Storage

RDDs

ID RDD Name Storage Level Cached Partitions Fraction Cached Size in Memory Size on Disk
826 *(1) Scan JDBCRelation(( SELECT _id AS brand_context_id, CBP_RISK AS cbp_risk, Kharaon_Risk AS kharon_risk, riskthreshold AS risk_threshold FROM dimrisk_customer_config ) AS t) [numPartitions=1] [brand_context_id#137991,cbp_risk#137992,kharon_risk#137993,risk_threshold#137994] PushedFilters: [], ReadSchema: struct<brand_context_id:string,cbp_risk:string,kharon_risk:string,risk_threshold:decimal(10,2)> Disk Memory Deserialized 1x Replicated 1 100.00% 0.0 B 1028.0 B
5083 AdaptiveSparkPlan isFinalPlan=false +- Project [brand_context_id#588978, supplier_id#588979, entity_name#588980, city#588981, state#588982, country#588983, supplier_type#588984, declaring_supplier_id#588985, threshold#588988, create_date#588989] +- Filter isnull(canonical_id#588986) +- InMemoryTableScan [brand_context_id#588978, canonical_id#588986, city#588981, country#588983, create_date#588989, declaring_supplier_id#588985, entity_name#588980, state#588982, supplier_id#588979, supplier_type#588984, threshold#588988], [isnull(canonical_id#588986)] +- InMemoryRelation [brand_context_id#588978, supplier_id#588979, entity_name#588980, city#588981, state#588982, country#588983, supplier_type#588984, declaring_supplier_id#588985, canonical_id#588986, is_primary#588987, threshold#588988, create_date#588989], StorageLevel(disk, memory, deserialized, 1 replicas) +- *(1) Scan JDBCRelation(( SELECT DISTINCT v.brand_context_id, v.sup... Disk Memory Deserialized 1x Replicated 1 100.00% 0.0 B 1123.0 B
5458 AdaptiveSparkPlan isFinalPlan=false +- Filter isnotnull(canonical_id#588986) +- InMemoryTableScan [brand_context_id#588978, supplier_id#588979, canonical_id#588986, is_primary#588987, entity_name#588980, city#588981, state#588982, country#588983, threshold#588988, create_date#588989], [isnotnull(canonical_id#588986)] +- InMemoryRelation [brand_context_id#588978, supplier_id#588979, entity_name#588980, city#588981, state#588982, country#588983, supplier_type#588984, declaring_supplier_id#588985, canonical_id#588986, is_primary#588987, threshold#588988, create_date#588989], StorageLevel(disk, memory, deserialized, 1 replicas) +- *(1) Scan JDBCRelation(( SELECT DISTINCT v.brand_context_id, v.supplier_id, v.entity_name, v.city, v.state, v.country, v.supplier_type, v.declaring_supplier_id, v.canonical_id, v.is_prima... Disk Memory Deserialized 1x Replicated 1 100.00% 0.0 B 450.8 KiB
6298 *(1) Project [Country#132459, ISO3#132460, ISO2#132461, Region#132462, GHG_Emissions#132463, Trade_Unions#132464, Wages#132465, Working_Time#132466, Gender_Based_Violence#132467, Hazardous_Chemicals#132468, Bribery_and_Corruption#132469, Water#132470, Health_and_Safety#132471, Forced_Labor#132472, Child_Labor#132473, Land_Use_and_Biodiversity#132474, lower(trim(Country#132459, None)) AS _country_key#137600, CASE WHEN ((((((((((((CASE WHEN isnotnull(Child_Labor#132473) THEN 1 ELSE 0 END + CASE WHEN isnotnull(Forced_Labor#132472) THEN 1 ELSE 0 END) + CASE WHEN isnotnull(Gender_Based_Violence#132467) THEN 1 ELSE 0 END) + CASE WHEN isnotnull(Wages#132465) THEN 1 ELSE 0 END) + CASE WHEN isnotnull(Working_Time#132466) THEN 1 ELSE 0 END) + CASE WHEN isnotnull(Trade_Unions#132464) THEN 1 ELSE 0 END) + CASE WHEN isnotnull(Health_and_Safety#132471) THEN 1 ELSE 0 END) + CASE WHEN isnotnull(GHG_Emissions#132463) THEN 1 ELSE 0 END) + CASE WHEN isnotnull(Hazardous_Chemicals#132468) THEN 1 ELSE 0 END) + CASE WHEN isnotnu... Disk Memory Deserialized 1x Replicated 1 100.00% 0.0 B 73.5 KiB
59220 AdaptiveSparkPlan isFinalPlan=false +- Project [brand_context_id#8983060, supplier_id#8983061, entity_name#8983062, city#8983063, state#8983064, country#8983065, supplier_type#8983066, declaring_supplier_id#8983067, threshold#8983070, create_date#8983071] +- Filter isnull(canonical_id#8983068) +- InMemoryTableScan [brand_context_id#8983060, canonical_id#8983068, city#8983063, country#8983065, create_date#8983071, declaring_supplier_id#8983067, entity_name#8983062, state#8983064, supplier_id#8983061, supplier_type#8983066, threshold#8983070], [isnull(canonical_id#8983068)] +- InMemoryRelation [brand_context_id#8983060, supplier_id#8983061, entity_name#8983062, city#8983063, state#8983064, country#8983065, supplier_type#8983066, declaring_supplier_id#8983067, canonical_id#8983068, is_primary#8983069, threshold#8983070, create_date#8983071], StorageLevel(disk, memory, deserialized, 1 replicas) +- *(1) Scan JDBCRelation(( SELECT DISTINCT v.bran... Disk Memory Deserialized 1x Replicated 1 100.00% 0.0 B 730.0 B
63187 AdaptiveSparkPlan isFinalPlan=false +- Filter isnotnull(canonical_id#8983068) +- InMemoryTableScan [brand_context_id#8983060, supplier_id#8983061, canonical_id#8983068, is_primary#8983069, entity_name#8983062, city#8983063, state#8983064, country#8983065, threshold#8983070, create_date#8983071], [isnotnull(canonical_id#8983068)] +- InMemoryRelation [brand_context_id#8983060, supplier_id#8983061, entity_name#8983062, city#8983063, state#8983064, country#8983065, supplier_type#8983066, declaring_supplier_id#8983067, canonical_id#8983068, is_primary#8983069, threshold#8983070, create_date#8983071], StorageLevel(disk, memory, deserialized, 1 replicas) +- *(1) Scan JDBCRelation(( SELECT DISTINCT v.brand_context_id, v.supplier_id, v.entity_name, v.city, v.state, v.country, v.supplier_type, v.declaring_supplier_id, v.canonical_id, ... Disk Memory Deserialized 1x Replicated 1 100.00% 0.0 B 450.7 KiB
65171 *(1) Scan JDBCRelation(( SELECT bigid, brandid AS brand_context_id, supplier_id, supplier_name, supplieruid, countries AS country, city, state, directsupplier AS direct_supplier_name, risk_type, risk_entity, norm_supplier_name, used_threshold, matched_percentage, kharon_id, CBP_risk_entity, calculated_datetime FROM Datahub_risk_identified_entries ) AS t) [numPartitions=1] [bigid#139550L,brand_context_id#139551,supplier_id#139552,supplier_name#139553,supplieruid#139554,country#139555,city#139556,state#139557,direct_supplier_name#139558,risk_type#139559,risk_entity#139560,norm_supplier_name#139561,used_threshold#139562,matched_percentage#139563,kharon_id#139564,CBP_risk_entity#139565,calculated_datetime#139566] PushedFilters: [], ReadSchema: struct<bigid:bigint,brand_context_id:string,supplier_id:string,supplier_name:string,supplieruid:s... Disk Memory Deserialized 1x Replicated 1 100.00% 5.3 KiB 0.0 B
66817 AdaptiveSparkPlan isFinalPlan=false +- MapInPandas <lambda>(brand_context_id#10676649, owner_supplier_id#10676344, facility_id#10676284, source#10676650)#10676655, [brand_context_id#10676656, owner_supplier_id#10676657, facility_id#10676658, source#10676659], false +- Project [66e4031c3b6f7d6b87f5df17 AS brand_context_id#10676649, owner_supplier_id#10676344, facility_id#10676284, master AS source#10676650] +- Filter isnotnull(owner_supplier_id#10676344) +- InMemoryTableScan [facility_id#10676284, owner_supplier_id#10676344], [isnotnull(owner_supplier_id#10676344)] +- InMemoryRelation [facility_id#10676284, facility_uid#10676341, name#10676342, brand_context_id#10676343, owner_supplier_id#10676344, country#10676288, state#10676289, city#10676290, region#10676345, is_unknown#10676346, value_processes#10676348, materials#10676350, tiers#10676351, first_created_date#10676352], StorageLevel(disk, memory, deserialized, 1 replicas) +- AdaptiveSparkPlan isFinal... Disk Memory Deserialized 1x Replicated 1 100.00% 2024.0 B 0.0 B
66960 AdaptiveSparkPlan isFinalPlan=false +- MapInPandas <lambda>(brand_context_id#10685029, owner_supplier_id#10684724, facility_id#10684664, source#10685030)#10685035, [brand_context_id#10685036, owner_supplier_id#10685037, facility_id#10685038, source#10685039], false +- Project [66e415fb6131ad65cad0c625 AS brand_context_id#10685029, owner_supplier_id#10684724, facility_id#10684664, master AS source#10685030] +- Filter isnotnull(owner_supplier_id#10684724) +- InMemoryTableScan [facility_id#10684664, owner_supplier_id#10684724], [isnotnull(owner_supplier_id#10684724)] +- InMemoryRelation [facility_id#10684664, facility_uid#10684721, name#10684722, brand_context_id#10684723, owner_supplier_id#10684724, country#10684668, state#10684669, city#10684670, region#10684725, is_unknown#10684726, value_processes#10684728, materials#10684730, tiers#10684731, first_created_date#10684732], StorageLevel(disk, memory, deserialized, 1 replicas) +- AdaptiveSparkPlan isFinal... Disk Memory Deserialized 1x Replicated 1 100.00% 1680.0 B 0.0 B
67103 AdaptiveSparkPlan isFinalPlan=false +- MapInPandas <lambda>(brand_context_id#10693409, owner_supplier_id#10693104, facility_id#10693044, source#10693410)#10693415, [brand_context_id#10693416, owner_supplier_id#10693417, facility_id#10693418, source#10693419], false +- Project [670df26d2115237fd2f21148 AS brand_context_id#10693409, owner_supplier_id#10693104, facility_id#10693044, master AS source#10693410] +- Filter isnotnull(owner_supplier_id#10693104) +- InMemoryTableScan [facility_id#10693044, owner_supplier_id#10693104], [isnotnull(owner_supplier_id#10693104)] +- InMemoryRelation [facility_id#10693044, facility_uid#10693101, name#10693102, brand_context_id#10693103, owner_supplier_id#10693104, country#10693048, state#10693049, city#10693050, region#10693105, is_unknown#10693106, value_processes#10693108, materials#10693110, tiers#10693111, first_created_date#10693112], StorageLevel(disk, memory, deserialized, 1 replicas) +- AdaptiveSparkPlan isFinal... Disk Memory Deserialized 1x Replicated 1 100.00% 18.8 KiB 0.0 B
67236 AdaptiveSparkPlan isFinalPlan=false +- MapInPandas <lambda>(brand_context_id#10701789, owner_supplier_id#10701484, facility_id#10701424, source#10701790)#10701795, [brand_context_id#10701796, owner_supplier_id#10701797, facility_id#10701798, source#10701799], false +- Project [67567d50561e73389d9a9a7d AS brand_context_id#10701789, owner_supplier_id#10701484, facility_id#10701424, master AS source#10701790] +- Filter isnotnull(owner_supplier_id#10701484) +- InMemoryTableScan [facility_id#10701424, owner_supplier_id#10701484], [isnotnull(owner_supplier_id#10701484)] +- InMemoryRelation [facility_id#10701424, facility_uid#10701481, name#10701482, brand_context_id#10701483, owner_supplier_id#10701484, country#10701428, state#10701429, city#10701430, region#10701485, is_unknown#10701486, value_processes#10701488, materials#10701490, tiers#10701491, first_created_date#10701492], StorageLevel(disk, memory, deserialized, 1 replicas) +- AdaptiveSparkPlan isFinal... Disk Memory Deserialized 1x Replicated 1 100.00% 16.0 B 0.0 B
67367 AdaptiveSparkPlan isFinalPlan=false +- MapInPandas <lambda>(brand_context_id#10710014, owner_supplier_id#10709709, facility_id#10709649, source#10710015)#10710020, [brand_context_id#10710021, owner_supplier_id#10710022, facility_id#10710023, source#10710024], false +- Project [6763c0e31bf4280a71df21ee AS brand_context_id#10710014, owner_supplier_id#10709709, facility_id#10709649, master AS source#10710015] +- Filter isnotnull(owner_supplier_id#10709709) +- InMemoryTableScan [facility_id#10709649, owner_supplier_id#10709709], [isnotnull(owner_supplier_id#10709709)] +- InMemoryRelation [facility_id#10709649, facility_uid#10709706, name#10709707, brand_context_id#10709708, owner_supplier_id#10709709, country#10709653, state#10709654, city#10709655, region#10709710, is_unknown#10709711, value_processes#10709713, materials#10709715, tiers#10709716, first_created_date#10709717], StorageLevel(disk, memory, deserialized, 1 replicas) +- AdaptiveSparkPlan isFinal... Disk Memory Deserialized 1x Replicated 1 100.00% 16.0 B 0.0 B
67506 AdaptiveSparkPlan isFinalPlan=false +- MapInPandas <lambda>(brand_context_id#10718239, owner_supplier_id#10717934, facility_id#10717874, source#10718240)#10718245, [brand_context_id#10718246, owner_supplier_id#10718247, facility_id#10718248, source#10718249], false +- Project [6763c0e31bf4280a71df21f3 AS brand_context_id#10718239, owner_supplier_id#10717934, facility_id#10717874, master AS source#10718240] +- Filter isnotnull(owner_supplier_id#10717934) +- InMemoryTableScan [facility_id#10717874, owner_supplier_id#10717934], [isnotnull(owner_supplier_id#10717934)] +- InMemoryRelation [facility_id#10717874, facility_uid#10717931, name#10717932, brand_context_id#10717933, owner_supplier_id#10717934, country#10717878, state#10717879, city#10717880, region#10717935, is_unknown#10717936, value_processes#10717938, materials#10717940, tiers#10717941, first_created_date#10717942], StorageLevel(disk, memory, deserialized, 1 replicas) +- AdaptiveSparkPlan isFinal... Disk Memory Deserialized 1x Replicated 1 100.00% 3.1 KiB 0.0 B
67604 AdaptiveSparkPlan isFinalPlan=false +- Project [supplier_id#10726113, CASE WHEN NOT (supplier_uid#10726114 = ) THEN supplier_uid#10726114 END AS supplier_uid#10726148, CASE WHEN NOT (supplier_name#10726115 = ) THEN supplier_name#10726115 END AS name#10726149, 6763c888f5905465154e0d84 AS brand_context_id#10726150, country#10726116, state#10726117, city#10726118, AS region#10726151, active AS status#10726152, false AS is_unknown#10726153, (upper(coalesce(is_nominated#10726119, )) = YES) AS is_nominated#10726154, master AS source_evidence#10726155, array_sort(array_union(coalesce(bridge_tiers#10726106, []), [1]), lambdafunction(if ((isnull(lambda left#10726158) AND isnull(lambda right#10726159))) 0 else if (isnull(lambda left#10726158)) 1 else if (isnull(lambda right#10726159)) -1 else if ((lambda left#10726158 < lambda right#10726159)) -1 else if ((lambda left#10726158 > lambda right#10726159)) 1 else 0, lambda left#10726158, lambda right#10726159, false), false) AS tiers#10726156, coalesce(chain_first_crea... Disk Memory Deserialized 1x Replicated 1 100.00% 14.3 KiB 0.0 B
67628 AdaptiveSparkPlan isFinalPlan=false +- Project [facility_id#10726254, CASE WHEN NOT (facility_uid#10726255 = ) THEN facility_uid#10726255 END AS facility_uid#10726311, CASE WHEN NOT (facility_name#10726256 = ) THEN facility_name#10726256 END AS name#10726312, 6763c888f5905465154e0d84 AS brand_context_id#10726313, CASE WHEN (isnotnull(owner_supplier_id#10726257) AND NOT (owner_supplier_id#10726257 = )) THEN owner_supplier_id#10726257 END AS owner_supplier_id#10726314, country#10726258, state#10726259, city#10726260, AS region#10726315, false AS is_unknown#10726316, pythonUDF0#10726477 AS value_processes#10726318, pythonUDF1#10726478 AS materials#10726320, coalesce(_owner_tiers#10726247, [1]) AS tiers#10726321, coalesce(chain_first_created_date#10726251, master_first_created_date#10726263) AS first_created_date#10726322] +- BatchEvalPython [_explode_csv_dedup(coalesce(value_process#10726261, ))#10726317, _explode_csv_dedup(coalesce(materials#10726262, ))#10726319], [pythonUDF0#10726477, pythonUDF1#107264... Disk Memory Deserialized 1x Replicated 1 100.00% 11.4 KiB 0.0 B
67643 AdaptiveSparkPlan isFinalPlan=false +- MapInPandas <lambda>(brand_context_id#10726619, owner_supplier_id#10726314, facility_id#10726254, source#10726620)#10726625, [brand_context_id#10726626, owner_supplier_id#10726627, facility_id#10726628, source#10726629], false +- Project [6763c888f5905465154e0d84 AS brand_context_id#10726619, owner_supplier_id#10726314, facility_id#10726254, master AS source#10726620] +- Filter isnotnull(owner_supplier_id#10726314) +- InMemoryTableScan [facility_id#10726254, owner_supplier_id#10726314], [isnotnull(owner_supplier_id#10726314)] +- InMemoryRelation [facility_id#10726254, facility_uid#10726311, name#10726312, brand_context_id#10726313, owner_supplier_id#10726314, country#10726258, state#10726259, city#10726260, region#10726315, is_unknown#10726316, value_processes#10726318, materials#10726320, tiers#10726321, first_created_date#10726322], StorageLevel(disk, memory, deserialized, 1 replicas) +- AdaptiveSparkPlan isFinal... Disk Memory Deserialized 1x Replicated 1 100.00% 2.9 KiB 0.0 B
67662 AdaptiveSparkPlan isFinalPlan=false +- Project [supplier_id#10726113 AS entity_id#10727753, brand_context_id#10726150, dim_id#10727747, raw_level#10727748 AS level#10727754, CASE WHEN (cast(raw_level#10727748 as double) >= 4.2) THEN Extreme WHEN (cast(raw_level#10727748 as double) >= 3.4) THEN High WHEN (cast(raw_level#10727748 as double) >= 2.6) THEN Moderate WHEN (cast(raw_level#10727748 as double) >= 1.8) THEN Medium WHEN (cast(raw_level#10727748 as double) >= 1.0) THEN Low ELSE Unknown END AS level_band#10727755, active AS status#10727756, 2026-10-16T08:22:46.270626+00:00 AS listed_at#10727757, 2026-10-16T08:22:46.270626+00:00 AS assessed_at#10727758, null AS matched_entity#10727759, null AS match_pct#10727760, null AS match_source#10727761, null AS threshold#10727762, null AS kharon_id#10727763] +- Filter (isnotnull(raw_level#10727748) AND NOT (raw_level#10727748 = )) +- Generate stack(13, risk_child_labor, cast(Child_Labor#132473 as string), risk_forced_labor, cast(Forced_Labor#132472 as str... Disk Memory Deserialized 1x Replicated 1 100.00% 35.5 KiB 0.0 B