mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 12:54:11 +08:00
dcafe3f271
# Summary This PR made some significant changes to the scripts around Release Scripts. At a high level: - Turned the quips into docs and updated links - Update the common.categorizes list in the hopes to make this the source of truth for releases- This is hard since the release_notes labels can be changed at will. An alternative would be to poll from github api. However, I think that is overkill. The notebook does a set compare and will show you knew categories. I think we want this to be manual so that the release note engineer will decided how to categorize. - Create cateogry group from speaking with folks on distributed and AO that told me these different release categories can be merged. - I am the newest person to Core and don't use ghstack soo made token getting a lil more generic. - Added a classifier.py file. This file will train a commit categorizer for you, hopefully with decent accuracy. I was able to achieve 75% accuracy. I drop the highest frequency class - "skip" since this creates a more useful cateogrizer. - I updated the categorize.py script so that the prompt will be what the classifier thinks, gated by a flag. - Added a readme that will hopefully help future release notes engineers. Pull Request resolved: https://github.com/pytorch/pytorch/pull/94560 Approved by: https://github.com/albanD
111 lines
2.5 KiB
Plaintext
111 lines
2.5 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"from pprint import pprint\n",
|
|
"from collections import Counter\n",
|
|
"import common\n",
|
|
"import math"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"commit_list_df = pd.read_csv(\"results/classifier/commitlist.csv\")\n",
|
|
"mean_authors=commit_list_df.query(\"category == 'Uncategorized' & topic != 'not user facing'\").author.to_list()\n",
|
|
"counts = Counter(mean_authors)\n",
|
|
"commit_list_df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"commit_list_df.category.describe()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# The number un categorized and no topic commits\n",
|
|
"no_category = commit_list_df.query(\"category == 'Uncategorized' & topic != 'not user facing'\")\n",
|
|
"print(len(no_category))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# check for cherry-picked commits\n",
|
|
"example_sha = '55c76baf579cb6593f87d1a23e9a49afeb55f15a'\n",
|
|
"commit_hashes = set(commit_list_df.commit_hash.to_list())\n",
|
|
"\n",
|
|
"example_sha[:11] in commit_hashes"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Get the difference between known categories and categories from commits\n",
|
|
"\n",
|
|
"diff_categories = set(commit_list_df.category.to_list()) - set(common.categories)\n",
|
|
"print(len(diff_categories))\n",
|
|
"pprint(diff_categories)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Counts of categories\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3"
|
|
},
|
|
"vscode": {
|
|
"interpreter": {
|
|
"hash": "a867c59af434d7534e61ccb37014830daefd5fcd3816cab68d595dde5e446f52"
|
|
}
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|