great-ai/example/train.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Train Domain classifier from the [semantic scholar dataset](https://api.semanticscholar.org/corpus)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import matplotlib.pyplot as plt\n",
    "from pathlib import Path\n",
    "import pandas as pd\n",
    "from sklearn import metrics, set_config\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.naive_bayes import ComplementNB\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "from good_ai.utilities.clean import clean\n",
    "from good_ai.utilities.parallel_map import parallel_map\n",
    "from good_ai.utilities.language import is_english, predict_language\n",
    "from good_ai import save_model, set_default_config, LargeFile\n",
    "\n",
    "from preprocess import preprocess\n",
    "from config import model_key"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Configuration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "PREFIX = \"domain-\"\n",
    "DATASET_KEY = \"ss-data\"\n",
    "MAX_FILE_COUNT = 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:good_ai:Defaults: configured ✅\n",
      "INFO:open_s3:Fetching online versions of ss-data\n",
      "INFO:open_s3:Found versions: [0]\n",
      "INFO:open_s3:Lastest version of ss-data-0 is 0\n",
      "INFO:open_s3:File ss-data-0 found in cache\n"
     ]
    }
   ],
   "source": [
    "set_default_config()\n",
    "corpus_path = LargeFile(DATASET_KEY).get()\n",
    "\n",
    "set_config(display=\"diagram\")\n",
    "plt.rcParams[\"figure.figsize\"] = (30, 15)\n",
    "plt.rcParams[\"figure.facecolor\"] = \"white\"\n",
    "plt.rcParams[\"font.size\"] = 12\n",
    "plt.rcParams[\"axes.xmargin\"] = 0"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 5/5 [00:00<00:00, 43873.47it/s]\n"
     ]
    }
   ],
   "source": [
    "def clean_file(p: Path) -> None:\n",
    "    try:\n",
    "        processed_path = p.with_name(f\"{PREFIX}{p.stem}{p.suffix}\")\n",
    "\n",
    "        if processed_path.exists():\n",
    "            return\n",
    "\n",
    "        with open(p) as f:\n",
    "            content = json.load(f)\n",
    "\n",
    "        result = {\n",
    "            preprocess(\n",
    "                clean(f'{c[\"title\"]} {c[\"abstract\"]}', convert_to_ascii=True)\n",
    "            ): c[\"domain\"]\n",
    "            for c in content\n",
    "            if (\n",
    "                c[\"domain\"]\n",
    "                and c[\"abstract\"]\n",
    "                and is_english(predict_language(c[\"abstract\"]))\n",
    "            )\n",
    "        }\n",
    "\n",
    "        with open(processed_path, \"w\") as f:\n",
    "            json.dump(result, f)\n",
    "    except Exception as e:\n",
    "        print(f\"Error ({e}) processing {p}\")\n",
    "\n",
    "\n",
    "parallel_map(\n",
    "    clean_file,\n",
    "    list(corpus_path.glob(\"s2-corpus-*.json\"))[:MAX_FILE_COUNT],\n",
    "    chunk_size=1,\n",
    ")\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 5 files\n",
      "Found 77176 documents\n"
     ]
    }
   ],
   "source": [
    "corpora = list(corpus_path.glob(f\"{PREFIX}*.json\"))[:MAX_FILE_COUNT]\n",
    "print(f\"Found {len(corpora)} files\")\n",
    "\n",
    "data = []\n",
    "for p in corpora:\n",
    "    with open(p) as f:\n",
    "        data.extend(json.load(f).items())\n",
    "\n",
    "print(f\"Found {len(data)} documents\")\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    [d[0] for d in data], [d[1] for d in data], test_size=0.1, random_state=1\n",
    ")\n",
    "\n",
    "X_train = [x for x, y in zip(X_train, y_train) for domain in y]\n",
    "y_train = [domain for x, y in zip(X_train, y_train) for domain in y]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Naive Bayes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 3 folds for each of 144 candidates, totalling 432 fits\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m/Users/andras/Projects/good-ai/example/train.ipynb Cell 10'\u001b[0m in \u001b[0;36m<cell line: 15>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/andras/Projects/good-ai/example/train.ipynb#ch0000009?line=0'>1</a>\u001b[0m classifier \u001b[39m=\u001b[39m GridSearchCV(\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/andras/Projects/good-ai/example/train.ipynb#ch0000009?line=1'>2</a>\u001b[0m     Pipeline(steps\u001b[39m=\u001b[39m[(\u001b[39m\"\u001b[39m\u001b[39mvectorizer\u001b[39m\u001b[39m\"\u001b[39m, TfidfVectorizer()), (\u001b[39m\"\u001b[39m\u001b[39mclassifier\u001b[39m\u001b[39m\"\u001b[39m, ComplementNB())]),\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/andras/Projects/good-ai/example/train.ipynb#ch0000009?line=2'>3</a>\u001b[0m     {\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/andras/Projects/good-ai/example/train.ipynb#ch0000009?line=12'>13</a>\u001b[0m     verbose\u001b[39m=\u001b[39m\u001b[39m1\u001b[39m,\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/andras/Projects/good-ai/example/train.ipynb#ch0000009?line=13'>14</a>\u001b[0m )\n\u001b[0;32m---> <a href='vscode-notebook-cell:/Users/andras/Projects/good-ai/example/train.ipynb#ch0000009?line=14'>15</a>\u001b[0m classifier\u001b[39m.\u001b[39;49mfit(X_train, y_train)\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/andras/Projects/good-ai/example/train.ipynb#ch0000009?line=16'>17</a>\u001b[0m results \u001b[39m=\u001b[39m pd\u001b[39m.\u001b[39mDataFrame(classifier\u001b[39m.\u001b[39mcv_results_)\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/andras/Projects/good-ai/example/train.ipynb#ch0000009?line=17'>18</a>\u001b[0m results\u001b[39m.\u001b[39msort_values(\u001b[39m\"\u001b[39m\u001b[39mrank_test_score\u001b[39m\u001b[39m\"\u001b[39m)\n",
      "File \u001b[0;32m~/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py:891\u001b[0m, in \u001b[0;36mBaseSearchCV.fit\u001b[0;34m(self, X, y, groups, **fit_params)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=884'>885</a>\u001b[0m     results \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_format_results(\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=885'>886</a>\u001b[0m         all_candidate_params, n_splits, all_out, all_more_results\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=886'>887</a>\u001b[0m     )\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=888'>889</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m results\n\u001b[0;32m--> <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=890'>891</a>\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_run_search(evaluate_candidates)\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=892'>893</a>\u001b[0m \u001b[39m# multimetric is determined here because in the case of a callable\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=893'>894</a>\u001b[0m \u001b[39m# self.scoring the return type is only known after calling\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=894'>895</a>\u001b[0m first_test_score \u001b[39m=\u001b[39m all_out[\u001b[39m0\u001b[39m][\u001b[39m\"\u001b[39m\u001b[39mtest_scores\u001b[39m\u001b[39m\"\u001b[39m]\n",
      "File \u001b[0;32m~/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py:1392\u001b[0m, in \u001b[0;36mGridSearchCV._run_search\u001b[0;34m(self, evaluate_candidates)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=1389'>1390</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_run_search\u001b[39m(\u001b[39mself\u001b[39m, evaluate_candidates):\n\u001b[1;32m   <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=1390'>1391</a>\u001b[0m     \u001b[39m\"\"\"Search all candidates in param_grid\"\"\"\u001b[39;00m\n\u001b[0;32m-> <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=1391'>1392</a>\u001b[0m     evaluate_candidates(ParameterGrid(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mparam_grid))\n",
      "File \u001b[0;32m~/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py:838\u001b[0m, in \u001b[0;36mBaseSearchCV.fit.<locals>.evaluate_candidates\u001b[0;34m(candidate_params, cv, more_results)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=829'>830</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mverbose \u001b[39m>\u001b[39m \u001b[39m0\u001b[39m:\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=830'>831</a>\u001b[0m     \u001b[39mprint\u001b[39m(\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=831'>832</a>\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39mFitting \u001b[39m\u001b[39m{0}\u001b[39;00m\u001b[39m folds for each of \u001b[39m\u001b[39m{1}\u001b[39;00m\u001b[39m candidates,\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=832'>833</a>\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39m totalling \u001b[39m\u001b[39m{2}\u001b[39;00m\u001b[39m fits\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m.\u001b[39mformat(\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=833'>834</a>\u001b[0m             n_splits, n_candidates, n_candidates \u001b[39m*\u001b[39m n_splits\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=834'>835</a>\u001b[0m         )\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=835'>836</a>\u001b[0m     )\n\u001b[0;32m--> <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=837'>838</a>\u001b[0m out \u001b[39m=\u001b[39m parallel(\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=838'>839</a>\u001b[0m     delayed(_fit_and_score)(\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=839'>840</a>\u001b[0m         clone(base_estimator),\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=840'>841</a>\u001b[0m         X,\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=841'>842</a>\u001b[0m         y,\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=842'>843</a>\u001b[0m         train\u001b[39m=\u001b[39;49mtrain,\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=843'>844</a>\u001b[0m         test\u001b[39m=\u001b[39;49mtest,\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=844'>845</a>\u001b[0m         parameters\u001b[39m=\u001b[39;49mparameters,\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=845'>846</a>\u001b[0m         split_progress\u001b[39m=\u001b[39;49m(split_idx, n_splits),\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=846'>847</a>\u001b[0m         candidate_progress\u001b[39m=\u001b[39;49m(cand_idx, n_candidates),\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=847'>848</a>\u001b[0m         \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mfit_and_score_kwargs,\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=848'>849</a>\u001b[0m     )\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=849'>850</a>\u001b[0m     \u001b[39mfor\u001b[39;49;00m (cand_idx, parameters), (split_idx, (train, test)) \u001b[39min\u001b[39;49;00m product(\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=850'>851</a>\u001b[0m         \u001b[39menumerate\u001b[39;49m(candidate_params), \u001b[39menumerate\u001b[39;49m(cv\u001b[39m.\u001b[39;49msplit(X, y, groups))\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=851'>852</a>\u001b[0m     )\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=852'>853</a>\u001b[0m )\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=854'>855</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mlen\u001b[39m(out) \u001b[39m<\u001b[39m \u001b[39m1\u001b[39m:\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=855'>856</a>\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=856'>857</a>\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39mNo fits were performed. \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=857'>858</a>\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39mWas the CV iterator empty? \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=858'>859</a>\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39mWere there no candidates?\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/sklearn/model_selection/_search.py?line=859'>860</a>\u001b[0m     )\n",
      "File \u001b[0;32m~/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py:1056\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=1052'>1053</a>\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_iterating \u001b[39m=\u001b[39m \u001b[39mFalse\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=1054'>1055</a>\u001b[0m \u001b[39mwith\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_backend\u001b[39m.\u001b[39mretrieval_context():\n\u001b[0;32m-> <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=1055'>1056</a>\u001b[0m     \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mretrieve()\n\u001b[1;32m   <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=1056'>1057</a>\u001b[0m \u001b[39m# Make sure that we get a last message telling us we are done\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=1057'>1058</a>\u001b[0m elapsed_time \u001b[39m=\u001b[39m time\u001b[39m.\u001b[39mtime() \u001b[39m-\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_start_time\n",
      "File \u001b[0;32m~/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py:935\u001b[0m, in \u001b[0;36mParallel.retrieve\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=932'>933</a>\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=933'>934</a>\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39mgetattr\u001b[39m(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_backend, \u001b[39m'\u001b[39m\u001b[39msupports_timeout\u001b[39m\u001b[39m'\u001b[39m, \u001b[39mFalse\u001b[39;00m):\n\u001b[0;32m--> <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=934'>935</a>\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_output\u001b[39m.\u001b[39mextend(job\u001b[39m.\u001b[39;49mget(timeout\u001b[39m=\u001b[39;49m\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mtimeout))\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=935'>936</a>\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/parallel.py?line=936'>937</a>\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_output\u001b[39m.\u001b[39mextend(job\u001b[39m.\u001b[39mget())\n",
      "File \u001b[0;32m~/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/_parallel_backends.py:542\u001b[0m, in \u001b[0;36mLokyBackend.wrap_future_result\u001b[0;34m(future, timeout)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/_parallel_backends.py?line=538'>539</a>\u001b[0m \u001b[39m\"\"\"Wrapper for Future.result to implement the same behaviour as\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/_parallel_backends.py?line=539'>540</a>\u001b[0m \u001b[39mAsyncResults.get from multiprocessing.\"\"\"\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/_parallel_backends.py?line=540'>541</a>\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m--> <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/_parallel_backends.py?line=541'>542</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m future\u001b[39m.\u001b[39;49mresult(timeout\u001b[39m=\u001b[39;49mtimeout)\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/_parallel_backends.py?line=542'>543</a>\u001b[0m \u001b[39mexcept\u001b[39;00m CfTimeoutError \u001b[39mas\u001b[39;00m e:\n\u001b[1;32m    <a href='file:///Users/andras/Projects/good-ai/.env/lib/python3.8/site-packages/joblib/_parallel_backends.py?line=543'>544</a>\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mTimeoutError\u001b[39;00m \u001b[39mfrom\u001b[39;00m \u001b[39me\u001b[39;00m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/concurrent/futures/_base.py:434\u001b[0m, in \u001b[0;36mFuture.result\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/concurrent/futures/_base.py?line=430'>431</a>\u001b[0m \u001b[39melif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_state \u001b[39m==\u001b[39m FINISHED:\n\u001b[1;32m    <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/concurrent/futures/_base.py?line=431'>432</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m__get_result()\n\u001b[0;32m--> <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/concurrent/futures/_base.py?line=433'>434</a>\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_condition\u001b[39m.\u001b[39;49mwait(timeout)\n\u001b[1;32m    <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/concurrent/futures/_base.py?line=435'>436</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_state \u001b[39min\u001b[39;00m [CANCELLED, CANCELLED_AND_NOTIFIED]:\n\u001b[1;32m    <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/concurrent/futures/_base.py?line=436'>437</a>\u001b[0m     \u001b[39mraise\u001b[39;00m CancelledError()\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/threading.py:302\u001b[0m, in \u001b[0;36mCondition.wait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/threading.py?line=299'>300</a>\u001b[0m \u001b[39mtry\u001b[39;00m:    \u001b[39m# restore state no matter what (e.g., KeyboardInterrupt)\u001b[39;00m\n\u001b[1;32m    <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/threading.py?line=300'>301</a>\u001b[0m     \u001b[39mif\u001b[39;00m timeout \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m--> <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/threading.py?line=301'>302</a>\u001b[0m         waiter\u001b[39m.\u001b[39;49macquire()\n\u001b[1;32m    <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/threading.py?line=302'>303</a>\u001b[0m         gotit \u001b[39m=\u001b[39m \u001b[39mTrue\u001b[39;00m\n\u001b[1;32m    <a href='file:///Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/threading.py?line=303'>304</a>\u001b[0m     \u001b[39melse\u001b[39;00m:\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "classifier = GridSearchCV(\n",
    "    Pipeline(steps=[(\"vectorizer\", TfidfVectorizer()), (\"classifier\", ComplementNB())]),\n",
    "    {\n",
    "        \"vectorizer__max_df\": [0.05, 0.1, 0.3],\n",
    "        \"vectorizer__min_df\": [5, 10, 30],\n",
    "        \"vectorizer__sublinear_tf\": [True, False],\n",
    "        \"classifier__alpha\": [0.001, 0.1, 0.5, 1],\n",
    "        \"classifier__fit_prior\": [True, False],\n",
    "    },\n",
    "    scoring=\"f1_macro\",\n",
    "    cv=3,\n",
    "    n_jobs=8,\n",
    "    verbose=1,\n",
    ")\n",
    "classifier.fit(X_train, y_train)\n",
    "\n",
    "results = pd.DataFrame(classifier.cv_results_)\n",
    "results.sort_values(\"rank_test_score\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-66a90396-2dfb-4b52-a994-80ecabfca944 {color: black;background-color: white;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 pre{padding: 0;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-toggleable {background-color: white;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-estimator:hover {background-color: #d4ebff;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-item {z-index: 1;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-parallel::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-parallel-item {display: flex;flex-direction: column;position: relative;background-color: white;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-parallel-item:only-child::after {width: 0;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;position: relative;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-label label {font-family: monospace;font-weight: bold;background-color: white;display: inline-block;line-height: 1.2em;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-label-container {position: relative;z-index: 2;text-align: center;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-66a90396-2dfb-4b52-a994-80ecabfca944 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-66a90396-2dfb-4b52-a994-80ecabfca944\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;vectorizer&#x27;,\n",
       "                 TfidfVectorizer(max_df=0.1, min_df=10, token_pattern=&#x27;[^ ]+&#x27;)),\n",
       "                (&#x27;classifier&#x27;, ComplementNB(alpha=0.5, fit_prior=False))])</pre><b>Please rerun this cell to show the HTML repr or trust the notebook.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"1cacd16e-7e8e-4eae-a3be-136207b88ec2\" type=\"checkbox\" ><label for=\"1cacd16e-7e8e-4eae-a3be-136207b88ec2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;vectorizer&#x27;,\n",
       "                 TfidfVectorizer(max_df=0.1, min_df=10, token_pattern=&#x27;[^ ]+&#x27;)),\n",
       "                (&#x27;classifier&#x27;, ComplementNB(alpha=0.5, fit_prior=False))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"4bac647f-8b08-44cd-bfe1-5e7028b9ff12\" type=\"checkbox\" ><label for=\"4bac647f-8b08-44cd-bfe1-5e7028b9ff12\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">TfidfVectorizer</label><div class=\"sk-toggleable__content\"><pre>TfidfVectorizer(max_df=0.1, min_df=10, token_pattern=&#x27;[^ ]+&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"4fa4de63-cc9b-4d7a-8b26-2922d3df86a5\" type=\"checkbox\" ><label for=\"4fa4de63-cc9b-4d7a-8b26-2922d3df86a5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ComplementNB</label><div class=\"sk-toggleable__content\"><pre>ComplementNB(alpha=0.5, fit_prior=False)</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('vectorizer',\n",
       "                 TfidfVectorizer(max_df=0.1, min_df=10, token_pattern='[^ ]+')),\n",
       "                ('classifier', ComplementNB(alpha=0.5, fit_prior=False))])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier = Pipeline(\n",
    "    steps=[\n",
    "        (\"vectorizer\", TfidfVectorizer(min_df=10, max_df=0.1, token_pattern=r\"[^ ]+\")),\n",
    "        (\"classifier\", ComplementNB(alpha=0.5, fit_prior=False)),\n",
    "    ]\n",
    ")\n",
    "\n",
    "classifier.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                       precision    recall  f1-score   support\n",
      "\n",
      "                  Art       0.44      0.43      0.43        86\n",
      "              Biology       0.79      0.75      0.77       567\n",
      "             Business       0.56      0.58      0.57       223\n",
      "            Chemistry       0.75      0.73      0.74       651\n",
      "     Computer Science       0.61      0.85      0.71       773\n",
      "            Economics       0.68      0.55      0.60       179\n",
      "          Engineering       0.56      0.32      0.41       499\n",
      "Environmental Science       0.48      0.32      0.38       132\n",
      "            Geography       0.57      0.19      0.29       182\n",
      "              Geology       0.67      0.66      0.66       144\n",
      "              History       0.43      0.22      0.30        58\n",
      "    Materials Science       0.66      0.84      0.74       630\n",
      "          Mathematics       0.79      0.59      0.67       285\n",
      "             Medicine       0.89      0.94      0.91      2151\n",
      "           Philosophy       0.68      0.23      0.35        64\n",
      "              Physics       0.75      0.62      0.68       364\n",
      "    Political Science       0.47      0.52      0.49       221\n",
      "           Psychology       0.55      0.62      0.58       321\n",
      "            Sociology       0.32      0.35      0.33       188\n",
      "\n",
      "             accuracy                           0.71      7718\n",
      "            macro avg       0.61      0.54      0.56      7718\n",
      "         weighted avg       0.71      0.71      0.70      7718\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2160x1080 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "predicted = classifier.predict(X_test)\n",
    "\n",
    "y_test_aligned = [p if p in y else y[0] for p, y in zip(predicted, y_test)]\n",
    "\n",
    "print(metrics.classification_report(y_test_aligned, predicted))\n",
    "metrics.ConfusionMatrixDisplay.from_predictions(\n",
    "    y_true=y_test_aligned,\n",
    "    y_pred=predicted,\n",
    "    xticks_rotation=\"vertical\",\n",
    "    normalize=\"pred\",\n",
    "    values_format=\".2f\",\n",
    ")\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:open_s3:Fetching online versions of domain-prediction-v2\n",
      "INFO:open_s3:Found versions: [3, 4]\n",
      "INFO:open_s3:Copying file for domain-prediction-v2-5\n",
      "INFO:open_s3:Compressing domain-prediction-v2-5\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5 to S3 from /var/folders/5g/yd_5_wg548q0yb4lnvg0y3q40000gn/T/large-file-e5pc9s_c\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz   262144/15169569 bytes (1.7%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz   524288/15169569 bytes (3.5%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz   786432/15169569 bytes (5.2%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  1048576/15169569 bytes (6.9%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  1310720/15169569 bytes (8.6%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  1572864/15169569 bytes (10.4%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  1835008/15169569 bytes (12.1%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  2097152/15169569 bytes (13.8%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  2359296/15169569 bytes (15.6%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  2621440/15169569 bytes (17.3%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  2883584/15169569 bytes (19.0%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  3145728/15169569 bytes (20.7%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  3407872/15169569 bytes (22.5%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  3670016/15169569 bytes (24.2%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  3932160/15169569 bytes (25.9%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  4194304/15169569 bytes (27.6%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  4456448/15169569 bytes (29.4%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  4718592/15169569 bytes (31.1%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  4980736/15169569 bytes (32.8%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  5242880/15169569 bytes (34.6%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  5505024/15169569 bytes (36.3%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  5767168/15169569 bytes (38.0%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  6029312/15169569 bytes (39.7%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  6291456/15169569 bytes (41.5%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  6553600/15169569 bytes (43.2%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  6815744/15169569 bytes (44.9%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  7077888/15169569 bytes (46.7%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  7340032/15169569 bytes (48.4%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  7602176/15169569 bytes (50.1%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  7864320/15169569 bytes (51.8%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  8126464/15169569 bytes (53.6%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  8388608/15169569 bytes (55.3%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  8650752/15169569 bytes (57.0%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  8912896/15169569 bytes (58.8%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  9175040/15169569 bytes (60.5%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  9437184/15169569 bytes (62.2%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  9699328/15169569 bytes (63.9%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz  9961472/15169569 bytes (65.7%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 10223616/15169569 bytes (67.4%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 10485760/15169569 bytes (69.1%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 10747904/15169569 bytes (70.9%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 11010048/15169569 bytes (72.6%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 11272192/15169569 bytes (74.3%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 11534336/15169569 bytes (76.0%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 11796480/15169569 bytes (77.8%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 12058624/15169569 bytes (79.5%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 12320768/15169569 bytes (81.2%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 12582912/15169569 bytes (82.9%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 12845056/15169569 bytes (84.7%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 13107200/15169569 bytes (86.4%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 13369344/15169569 bytes (88.1%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 13631488/15169569 bytes (89.9%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 13893632/15169569 bytes (91.6%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 14155776/15169569 bytes (93.3%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 14417920/15169569 bytes (95.0%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 14680064/15169569 bytes (96.8%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 14907425/15169569 bytes (98.3%)\n",
      "INFO:open_s3:Uploading domain-prediction-v2-5.tar.gz 15169569/15169569 bytes (100.0%)\n",
      "INFO:open_s3:Removing old version (keep_last_n=1): domain-prediction-v2/3\n",
      "INFO:models:Model domain-prediction-v2 uploaded with version 5\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "save_model(classifier, key=model_key, keep_last_n=1)"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "b1d2807ee4cacf26d55377aa5a9287d91820f3fc1d1a8b3c12cb9914c0c55aa2"
  },
  "kernelspec": {
   "display_name": "Python 3.9.2 ('.env': venv)",
   "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": "3.8.5"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}