exp_naming.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from azureml.core import Experiment, Run, Workspace\n",
    "from pygit2 import Repository\n",
    "import re\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_branch_name(given_branch_name=None, regex_pattern='[^a-zA-Z]'):\n",
    "    \"\"\"\n",
    "    *Get the branch name during the local/remote run.\n",
    "    *The ML experiment name, compute name is derived from\n",
    "    branch name (master or feature)\n",
    "\n",
    "    *Args:\n",
    "        *given_branch_name: Provide the branch name\n",
    "            to override default behavior.\n",
    "        *regex_pattern: for formatting the experiment/compute name\n",
    "\n",
    "    *Returns:\n",
    "        *dict_names: Holds branch name pre-post applying the regex\n",
    "    \"\"\"\n",
    "\n",
    "    if given_branch_name is None:\n",
    "        # This provides the branch name as \"master\" when merging to master and\n",
    "        # \"merge\" for PR.\n",
    "        branch_name = os.getenv('BUILD_SOURCEBRANCHNAME')\n",
    "        # Get the feature branch name during a PR. Format - refs/heads/<feature\n",
    "        # branch name>\n",
    "        branch_name_pr = os.getenv('SYSTEM_PULLREQUEST_SOURCEBRANCH')\n",
    "\n",
    "        if branch_name is None:\n",
    "            # works for feature branch run\n",
    "            branch_name = Repository('.').head.shorthand\n",
    "\n",
    "        elif branch_name_pr is not None:  # For PRs\n",
    "            branch_name = branch_name_pr\n",
    "            branch_name = branch_name.replace('refs/heads/', '')\n",
    "    else:\n",
    "        branch_name = given_branch_name\n",
    "\n",
    "    # apply regex to format experiment name\n",
    "    regex = re.compile(regex_pattern)\n",
    "    branch_name_org = branch_name\n",
    "    branch_name = regex.sub('', branch_name_org)\n",
    "\n",
    "    dict_names = {\n",
    "        'branch_name_org': branch_name_org,\n",
    "        'branch_name': branch_name\n",
    "    }\n",
    "\n",
    "    return dict_names\n",
    "\n",
    "\n",
    "def make_resource_name(prefix, suffix, max_len, sep='-'):\n",
    "    '''\n",
    "    *This method helps forming resource names for\n",
    "    experiment and compute targets as specified by\n",
    "    input params\n",
    "    *project max_len:36, compute max_len:16\n",
    "\n",
    "    *Args:\n",
    "        *prefix: custom prefix\n",
    "        *suffix: custom suffix\n",
    "        *max_len: constraints on resource name length\n",
    "        *sep: custom formatter\n",
    "\n",
    "    *Returns:\n",
    "        *resource_name: newly formed resource name\n",
    "\n",
    "    '''\n",
    "    # suffix will be abbreviated if it is longer than\n",
    "    # (max_length - len(prefix) - len(sep))\n",
    "    chrs_illgl = r'_|/|\\.'\n",
    "    suffix_max_len = min(len(suffix), max_len - len(prefix) - len(sep))\n",
    "    suffix_cut = suffix[0:suffix_max_len]\n",
    "    # replace illegal chrs w/ dash, ensure no trailing dash\n",
    "    suffix_rep = re.sub(chrs_illgl, '-', suffix_cut).rstrip('-')\n",
    "    resource_name = sep.join([prefix, suffix_rep])\n",
    "\n",
    "    return resource_name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Warning: Falling back to use azure cli login credentials.\n",
      "If you run your code in unattended mode, i.e., where you can't give a user input, then we recommend to use ServicePrincipalAuthentication or MsiAuthentication.\n",
      "Please refer to aka.ms/aml-notebook-auth for different authentication mechanisms in azureml-sdk.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found workspace avadevitsmlsvc at location westus2\n"
     ]
    }
   ],
   "source": [
    "ws = Workspace.from_config(\"compute/aml_config/config.json\")\n",
    "print(\"Found workspace {} at location {}\".format(ws.name, ws.location))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Experiment: tacocat-rgblayer\n"
     ]
    }
   ],
   "source": [
    "prefix = 'tacocat'\n",
    "repo_name = get_branch_name()['branch_name']\n",
    "project_name = make_resource_name(prefix, repo_name, max_len=36)\n",
    "exp = Experiment(workspace=ws, name=project_name)\n",
    "print(\"Experiment: {}\".format(exp.name))"
   ]
  }
 ],
 "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",
   "version": "3.6.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}