Initial commit

979ccaa3 · William Stonewall Monroe · 979ccaa3 · 979ccaa3 · 979ccaa3 · 979ccaa3
Commit 979ccaa3 authored Mar 16, 2020 by William Stonewall Monroe
--- a/.ipynb_checkpoints/importSACCTinfo-checkpoint.ipynb
+++ b/.ipynb_checkpoints/importSACCTinfo-checkpoint.ipynb
--- a/generateUseReport.sh
+++ b/generateUseReport.sh
+#!/bin/sh
+
+directoryToUse="/data/user/wsmonroe/VariousNeurology/neurobiology/"
+sacct -P -u lianov,kmv,mkbiles,kbuford,mdefende,pinarde,lelandf,marcello,fatrina,snolin,ssrira0,pstew,jvice02,ishant,docviv,sthyme,gkiosch,ajbauman,cgduke,rphill3,jjday,jmmiz,jtuscher,rmhauser,flubin --starttime=2019-01-01 --format user,start,jobid,jobname,state,partition,maxrss,reqmem,reqcpus,node,nnodes,elapsed >> "$directoryToUse"neurobiologyusage.txt
--- a/importSACCTinfo.ipynb
+++ b/importSACCTinfo.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-16T20:57:10.405006Z",
+     "start_time": "2020-03-16T20:56:55.837670Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import pandas_profiling"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-16T20:57:11.865980Z",
+     "start_time": "2020-03-16T20:57:10.414986Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('neurobiologyusage.txt',delimiter='|')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-16T20:57:11.932878Z",
+     "start_time": "2020-03-16T20:57:11.905219Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>User</th>\n",
+       "      <th>Start</th>\n",
+       "      <th>JobID</th>\n",
+       "      <th>JobName</th>\n",
+       "      <th>State</th>\n",
+       "      <th>Partition</th>\n",
+       "      <th>MaxRSS</th>\n",
+       "      <th>ReqMem</th>\n",
+       "      <th>ReqCPUS</th>\n",
+       "      <th>NodeList</th>\n",
+       "      <th>NNodes</th>\n",
+       "      <th>Elapsed</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>mdefende</td>\n",
+       "      <td>2019-01-06T22:00:21</td>\n",
+       "      <td>2040834</td>\n",
+       "      <td>_interactive</td>\n",
+       "      <td>COMPLETED</td>\n",
+       "      <td>medium</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>10000Mc</td>\n",
+       "      <td>1</td>\n",
+       "      <td>c0088</td>\n",
+       "      <td>1</td>\n",
+       "      <td>16:04:23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2019-01-06T22:00:21</td>\n",
+       "      <td>2040834.batch</td>\n",
+       "      <td>batch</td>\n",
+       "      <td>COMPLETED</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1394528K</td>\n",
+       "      <td>10000Mc</td>\n",
+       "      <td>1</td>\n",
+       "      <td>c0088</td>\n",
+       "      <td>1</td>\n",
+       "      <td>16:04:23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>lianov</td>\n",
+       "      <td>2019-01-07T16:15:21</td>\n",
+       "      <td>2043373</td>\n",
+       "      <td>Pipe_trim_galore</td>\n",
+       "      <td>COMPLETED</td>\n",
+       "      <td>medium</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2000Mc</td>\n",
+       "      <td>1</td>\n",
+       "      <td>c0038</td>\n",
+       "      <td>1</td>\n",
+       "      <td>00:18:41</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2019-01-07T16:15:21</td>\n",
+       "      <td>2043373.batch</td>\n",
+       "      <td>batch</td>\n",
+       "      <td>COMPLETED</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>58592K</td>\n",
+       "      <td>2000Mc</td>\n",
+       "      <td>1</td>\n",
+       "      <td>c0038</td>\n",
+       "      <td>1</td>\n",
+       "      <td>00:18:41</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>lianov</td>\n",
+       "      <td>2019-01-07T16:15:21</td>\n",
+       "      <td>2043374</td>\n",
+       "      <td>Pipe_trim_galore</td>\n",
+       "      <td>COMPLETED</td>\n",
+       "      <td>medium</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2000Mc</td>\n",
+       "      <td>1</td>\n",
+       "      <td>c0063</td>\n",
+       "      <td>1</td>\n",
+       "      <td>00:15:48</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       User                Start          JobID           JobName      State  \\\n",
+       "0  mdefende  2019-01-06T22:00:21        2040834      _interactive  COMPLETED   \n",
+       "1       NaN  2019-01-06T22:00:21  2040834.batch             batch  COMPLETED   \n",
+       "2    lianov  2019-01-07T16:15:21        2043373  Pipe_trim_galore  COMPLETED   \n",
+       "3       NaN  2019-01-07T16:15:21  2043373.batch             batch  COMPLETED   \n",
+       "4    lianov  2019-01-07T16:15:21        2043374  Pipe_trim_galore  COMPLETED   \n",
+       "\n",
+       "  Partition    MaxRSS   ReqMem  ReqCPUS NodeList  NNodes   Elapsed  \n",
+       "0    medium       NaN  10000Mc        1    c0088       1  16:04:23  \n",
+       "1       NaN  1394528K  10000Mc        1    c0088       1  16:04:23  \n",
+       "2    medium       NaN   2000Mc        1    c0038       1  00:18:41  \n",
+       "3       NaN    58592K   2000Mc        1    c0038       1  00:18:41  \n",
+       "4    medium       NaN   2000Mc        1    c0063       1  00:15:48  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-16T20:57:14.154962Z",
+     "start_time": "2020-03-16T20:57:11.967976Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['medium', nan, 'medium', ..., 'medium', nan, nan], dtype=object)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[['jid','step']] = df.JobID.str.split(\".\",expand=True) \n",
+    "df.Partition.values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2020-03-16T20:56:57.392Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/ipykernel_launcher.py:4: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame\n",
+      "\n",
+      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
+      "  after removing the cwd from sys.path.\n",
+      "/home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/pandas/core/generic.py:7626: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame\n",
+      "\n",
+      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
+      "  self._update_inplace(new_data)\n",
+      "/home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2961: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame\n",
+      "\n",
+      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
+      "  exec(code_obj, self.user_global_ns, self.user_ns)\n"
+     ]
+    }
+   ],
+   "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": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:wsmplayground]",
+   "language": "python",
+   "name": "conda-env-wsmplayground-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
+%% Cell type:code id: tags:
+
+``` python
+import numpy as np
+import pandas as pd
+import pandas_profiling
+```
+
+%% Cell type:code id: tags:
+
+``` python
+df = pd.read_csv('neurobiologyusage.txt',delimiter='|')
+```
+
+%% Cell type:code id: tags:
+
+``` python
+df.head()
+```
+
+%% Output
+
+           User                Start          JobID           JobName      State  \
+    0  mdefende  2019-01-06T22:00:21        2040834      _interactive  COMPLETED
+    1       NaN  2019-01-06T22:00:21  2040834.batch             batch  COMPLETED
+    2    lianov  2019-01-07T16:15:21        2043373  Pipe_trim_galore  COMPLETED
+    3       NaN  2019-01-07T16:15:21  2043373.batch             batch  COMPLETED
+    4    lianov  2019-01-07T16:15:21        2043374  Pipe_trim_galore  COMPLETED
+    
+      Partition    MaxRSS   ReqMem  ReqCPUS NodeList  NNodes   Elapsed
+    0    medium       NaN  10000Mc        1    c0088       1  16:04:23
+    1       NaN  1394528K  10000Mc        1    c0088       1  16:04:23
+    2    medium       NaN   2000Mc        1    c0038       1  00:18:41
+    3       NaN    58592K   2000Mc        1    c0038       1  00:18:41
+    4    medium       NaN   2000Mc        1    c0063       1  00:15:48
+
+%% Cell type:code id: tags:
+
+``` python
+df[['jid','step']] = df.JobID.str.split(".",expand=True)
+df.Partition.values
+```
+
+%% Output
+
+    array(['medium', nan, 'medium', ..., 'medium', nan, nan], dtype=object)
+
+%% Cell type:code id: tags:
+
+``` python
+batchDF=df.dropna(subset=["MaxRSS"])
+userDF=df.dropna(subset=["User"])
+for jid in df.jid.unique():
+    userDF['MaxRSS'][userDF['jid'] == jid]=batchDF['MaxRSS'][batchDF['jid'] == jid]
+
+    #print(userDF[userDF['jid'] == jid])
+
+userDF.head()
+```
+
+%% Output
+
+    /home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/ipykernel_launcher.py:4: SettingWithCopyWarning:
+    A value is trying to be set on a copy of a slice from a DataFrame
+    
+    See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
+      after removing the cwd from sys.path.
+    /home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/pandas/core/generic.py:7626: SettingWithCopyWarning:
+    A value is trying to be set on a copy of a slice from a DataFrame
+    
+    See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
+      self._update_inplace(new_data)
+    /home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2961: SettingWithCopyWarning:
+    A value is trying to be set on a copy of a slice from a DataFrame
+    
+    See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
+      exec(code_obj, self.user_global_ns, self.user_ns)
+
+%% Cell type:code id: tags:
+
+``` python
+```
--- a/neurobiologyusage.txt
+++ b/neurobiologyusage.txt