|
2 | 2 | "cells": [ |
3 | 3 | { |
4 | 4 | "cell_type": "code", |
5 | | - "execution_count": 1, |
| 5 | + "execution_count": 7, |
6 | 6 | "id": "13626f75", |
7 | 7 | "metadata": {}, |
8 | 8 | "outputs": [ |
|
12 | 12 | "text": [ |
13 | 13 | "/mnt/sdd1/atharvas/formulacode/datasmith\n" |
14 | 14 | ] |
15 | | - }, |
16 | | - { |
17 | | - "name": "stderr", |
18 | | - "output_type": "stream", |
19 | | - "text": [ |
20 | | - "09:16:49 WARNING simple_useragent.core: Falling back to historic user agent.\n" |
21 | | - ] |
22 | 15 | } |
23 | 16 | ], |
24 | 17 | "source": [ |
|
35 | 28 | }, |
36 | 29 | { |
37 | 30 | "cell_type": "code", |
38 | | - "execution_count": 2, |
| 31 | + "execution_count": 11, |
39 | 32 | "id": "b4179f19", |
40 | 33 | "metadata": {}, |
41 | 34 | "outputs": [], |
|
49 | 42 | " --limit-per-repo 2\n", |
50 | 43 | " --max-attempts 3\n", |
51 | 44 | " --max-steps 10\n", |
52 | | - "\"\"\".strip().replace(\"\\n\", \" \")" |
| 45 | + "\"\"\".strip().replace(\"\\n\", \" \")\n", |
| 46 | + "cr = ContextRegistry.load_from_file(Path(\"scratch/artifacts/pipeflush/context_registry.json\"))" |
53 | 47 | ] |
54 | 48 | }, |
55 | 49 | { |
56 | 50 | "cell_type": "code", |
57 | | - "execution_count": 3, |
| 51 | + "execution_count": null, |
58 | 52 | "id": "6624689c", |
59 | 53 | "metadata": {}, |
60 | 54 | "outputs": [ |
|
230 | 224 | } |
231 | 225 | ], |
232 | 226 | "source": [ |
233 | | - "cr = ContextRegistry.load_from_file(Path(\"scratch/artifacts/pipeflush/context_registry.json\"))\n", |
234 | 227 | "commit_pth = Path(\"scratch/artifacts/pipeflush/commits_perfonly.parquet\")\n", |
235 | 228 | "commit_df = pd.read_parquet(commit_pth)\n", |
236 | 229 | "commit_df.head()" |
237 | 230 | ] |
238 | 231 | }, |
239 | 232 | { |
240 | 233 | "cell_type": "code", |
241 | | - "execution_count": 4, |
| 234 | + "execution_count": 9, |
242 | 235 | "id": "79905eb5", |
243 | 236 | "metadata": {}, |
244 | 237 | "outputs": [ |
|
295 | 288 | }, |
296 | 289 | { |
297 | 290 | "cell_type": "code", |
298 | | - "execution_count": 5, |
| 291 | + "execution_count": 12, |
299 | 292 | "id": "567cdaa5", |
300 | 293 | "metadata": {}, |
301 | 294 | "outputs": [ |
302 | 295 | { |
303 | 296 | "name": "stderr", |
304 | 297 | "output_type": "stream", |
305 | 298 | "text": [ |
306 | | - "09:17:16 INFO datasmith.docker.context: Context registry saved to scratch/artifacts/pipeflush/chunk_0/context_registry.json\n", |
307 | | - "09:17:36 INFO datasmith.docker.context: Context registry saved to scratch/artifacts/pipeflush/chunk_1/context_registry.json\n", |
308 | | - "09:17:58 INFO datasmith.docker.context: Context registry saved to scratch/artifacts/pipeflush/chunk_2/context_registry.json\n" |
| 299 | + "09:51:55 INFO datasmith.docker.context: Context registry saved to scratch/artifacts/pipeflush/chunk_0/context_registry.json\n", |
| 300 | + "09:51:59 INFO datasmith.docker.context: Context registry saved to scratch/artifacts/pipeflush/chunk_1/context_registry.json\n", |
| 301 | + "09:52:08 INFO datasmith.docker.context: Context registry saved to scratch/artifacts/pipeflush/chunk_2/context_registry.json\n" |
309 | 302 | ] |
310 | 303 | } |
311 | 304 | ], |
|
338 | 331 | }, |
339 | 332 | { |
340 | 333 | "cell_type": "code", |
341 | | - "execution_count": 6, |
| 334 | + "execution_count": 13, |
342 | 335 | "id": "3fafdd1c", |
343 | 336 | "metadata": {}, |
344 | 337 | "outputs": [ |
|
390 | 383 | }, |
391 | 384 | { |
392 | 385 | "cell_type": "code", |
393 | | - "execution_count": null, |
| 386 | + "execution_count": 20, |
394 | 387 | "id": "f5133158", |
395 | 388 | "metadata": {}, |
396 | | - "outputs": [], |
397 | | - "source": [] |
| 389 | + "outputs": [ |
| 390 | + { |
| 391 | + "data": { |
| 392 | + "text/plain": [ |
| 393 | + "array([47.51953125, 47.51785714, 47.52559055])" |
| 394 | + ] |
| 395 | + }, |
| 396 | + "execution_count": 20, |
| 397 | + "metadata": {}, |
| 398 | + "output_type": "execute_result" |
| 399 | + } |
| 400 | + ], |
| 401 | + "source": [ |
| 402 | + "import numpy as np\n", |
| 403 | + "\n", |
| 404 | + "lens = np.array([len(d) for d in [df1, df2, df3]])\n", |
| 405 | + "ratios = np.array(ratios)\n", |
| 406 | + "\n", |
| 407 | + "l2r = lens * 15 / ratios # min\n", |
| 408 | + "l2r_hrs = l2r / 60\n", |
| 409 | + "l2r_hrs" |
| 410 | + ] |
398 | 411 | } |
399 | 412 | ], |
400 | 413 | "metadata": { |
|
0 commit comments