importSACCTinfo.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import pandas_profiling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('userusage.txt',delimiter='|')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[['jid','step']] = df.JobID.str.split(\".\",expand=True) \n",
    "df.Partition.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "batchDF=df.dropna(subset=[\"MaxRSS\"])\n",
    "userDF=df.dropna(subset=[\"User\"])\n",
    "for jid in df.jid.unique():\n",
    "    userDF['MaxRSS'][userDF['jid'] == jid]=batchDF['MaxRSS'][batchDF['jid'] == jid]\n",
    "    \n",
    "    #print(userDF[userDF['jid'] == jid])\n",
    "    \n",
    "userDF.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# add more graphs here\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python",
   "pygments_lexer": "ipython3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}