erhan/abap-llm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Stage 1 data: strict version dedup (older v* vs next newer v*); counts updated

Browse Source 
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 22:23:04 +02:00
parent 0677d035da
commit 7b8ca01bde
5 changed files with 179 additions and 211 deletions
Download Patch File Download Diff File Expand all files Collapse all files

240
train/data/stats.json
View File

@@ -5,84 +5,42 @@
"estimate_tokens": 2636112,
"records": 370,
"tokens_before_dedup": 2806501,
"tokens_after_dedup": 2699110,
"records_after_dedup": 351,
"tokens_after_split": 2701996,
"tokens_after_dedup": 2658082,
"records_after_dedup": 353,
"tokens_after_split": 2660834,
"objects_with_versions": 39,
"families": 269,
"versions_kept": 319,
"versions_removed": 16,
"strict_rule_would_remove_more": 8,
"versions_kept": 323,
"versions_removed": 12,
"other_branch_comparisons": 0,
"removed_versions": [
{
"object": "ZBP_DEMO_ABAP_RAP_RO_U (CLAS)",
"version": "v758",
"newest": "main",
"diff": 0.015,
"tokens": 10696
"object": "ZCL_DEMO_ABAP_OBJECTS (CLAS)",
"version": "v755",
"newest": "v757",
"diff": 0.01,
"tokens": 14944
},
{
"object": "ZDEMO_ABAP_RAP_RO_M (BDEF)",
"object": "ZDEMO_ABAP_RAP_DRAFT_M (BDEF)",
"version": "v756",
"newest": "main",
"diff": 0.037,
"tokens": 259
},
{
"object": "ZDEMO_ABAP_RAP_RO_U (BDEF)",
"version": "v756",
"newest": "main",
"diff": 0.043,
"tokens": 236
},
{
"object": "ZDEMO_ABAP_CDS_VE_ASSOC_E (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.026,
"tokens": 542
},
{
"object": "ZDEMO_ABAP_CDS_VE_JOINS (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.009,
"tokens": 1827
},
{
"object": "ZDEMO_ABAP_CDS_VE_AGG_EXP (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.019,
"tokens": 804
},
{
"object": "ZDEMO_ABAP_CDS_VE_SEL (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.029,
"tokens": 3273
},
{
"object": "ZDEMO_ABAP_CDS_VE_ASSOC (DDLS)",
"version": "v757",
"newest": "main",
"diff": 0.008,
"tokens": 2451
},
{
"object": "ZDEMO_ABAP_FLI_VE (DDLS)",
"version": "v816",
"newest": "main",
"diff": 0.0,
"tokens": 168
"newest": "v757",
"diff": 0.033,
"tokens": 302
},
{
"object": "ZCL_DEMO_ABAP_DTYPE_DOBJ (CLAS)",
"version": "v816",
"newest": "main",
"diff": 0.009,
"tokens": 27407
"version": "v756",
"newest": "v757",
"diff": 0.015,
"tokens": 21263
},
{
"object": "ZCL_DEMO_ABAP_DTYPE_DOBJ (CLAS)",
"version": "v755",
"newest": "v756",
"diff": 0.047,
"tokens": 20431
},
{
"object": "ZCL_DEMO_ABAP_DISPLAY (CLAS)",
@@ -92,11 +50,32 @@
"tokens": 1677
},
{
"object": "ZCL_DEMO_ABAP_UNIT_TEST (CLAS)",
"version": "v758",
"newest": "main",
"diff": 0.034,
"tokens": 19799
"object": "ZCL_DEMO_ABAP_INTERNAL_TABLES (CLAS)",
"version": "v755",
"newest": "v757",
"diff": 0.01,
"tokens": 17309
},
{
"object": "ZCL_DEMO_ABAP_DYNAMIC_PROG (CLAS)",
"version": "v756",
"newest": "v757",
"diff": 0.021,
"tokens": 25883
},
{
"object": "ZCL_DEMO_ABAP_SQL (CLAS)",
"version": "v755",
"newest": "v757",
"diff": 0.035,
"tokens": 14949
},
{
"object": "ZCL_DEMO_ABAP_CONSTRUCTOR_EXPR (CLAS)",
"version": "v755",
"newest": "v757",
"diff": 0.048,
"tokens": 13893
},
{
"object": "ZDEMO_ABAP_DYNPRO (PROG)",
@@ -112,13 +91,6 @@
"diff": 0.005,
"tokens": 2474
},
{
"object": "ZCL_DEMO_ABAP_NUMERIC_OP (CLAS)",
"version": "v816",
"newest": "main",
"diff": 0.003,
"tokens": 20484
},
{
"object": "ZDEMO_ABAP_ALV (PROG)",
"version": "v757",
@@ -127,22 +99,22 @@
"tokens": 7268
}
],
"split_docs": 43,
"hard_line_splits": 17,
"split_docs": 41,
"hard_line_splits": 15,
"pieces_over_limit": 0,
"train": {
"docs": 374,
"tokens": 2567180,
"tokens": 2525568,
"min": 49,
"p50": 4904,
"p90": 15638,
"p50": 4770,
"p90": 15590,
"p99": 16177,
"max": 16252
},
"valid": {
"docs": 20,
"tokens": 134816,
"min": 92,
"tokens": 135266,
"min": 135,
"p50": 7589,
"p90": 15317,
"p99": 16273,
@@ -150,10 +122,10 @@
},
"all": {
"docs": 394,
"tokens": 2701996,
"tokens": 2660834,
"min": 49,
"p50": 4904,
"p90": 15608,
"p50": 4797,
"p90": 15577,
"p99": 16217,
"max": 16273
},
@@ -173,22 +145,22 @@
},
"share_final": {
"CLAS": [
1297878,
48.0
1247458,
46.9
],
"other": [
101390,
3.8
110648,
4.2
],
"DOC": [
1302728,
48.2
49.0
]
},
"by_type": {
"CLAS": {
"docs": 194,
"tokens": 1297878
"docs": 187,
"tokens": 1247458
},
"mixed(4)": {
"docs": 6,
@@ -203,12 +175,12 @@
"tokens": 1792
},
"BDEF": {
"docs": 4,
"tokens": 1069
"docs": 5,
"tokens": 1262
},
"DDLS": {
"docs": 21,
"tokens": 11549
"docs": 27,
"tokens": 20614
},
"mixed(3)": {
"docs": 2,
@@ -423,6 +395,17 @@
1144
]
},
{
"object": [
"ZCL_DEMO_ABAP_NUMERIC_OP__V816 (CLAS)"
],
"tokens": 19769,
"pieces": 2,
"piece_tokens": [
15819,
4012
]
},
{
"object": [
"05_Constructor_Expressions__P01 (DOC)"
@@ -434,28 +417,6 @@
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)"
@@ -632,6 +593,17 @@
4797
]
},
{
"object": [
"ZCL_DEMO_ABAP_UNIT_TEST__V758 (CLAS)"
],
"tokens": 16394,
"pieces": 2,
"piece_tokens": [
15301,
1187
]
},
{
"object": [
"ZCL_DEMO_ABAP_DYNAMIC_PROG__V757 (CLAS)"
@@ -676,28 +648,6 @@
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)"