类水表占总水表的比例",
|
||
"type": "ratio",
|
||
"title": "水表类型占比分布",
|
||
"examples": [
|
||
"各类水表占比是多少？",
|
||
"哪种类型的水表使用最广泛？"
|
||
],
|
||
"variables": [],
|
||
"dialect_sql": {
|
||
"mysql": "SELECT meter_type AS dim_value, COUNT(*) * 100.0 / (SELECT COUNT(*) FROM `data-ge.water_meter_info`) AS ratio_percent FROM `data-ge.water_meter_info` GROUP BY meter_type ORDER BY ratio_percent DESC"
|
||
},
|
||
"applicability": {
|
||
"constraints": {
|
||
"notes": [],
|
||
"fk_join_available": false,
|
||
"dim_cardinality_hint": 5
|
||
},
|
||
"time_column": "nullable",
|
||
"required_columns": [
|
||
"meter_type"
|
||
]
|
||
},
|
||
"business_caliber": "按水表类型分类计算其占比，粒度=水表类型"
|
||
},
|
||
{
|
||
"id": "snpt_water_meter_subtype_distribution",
|
||
"desc": "展示不同水表子类型的数量及比例",
|
||
"type": "aggregate",
|
||
"title": "水表子类型分布情况",
|
||
"examples": [
|
||
"各种子类型水表的数量和占比",
|
||
"哪种子类型水表最多？"
|
||
],
|
||
"variables": [],
|
||
"dialect_sql": {
|
||
"mysql": "SELECT meter_subtype AS dim_value, COUNT(*) AS count_value, ROUND(COUNT(*) * 100.0 / (SELECT COUNT(*) FROM `data-ge.water_meter_info`), 2) AS percentage FROM `data-ge.water_meter_info` GROUP BY meter_subtype ORDER BY count_value DESC"
|
||
},
|
||
"applicability": {
|
||
"constraints": {
|
||
"notes": [],
|
||
"fk_join_available": false,
|
||
"dim_cardinality_hint": 9
|
||
},
|
||
"time_column": "nullable",
|
||
"required_columns": [
|
||
"meter_subtype"
|
||
]
|
||
},
|
||
"business_caliber": "按水表子类型进行计数和百分比统计，粒度=水表子类型"
|
||
},
|
||
{
|
||
"id": "snpt_water_meter_installation_position_stats",
|
||
"desc": "统计不同安装位置下的水表数量",
|
||
"type": "aggregate",
|
||
"title": "安装位置分布统计",
|
||
"examples": [
|
||
"各种安装位置的水表数量",
|
||
"哪种安装位置最为常见？"
|
||
],
|
||
"variables": [],
|
||
"dialect_sql": {
|
||
"mysql": "SELECT installation_position AS dim_value, COUNT(*) AS count_value FROM `data-ge.water_meter_info` GROUP BY installation_position ORDER BY count_value DESC"
|
||
},
|
||
"applicability": {
|
||
"constraints": {
|
||
"notes": [],
|
||
"fk_join_available": false,
|
||
"dim_cardinality_hint": 4
|
||
},
|
||
"time_column": "nullable",
|
||
"required_columns": [
|
||
"installation_position"
|
||
]
|
||
},
|
||
"business_caliber": "按安装位置对水表进行分组计数，粒度=安装位置"
|
||
},
|
||
{
|
||
"id": "snpt_water_meter_grain_check",
|
||
"desc": "验证 account_id 和 service_point_id 是否构成唯一组合",
|
||
"type": "quality",
|
||
"title": "主键粒度校验",
|
||
"examples": [
|
||
"这张表的数据粒度是否正确？",
|
||
"是否存在重复的服务点记录？"
|
||
],
|
||
"variables": [],
|
||
"dialect_sql": {
|
||
"mysql": "SELECT IF(COUNT(*) = COUNT(DISTINCT account_id, service_point_id), 'PASS', 'FAIL') AS grain_check_result FROM `data-ge.water_meter_info`"
|
||
},
|
||
"applicability": {
|
||
"constraints": {
|
||
"notes": [],
|
||
"fk_join_available": false,
|
||
"dim_cardinality_hint": null
|
||
},
|
||
"time_column": "nullable",
|
||
"required_columns": [
|
||
"account_id",
|
||
"service_point_id"
|
||
]
|
||
},
|
||
"business_caliber": "检验数据是否符合预期的主键粒度（account_id + service_point_id）"
|
||
},
|
||
{
|
||
"id": "snpt_water_meter_sample_records",
|
||
"desc": "随机抽取部分水表信息用于查看结构",
|
||
"type": "sample",
|
||
"title": "样本抽取",
|
||
"examples": [
|
||
"给我看几条水表数据的例子",
|
||
"抽查一些原始数据看看格式"
|
||
],
|
||
"variables": [
|
||
{
|
||
"name": "limit_rows",
|
||
"type": "int",
|
||
"default": 5
|
||
}
|
||
],
|
||
"dialect_sql": {
|
||
"mysql": "SELECT * FROM `data-ge.water_meter_info` ORDER BY RAND() LIMIT {{limit_rows}}"
|
||
},
|
||
"applicability": {
|
||
"constraints": {
|
||
"notes": [],
|
||
"fk_join_available": false,
|
||
"dim_cardinality_hint": null
|
||
},
|
||
"time_column": "nullable",
|
||
"required_columns": []
|
||
},
|
||
"business_caliber": "从全量数据中随机采样若干条记录供参考"
|
||
}
|
||
] |