From 104dc621a00a9229c01f929a780d72fa9dda80a1 Mon Sep 17 00:00:00 2001
From: John-Paul Robinson <jpr@uab.edu>
Date: Fri, 2 Dec 2022 10:57:27 -0600
Subject: [PATCH] Create notebook to merge multiple atime reports into single
report
Takes a directory of atime reports generated by array job and
merges into a single per-user report.
---
max-access-per-user-merged.ipynb | 288 +++++++++++++++++++++++++++++++
1 file changed, 288 insertions(+)
create mode 100644 max-access-per-user-merged.ipynb
diff --git a/max-access-per-user-merged.ipynb b/max-access-per-user-merged.ipynb
new file mode 100644
index 0000000..aa4e14a
--- /dev/null
+++ b/max-access-per-user-merged.ipynb
@@ -0,0 +1,288 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "0f3842e0",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import datetime\n",
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt\n",
+ "from urllib.parse import unquote\n",
+ "import sys\n",
+ "import os\n",
+ "import glob\n",
+ "\n",
+ "recs = []\n",
+ "count=0\n",
+ "progress=0\n",
+ "\n",
+ "report_name = \"temporary-scratch\"\n",
+ "dir = \"data/list-17075953.list.gather-info.d\"\n",
+ "#report_name = \"temporary-scratch\"\n",
+ "#dir = 'data/list-17094088.list.gather-info.d'\n",
+ "\n",
+ "os.chdir(dir)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "3b8c0042",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#os.chdir('../..')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b379845f",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!pwd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "d3d9f107",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!which python"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "c2a94675",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "frames = []\n",
+ "\n",
+ "for file in glob.glob(\"*.gz\"):\n",
+ " print(f\"processing: {file}\")\n",
+ " # combine picked dfs into one df\n",
+ " # https://pandas.pydata.org/pandas-docs/stable/user_guide/merging.html\n",
+ " df = pd.read_pickle(file)\n",
+ " frames.append(df)\n",
+ "\n",
+ "df = pd.concat(frames)\n",
+ "del(frames)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "a6a4e9bf",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df.info()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "4ca6e641",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(f\"max atime: {df['atime'].max()}\\n\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "cc576380",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df.groupby([\"uid\"], sort=False)[\"atime\"].max().sort_values()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "1a482ac6",
+ "metadata": {},
+ "source": [
+ "Get user names https://stackoverflow.com/a/421670/8928529"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "7c4e531e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pwd\n",
+ "def getuser(uid):\n",
+ " return pwd.getpwuid(int(uid))[0].split(\":\")[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "6980fc30",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# set uname for uid\n",
+ "for uid in sorted(df[\"uid\"].unique()):\n",
+ " uname = pwd.getpwuid(int(uid))[0].split(\":\")[0]\n",
+ " print(\"uid: {} name: {}\".format(uid, uname))\n",
+ " df.loc[df[\"uid\"]==uid, [\"uname\"]] = uname"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "29af2c16",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "space=df.groupby([\"uname\"], sort=False)[\"size\"].sum().sort_values().to_frame()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "77b361b1",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "space[\"GB\"]=space[\"size\"]/1000/1000/1000\n",
+ "space[\"GiB\"]=space[\"size\"]/1024/1024/1024"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "90b897a5",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "space=df.groupby([\"uname\"], sort=False)[\"size\"].sum().sort_values().to_frame()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "5065d98e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "space"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "1bf8adb7",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "atime=df.groupby([\"uname\"], sort=False)[\"atime\"].max().sort_values().to_frame()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "fb33c1de",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "atime.rename(columns={\"atime\": \"newest\"}, inplace=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "ce376ec2",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "atime[\"oldest\"]=df.groupby([\"uname\"], sort=False)[\"atime\"].min().sort_values().to_frame()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "6fd5346a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "atime[\"newest_date\"] = pd.to_datetime(atime[\"newest\"].dt.strftime('%Y-%m-%d'))\n",
+ "atime[\"oldest_date\"] = pd.to_datetime(atime[\"oldest\"].dt.strftime('%Y-%m-%d'))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "422ecc0c",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "report=pd.concat([atime, space], axis=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "1c979329",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "pd.set_option('display.max_rows', None)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "32139106",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# https://stackoverflow.com/a/20937592/8928529\n",
+ "pd.options.display.float_format = '{:,.2f}'.format"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "8d40d60f",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "report[[\"newest_date\", \"oldest_date\", \"GB\", \"GiB\"]]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "871995b1",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(f\"report: {report_name}\")\n",
+ "print(report[[\"newest_date\", \"oldest_date\", \"GB\", \"GiB\"]])\n",
+ "print(\"--------\\ntotals: {0:,.2f}GB {1:,.2f}GiB\".format(report['GB'].sum(), report['GiB'].sum()))"
+ ]
+ }
+ ],
+ "metadata": {
+ "language_info": {
+ "name": "python",
+ "pygments_lexer": "ipython3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--
GitLab