JetBrains-Research/commit-message-editing-visualization
0
1{2 "cells": [3 {4 "metadata": {},5 "cell_type": "markdown",6 "source": "# Data Stats",7 "id": "694a6cc631d4ab93"8 },9 {10 "metadata": {11 "ExecuteTime": {12 "end_time": "2024-10-15T18:43:07.644299Z",13 "start_time": "2024-10-15T18:43:02.316453Z"14 }15 },16 "cell_type": "code",17 "source": [18 "from datasets import load_dataset\n",19 "\n",20 "\n",21 "df = load_dataset(\"JetBrains-Research/synthetic-commit-msg-edits\", \"all_pairs\", split=\"train\").to_pandas()\n",22 "df.head()"23 ],24 "id": "ed42f4f83199feb2",25 "outputs": [26 {27 "name": "stderr",28 "output_type": "stream",29 "text": [30 "Downloading data: 100%|██████████| 6.35M/6.35M [00:00<00:00, 9.95MB/s]\n"31 ]32 },33 {34 "data": {35 "text/plain": [36 "Generating train split: 0 examples [00:00, ? examples/s]"37 ],38 "application/vnd.jupyter.widget-view+json": {39 "version_major": 2,40 "version_minor": 0,41 "model_id": "1a0523289d424b29974b60d017643280"42 }43 },44 "metadata": {},45 "output_type": "display_data"46 },47 {48 "data": {49 "text/plain": [50 " hash repo \\\n",51 "0 2febb99eee8ed71c9122db88ca58dd33be0b9550 mesonbuild/meson \n",52 "1 2febb99eee8ed71c9122db88ca58dd33be0b9550 mesonbuild/meson \n",53 "2 2febb99eee8ed71c9122db88ca58dd33be0b9550 mesonbuild/meson \n",54 "3 2febb99eee8ed71c9122db88ca58dd33be0b9550 mesonbuild/meson \n",55 "4 2febb99eee8ed71c9122db88ca58dd33be0b9550 mesonbuild/meson \n",56 "\n",57 " G_text \\\n",58 "0 Enhance OptionOverrideProxy and simplify optio... \n",59 "1 Enhance OptionOverrideProxy and simplify optio... \n",60 "2 Enhance OptionOverrideProxy and simplify optio... \n",61 "3 Enhance OptionOverrideProxy and simplify optio... \n",62 "4 Enhance OptionOverrideProxy and simplify optio... \n",63 "\n",64 " E_text G_type \\\n",65 "0 Enhance OptionOverrideProxy for multiple optio... synthetic_backward \n",66 "1 Refactor OptionOverrideProxy and Backend class... synthetic_backward \n",67 "2 Refactor OptionOverrideProxy and backend optio... synthetic_backward \n",68 "3 Refactor: Enhance OptionOverrideProxy for mult... synthetic_backward \n",69 "4 Refactor OptionOverrideProxy and add target-sp... synthetic_backward \n",70 "\n",71 " E_type is_related \n",72 "0 expert_labeled True \n",73 "1 synthetic_forward True \n",74 "2 synthetic_forward True \n",75 "3 synthetic_forward True \n",76 "4 synthetic_forward_from_backward False "77 ],78 "text/html": [79 "<div>\n",80 "<style scoped>\n",81 " .dataframe tbody tr th:only-of-type {\n",82 " vertical-align: middle;\n",83 " }\n",84 "\n",85 " .dataframe tbody tr th {\n",86 " vertical-align: top;\n",87 " }\n",88 "\n",89 " .dataframe thead th {\n",90 " text-align: right;\n",91 " }\n",92 "</style>\n",93 "<table border=\"1\" class=\"dataframe\">\n",94 " <thead>\n",95 " <tr style=\"text-align: right;\">\n",96 " <th></th>\n",97 " <th>hash</th>\n",98 " <th>repo</th>\n",99 " <th>G_text</th>\n",100 " <th>E_text</th>\n",101 " <th>G_type</th>\n",102 " <th>E_type</th>\n",103 " <th>is_related</th>\n",104 " </tr>\n",105 " </thead>\n",106 " <tbody>\n",107 " <tr>\n",108 " <th>0</th>\n",109 " <td>2febb99eee8ed71c9122db88ca58dd33be0b9550</td>\n",110 " <td>mesonbuild/meson</td>\n",111 " <td>Enhance OptionOverrideProxy and simplify optio...</td>\n",112 " <td>Enhance OptionOverrideProxy for multiple optio...</td>\n",113 " <td>synthetic_backward</td>\n",114 " <td>expert_labeled</td>\n",115 " <td>True</td>\n",116 " </tr>\n",117 " <tr>\n",118 " <th>1</th>\n",119 " <td>2febb99eee8ed71c9122db88ca58dd33be0b9550</td>\n",120 " <td>mesonbuild/meson</td>\n",121 " <td>Enhance OptionOverrideProxy and simplify optio...</td>\n",122 " <td>Refactor OptionOverrideProxy and Backend class...</td>\n",123 " <td>synthetic_backward</td>\n",124 " <td>synthetic_forward</td>\n",125 " <td>True</td>\n",126 " </tr>\n",127 " <tr>\n",128 " <th>2</th>\n",129 " <td>2febb99eee8ed71c9122db88ca58dd33be0b9550</td>\n",130 " <td>mesonbuild/meson</td>\n",131 " <td>Enhance OptionOverrideProxy and simplify optio...</td>\n",132 " <td>Refactor OptionOverrideProxy and backend optio...</td>\n",133 " <td>synthetic_backward</td>\n",134 " <td>synthetic_forward</td>\n",135 " <td>True</td>\n",136 " </tr>\n",137 " <tr>\n",138 " <th>3</th>\n",139 " <td>2febb99eee8ed71c9122db88ca58dd33be0b9550</td>\n",140 " <td>mesonbuild/meson</td>\n",141 " <td>Enhance OptionOverrideProxy and simplify optio...</td>\n",142 " <td>Refactor: Enhance OptionOverrideProxy for mult...</td>\n",143 " <td>synthetic_backward</td>\n",144 " <td>synthetic_forward</td>\n",145 " <td>True</td>\n",146 " </tr>\n",147 " <tr>\n",148 " <th>4</th>\n",149 " <td>2febb99eee8ed71c9122db88ca58dd33be0b9550</td>\n",150 " <td>mesonbuild/meson</td>\n",151 " <td>Enhance OptionOverrideProxy and simplify optio...</td>\n",152 " <td>Refactor OptionOverrideProxy and add target-sp...</td>\n",153 " <td>synthetic_backward</td>\n",154 " <td>synthetic_forward_from_backward</td>\n",155 " <td>False</td>\n",156 " </tr>\n",157 " </tbody>\n",158 "</table>\n",159 "</div>"160 ]161 },162 "execution_count": 3,163 "metadata": {},164 "output_type": "execute_result"165 }166 ],167 "execution_count": 3168 },169 {170 "metadata": {},171 "cell_type": "markdown",172 "source": "## Full",173 "id": "922e7a73f11a4aec"174 },175 {176 "metadata": {177 "ExecuteTime": {178 "end_time": "2024-10-15T18:43:14.266540Z",179 "start_time": "2024-10-15T18:43:14.262103Z"180 }181 },182 "cell_type": "code",183 "source": "len(df.loc[df.is_related])",184 "id": "562d9c53da109d1a",185 "outputs": [186 {187 "data": {188 "text/plain": [189 "656"190 ]191 },192 "execution_count": 4,193 "metadata": {},194 "output_type": "execute_result"195 }196 ],197 "execution_count": 4198 },199 {200 "metadata": {201 "ExecuteTime": {202 "end_time": "2024-10-15T18:43:18.073966Z",203 "start_time": "2024-10-15T18:43:18.069219Z"204 }205 },206 "cell_type": "code",207 "source": "df.loc[df.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",208 "id": "b4f3c96a4b676a0d",209 "outputs": [210 {211 "data": {212 "text/plain": [213 "43.733333333333334"214 ]215 },216 "execution_count": 5,217 "metadata": {},218 "output_type": "execute_result"219 }220 ],221 "execution_count": 5222 },223 {224 "metadata": {225 "ExecuteTime": {226 "end_time": "2024-10-15T18:43:19.026689Z",227 "start_time": "2024-10-15T18:43:19.021680Z"228 }229 },230 "cell_type": "code",231 "source": "len(df.loc[~df.is_related])",232 "id": "54d9f32f1d18844f",233 "outputs": [234 {235 "data": {236 "text/plain": [237 "5140"238 ]239 },240 "execution_count": 6,241 "metadata": {},242 "output_type": "execute_result"243 }244 ],245 "execution_count": 6246 },247 {248 "metadata": {249 "ExecuteTime": {250 "end_time": "2024-10-15T18:43:19.484304Z",251 "start_time": "2024-10-15T18:43:19.480012Z"252 }253 },254 "cell_type": "code",255 "source": "df.loc[~df.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",256 "id": "679761631517b9e4",257 "outputs": [258 {259 "data": {260 "text/plain": [261 "342.6666666666667"262 ]263 },264 "execution_count": 7,265 "metadata": {},266 "output_type": "execute_result"267 }268 ],269 "execution_count": 7270 },271 {272 "metadata": {},273 "cell_type": "markdown",274 "source": "## Expert-labeled",275 "id": "84561ea89717d61a"276 },277 {278 "metadata": {279 "ExecuteTime": {280 "end_time": "2024-10-15T18:45:52.905631Z",281 "start_time": "2024-10-15T18:45:52.901913Z"282 }283 },284 "cell_type": "code",285 "source": "_ = df.loc[(df.G_type == \"initial\") & (df.E_type == \"expert_labeled\")]",286 "id": "be1c800f45cef26e",287 "outputs": [],288 "execution_count": 36289 },290 {291 "metadata": {292 "ExecuteTime": {293 "end_time": "2024-10-15T18:45:53.234109Z",294 "start_time": "2024-10-15T18:45:53.230986Z"295 }296 },297 "cell_type": "code",298 "source": "len(_.loc[_.is_related])",299 "id": "1d092dff4d39bcd1",300 "outputs": [301 {302 "data": {303 "text/plain": [304 "57"305 ]306 },307 "execution_count": 37,308 "metadata": {},309 "output_type": "execute_result"310 }311 ],312 "execution_count": 37313 },314 {315 "metadata": {316 "ExecuteTime": {317 "end_time": "2024-10-15T18:45:53.629311Z",318 "start_time": "2024-10-15T18:45:53.625620Z"319 }320 },321 "cell_type": "code",322 "source": "_.loc[_.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",323 "id": "a06a532cd5a29725",324 "outputs": [325 {326 "data": {327 "text/plain": [328 "3.8"329 ]330 },331 "execution_count": 38,332 "metadata": {},333 "output_type": "execute_result"334 }335 ],336 "execution_count": 38337 },338 {339 "metadata": {340 "ExecuteTime": {341 "end_time": "2024-10-15T18:45:53.956790Z",342 "start_time": "2024-10-15T18:45:53.953842Z"343 }344 },345 "cell_type": "code",346 "source": "len(_.loc[~_.is_related])",347 "id": "5e19c8a6309b62aa",348 "outputs": [349 {350 "data": {351 "text/plain": [352 "0"353 ]354 },355 "execution_count": 39,356 "metadata": {},357 "output_type": "execute_result"358 }359 ],360 "execution_count": 39361 },362 {363 "metadata": {364 "ExecuteTime": {365 "end_time": "2024-10-15T18:46:02.554527Z",366 "start_time": "2024-10-15T18:46:02.551084Z"367 }368 },369 "cell_type": "code",370 "source": "_.loc[~_.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",371 "id": "e43179c5dcab5eb2",372 "outputs": [373 {374 "data": {375 "text/plain": [376 "nan"377 ]378 },379 "execution_count": 40,380 "metadata": {},381 "output_type": "execute_result"382 }383 ],384 "execution_count": 40385 },386 {387 "metadata": {},388 "cell_type": "markdown",389 "source": "## Backward",390 "id": "70ee052fae2f88e3"391 },392 {393 "metadata": {394 "ExecuteTime": {395 "end_time": "2024-10-15T18:44:33.559606Z",396 "start_time": "2024-10-15T18:44:33.556802Z"397 }398 },399 "cell_type": "code",400 "source": "_ = df.loc[(df.G_type == \"synthetic_backward\") & (~df.E_type.isin([\"synthetic_forward\", \"synthetic_forward_from_backward\"]))]",401 "id": "99f51ecc55c4db35",402 "outputs": [],403 "execution_count": 20404 },405 {406 "metadata": {407 "ExecuteTime": {408 "end_time": "2024-10-15T18:44:33.958325Z",409 "start_time": "2024-10-15T18:44:33.955847Z"410 }411 },412 "cell_type": "code",413 "source": "len(_.loc[_.is_related])",414 "id": "6ff29390c8e127c2",415 "outputs": [416 {417 "data": {418 "text/plain": [419 "104"420 ]421 },422 "execution_count": 21,423 "metadata": {},424 "output_type": "execute_result"425 }426 ],427 "execution_count": 21428 },429 {430 "metadata": {431 "ExecuteTime": {432 "end_time": "2024-10-15T18:44:34.455560Z",433 "start_time": "2024-10-15T18:44:34.452303Z"434 }435 },436 "cell_type": "code",437 "source": "_.loc[_.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",438 "id": "e1ae04e1ecfb2040",439 "outputs": [440 {441 "data": {442 "text/plain": [443 "7.428571428571429"444 ]445 },446 "execution_count": 22,447 "metadata": {},448 "output_type": "execute_result"449 }450 ],451 "execution_count": 22452 },453 {454 "metadata": {455 "ExecuteTime": {456 "end_time": "2024-10-15T18:44:34.903849Z",457 "start_time": "2024-10-15T18:44:34.901226Z"458 }459 },460 "cell_type": "code",461 "source": "len(_.loc[~_.is_related])",462 "id": "125c4c335e7761da",463 "outputs": [464 {465 "data": {466 "text/plain": [467 "1048"468 ]469 },470 "execution_count": 23,471 "metadata": {},472 "output_type": "execute_result"473 }474 ],475 "execution_count": 23476 },477 {478 "metadata": {479 "ExecuteTime": {480 "end_time": "2024-10-15T18:44:35.783538Z",481 "start_time": "2024-10-15T18:44:35.778676Z"482 }483 },484 "cell_type": "code",485 "source": "_.loc[~_.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",486 "id": "4782f1d6e6863f89",487 "outputs": [488 {489 "data": {490 "text/plain": [491 "74.85714285714286"492 ]493 },494 "execution_count": 24,495 "metadata": {},496 "output_type": "execute_result"497 }498 ],499 "execution_count": 24500 },501 {502 "metadata": {},503 "cell_type": "markdown",504 "source": "## Forward",505 "id": "bf61a4b422f779fa"506 },507 {508 "metadata": {},509 "cell_type": "markdown",510 "source": "### From human",511 "id": "1429f9f99acf75d"512 },513 {514 "metadata": {515 "ExecuteTime": {516 "end_time": "2024-10-15T18:46:21.359807Z",517 "start_time": "2024-10-15T18:46:21.356451Z"518 }519 },520 "cell_type": "code",521 "source": "_ = df.loc[(df.G_type == \"initial\") & (df.E_type == \"synthetic_forward\")]",522 "id": "e13d55b0124f04b3",523 "outputs": [],524 "execution_count": 41525 },526 {527 "metadata": {528 "ExecuteTime": {529 "end_time": "2024-10-15T18:46:21.798508Z",530 "start_time": "2024-10-15T18:46:21.795885Z"531 }532 },533 "cell_type": "code",534 "source": "len(_.loc[_.is_related])",535 "id": "b8353390df7da427",536 "outputs": [537 {538 "data": {539 "text/plain": [540 "177"541 ]542 },543 "execution_count": 42,544 "metadata": {},545 "output_type": "execute_result"546 }547 ],548 "execution_count": 42549 },550 {551 "metadata": {552 "ExecuteTime": {553 "end_time": "2024-10-15T18:46:22.163595Z",554 "start_time": "2024-10-15T18:46:22.160176Z"555 }556 },557 "cell_type": "code",558 "source": "_.loc[_.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",559 "id": "ac89afde65efd73d",560 "outputs": [561 {562 "data": {563 "text/plain": [564 "11.8"565 ]566 },567 "execution_count": 43,568 "metadata": {},569 "output_type": "execute_result"570 }571 ],572 "execution_count": 43573 },574 {575 "metadata": {576 "ExecuteTime": {577 "end_time": "2024-10-15T18:46:22.552314Z",578 "start_time": "2024-10-15T18:46:22.549570Z"579 }580 },581 "cell_type": "code",582 "source": "len(_.loc[~_.is_related])",583 "id": "9b6cb335e3bbb7ff",584 "outputs": [585 {586 "data": {587 "text/plain": [588 "0"589 ]590 },591 "execution_count": 44,592 "metadata": {},593 "output_type": "execute_result"594 }595 ],596 "execution_count": 44597 },598 {599 "metadata": {600 "ExecuteTime": {601 "end_time": "2024-10-15T18:46:23.237736Z",602 "start_time": "2024-10-15T18:46:23.234085Z"603 }604 },605 "cell_type": "code",606 "source": "__.loc[~__.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",607 "id": "fe22189a70fc4149",608 "outputs": [609 {610 "data": {611 "text/plain": [612 "nan"613 ]614 },615 "execution_count": 45,616 "metadata": {},617 "output_type": "execute_result"618 }619 ],620 "execution_count": 45621 },622 {623 "metadata": {},624 "cell_type": "markdown",625 "source": "### From backward",626 "id": "ace7afb876fb88a0"627 },628 {629 "metadata": {630 "ExecuteTime": {631 "end_time": "2024-10-15T18:47:06.641374Z",632 "start_time": "2024-10-15T18:47:06.637018Z"633 }634 },635 "cell_type": "code",636 "source": "_ = df.loc[(df.G_type == \"synthetic_backward\") & (df.E_type.isin([\"synthetic_forward\", \"synthetic_forward_from_backward\"]))]",637 "id": "88800960dbff619a",638 "outputs": [],639 "execution_count": 53640 },641 {642 "metadata": {643 "ExecuteTime": {644 "end_time": "2024-10-15T18:47:15.358650Z",645 "start_time": "2024-10-15T18:47:15.355108Z"646 }647 },648 "cell_type": "code",649 "source": "len(_.loc[_.is_related])",650 "id": "890613156e005c83",651 "outputs": [652 {653 "data": {654 "text/plain": [655 "318"656 ]657 },658 "execution_count": 56,659 "metadata": {},660 "output_type": "execute_result"661 }662 ],663 "execution_count": 56664 },665 {666 "metadata": {667 "ExecuteTime": {668 "end_time": "2024-10-15T18:47:15.579415Z",669 "start_time": "2024-10-15T18:47:15.576016Z"670 }671 },672 "cell_type": "code",673 "source": "_.loc[_.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",674 "id": "999f91382a2c8ff6",675 "outputs": [676 {677 "data": {678 "text/plain": [679 "22.714285714285715"680 ]681 },682 "execution_count": 57,683 "metadata": {},684 "output_type": "execute_result"685 }686 ],687 "execution_count": 57688 },689 {690 "metadata": {691 "ExecuteTime": {692 "end_time": "2024-10-15T18:47:15.834218Z",693 "start_time": "2024-10-15T18:47:15.831258Z"694 }695 },696 "cell_type": "code",697 "source": "len(_.loc[~_.is_related])",698 "id": "d347941cbb4b2db1",699 "outputs": [700 {701 "data": {702 "text/plain": [703 "3753"704 ]705 },706 "execution_count": 58,707 "metadata": {},708 "output_type": "execute_result"709 }710 ],711 "execution_count": 58712 },713 {714 "metadata": {715 "ExecuteTime": {716 "end_time": "2024-10-15T18:47:16.138798Z",717 "start_time": "2024-10-15T18:47:16.133397Z"718 }719 },720 "cell_type": "code",721 "source": "_.loc[~_.is_related].groupby([\"hash\", \"repo\"]).G_text.count().mean()",722 "id": "2db4d96713a8634d",723 "outputs": [724 {725 "data": {726 "text/plain": [727 "268.07142857142856"728 ]729 },730 "execution_count": 59,731 "metadata": {},732 "output_type": "execute_result"733 }734 ],735 "execution_count": 59736 }737 ],738 "metadata": {739 "kernelspec": {740 "display_name": "Python 3",741 "language": "python",742 "name": "python3"743 },744 "language_info": {745 "codemirror_mode": {746 "name": "ipython",747 "version": 2748 },749 "file_extension": ".py",750 "mimetype": "text/x-python",751 "name": "python",752 "nbconvert_exporter": "python",753 "pygments_lexer": "ipython2",754 "version": "2.7.6"755 }756 },757 "nbformat": 4,758 "nbformat_minor": 5759}760