Graheet commited on
Commit
567645a
·
1 Parent(s): a97efc6

Update DataOps env: semantic contract, inference, server, and docs polish

Browse files
.dataops_policy_cache.json CHANGED
@@ -1,5 +1,17 @@
1
  {
2
  "patterns": {
 
 
 
 
 
 
 
 
 
 
 
 
3
  "0fa3f35b7f17ba183b55874ed34f34b9dfd42a96": {
4
  "actions": {
5
  "fill_missing(row_id=34, column='city', value='Denver')": {
@@ -12,6 +24,18 @@
12
  }
13
  }
14
  },
 
 
 
 
 
 
 
 
 
 
 
 
15
  "11ef7431147857285b2046abba4c938d39542f56": {
16
  "actions": {
17
  "normalize_column(column='email')": {
@@ -24,6 +48,78 @@
24
  }
25
  }
26
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "468a9ffd1e161a3b120e50a2d283b5a2bea91b78": {
28
  "actions": {
29
  "delete_row(row_id=23)": {
@@ -48,6 +144,90 @@
48
  }
49
  }
50
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  "84f1a657f98b24e5c81396ebede79cb10b4bd759": {
52
  "actions": {
53
  "remove_duplicate(row_id=33)": {
@@ -60,6 +240,30 @@
60
  }
61
  }
62
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  "a4f3a4b48581add24c1541d266ca386ca1048501": {
64
  "actions": {
65
  "normalize_column(column='name')": {
@@ -84,6 +288,18 @@
84
  }
85
  }
86
  },
 
 
 
 
 
 
 
 
 
 
 
 
87
  "bac5c03eaec86e5eca3602c18787e7b8dd71ce77": {
88
  "actions": {
89
  "fill_missing(row_id=35, column='email', value='peak.systems@example.com')": {
@@ -96,6 +312,42 @@
96
  }
97
  }
98
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
  "c9a1695ddb1fd7a56fcd89d0855f3e6c3cc0539f": {
100
  "actions": {
101
  "remove_duplicate(row_id=13)": {
@@ -108,6 +360,42 @@
108
  }
109
  }
110
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
  "e133231c2a2fe412ce1265f027ce61ff2616d497": {
112
  "actions": {
113
  "remove_duplicate(row_id=22)": {
@@ -119,9 +407,45 @@
119
  "successes": 0
120
  }
121
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
122
  }
123
  },
124
  "states": {
 
 
 
 
 
 
 
 
 
 
 
 
125
  "0cc9851ce3eac00c3a8ba813a0bbe5086b6b28c7": {
126
  "actions": {
127
  "fill_missing(row_id=35, column='email', value='peak.systems@example.com')": {
@@ -134,6 +458,18 @@
134
  }
135
  }
136
  },
 
 
 
 
 
 
 
 
 
 
 
 
137
  "338f581f2bb3d33b1ca9113338487576d7221075": {
138
  "actions": {
139
  "remove_duplicate(row_id=13)": {
@@ -158,6 +494,66 @@
158
  }
159
  }
160
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
161
  "4cdcb94d06f82ed5c380e36d4737c98095c1d8e5": {
162
  "actions": {
163
  "fill_missing(row_id=34, column='city', value='Denver')": {
@@ -170,6 +566,30 @@
170
  }
171
  }
172
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  "72db3bd5a5ba3a4f64815e20b59ccf3b9ce6b2ad": {
174
  "actions": {
175
  "remove_duplicate(row_id=33)": {
@@ -182,6 +602,66 @@
182
  }
183
  }
184
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
185
  "a3e1f7d06da6a2a3bfc3ca13a3a9ae20ff116705": {
186
  "actions": {
187
  "delete_row(row_id=23)": {
@@ -194,6 +674,54 @@
194
  }
195
  }
196
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
197
  "be2f2def033a20dab83499d31cbe7ac8ba296d8e": {
198
  "actions": {
199
  "normalize_column(column='name')": {
@@ -206,6 +734,18 @@
206
  }
207
  }
208
  },
 
 
 
 
 
 
 
 
 
 
 
 
209
  "c02de8edbfcfa72f061a9ac1827b98c070f1208e": {
210
  "actions": {
211
  "remove_duplicate(row_id=22)": {
@@ -230,6 +770,66 @@
230
  }
231
  }
232
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  "f1c2df4babd9a79a88196afded5618bb0ce3d72b": {
234
  "actions": {
235
  "normalize_column(column='email')": {
@@ -241,6 +841,30 @@
241
  "successes": 0
242
  }
243
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
244
  }
245
  },
246
  "version": 1
 
1
  {
2
  "patterns": {
3
+ "04941bd4fae9e4d5ad285866a4cff357f8415710": {
4
+ "actions": {
5
+ "fix_value(record_id='34', field='city', value='Miami', confidence=0.75)": {
6
+ "attempts": 1,
7
+ "cumulative_reward": 0.75,
8
+ "failures": 0,
9
+ "last_error": null,
10
+ "progresses": 1,
11
+ "successes": 0
12
+ }
13
+ }
14
+ },
15
  "0fa3f35b7f17ba183b55874ed34f34b9dfd42a96": {
16
  "actions": {
17
  "fill_missing(row_id=34, column='city', value='Denver')": {
 
24
  }
25
  }
26
  },
27
+ "11c4905093da8d0a938063d9d6d6f5825df2852d": {
28
+ "actions": {
29
+ "fix_value(record_id='14', field='email', value='li.wei.example.com', confidence=0.8)": {
30
+ "attempts": 1,
31
+ "cumulative_reward": -0.6,
32
+ "failures": 1,
33
+ "last_error": "step_error",
34
+ "progresses": 0,
35
+ "successes": 0
36
+ }
37
+ }
38
+ },
39
  "11ef7431147857285b2046abba4c938d39542f56": {
40
  "actions": {
41
  "normalize_column(column='email')": {
 
48
  }
49
  }
50
  },
51
+ "13ea433aadce1c77acf8f43a791e79d2b932eca0": {
52
+ "actions": {
53
+ "detect_issue(record_id='11', field='email', confidence=0.85)": {
54
+ "attempts": 1,
55
+ "cumulative_reward": 0.25,
56
+ "failures": 0,
57
+ "last_error": null,
58
+ "progresses": 1,
59
+ "successes": 0
60
+ }
61
+ }
62
+ },
63
+ "1442f1407527d7bc1ea5f9c4935ea81b0a8bca79": {
64
+ "actions": {
65
+ "fix_value(record_id='13', field='email', value='omar.hassan@example.com', confidence=0.8)": {
66
+ "attempts": 1,
67
+ "cumulative_reward": -0.75,
68
+ "failures": 1,
69
+ "last_error": "step_error",
70
+ "progresses": 0,
71
+ "successes": 0
72
+ }
73
+ }
74
+ },
75
+ "25c04e846ec996fac4c361e9341e37e30df1892c": {
76
+ "actions": {
77
+ "detect_issue(record_id='35', field='email', confidence=0.85)": {
78
+ "attempts": 1,
79
+ "cumulative_reward": 0.25,
80
+ "failures": 0,
81
+ "last_error": null,
82
+ "progresses": 1,
83
+ "successes": 0
84
+ }
85
+ }
86
+ },
87
+ "2e24f4b95399876aca662404e3f119889922c738": {
88
+ "actions": {
89
+ "cannot_determine(record_id='23', field='age', confidence=0.8)": {
90
+ "attempts": 1,
91
+ "cumulative_reward": 0.2,
92
+ "failures": 0,
93
+ "last_error": null,
94
+ "progresses": 1,
95
+ "successes": 0
96
+ }
97
+ }
98
+ },
99
+ "3141c57792570551e62e76356e98ee391763b086": {
100
+ "actions": {
101
+ "detect_issue(record_id='13', field='email', confidence=0.85)": {
102
+ "attempts": 1,
103
+ "cumulative_reward": -0.45,
104
+ "failures": 1,
105
+ "last_error": "step_error",
106
+ "progresses": 0,
107
+ "successes": 0
108
+ }
109
+ }
110
+ },
111
+ "40e59cdcb7f8dca17021c900448aa53187c754ab": {
112
+ "actions": {
113
+ "skip(record_id='0', field='record', confidence=0.0)": {
114
+ "attempts": 1,
115
+ "cumulative_reward": 0.0,
116
+ "failures": 1,
117
+ "last_error": null,
118
+ "progresses": 0,
119
+ "successes": 0
120
+ }
121
+ }
122
+ },
123
  "468a9ffd1e161a3b120e50a2d283b5a2bea91b78": {
124
  "actions": {
125
  "delete_row(row_id=23)": {
 
144
  }
145
  }
146
  },
147
+ "4f310f9099d60bed685d35697d6ac8ef298aec50": {
148
+ "actions": {
149
+ "detect_issue(record_id='23', field='age', confidence=0.9)": {
150
+ "attempts": 1,
151
+ "cumulative_reward": 0.45,
152
+ "failures": 0,
153
+ "last_error": null,
154
+ "progresses": 1,
155
+ "successes": 0
156
+ }
157
+ }
158
+ },
159
+ "528db17f5677fe3de252da0fe7366a7c54f85cf5": {
160
+ "actions": {
161
+ "skip(record_id='0', field='record', confidence=0.0)": {
162
+ "attempts": 1,
163
+ "cumulative_reward": -0.15,
164
+ "failures": 1,
165
+ "last_error": null,
166
+ "progresses": 0,
167
+ "successes": 0
168
+ }
169
+ }
170
+ },
171
+ "59855d529f4f372a2c0781d87eb21b73b272ebf3": {
172
+ "actions": {
173
+ "skip(record_id='0', field='record', confidence=0.0)": {
174
+ "attempts": 1,
175
+ "cumulative_reward": 0.0,
176
+ "failures": 1,
177
+ "last_error": null,
178
+ "progresses": 0,
179
+ "successes": 0
180
+ }
181
+ }
182
+ },
183
+ "62952008c654d45d935c6f01a697e8308bbcb40b": {
184
+ "actions": {
185
+ "skip(record_id='0', field='record', confidence=0.0)": {
186
+ "attempts": 1,
187
+ "cumulative_reward": 0.0,
188
+ "failures": 1,
189
+ "last_error": null,
190
+ "progresses": 0,
191
+ "successes": 0
192
+ }
193
+ }
194
+ },
195
+ "7084bdd5bfd69e211ee3c6fd770348e11be8b538": {
196
+ "actions": {
197
+ "fix_value(record_id='11', field='email', value='omar.hassan@example.com', confidence=0.8)": {
198
+ "attempts": 1,
199
+ "cumulative_reward": 0.75,
200
+ "failures": 0,
201
+ "last_error": null,
202
+ "progresses": 1,
203
+ "successes": 0
204
+ }
205
+ }
206
+ },
207
+ "75e1b7c3382cf59433f18e84274740c702e71c9c": {
208
+ "actions": {
209
+ "fix_value(record_id='23', field='email', value='evan.cole@example.com', confidence=0.8)": {
210
+ "attempts": 1,
211
+ "cumulative_reward": -0.7,
212
+ "failures": 1,
213
+ "last_error": "step_error",
214
+ "progresses": 0,
215
+ "successes": 0
216
+ }
217
+ }
218
+ },
219
+ "77c8146f7a2f152172eb8e4955cb5b1d98996d05": {
220
+ "actions": {
221
+ "fix_value(record_id='13', field='email', value='omar.hassan@example.com', confidence=0.8)": {
222
+ "attempts": 1,
223
+ "cumulative_reward": -0.8,
224
+ "failures": 1,
225
+ "last_error": "step_error",
226
+ "progresses": 0,
227
+ "successes": 0
228
+ }
229
+ }
230
+ },
231
  "84f1a657f98b24e5c81396ebede79cb10b4bd759": {
232
  "actions": {
233
  "remove_duplicate(row_id=33)": {
 
240
  }
241
  }
242
  },
243
+ "987c9a048f7b1e92e6dbb5aacbc8d1ec53f05a21": {
244
+ "actions": {
245
+ "detect_issue(record_id='34', field='city', confidence=0.85)": {
246
+ "attempts": 1,
247
+ "cumulative_reward": 0.25,
248
+ "failures": 0,
249
+ "last_error": null,
250
+ "progresses": 1,
251
+ "successes": 0
252
+ }
253
+ }
254
+ },
255
+ "a08daa22430e2593a7f46a196bf5dbcbf6eb0a89": {
256
+ "actions": {
257
+ "fix_value(record_id='35', field='email', value='peak.systems@example.com', confidence=0.75)": {
258
+ "attempts": 1,
259
+ "cumulative_reward": 0.75,
260
+ "failures": 0,
261
+ "last_error": null,
262
+ "progresses": 1,
263
+ "successes": 0
264
+ }
265
+ }
266
+ },
267
  "a4f3a4b48581add24c1541d266ca386ca1048501": {
268
  "actions": {
269
  "normalize_column(column='name')": {
 
288
  }
289
  }
290
  },
291
+ "b5b065adffaa8ffab7b955c9daffd0e76328c49e": {
292
+ "actions": {
293
+ "skip(record_id='0', field='record', confidence=0.0)": {
294
+ "attempts": 1,
295
+ "cumulative_reward": -0.15,
296
+ "failures": 1,
297
+ "last_error": null,
298
+ "progresses": 0,
299
+ "successes": 0
300
+ }
301
+ }
302
+ },
303
  "bac5c03eaec86e5eca3602c18787e7b8dd71ce77": {
304
  "actions": {
305
  "fill_missing(row_id=35, column='email', value='peak.systems@example.com')": {
 
312
  }
313
  }
314
  },
315
+ "bd1569c12944472549e2dd4209e99f59bd0bcace": {
316
+ "actions": {
317
+ "cannot_determine(record_id='23', field='age', confidence=0.8)": {
318
+ "attempts": 1,
319
+ "cumulative_reward": 0.25,
320
+ "failures": 0,
321
+ "last_error": null,
322
+ "progresses": 1,
323
+ "successes": 0
324
+ }
325
+ }
326
+ },
327
+ "c03d4bf5313672c6a7fdec4341cfdec496b2412d": {
328
+ "actions": {
329
+ "detect_issue(record_id='23', field='email', confidence=0.85)": {
330
+ "attempts": 1,
331
+ "cumulative_reward": 0.25,
332
+ "failures": 0,
333
+ "last_error": null,
334
+ "progresses": 1,
335
+ "successes": 0
336
+ }
337
+ }
338
+ },
339
+ "c207f77a965736c5ecf1d05a0655c299d9c330ca": {
340
+ "actions": {
341
+ "fix_value(record_id='23', field='email', value='evan.cole@example.com', confidence=0.8)": {
342
+ "attempts": 1,
343
+ "cumulative_reward": -0.7,
344
+ "failures": 1,
345
+ "last_error": "step_error",
346
+ "progresses": 0,
347
+ "successes": 0
348
+ }
349
+ }
350
+ },
351
  "c9a1695ddb1fd7a56fcd89d0855f3e6c3cc0539f": {
352
  "actions": {
353
  "remove_duplicate(row_id=13)": {
 
360
  }
361
  }
362
  },
363
+ "ccd9f8c0652ad477c56d438cef96f0a4feb1baa5": {
364
+ "actions": {
365
+ "cannot_determine(record_id='23', field='age', confidence=0.8)": {
366
+ "attempts": 1,
367
+ "cumulative_reward": 0.2,
368
+ "failures": 0,
369
+ "last_error": null,
370
+ "progresses": 1,
371
+ "successes": 0
372
+ }
373
+ }
374
+ },
375
+ "d56199e1b129e467d270a9592b523f9da84c28a7": {
376
+ "actions": {
377
+ "fix_value(record_id='23', field='email', value='evan.cole@example.com', confidence=0.8)": {
378
+ "attempts": 1,
379
+ "cumulative_reward": -0.7,
380
+ "failures": 1,
381
+ "last_error": "step_error",
382
+ "progresses": 0,
383
+ "successes": 0
384
+ }
385
+ }
386
+ },
387
+ "de87365ad5c85e54d645355ba6f8b23cb10822f2": {
388
+ "actions": {
389
+ "skip(record_id='0', field='record', confidence=0.0)": {
390
+ "attempts": 1,
391
+ "cumulative_reward": -0.15,
392
+ "failures": 1,
393
+ "last_error": null,
394
+ "progresses": 0,
395
+ "successes": 0
396
+ }
397
+ }
398
+ },
399
  "e133231c2a2fe412ce1265f027ce61ff2616d497": {
400
  "actions": {
401
  "remove_duplicate(row_id=22)": {
 
407
  "successes": 0
408
  }
409
  }
410
+ },
411
+ "e207ce6c4cf4ef62ce0288a8b9eb85af110fca3c": {
412
+ "actions": {
413
+ "detect_issue(record_id='14', field='email', confidence=0.85)": {
414
+ "attempts": 1,
415
+ "cumulative_reward": 0.25,
416
+ "failures": 0,
417
+ "last_error": null,
418
+ "progresses": 1,
419
+ "successes": 0
420
+ }
421
+ }
422
+ },
423
+ "fb8a8008e048a08b03a7a0dff159f04951aa39f7": {
424
+ "actions": {
425
+ "skip(record_id='0', field='record', confidence=0.0)": {
426
+ "attempts": 1,
427
+ "cumulative_reward": -0.15,
428
+ "failures": 1,
429
+ "last_error": null,
430
+ "progresses": 0,
431
+ "successes": 0
432
+ }
433
+ }
434
  }
435
  },
436
  "states": {
437
+ "0aed36e6cfecb7393f9b16f96e8b7575e99df224": {
438
+ "actions": {
439
+ "fix_value(record_id='34', field='city', value='Miami', confidence=0.75)": {
440
+ "attempts": 1,
441
+ "cumulative_reward": 0.75,
442
+ "failures": 0,
443
+ "last_error": null,
444
+ "progresses": 1,
445
+ "successes": 0
446
+ }
447
+ }
448
+ },
449
  "0cc9851ce3eac00c3a8ba813a0bbe5086b6b28c7": {
450
  "actions": {
451
  "fill_missing(row_id=35, column='email', value='peak.systems@example.com')": {
 
458
  }
459
  }
460
  },
461
+ "19342d4ceda87bc21ffe8eac086a763c57645fba": {
462
+ "actions": {
463
+ "fix_value(record_id='23', field='email', value='evan.cole@example.com', confidence=0.8)": {
464
+ "attempts": 1,
465
+ "cumulative_reward": -0.7,
466
+ "failures": 1,
467
+ "last_error": "step_error",
468
+ "progresses": 0,
469
+ "successes": 0
470
+ }
471
+ }
472
+ },
473
  "338f581f2bb3d33b1ca9113338487576d7221075": {
474
  "actions": {
475
  "remove_duplicate(row_id=13)": {
 
494
  }
495
  }
496
  },
497
+ "36b47fa93aa11f17becb90f18dbf6582fb2ec514": {
498
+ "actions": {
499
+ "detect_issue(record_id='34', field='city', confidence=0.85)": {
500
+ "attempts": 1,
501
+ "cumulative_reward": 0.25,
502
+ "failures": 0,
503
+ "last_error": null,
504
+ "progresses": 1,
505
+ "successes": 0
506
+ }
507
+ }
508
+ },
509
+ "3c7910b58561fe75695c7e75c890096daccd7b38": {
510
+ "actions": {
511
+ "skip(record_id='0', field='record', confidence=0.0)": {
512
+ "attempts": 1,
513
+ "cumulative_reward": 0.0,
514
+ "failures": 1,
515
+ "last_error": null,
516
+ "progresses": 0,
517
+ "successes": 0
518
+ }
519
+ }
520
+ },
521
+ "3e8c0a9c3535062944e96f272d9cf4ca22f79f00": {
522
+ "actions": {
523
+ "cannot_determine(record_id='23', field='age', confidence=0.8)": {
524
+ "attempts": 1,
525
+ "cumulative_reward": 0.2,
526
+ "failures": 0,
527
+ "last_error": null,
528
+ "progresses": 1,
529
+ "successes": 0
530
+ }
531
+ }
532
+ },
533
+ "40f3f342f9cb468fd99daca73da0d942239bb7b4": {
534
+ "actions": {
535
+ "skip(record_id='0', field='record', confidence=0.0)": {
536
+ "attempts": 1,
537
+ "cumulative_reward": -0.15,
538
+ "failures": 1,
539
+ "last_error": null,
540
+ "progresses": 0,
541
+ "successes": 0
542
+ }
543
+ }
544
+ },
545
+ "45d87b29a7188d7bcccc402f83102298096821db": {
546
+ "actions": {
547
+ "detect_issue(record_id='23', field='age', confidence=0.9)": {
548
+ "attempts": 1,
549
+ "cumulative_reward": 0.45,
550
+ "failures": 0,
551
+ "last_error": null,
552
+ "progresses": 1,
553
+ "successes": 0
554
+ }
555
+ }
556
+ },
557
  "4cdcb94d06f82ed5c380e36d4737c98095c1d8e5": {
558
  "actions": {
559
  "fill_missing(row_id=34, column='city', value='Denver')": {
 
566
  }
567
  }
568
  },
569
+ "65bcacf43bf1ce915763534104bc656020107890": {
570
+ "actions": {
571
+ "skip(record_id='0', field='record', confidence=0.0)": {
572
+ "attempts": 1,
573
+ "cumulative_reward": -0.15,
574
+ "failures": 1,
575
+ "last_error": null,
576
+ "progresses": 0,
577
+ "successes": 0
578
+ }
579
+ }
580
+ },
581
+ "6e6d11d30bea4e58656ab07e496e96453de01c9d": {
582
+ "actions": {
583
+ "skip(record_id='0', field='record', confidence=0.0)": {
584
+ "attempts": 1,
585
+ "cumulative_reward": 0.0,
586
+ "failures": 1,
587
+ "last_error": null,
588
+ "progresses": 0,
589
+ "successes": 0
590
+ }
591
+ }
592
+ },
593
  "72db3bd5a5ba3a4f64815e20b59ccf3b9ce6b2ad": {
594
  "actions": {
595
  "remove_duplicate(row_id=33)": {
 
602
  }
603
  }
604
  },
605
+ "7b4a5e7c8bbacb89333063960c2d5ca4e9696830": {
606
+ "actions": {
607
+ "detect_issue(record_id='35', field='email', confidence=0.85)": {
608
+ "attempts": 1,
609
+ "cumulative_reward": 0.25,
610
+ "failures": 0,
611
+ "last_error": null,
612
+ "progresses": 1,
613
+ "successes": 0
614
+ }
615
+ }
616
+ },
617
+ "810a123bc9615210a00c051d417ddeaa4e1d79c2": {
618
+ "actions": {
619
+ "skip(record_id='0', field='record', confidence=0.0)": {
620
+ "attempts": 1,
621
+ "cumulative_reward": -0.15,
622
+ "failures": 1,
623
+ "last_error": null,
624
+ "progresses": 0,
625
+ "successes": 0
626
+ }
627
+ }
628
+ },
629
+ "8cabdafb03a4fcdafa3062aaa1afd72273f15e70": {
630
+ "actions": {
631
+ "fix_value(record_id='11', field='email', value='omar.hassan@example.com', confidence=0.8)": {
632
+ "attempts": 1,
633
+ "cumulative_reward": 0.75,
634
+ "failures": 0,
635
+ "last_error": null,
636
+ "progresses": 1,
637
+ "successes": 0
638
+ }
639
+ }
640
+ },
641
+ "8e0b9dc44fda5371173de5e183d95645bfab49b7": {
642
+ "actions": {
643
+ "detect_issue(record_id='11', field='email', confidence=0.85)": {
644
+ "attempts": 1,
645
+ "cumulative_reward": 0.25,
646
+ "failures": 0,
647
+ "last_error": null,
648
+ "progresses": 1,
649
+ "successes": 0
650
+ }
651
+ }
652
+ },
653
+ "920ec2b49e603797712a90ac2f45fa52f20fd9fa": {
654
+ "actions": {
655
+ "fix_value(record_id='35', field='email', value='peak.systems@example.com', confidence=0.75)": {
656
+ "attempts": 1,
657
+ "cumulative_reward": 0.75,
658
+ "failures": 0,
659
+ "last_error": null,
660
+ "progresses": 1,
661
+ "successes": 0
662
+ }
663
+ }
664
+ },
665
  "a3e1f7d06da6a2a3bfc3ca13a3a9ae20ff116705": {
666
  "actions": {
667
  "delete_row(row_id=23)": {
 
674
  }
675
  }
676
  },
677
+ "a448bc2b9a94786dff96162ec647b27b6a856a06": {
678
+ "actions": {
679
+ "fix_value(record_id='13', field='email', value='omar.hassan@example.com', confidence=0.8)": {
680
+ "attempts": 1,
681
+ "cumulative_reward": -0.75,
682
+ "failures": 1,
683
+ "last_error": "step_error",
684
+ "progresses": 0,
685
+ "successes": 0
686
+ }
687
+ }
688
+ },
689
+ "a797cf83a440f34bf1b8ef60726f39b9e3864f13": {
690
+ "actions": {
691
+ "cannot_determine(record_id='23', field='age', confidence=0.8)": {
692
+ "attempts": 1,
693
+ "cumulative_reward": 0.25,
694
+ "failures": 0,
695
+ "last_error": null,
696
+ "progresses": 1,
697
+ "successes": 0
698
+ }
699
+ }
700
+ },
701
+ "adb100a72ec60305c8b6f8f22d1b0394f34d36b9": {
702
+ "actions": {
703
+ "cannot_determine(record_id='23', field='age', confidence=0.8)": {
704
+ "attempts": 1,
705
+ "cumulative_reward": 0.2,
706
+ "failures": 0,
707
+ "last_error": null,
708
+ "progresses": 1,
709
+ "successes": 0
710
+ }
711
+ }
712
+ },
713
+ "baac8e73d1022fe8e47f059a428cf69e0f1d17fb": {
714
+ "actions": {
715
+ "fix_value(record_id='13', field='email', value='omar.hassan@example.com', confidence=0.8)": {
716
+ "attempts": 1,
717
+ "cumulative_reward": -0.8,
718
+ "failures": 1,
719
+ "last_error": "step_error",
720
+ "progresses": 0,
721
+ "successes": 0
722
+ }
723
+ }
724
+ },
725
  "be2f2def033a20dab83499d31cbe7ac8ba296d8e": {
726
  "actions": {
727
  "normalize_column(column='name')": {
 
734
  }
735
  }
736
  },
737
+ "be9e378b859608b413359a3497e7f21cd7274bb2": {
738
+ "actions": {
739
+ "detect_issue(record_id='13', field='email', confidence=0.85)": {
740
+ "attempts": 1,
741
+ "cumulative_reward": -0.45,
742
+ "failures": 1,
743
+ "last_error": "step_error",
744
+ "progresses": 0,
745
+ "successes": 0
746
+ }
747
+ }
748
+ },
749
  "c02de8edbfcfa72f061a9ac1827b98c070f1208e": {
750
  "actions": {
751
  "remove_duplicate(row_id=22)": {
 
770
  }
771
  }
772
  },
773
+ "d926264c08977bb595608f0f36f70bd3fa6772c7": {
774
+ "actions": {
775
+ "fix_value(record_id='23', field='email', value='evan.cole@example.com', confidence=0.8)": {
776
+ "attempts": 1,
777
+ "cumulative_reward": -0.7,
778
+ "failures": 1,
779
+ "last_error": "step_error",
780
+ "progresses": 0,
781
+ "successes": 0
782
+ }
783
+ }
784
+ },
785
+ "dd0ba9dfd8e0d2ae2ce6bb46eb95cbb592154605": {
786
+ "actions": {
787
+ "detect_issue(record_id='23', field='email', confidence=0.85)": {
788
+ "attempts": 1,
789
+ "cumulative_reward": 0.25,
790
+ "failures": 0,
791
+ "last_error": null,
792
+ "progresses": 1,
793
+ "successes": 0
794
+ }
795
+ }
796
+ },
797
+ "e013e5e1953c13426b1530335853a2eb7469f8b3": {
798
+ "actions": {
799
+ "fix_value(record_id='23', field='email', value='evan.cole@example.com', confidence=0.8)": {
800
+ "attempts": 1,
801
+ "cumulative_reward": -0.7,
802
+ "failures": 1,
803
+ "last_error": "step_error",
804
+ "progresses": 0,
805
+ "successes": 0
806
+ }
807
+ }
808
+ },
809
+ "e1f5ef8958b3eaca953c873c6b16bad06ef4cd38": {
810
+ "actions": {
811
+ "skip(record_id='0', field='record', confidence=0.0)": {
812
+ "attempts": 1,
813
+ "cumulative_reward": -0.15,
814
+ "failures": 1,
815
+ "last_error": null,
816
+ "progresses": 0,
817
+ "successes": 0
818
+ }
819
+ }
820
+ },
821
+ "e2918aee6468be696070506760ea59e38a8d2b60": {
822
+ "actions": {
823
+ "fix_value(record_id='14', field='email', value='li.wei.example.com', confidence=0.8)": {
824
+ "attempts": 1,
825
+ "cumulative_reward": -0.6,
826
+ "failures": 1,
827
+ "last_error": "step_error",
828
+ "progresses": 0,
829
+ "successes": 0
830
+ }
831
+ }
832
+ },
833
  "f1c2df4babd9a79a88196afded5618bb0ce3d72b": {
834
  "actions": {
835
  "normalize_column(column='email')": {
 
841
  "successes": 0
842
  }
843
  }
844
+ },
845
+ "fa2129eda93b530f1f7bac7598ffea900bb8bd79": {
846
+ "actions": {
847
+ "skip(record_id='0', field='record', confidence=0.0)": {
848
+ "attempts": 1,
849
+ "cumulative_reward": 0.0,
850
+ "failures": 1,
851
+ "last_error": null,
852
+ "progresses": 0,
853
+ "successes": 0
854
+ }
855
+ }
856
+ },
857
+ "fb99b6a2297e07d5a7ceebc7200a4ab9eced8278": {
858
+ "actions": {
859
+ "detect_issue(record_id='14', field='email', confidence=0.85)": {
860
+ "attempts": 1,
861
+ "cumulative_reward": 0.25,
862
+ "failures": 0,
863
+ "last_error": null,
864
+ "progresses": 1,
865
+ "successes": 0
866
+ }
867
+ }
868
  }
869
  },
870
  "version": 1
Dockerfile CHANGED
@@ -25,3 +25,4 @@ USER appuser
25
  EXPOSE 7860
26
 
27
  CMD ["sh", "-c", "uvicorn server.app:app --host 0.0.0.0 --port ${PORT:-7860}"]
 
 
25
  EXPOSE 7860
26
 
27
  CMD ["sh", "-c", "uvicorn server.app:app --host 0.0.0.0 --port ${PORT:-7860}"]
28
+
__pycache__/env.cpython-313.pyc CHANGED
Binary files a/__pycache__/env.cpython-313.pyc and b/__pycache__/env.cpython-313.pyc differ
 
__pycache__/grader.cpython-313.pyc CHANGED
Binary files a/__pycache__/grader.cpython-313.pyc and b/__pycache__/grader.cpython-313.pyc differ
 
__pycache__/inference.cpython-313.pyc CHANGED
Binary files a/__pycache__/inference.cpython-313.pyc and b/__pycache__/inference.cpython-313.pyc differ
 
__pycache__/models.cpython-313.pyc CHANGED
Binary files a/__pycache__/models.cpython-313.pyc and b/__pycache__/models.cpython-313.pyc differ
 
__pycache__/task.cpython-313.pyc CHANGED
Binary files a/__pycache__/task.cpython-313.pyc and b/__pycache__/task.cpython-313.pyc differ
 
inference.py CHANGED
@@ -1,5 +1,4 @@
1
  """Inference entrypoints for ``dataops-gym``.
2
-
3
  This runner keeps the hackathon-required OpenAI-compatible model interface, but
4
  adds a stronger local planner so baseline behavior is still competitive and
5
  reproducible when the model is weak, unavailable, or partially aligned.
@@ -41,7 +40,6 @@ SYSTEM_PROMPT = textwrap.dedent(
41
  """
42
  You control a data-cleaning environment.
43
  Reply with exactly one action string and nothing else.
44
-
45
  Only choose from the candidate actions provided by the user prompt.
46
  Favor actions that remove visible issues quickly and avoid actions that were
47
  already blocked because they caused errors or no progress.
@@ -580,7 +578,6 @@ def build_user_prompt(
580
  Last action error: {last_error or "null"}
581
  Blocked actions:
582
  {blocked_text}
583
-
584
  Choose exactly one action from this candidate list:
585
  {candidates_text}
586
  """
 
1
  """Inference entrypoints for ``dataops-gym``.
 
2
  This runner keeps the hackathon-required OpenAI-compatible model interface, but
3
  adds a stronger local planner so baseline behavior is still competitive and
4
  reproducible when the model is weak, unavailable, or partially aligned.
 
40
  """
41
  You control a data-cleaning environment.
42
  Reply with exactly one action string and nothing else.
 
43
  Only choose from the candidate actions provided by the user prompt.
44
  Favor actions that remove visible issues quickly and avoid actions that were
45
  already blocked because they caused errors or no progress.
 
578
  Last action error: {last_error or "null"}
579
  Blocked actions:
580
  {blocked_text}
 
581
  Choose exactly one action from this candidate list:
582
  {candidates_text}
583
  """
models.py CHANGED
@@ -1,5 +1,4 @@
1
  """Shared data models for ``dataops-gym``.
2
-
3
  This module is responsible for defining typed request, response, and domain
4
  schemas used across task execution, inference, grading, and server layers.
5
  """
 
1
  """Shared data models for ``dataops-gym``.
 
2
  This module is responsible for defining typed request, response, and domain
3
  schemas used across task execution, inference, grading, and server layers.
4
  """
server/__pycache__/app.cpython-313.pyc CHANGED
Binary files a/server/__pycache__/app.cpython-313.pyc and b/server/__pycache__/app.cpython-313.pyc differ
 
server/app.py CHANGED
@@ -1,5 +1,4 @@
1
  """Application server bootstrap for ``dataops-gym``.
2
-
3
  This module is responsible for exposing runtime APIs, health endpoints, and
4
  deployment-facing application setup for the environment.
5
  """
@@ -50,7 +49,7 @@ app = FastAPI(
50
  ),
51
  contact={
52
  "name": "DataOps Gym",
53
- "url": "https://github.com/graheetphartyal23/Dataops--GYM",
54
  },
55
  docs_url=None,
56
  )
@@ -114,7 +113,6 @@ def custom_docs() -> HTMLResponse:
114
  .swagger-ui, .swagger-ui .topbar { background: #0b1020 !important; }
115
  .swagger-ui .topbar { border-bottom: 1px solid #1f2937 !important; }
116
  .swagger-ui .topbar a, .swagger-ui .topbar span { color: #e5e7eb !important; }
117
-
118
  /* Keep top API details readable: white card + black text */
119
  .swagger-ui .info {
120
  background: #ffffff !important;
@@ -130,7 +128,6 @@ def custom_docs() -> HTMLResponse:
130
  color: #111827 !important;
131
  }
132
  .swagger-ui .info ul { margin: 10px 0 0 18px !important; }
133
-
134
  /* Default + Schemas sections as white cards with black text */
135
  .swagger-ui .opblock-tag {
136
  background: #ffffff !important;
 
1
  """Application server bootstrap for ``dataops-gym``.
 
2
  This module is responsible for exposing runtime APIs, health endpoints, and
3
  deployment-facing application setup for the environment.
4
  """
 
49
  ),
50
  contact={
51
  "name": "DataOps Gym",
52
+ "url": "https://github.com/graheetphartyal23/DataOps-GYM",
53
  },
54
  docs_url=None,
55
  )
 
113
  .swagger-ui, .swagger-ui .topbar { background: #0b1020 !important; }
114
  .swagger-ui .topbar { border-bottom: 1px solid #1f2937 !important; }
115
  .swagger-ui .topbar a, .swagger-ui .topbar span { color: #e5e7eb !important; }
 
116
  /* Keep top API details readable: white card + black text */
117
  .swagger-ui .info {
118
  background: #ffffff !important;
 
128
  color: #111827 !important;
129
  }
130
  .swagger-ui .info ul { margin: 10px 0 0 18px !important; }
 
131
  /* Default + Schemas sections as white cards with black text */
132
  .swagger-ui .opblock-tag {
133
  background: #ffffff !important;
task.py CHANGED
@@ -1,5 +1,4 @@
1
  """Task definitions for ``dataops-gym``.
2
-
3
  This module defines the benchmark scenarios used by the OpenEnv environment.
4
  Each public task family keeps the hackathon-facing `easy` / `medium` / `hard`
5
  shape while internally supporting deterministic variants so the benchmark is
@@ -483,4 +482,4 @@ def hard_conflict_resolution_task(variant: int | None = None) -> TaskDefinition:
483
 
484
  easy_cleaning_task.variant_count = 2
485
  medium_normalization_task.variant_count = 2
486
- hard_conflict_resolution_task.variant_count = 2
 
1
  """Task definitions for ``dataops-gym``.
 
2
  This module defines the benchmark scenarios used by the OpenEnv environment.
3
  Each public task family keeps the hackathon-facing `easy` / `medium` / `hard`
4
  shape while internally supporting deterministic variants so the benchmark is
 
482
 
483
  easy_cleaning_task.variant_count = 2
484
  medium_normalization_task.variant_count = 2
485
+ hard_conflict_resolution_task.variant_count = 2
utils/__pycache__/__init__.cpython-313.pyc ADDED
Binary file (183 Bytes). View file