Stage 1 data: version dedup, splitting of long documents, family split; 748 iterations

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat
This commit is contained in:
Kral
2026-10-03 22:09:15 +02:00
parent e083c9ca13
commit 0677d035da
5 changed files with 1014 additions and 421 deletions

View File

@@ -3,348 +3,220 @@
"seed": 20261003,
"max_len": 16384,
"estimate_tokens": 2636112,
"real_tokens": 2806501,
"ratio_real_to_estimate": 1.065,
"all": {
"docs": 370,
"tokens": 2806501,
"min": 49,
"p50": 5195,
"p90": 16923,
"p99": 21483,
"max": 31552
},
"kept": {
"docs": 325,
"tokens": 1966365,
"min": 49,
"p50": 4027,
"p90": 14998,
"p99": 16217,
"max": 16273
},
"train": {
"docs": 309,
"tokens": 1886475,
"min": 49,
"p50": 4403,
"p90": 14998,
"p99": 16217,
"max": 16273
},
"valid": {
"docs": 16,
"tokens": 79890,
"min": 130,
"p50": 3392,
"p90": 16027,
"p99": 16129,
"max": 16129
},
"removed": [
"records": 370,
"tokens_before_dedup": 2806501,
"tokens_after_dedup": 2699110,
"records_after_dedup": 351,
"tokens_after_split": 2701996,
"objects_with_versions": 39,
"families": 269,
"versions_kept": 319,
"versions_removed": 16,
"strict_rule_would_remove_more": 8,
"removed_versions": [
{
"objects": [
"ZCL_DEMO_ABAP_OBJECTS (CLAS)"
],
"tokens": 17042
"object": "ZBP_DEMO_ABAP_RAP_RO_U (CLAS)",
"version": "v758",
"newest": "main",
"diff": 0.015,
"tokens": 10696
},
{
"objects": [
"ZCL_DEMO_ABAP_STRUCTURES (CLAS)"
],
"tokens": 16628
"object": "ZDEMO_ABAP_RAP_RO_M (BDEF)",
"version": "v756",
"newest": "main",
"diff": 0.037,
"tokens": 259
},
{
"objects": [
"32_Performance_Notes__P03 (DOC)"
],
"tokens": 16742
"object": "ZDEMO_ABAP_RAP_RO_U (BDEF)",
"version": "v756",
"newest": "main",
"diff": 0.043,
"tokens": 236
},
{
"objects": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES (CLAS)"
],
"tokens": 19117
"object": "ZDEMO_ABAP_CDS_VE_ASSOC_E (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.026,
"tokens": 542
},
{
"objects": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES (CLAS)"
],
"tokens": 18883
"object": "ZDEMO_ABAP_CDS_VE_JOINS (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.009,
"tokens": 1827
},
{
"objects": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG__V755 (CLAS)"
],
"tokens": 19801
"object": "ZDEMO_ABAP_CDS_VE_AGG_EXP (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.019,
"tokens": 804
},
{
"objects": [
"23_Date_and_Time (DOC)"
],
"tokens": 20347
"object": "ZDEMO_ABAP_CDS_VE_SEL (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.029,
"tokens": 3273
},
{
"objects": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES__V757 (CLAS)"
],
"tokens": 17477
"object": "ZDEMO_ABAP_CDS_VE_ASSOC (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.008,
"tokens": 2451
},
{
"objects": [
"07_String_Processing__P02 (DOC)"
],
"tokens": 17916
"object": "ZDEMO_ABAP_FLI_VE (DDLS)",
"version": "v816",
"newest": "main",
"diff": 0.0,
"tokens": 168
},
{
"objects": [
"ZCL_DEMO_ABAP_CONSTRUCTOR_EXPR (CLAS)"
],
"tokens": 17368
"object": "ZCL_DEMO_ABAP_DTYPE_DOBJ (CLAS)",
"version": "v816",
"newest": "main",
"diff": 0.009,
"tokens": 27407
},
{
"objects": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG__V758 (CLAS)"
],
"tokens": 31552
"object": "ZCL_DEMO_ABAP_DISPLAY (CLAS)",
"version": "v755",
"newest": "v757",
"diff": 0.02,
"tokens": 1677
},
{
"objects": [
"ZCL_DEMO_ABAP_STRING_PROC__V757 (CLAS)"
],
"tokens": 19499
"object": "ZCL_DEMO_ABAP_UNIT_TEST (CLAS)",
"version": "v758",
"newest": "main",
"diff": 0.034,
"tokens": 19799
},
{
"objects": [
"04_ABAP_Object_Orientation__P06 (DOC)"
],
"tokens": 16694
"object": "ZDEMO_ABAP_DYNPRO (PROG)",
"version": "v757",
"newest": "v816",
"diff": 0.001,
"tokens": 8026
},
{
"objects": [
"ZCL_DEMO_ABAP_DTYPE_DOBJ__V758 (CLAS)"
],
"tokens": 18368
"object": "ZBP_DEMO_ABAP_RAP_DRAFT_M (CLAS)",
"version": "v757",
"newest": "v758",
"diff": 0.005,
"tokens": 2474
},
{
"objects": [
"06_Dynamic_Programming__P07 (DOC)"
],
"tokens": 23994
"object": "ZCL_DEMO_ABAP_NUMERIC_OP (CLAS)",
"version": "v816",
"newest": "main",
"diff": 0.003,
"tokens": 20484
},
{
"objects": [
"28_Regular_Expressions (DOC)"
],
"tokens": 17900
},
{
"objects": [
"06_Dynamic_Programming__P06 (DOC)"
],
"tokens": 16923
},
{
"objects": [
"ZCL_DEMO_ABAP_NUMERIC_OP__V816 (CLAS)"
],
"tokens": 19769
},
{
"objects": [
"05_Constructor_Expressions__P01 (DOC)"
],
"tokens": 17349
},
{
"objects": [
"ZCL_DEMO_ABAP_DTYPE_DOBJ__V755 (CLAS)"
],
"tokens": 17237
},
{
"objects": [
"ZCL_DEMO_ABAP_DTYPE_DOBJ__V756 (CLAS)"
],
"tokens": 18069
},
{
"objects": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG (CLAS)"
],
"tokens": 17923
},
{
"objects": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG (CLAS)"
],
"tokens": 16924
},
{
"objects": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG (CLAS)"
],
"tokens": 16770
},
{
"objects": [
"14_ABAP_Unit_Tests__P03 (DOC)"
],
"tokens": 18549
},
{
"objects": [
"ZCL_DEMO_ABAP_STRING_PROC__V758 (CLAS)"
],
"tokens": 22096
},
{
"objects": [
"22_Released_ABAP_Classes__P01 (DOC)"
],
"tokens": 19022
},
{
"objects": [
"21_XML_JSON__P01 (DOC)"
],
"tokens": 16625
},
{
"objects": [
"29_Numeric_Operations__P01 (DOC)"
],
"tokens": 17805
},
{
"objects": [
"03_ABAP_SQL__P01 (DOC)"
],
"tokens": 17305
},
{
"objects": [
"ZCL_DEMO_ABAP_DTYPE_DOBJ__V757 (CLAS)"
],
"tokens": 18308
},
{
"objects": [
"14_ABAP_Unit_Tests__P04 (DOC)"
],
"tokens": 17633
},
{
"objects": [
"24_Builtin_Functions (DOC)"
],
"tokens": 16851
},
{
"objects": [
"ZCL_DEMO_ABAP_NUMERIC_OP (CLAS)"
],
"tokens": 19740
},
{
"objects": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES__V758 (CLAS)"
],
"tokens": 17355
},
{
"objects": [
"ZCL_DEMO_ABAP_BUILTIN_FUNC (CLAS)"
],
"tokens": 20446
},
{
"objects": [
"ZCL_DEMO_ABAP_STRING_PROC (CLAS)"
],
"tokens": 20311
},
{
"objects": [
"ZCL_DEMO_ABAP_UNIT_TEST__V758 (CLAS)"
],
"tokens": 16394
},
{
"objects": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG__V757 (CLAS)"
],
"tokens": 21483
},
{
"objects": [
"ZCL_DEMO_ABAP_DATE_TIME (CLAS)"
],
"tokens": 18634
},
{
"objects": [
"ZCL_DEMO_ABAP_XML_JSON (CLAS)"
],
"tokens": 16825
},
{
"objects": [
"ZCL_DEMO_ABAP_SQL (CLAS)"
],
"tokens": 18283
},
{
"objects": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES__V755 (CLAS)"
],
"tokens": 17309
},
{
"objects": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG__V756 (CLAS)"
],
"tokens": 20979
},
{
"objects": [
"16_Data_Types_and_Objects__P02 (DOC)"
],
"tokens": 17891
"object": "ZDEMO_ABAP_ALV (PROG)",
"version": "v757",
"newest": "v816",
"diff": 0.002,
"tokens": 7268
}
],
"split_docs": 43,
"hard_line_splits": 17,
"pieces_over_limit": 0,
"train": {
"docs": 374,
"tokens": 2567180,
"min": 49,
"p50": 4904,
"p90": 15638,
"p99": 16177,
"max": 16252
},
"valid": {
"docs": 20,
"tokens": 134816,
"min": 92,
"p50": 7589,
"p90": 15317,
"p99": 16273,
"max": 16273
},
"all": {
"docs": 394,
"tokens": 2701996,
"min": 49,
"p50": 4904,
"p90": 15608,
"p99": 16217,
"max": 16273
},
"share_before_dedup": {
"CLAS": [
1378559,
49.1
],
"other": [
126244,
4.5
],
"DOC": [
1301698,
46.4
]
},
"share_final": {
"CLAS": [
1297878,
48.0
],
"other": [
101390,
3.8
],
"DOC": [
1302728,
48.2
]
},
"by_type": {
"CLAS": {
"docs": 147,
"tokens": 827969
"docs": 194,
"tokens": 1297878
},
"mixed(4)": {
"docs": 6,
"tokens": 28405
},
"DOC": {
"docs": 106,
"tokens": 1012152
"docs": 138,
"tokens": 1302728
},
"INTF": {
"docs": 7,
"tokens": 1792
},
"BDEF": {
"docs": 6,
"tokens": 1564
"docs": 4,
"tokens": 1069
},
"DDLS": {
"docs": 27,
"tokens": 20614
"docs": 21,
"tokens": 11549
},
"mixed(3)": {
"docs": 2,
"tokens": 6667
},
"PROG": {
"docs": 13,
"tokens": 55365
"docs": 11,
"tokens": 40071
},
"DDLX": {
"docs": 6,
@@ -363,8 +235,480 @@
"tokens": 2026
}
},
"source": [
"abap-cheat-sheets"
"split_info": [
{
"object": [
"ZCL_DEMO_ABAP_OBJECTS (CLAS)"
],
"tokens": 17042,
"pieces": 2,
"piece_tokens": [
14777,
2342
]
},
{
"object": [
"ZCL_DEMO_ABAP_STRUCTURES (CLAS)"
],
"tokens": 16628,
"pieces": 2,
"piece_tokens": [
14200,
2503
]
},
{
"object": [
"32_Performance_Notes__P03 (DOC)"
],
"tokens": 16742,
"pieces": 2,
"piece_tokens": [
15846,
961
]
},
{
"object": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES (CLAS)"
],
"tokens": 19117,
"pieces": 2,
"piece_tokens": [
14425,
4770
]
},
{
"object": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES (CLAS)"
],
"tokens": 18883,
"pieces": 2,
"piece_tokens": [
14607,
4324
]
},
{
"object": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG__V755 (CLAS)"
],
"tokens": 19801,
"pieces": 2,
"piece_tokens": [
15826,
4036
]
},
{
"object": [
"23_Date_and_Time (DOC)"
],
"tokens": 20347,
"pieces": 2,
"piece_tokens": [
10310,
10098
]
},
{
"object": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES__V757 (CLAS)"
],
"tokens": 17477,
"pieces": 2,
"piece_tokens": [
2125,
15451
]
},
{
"object": [
"07_String_Processing__P02 (DOC)"
],
"tokens": 17916,
"pieces": 2,
"piece_tokens": [
11096,
6879
]
},
{
"object": [
"ZCL_DEMO_ABAP_CONSTRUCTOR_EXPR (CLAS)"
],
"tokens": 17368,
"pieces": 2,
"piece_tokens": [
14031,
3415
]
},
{
"object": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG__V758 (CLAS)"
],
"tokens": 31552,
"pieces": 2,
"piece_tokens": [
15833,
15780
]
},
{
"object": [
"ZCL_DEMO_ABAP_STRING_PROC__V757 (CLAS)"
],
"tokens": 19499,
"pieces": 2,
"piece_tokens": [
15831,
3729
]
},
{
"object": [
"04_ABAP_Object_Orientation__P06 (DOC)"
],
"tokens": 16694,
"pieces": 2,
"piece_tokens": [
9045,
7716
]
},
{
"object": [
"ZCL_DEMO_ABAP_DTYPE_DOBJ__V758 (CLAS)"
],
"tokens": 18368,
"pieces": 2,
"piece_tokens": [
15833,
2600
]
},
{
"object": [
"06_Dynamic_Programming__P07 (DOC)"
],
"tokens": 23994,
"pieces": 2,
"piece_tokens": [
15836,
8221
]
},
{
"object": [
"28_Regular_Expressions (DOC)"
],
"tokens": 17900,
"pieces": 2,
"piece_tokens": [
15031,
2930
]
},
{
"object": [
"06_Dynamic_Programming__P06 (DOC)"
],
"tokens": 16923,
"pieces": 2,
"piece_tokens": [
15842,
1144
]
},
{
"object": [
"05_Constructor_Expressions__P01 (DOC)"
],
"tokens": 17349,
"pieces": 2,
"piece_tokens": [
15147,
2265
]
},
{
"object": [
"ZCL_DEMO_ABAP_DTYPE_DOBJ__V755 (CLAS)"
],
"tokens": 17237,
"pieces": 2,
"piece_tokens": [
15833,
1469
]
},
{
"object": [
"ZCL_DEMO_ABAP_DTYPE_DOBJ__V756 (CLAS)"
],
"tokens": 18069,
"pieces": 2,
"piece_tokens": [
15842,
2292
]
},
{
"object": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG (CLAS)"
],
"tokens": 17923,
"pieces": 2,
"piece_tokens": [
15329,
2672
]
},
{
"object": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG (CLAS)"
],
"tokens": 16924,
"pieces": 2,
"piece_tokens": [
15749,
1223
]
},
{
"object": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG (CLAS)"
],
"tokens": 16770,
"pieces": 2,
"piece_tokens": [
14210,
2608
]
},
{
"object": [
"14_ABAP_Unit_Tests__P03 (DOC)"
],
"tokens": 18549,
"pieces": 2,
"piece_tokens": [
15834,
2782
]
},
{
"object": [
"ZCL_DEMO_ABAP_STRING_PROC__V758 (CLAS)"
],
"tokens": 22096,
"pieces": 2,
"piece_tokens": [
15814,
6342
]
},
{
"object": [
"22_Released_ABAP_Classes__P01 (DOC)"
],
"tokens": 19022,
"pieces": 2,
"piece_tokens": [
14661,
4430
]
},
{
"object": [
"21_XML_JSON__P01 (DOC)"
],
"tokens": 16625,
"pieces": 2,
"piece_tokens": [
9855,
6839
]
},
{
"object": [
"29_Numeric_Operations__P01 (DOC)"
],
"tokens": 17805,
"pieces": 2,
"piece_tokens": [
15849,
2025
]
},
{
"object": [
"03_ABAP_SQL__P01 (DOC)"
],
"tokens": 17305,
"pieces": 2,
"piece_tokens": [
14168,
3198
]
},
{
"object": [
"ZCL_DEMO_ABAP_DTYPE_DOBJ__V757 (CLAS)"
],
"tokens": 18308,
"pieces": 2,
"piece_tokens": [
15842,
2531
]
},
{
"object": [
"14_ABAP_Unit_Tests__P04 (DOC)"
],
"tokens": 17633,
"pieces": 2,
"piece_tokens": [
15834,
1866
]
},
{
"object": [
"24_Builtin_Functions (DOC)"
],
"tokens": 16851,
"pieces": 2,
"piece_tokens": [
12541,
4365
]
},
{
"object": [
"ZCL_DEMO_ABAP_NUMERIC_OP (CLAS)"
],
"tokens": 19740,
"pieces": 2,
"piece_tokens": [
15825,
3964
]
},
{
"object": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES__V758 (CLAS)"
],
"tokens": 17355,
"pieces": 2,
"piece_tokens": [
15832,
1584
]
},
{
"object": [
"ZCL_DEMO_ABAP_BUILTIN_FUNC (CLAS)"
],
"tokens": 20446,
"pieces": 2,
"piece_tokens": [
15454,
5071
]
},
{
"object": [
"ZCL_DEMO_ABAP_STRING_PROC (CLAS)"
],
"tokens": 20311,
"pieces": 2,
"piece_tokens": [
15590,
4797
]
},
{
"object": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG__V757 (CLAS)"
],
"tokens": 21483,
"pieces": 2,
"piece_tokens": [
15815,
5730
]
},
{
"object": [
"ZCL_DEMO_ABAP_DATE_TIME (CLAS)"
],
"tokens": 18634,
"pieces": 2,
"piece_tokens": [
15577,
3138
]
},
{
"object": [
"ZCL_DEMO_ABAP_XML_JSON (CLAS)"
],
"tokens": 16825,
"pieces": 2,
"piece_tokens": [
15753,
1154
]
},
{
"object": [
"ZCL_DEMO_ABAP_SQL (CLAS)"
],
"tokens": 18283,
"pieces": 2,
"piece_tokens": [
12526,
5831
]
},
{
"object": [
"ZCL_DEMO_ABAP_INTERNAL_TABLES__V755 (CLAS)"
],
"tokens": 17309,
"pieces": 2,
"piece_tokens": [
2124,
15283
]
},
{
"object": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG__V756 (CLAS)"
],
"tokens": 20979,
"pieces": 2,
"piece_tokens": [
15831,
5210
]
},
{
"object": [
"16_Data_Types_and_Objects__P02 (DOC)"
],
"tokens": 17891,
"pieces": 2,
"piece_tokens": [
14421,
3541
]
}
],
"iterations_2_epochs": 618
"iterations_2_epochs": 748
}