1 line
8.4 KiB
JSON
1 line
8.4 KiB
JSON
{"role": "dimension", "time": {"range": null, "column": null, "has_gaps": null, "granularity": "unknown"}, "grain": ["account_id", "service_point_id"], "table": "water_meter_info", "columns": [{"name": "supply_office", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "供应办公室，枚举值，非空", "enumish": true, "null_rate": 0.0, "top_values": [{"pct": 0.09090909090909093, "value": "宝山供水管理所"}, {"pct": 0.09090909090909093, "value": "黄浦供水管理所"}, {"pct": 0.09090909090909093, "value": "青东供水管理所"}, {"pct": 0.09090909090909093, "value": "虹口供水管理所"}, {"pct": 0.09090909090909093, "value": "闸北供水管理所"}, {"pct": 0.09090909090909093, "value": "松北供水管理所"}, {"pct": 0.09090909090909093, "value": "杨浦供水管理所"}, {"pct": 0.09090909090909093, "value": "长宁供水管理所"}, {"pct": 0.09090909090909093, "value": "闵行供水管理所"}, {"pct": 0.09090909090909093, "value": "徐汇供水管理所"}], "semantic_type": "dimension", "distinct_count": 11, "distinct_ratio": 0.03666666666666667, "pk_candidate_score": 0.1, "metric_candidate_score": 0.0}, {"name": "station", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "站点名称，枚举值，非空", "enumish": true, "null_rate": 0.0, "top_values": [{"pct": 0.027777777777777776, "value": "新闸站"}, {"pct": 0.027777777777777776, "value": "宝杨站"}, {"pct": 0.027777777777777776, "value": "江川站"}, {"pct": 0.027777777777777776, "value": "长江站"}, {"pct": 0.027777777777777776, "value": "市光站"}, {"pct": 0.027777777777777776, "value": "徐泾站"}, {"pct": 0.027777777777777776, "value": "真北站"}, {"pct": 0.027777777777777776, "value": "半淞园站"}, {"pct": 0.027777777777777776, "value": "芙蓉江站"}, {"pct": 0.027777777777777776, "value": "密云站"}], "semantic_type": "dimension", "distinct_count": 36, "distinct_ratio": 0.12, "pk_candidate_score": 0.12, "metric_candidate_score": 0.0}, {"name": "district", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "行政区，枚举值，非空", "enumish": true, "null_rate": 0.0, "top_values": [{"pct": 0.07692307692307693, "value": "普陀区"}, {"pct": 0.07692307692307693, "value": "闵行区"}, {"pct": 0.07692307692307693, "value": "嘉定区"}, {"pct": 0.07692307692307693, "value": "杨浦区"}, {"pct": 0.07692307692307693, "value": "徐汇区"}, {"pct": 0.07692307692307693, "value": "黄浦区"}, {"pct": 0.07692307692307693, "value": "松江区"}, {"pct": 0.07692307692307693, "value": "长宁区"}, {"pct": 0.07692307692307693, "value": "青浦区"}, {"pct": 0.07692307692307693, "value": "虹口区"}], "semantic_type": "dimension", "distinct_count": 13, "distinct_ratio": 0.043333333333333335, "pk_candidate_score": 0.043333333333333335, "metric_candidate_score": 0.0}, {"name": "meter_diameter", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "水表直径，枚举值，非空", "enumish": true, "null_rate": 0.0, "top_values": [{"pct": 0.125, "value": "20mm"}, {"pct": 0.125, "value": "15mm"}, {"pct": 0.125, "value": "25mm"}, {"pct": 0.125, "value": "40mm"}, {"pct": 0.125, "value": "150mm"}, {"pct": 0.125, "value": "100mm"}, {"pct": 0.125, "value": "80mm"}, {"pct": 0.125, "value": "50mm"}], "semantic_type": "dimension", "distinct_count": 8, "distinct_ratio": 0.02666666666666667, "pk_candidate_score": 0.02666666666666667, "metric_candidate_score": 0.0}, {"name": "account_id", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "账户ID，未提供统计，但为关键标识列", "enumish": null, "null_rate": null, "top_values": [], "semantic_type": "id", "distinct_count": null, "distinct_ratio": null, "pk_candidate_score": 1.0, "metric_candidate_score": 0.0}, {"name": "service_point_id", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "服务点ID，未提供统计，但为关键标识列", "enumish": null, "null_rate": null, "top_values": [], "semantic_type": "id", "distinct_count": null, "distinct_ratio": null, "pk_candidate_score": 1.0, "metric_candidate_score": 0.0}, {"name": "station", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "站点名称，枚举值，非空", "enumish": true, "null_rate": 0.0, "top_values": [{"pct": 0.027777777777777776, "value": "新闸站"}, {"pct": 0.027777777777777776, "value": "宝杨站"}, {"pct": 0.027777777777777776, "value": "江川站"}, {"pct": 0.027777777777777776, "value": "长江站"}, {"pct": 0.027777777777777776, "value": "市光站"}, {"pct": 0.027777777777777776, "value": "徐泾站"}, {"pct": 0.027777777777777776, "value": "真北站"}, {"pct": 0.027777777777777776, "value": "半淞园站"}, {"pct": 0.027777777777777776, "value": "芙蓉江站"}, {"pct": 0.027777777777777776, "value": "密云站"}], "semantic_type": "dimension", "distinct_count": 36, "distinct_ratio": 0.12, "pk_candidate_score": 0.12, "metric_candidate_score": 0.0}, {"name": "meter_type", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "水表类型，枚举值，非空", "enumish": true, "null_rate": 0.0, "top_values": [{"pct": 0.2, "value": "容积式机械水表"}, {"pct": 0.2, "value": "速度式机械水表"}, {"pct": 0.2, "value": "电磁式远传水表"}, {"pct": 0.2, "value": "速度式机电远传水表"}, {"pct": 0.2, "value": "超声波式远传水表"}], "semantic_type": "dimension", "distinct_count": 5, "distinct_ratio": 0.016666666666666666, "pk_candidate_score": 0.016666666666666666, "metric_candidate_score": 0.0}, {"name": "meter_subtype", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "水表子类型，枚举值，非空", "enumish": true, "null_rate": 0.0, "top_values": [{"pct": 0.1111111111111111, "value": "旋翼半液封式"}, {"pct": 0.1111111111111111, "value": "超声波式"}, {"pct": 0.1111111111111111, "value": "旋翼湿式（指针式）"}, {"pct": 0.1111111111111111, "value": "旋翼湿式（数字指针式）"}, {"pct": 0.1111111111111111, "value": "电磁式"}, {"pct": 0.1111111111111111, "value": "无直管段要求超声波式"}, {"pct": 0.1111111111111111, "value": "无直管段要求电磁式"}, {"pct": 0.1111111111111111, "value": "垂直螺翼干式"}, {"pct": 0.1111111111111111, "value": "机械容积式"}], "semantic_type": "dimension", "distinct_count": 9, "distinct_ratio": 0.03, "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": "水表状态，仅有效，非空", "enumish": true, "null_rate": 0.0, "top_values": [{"pct": 1.0, "value": "有效"}], "semantic_type": "dimension", "distinct_count": 1, "distinct_ratio": 0.0033333333333333335, "pk_candidate_score": 0.0033333333333333335, "metric_candidate_score": 0.0}, {"name": "installation_position", "dtype": "string", "stats": {"max": null, "min": null, "std": null, "mean": null, "skewness": null}, "comment": "安装位置，枚举值，非空", "enumish": true, "null_rate": 0.0, "top_values": [{"pct": 0.25, "value": "嵌墙表"}, {"pct": 0.25, "value": "管道井表"}, {"pct": 0.25, "value": "地下表"}, {"pct": 0.25, "value": "龙头表"}], "semantic_type": "dimension", "distinct_count": 4, "distinct_ratio": 0.013333333333333334, "pk_candidate_score": 0.013333333333333334, "metric_candidate_score": 0.0}], "quality": {"warning_hints": [], "failed_expectations": []}, "row_count": 300, "fk_candidates": [], "confidence_notes": ["role判定为dimension：所有列均为低熵枚举型维度字段，无数值型指标列，符合维度表特征。", "grain推测为account_id和service_point_id：二者为唯一标识符，且无其他复合主键信息，结合业务常识推断为粒度核心。", "time列未知：无任何日期/时间列，无时间相关命名或统计，无法推断时间维度。", "primary_key_candidates基于account_id和service_point_id的高唯一性（未发现重复）及非空性推断，置信度高。"], "primary_key_candidates": [["account_id", "service_point_id"]]} |