{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "pRQZOrAplLuo"
   },
   "source": [
    "Contributors: **Rohit Singh Rathaur, Girish L.** \n",
    "\n",
    "Copyright [2021](2021) [*Rohit Singh Rathaur, BIT Mesra and Girish L., CIT GUBBI, Karnataka*]\n",
    "\n",
    "Licensed under the Apache License, Version 2.0 (the \"License\");\n",
    "you may not use this file except in compliance with the License.\n",
    "You may obtain a copy of the License at\n",
    "\n",
    "    http://www.apache.org/licenses/LICENSE-2.0\n",
    "\n",
    "Unless required by applicable law or agreed to in writing, software\n",
    "distributed under the License is distributed on an \"AS IS\" BASIS,\n",
    "WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
    "See the License for the specific language governing permissions and\n",
    "limitations under the License."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "6rUjno0va6DX"
   },
   "outputs": [],
   "source": [
    "#import some necessary librairies\n",
    "\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)<\n",
    "\n",
    "\n",
    "# To plot pretty figures\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "plt.rcParams['axes.labelsize'] = 14\n",
    "plt.rcParams['xtick.labelsize'] = 12\n",
    "plt.rcParams['ytick.labelsize'] = 12\n",
    "\n",
    "\n",
    "import seaborn as sns\n",
    "color = sns.color_palette()\n",
    "sns.set_style('darkgrid')\n",
    "\n",
    "import warnings\n",
    "def ignore_warn(*args, **kwargs):\n",
    "    pass\n",
    "warnings.warn = ignore_warn #ignore annoying warning (from sklearn and seaborn)\n",
    "\n",
    "\n",
    "from scipy import stats\n",
    "from scipy.stats import norm, skew #for some statistics\n",
    "\n",
    "\n",
    "pd.set_option('display.float_format', lambda x: '{:.3f}'.format(x)) #Limiting floats output to 3 decimal points\n",
    "\n",
    "\n",
    "from subprocess import check_output\n",
    "#print(check_output([\"ls\", \"../input\"]).decode(\"utf8\")) #check the files available in the directory"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "K4CRikWVbT1d"
   },
   "source": [
    "# **X.npy data /all data stored in the npy format**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "geh5BNM3bhmT",
    "outputId": "0f5af44d-de19-438b-e4de-5f703c59a687"
   },
   "outputs": [],
   "source": [
    "from google.colab import drive\n",
    "drive.mount('/gdrive')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "PanwhFGBbDV7"
   },
   "outputs": [],
   "source": [
    "# we are here loading the all dataset and showing the all features and sort them per server\n",
    "X = np.load('/gdrive/MyDrive/LFN Anuket/Analysis/data/X.npy', allow_pickle=True)\n",
    "dframe = pd.DataFrame(data=X,columns=['ellis-cpu.idle_perc', 'ralf-load.avg_15_min', 'bono-net.in_errors_sec', 'homer-net.out_bytes_sec', 'ellis-io.write_req_sec', 'homer-mem.total_mb', 'homestead-load.avg_1_min', 'homer-load.avg_1_min', 'sprout-cpu.stolen_perc', 'ralf-cpu.idle_perc', 'sprout-io.read_req_sec', 'homestead-net.in_bytes_sec', 'homer-disk.space_used_perc', 'bono-net.out_packets_sec', 'homer-cpu.wait_perc', 'ellis-net.in_packets_sec', 'bono-mem.free_mb', 'ellis-io.read_req_sec', 'bono-mem.usable_mb', 'bono-net.in_packets_dropped_sec', 'homestead-mem.free_mb', 'homer-io.write_time_sec', 'sprout-io.write_time_sec', 'homestead-net.in_errors_sec', 'homestead-mem.usable_perc', 'homestead-net.in_packets_dropped_sec', 'homestead-io.write_req_sec', 'bono-net.in_bytes_sec', 'homestead-disk.space_used_perc', 'homer-net.out_packets_sec', 'bono-mem.usable_perc', 'ralf-net.out_errors_sec', 'homestead-load.avg_5_min', 'sprout-io.read_kbytes_sec', 'sprout-net.out_errors_sec', 'homestead-io.write_kbytes_sec', 'homestead-net.in_packets_sec', 'sprout-mem.usable_mb', 'homestead-cpu.idle_perc', 'ralf-io.write_time_sec', 'ralf-io.write_kbytes_sec', 'ralf-io.write_req_sec', 'ellis-net.out_bytes_sec', 'bono-io.read_kbytes_sec', 'bono-disk.space_used_perc', 'homer-net.in_packets_dropped_sec', 'ralf-mem.usable_mb', 'bono-load.avg_15_min', 'bono-io.read_time_sec', 'sprout-mem.usable_perc', 'bono-cpu.idle_perc', 'homer-mem.usable_perc', 'homestead-cpu.stolen_perc', 'ralf-io.read_req_sec', 'homer-cpu.idle_perc', 'homestead-mem.total_mb', 'ralf-load.avg_1_min', 'homer-io.read_kbytes_sec', 'homestead-io.read_req_sec', 'ellis-mem.free_mb', 'bono-io.write_time_sec', 'ellis-net.out_errors_sec', 'ellis-cpu.stolen_perc', 'ellis-mem.usable_perc', 'ralf-disk.inode_used_perc', 'sprout-load.avg_15_min', 'ellis-io.read_time_sec', 'ralf-net.out_packets_sec', 'sprout-io.write_req_sec', 'bono-cpu.stolen_perc', 'homestead-load.avg_15_min', 'bono-cpu.system_perc', 'homestead-net.out_packets_sec', 'ellis-io.write_kbytes_sec', 'sprout-cpu.idle_perc', 'ellis-mem.total_mb', 'homer-mem.usable_mb', 'bono-load.avg_5_min', 'ellis-load.avg_5_min', 'homer-cpu.stolen_perc', 'sprout-net.out_bytes_sec', 'homestead-mem.usable_mb', 'homestead-disk.inode_used_perc', 'ralf-net.in_packets_dropped_sec', 'sprout-io.write_kbytes_sec', 'ellis-load.avg_15_min', 'homer-load.avg_5_min', 'ralf-mem.usable_perc', 'bono-net.out_bytes_sec', 'ellis-cpu.system_perc', 'homer-io.read_time_sec', 'ellis-disk.inode_used_perc', 'homestead-io.read_time_sec', 'sprout-net.in_bytes_sec', 'bono-io.write_kbytes_sec', 'homestead-io.read_kbytes_sec', 'ellis-net.in_errors_sec', 'sprout-io.read_time_sec', 'homer-disk.inode_used_perc', 'ralf-cpu.wait_perc', 'homer-load.avg_15_min', 'sprout-load.avg_5_min', 'homer-io.read_req_sec', 'ralf-mem.total_mb', 'homer-mem.free_mb', 'homer-net.in_packets_sec', 'homestead-net.out_bytes_sec', 'sprout-disk.inode_used_perc', 'ellis-mem.usable_mb', 'homer-io.write_kbytes_sec', 'homer-net.out_errors_sec', 'homer-cpu.system_perc', 'ellis-io.read_kbytes_sec', 'sprout-load.avg_1_min', 'sprout-cpu.system_perc', 'ralf-cpu.stolen_perc', 'bono-mem.total_mb', 'bono-net.out_errors_sec', 'ellis-io.write_time_sec', 'ralf-io.read_time_sec', 'sprout-cpu.wait_perc', 'ellis-cpu.wait_perc', 'ralf-disk.space_used_perc', 'ralf-net.out_bytes_sec', 'ellis-net.in_packets_dropped_sec', 'homer-net.in_bytes_sec', 'ellis-net.in_bytes_sec', 'bono-cpu.wait_perc', 'ralf-net.in_packets_sec', 'sprout-mem.total_mb', 'ralf-net.in_bytes_sec', 'bono-load.avg_1_min', 'sprout-net.in_packets_sec', 'bono-io.write_req_sec', 'ralf-load.avg_5_min', 'ralf-net.in_errors_sec', 'bono-disk.inode_used_perc', 'homestead-io.write_time_sec', 'ellis-net.out_packets_sec', 'sprout-disk.space_used_perc', 'ralf-io.read_kbytes_sec', 'homestead-cpu.system_perc', 'sprout-mem.free_mb', 'homer-net.in_errors_sec', 'homestead-net.out_errors_sec', 'homer-io.write_req_sec', 'sprout-net.in_errors_sec', 'ellis-disk.space_used_perc', 'sprout-net.out_packets_sec', 'sprout-net.in_packets_dropped_sec', 'ralf-cpu.system_perc', 'ralf-mem.free_mb', 'bono-io.read_req_sec', 'bono-net.in_packets_sec', 'homestead-cpu.wait_perc', 'ellis-load.avg_1_min'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "nAia0RRkbcSV"
   },
   "outputs": [],
   "source": [
    "dframesorted = dframe.sort_index(axis=1, ascending=True, inplace=False, kind='quicksort')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 270
    },
    "id": "76XHMM3cfWGW",
    "outputId": "87965d6f-7c2a-4c39-ed9e-f372a0ade7ca"
   },
   "outputs": [],
   "source": [
    "dframesorted.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "lKCAS0m7fe5F"
   },
   "outputs": [],
   "source": [
    "#dframesorted.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "vnThYldxXdaw",
    "outputId": "696f7fee-55eb-4d38-d471-17d1dd4e2e7e"
   },
   "outputs": [],
   "source": [
    "# here we print the name col to select later metrics per server. \n",
    "print('Column names are: ',list(dframesorted.columns))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "8-pffUQBXojo"
   },
   "source": [
    "# **X_126bis / all data with less 30 features and csv format**\n",
    "cpu.stolen_perc\n",
    "\n",
    "mem.total_mb\n",
    "\n",
    "net.in_errors_sec\n",
    "\n",
    "net.in_packets_dropped_sec\n",
    "\n",
    "net.out_errors_sec"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "HE4xoUdNXgLi",
    "outputId": "16443f8c-111b-4023-d192-345e02c5a49f"
   },
   "outputs": [],
   "source": [
    "X_126bis = dframesorted.drop(['sprout-cpu.stolen_perc', 'sprout-mem.total_mb', 'sprout-net.in_errors_sec', 'sprout-net.in_packets_dropped_sec', 'sprout-net.out_errors_sec','homer-cpu.stolen_perc', 'homer-mem.total_mb', 'homer-net.in_errors_sec', 'homer-net.in_packets_dropped_sec', 'homer-net.out_errors_sec','ellis-cpu.stolen_perc', 'ellis-mem.total_mb', 'ellis-net.in_errors_sec', 'ellis-net.in_packets_dropped_sec', 'ellis-net.out_errors_sec', 'bono-cpu.stolen_perc', 'bono-mem.total_mb', 'bono-net.in_errors_sec', 'bono-net.in_packets_dropped_sec', 'bono-net.out_errors_sec', 'ralf-cpu.stolen_perc', 'ralf-mem.total_mb', 'ralf-net.in_errors_sec', 'ralf-net.in_packets_dropped_sec', 'ralf-net.out_errors_sec', 'homestead-cpu.stolen_perc', 'homestead-mem.total_mb', 'homestead-net.in_errors_sec', 'homestead-net.in_packets_dropped_sec', 'homestead-net.out_errors_sec'], axis =1)\n",
    "\n",
    "dframesorted.shape, X_126bis.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "5_8LHtazXvwf"
   },
   "outputs": [],
   "source": [
    "X_126bis.to_csv('X_126bis.csv', sep=',')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "sknAZgiPX6_2"
   },
   "source": [
    "# **df_Ellis.csv / extract the ellis server metrics**\n",
    "1) Ellis Server with 26 metrics\n",
    "\n",
    "2) subselection of the Ellis metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "S6n-hPD3X43P"
   },
   "outputs": [],
   "source": [
    "# this function select column from the global df and create a new df with them\n",
    "def select_columns(data_frame, column_names):\n",
    "    new_frame = data_frame.loc[:, column_names]\n",
    "    return new_frame\n",
    "\n",
    "selected_columns = ['ellis-cpu.idle_perc', 'ellis-cpu.stolen_perc', 'ellis-cpu.system_perc', 'ellis-cpu.wait_perc', 'ellis-disk.inode_used_perc', 'ellis-disk.space_used_perc', 'ellis-io.read_kbytes_sec', 'ellis-io.read_req_sec', 'ellis-io.read_time_sec', 'ellis-io.write_kbytes_sec', 'ellis-io.write_req_sec', 'ellis-io.write_time_sec', 'ellis-load.avg_15_min', 'ellis-load.avg_1_min', 'ellis-load.avg_5_min', 'ellis-mem.free_mb', 'ellis-mem.total_mb', 'ellis-mem.usable_mb', 'ellis-mem.usable_perc', 'ellis-net.in_bytes_sec', 'ellis-net.in_errors_sec', 'ellis-net.in_packets_dropped_sec', 'ellis-net.in_packets_sec', 'ellis-net.out_bytes_sec', 'ellis-net.out_errors_sec', 'ellis-net.out_packets_sec']\n",
    "df_Ellis = select_columns(dframesorted, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 241
    },
    "id": "VU27zosAYA0b",
    "outputId": "32ed0bbb-0386-40c8-ba57-0787d3afda76"
   },
   "outputs": [],
   "source": [
    "df_Ellis.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0k96D8aDYFw-"
   },
   "source": [
    "# **df_Ellis_7 / focus on the main 6 metrics**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "zVxKNXtfYCph"
   },
   "outputs": [],
   "source": [
    "selected_columns= ['ellis-load.avg_1_min', 'ellis-cpu.wait_perc', 'ellis-net.out_packets_sec', 'ellis-cpu.system_perc', 'ellis-net.in_bytes_sec', 'ellis-mem.free_mb']\n",
    "df_Ellis_7 = select_columns(df_Ellis, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "7y_uHZ5TYJiD",
    "outputId": "5aef0247-67d8-4d19-c337-54075e096e07"
   },
   "outputs": [],
   "source": [
    "df_Ellis_7.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/New/df_Ellis.csv')\n",
    "df_Ellis_7.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "e9c4-7mZYLpq",
    "outputId": "020a0e5f-a63a-4918-db1b-a9e1081ce38e"
   },
   "outputs": [],
   "source": [
    "df_Ellis_7.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "iFy_Het0cqh7",
    "outputId": "ad2ea7ad-1c70-4539-a558-bee07b0a8a19"
   },
   "outputs": [],
   "source": [
    "timestamp  = pd.read_csv(\"/gdrive/MyDrive/LFN Anuket/Analysis/data/timestamp.csv\")\n",
    "timestamp.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "q2-Wt45vdTzt"
   },
   "outputs": [],
   "source": [
    "df1 = timestamp[\"Timestamp\"]\n",
    "df1\n",
    "df1.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/TimestampNew.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "dcpx8F6ReZzb",
    "outputId": "7009dff8-ee1a-43ee-b990-1bfba586cce9"
   },
   "outputs": [],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "mybijUDWfdcH"
   },
   "outputs": [],
   "source": [
    "#df_Ellis_7.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/New/df_EllisTime.csv') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 419
    },
    "id": "2TddekZAfiad",
    "outputId": "be25c51a-d1c0-4da8-9838-72fb59d85369"
   },
   "outputs": [],
   "source": [
    "df_Ellis_7"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "7gstjLldYT_r"
   },
   "outputs": [],
   "source": [
    "# df_Ellis_7.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "bFMkMFqhs5pm"
   },
   "outputs": [],
   "source": [
    "# investigate why we need this float transformation. \n",
    "df_Ellis_7 = df_Ellis_7.astype(np.float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 882
    },
    "id": "mWxDJNMwtGYs",
    "outputId": "73a4a63a-4bd6-4ef0-b140-4ef299152fa2"
   },
   "outputs": [],
   "source": [
    "# we show here the hist\n",
    "df_Ellis_7.hist(bins=100,figsize=(20,15))\n",
    "#save_fig(\"attribute_histogram_plots\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "dedoBLq_tIG_"
   },
   "outputs": [],
   "source": [
    "df_Ellis_7.to_csv('df_Ellis_7.csv', sep=';')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "sObmuXeWtLL0",
    "outputId": "e2bbea48-8fb3-4671-a4dc-5f9f2e464b59"
   },
   "outputs": [],
   "source": [
    "# we show here the boxplot\n",
    "plt.figure(figsize=(20,20))\n",
    "#df_Ellis_7.boxplot(figsize=(20,20))\n",
    "ax = sns.boxplot(x=\"variable\", y=\"value\", data=pd.melt(df_Ellis_7))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "wxNTLGMHtOF_"
   },
   "outputs": [],
   "source": [
    "# the gray related metrics will be dropped when using the df_Ellis\n",
    "\n",
    "#del df_Ellis['ellis-cpu.stolen_perc']\n",
    "#del df_Ellis['ellis-mem.total_mb']\n",
    "#del df_Ellis['ellis-net.in_errors_sec']\n",
    "#del df_Ellis['ellis-net.in_packets_dropped_sec']\n",
    "#del df_Ellis['ellis-net.out_errors_sec']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "pcmqBw0gtUT5",
    "outputId": "b0da529e-8895-483a-d7d1-e450fc6762e0"
   },
   "outputs": [],
   "source": [
    "# we establish the corrmartrice\n",
    "correaltionMatrice = df_Ellis_7.corr()\n",
    "f, ax = plt.subplots(figsize=(30, 20))\n",
    "sns.heatmap(correaltionMatrice, cbar=True, vmin=0, vmax=1, square=True, annot=True);\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 411
    },
    "id": "7yZNvlQ2tWlu",
    "outputId": "dc56cd65-e5e5-4179-aac9-6c6aac43c0eb"
   },
   "outputs": [],
   "source": [
    "mask = np.zeros_like(correaltionMatrice)\n",
    "mask[np.triu_indices_from(mask)] = True\n",
    "with sns.axes_style(\"white\"):\n",
    "     ax = sns.heatmap(correaltionMatrice, mask=mask, vmin=0,vmax=1, square=True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "Whxt9FahtZ6i",
    "outputId": "f6dd23c3-82b5-4dd1-9f18-6bd373ff9322"
   },
   "outputs": [],
   "source": [
    "df_Ellis_7.shape\n",
    "df_Ellis_7.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "Tmzw5MYctb3h",
    "outputId": "65c21482-29fa-42e3-eb8f-50414bb9c656"
   },
   "outputs": [],
   "source": [
    "# we show here the scatter_matrix\n",
    "from pandas.plotting import scatter_matrix\n",
    "scatter_matrix(df_Ellis_7, alpha=0.2, figsize=(30,30))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "kcMuENePteVx",
    "outputId": "7ed8fd61-a02c-4a01-f661-69938c0028ad"
   },
   "outputs": [],
   "source": [
    "# we show here the scatter_matrix (kde)\n",
    "\n",
    "scatter_matrix(df_Ellis_7, alpha=0.2, figsize=(30, 30), diagonal='kde')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "thrxP0LQth88",
    "outputId": "d15b9169-79b7-47a0-e19f-b8477dd2b287"
   },
   "outputs": [],
   "source": [
    "#scatterplot the most obvious variable related to SalePrice\n",
    "sns.pairplot(df_Ellis_7, size = 2.5)\n",
    "plt.show();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "HNMDfsExILYz"
   },
   "source": [
    "# **Bono**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "mxaAX85otljN"
   },
   "outputs": [],
   "source": [
    "# this function select column from the global df and create a new df with them\n",
    "def select_columns(data_frame, column_names):\n",
    "    new_frame = data_frame.loc[:, column_names]\n",
    "    return new_frame\n",
    "\n",
    "selected_columns = ['bono-cpu.idle_perc', 'bono-cpu.stolen_perc', 'bono-cpu.system_perc', 'bono-cpu.wait_perc', 'bono-disk.inode_used_perc', 'bono-disk.space_used_perc', 'bono-io.read_kbytes_sec', 'bono-io.read_req_sec', 'bono-io.read_time_sec', 'bono-io.write_kbytes_sec', 'bono-io.write_req_sec', 'bono-io.write_time_sec', 'bono-load.avg_15_min', 'bono-load.avg_1_min', 'bono-load.avg_5_min', 'bono-mem.free_mb', 'bono-mem.total_mb', 'bono-mem.usable_mb', 'bono-mem.usable_perc', 'bono-net.in_bytes_sec', 'bono-net.in_errors_sec', 'bono-net.in_packets_dropped_sec', 'bono-net.in_packets_sec', 'bono-net.out_bytes_sec', 'bono-net.out_errors_sec', 'bono-net.out_packets_sec']\n",
    "df_Bono = select_columns(dframesorted, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 241
    },
    "id": "EKi0wnvUIlZb",
    "outputId": "4e7d2685-b09c-43ae-9217-d7210a253950"
   },
   "outputs": [],
   "source": [
    "df_Bono.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "gGCA3rWuJdQx"
   },
   "outputs": [],
   "source": [
    "selected_columns= ['bono-load.avg_1_min', 'bono-cpu.wait_perc', 'bono-net.out_packets_sec', 'bono-cpu.system_perc', 'bono-net.in_bytes_sec', 'bono-mem.free_mb']\n",
    "df_Bono_7 = select_columns(df_Bono, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "9ZyhiI6AJo1Y",
    "outputId": "9308469b-ba98-4152-dafa-308d3b6f7b04"
   },
   "outputs": [],
   "source": [
    "df_Bono_7.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/bono/df_Bono.csv')\n",
    "df_Bono_7.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "4ZUXUW35J2fr",
    "outputId": "fc474730-e953-4f09-8633-ece4e493d9de"
   },
   "outputs": [],
   "source": [
    "df_Bono_7.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "QeQ3_oHsJ5BN"
   },
   "source": [
    "# **Sprout**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "gAQmKdKfJ3st"
   },
   "outputs": [],
   "source": [
    "# this function select column from the global df and create a new df with them\n",
    "def select_columns(data_frame, column_names):\n",
    "    new_frame = data_frame.loc[:, column_names]\n",
    "    return new_frame\n",
    "\n",
    "selected_columns = ['sprout-cpu.idle_perc', 'sprout-cpu.stolen_perc', 'sprout-cpu.system_perc', 'sprout-cpu.wait_perc', 'sprout-disk.inode_used_perc', 'sprout-disk.space_used_perc', 'sprout-io.read_kbytes_sec', 'sprout-io.read_req_sec', 'sprout-io.read_time_sec', 'sprout-io.write_kbytes_sec', 'sprout-io.write_req_sec', 'sprout-io.write_time_sec', 'sprout-load.avg_15_min', 'sprout-load.avg_1_min', 'sprout-load.avg_5_min', 'sprout-mem.free_mb', 'sprout-mem.total_mb', 'sprout-mem.usable_mb', 'sprout-mem.usable_perc', 'sprout-net.in_bytes_sec', 'sprout-net.in_errors_sec', 'sprout-net.in_packets_dropped_sec', 'sprout-net.in_packets_sec', 'sprout-net.out_bytes_sec', 'sprout-net.out_errors_sec', 'sprout-net.out_packets_sec']\n",
    "df_Sprout = select_columns(dframesorted, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 241
    },
    "id": "wjdR0R7YMOyT",
    "outputId": "4600cd66-0456-4da2-8723-17b5079f7f6b"
   },
   "outputs": [],
   "source": [
    "df_Sprout.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "6Tfi58LJMUNu"
   },
   "outputs": [],
   "source": [
    "selected_columns= ['sprout-load.avg_1_min', 'sprout-cpu.wait_perc', 'sprout-net.out_packets_sec', 'sprout-cpu.system_perc', 'sprout-net.in_bytes_sec', 'sprout-mem.free_mb']\n",
    "df_Sprout_7 = select_columns(df_Sprout, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "fP5NM3VjM0Uw",
    "outputId": "163390b3-9ce0-406a-d9c9-88687d696c66"
   },
   "outputs": [],
   "source": [
    "df_Sprout_7.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/sprout/df_Sprout.csv')\n",
    "df_Sprout_7.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Ybl5WrSYM9Q0",
    "outputId": "50f23729-a029-440f-dc6f-828308bb342c"
   },
   "outputs": [],
   "source": [
    "df_Sprout_7.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "AvKCUZL5NKKz"
   },
   "source": [
    "# **Homestead**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "EaXOAy7BNF8s"
   },
   "outputs": [],
   "source": [
    "# this function select column from the global df and create a new df with them\n",
    "def select_columns(data_frame, column_names):\n",
    "    new_frame = data_frame.loc[:, column_names]\n",
    "    return new_frame\n",
    "\n",
    "selected_columns = ['homestead-cpu.idle_perc', 'homestead-cpu.stolen_perc', 'homestead-cpu.system_perc', 'homestead-cpu.wait_perc', 'homestead-disk.inode_used_perc', 'homestead-disk.space_used_perc', 'homestead-io.read_kbytes_sec', 'homestead-io.read_req_sec', 'homestead-io.read_time_sec', 'homestead-io.write_kbytes_sec', 'homestead-io.write_req_sec', 'homestead-io.write_time_sec', 'homestead-load.avg_15_min', 'homestead-load.avg_1_min', 'homestead-load.avg_5_min', 'homestead-mem.free_mb', 'homestead-mem.total_mb', 'homestead-mem.usable_mb', 'homestead-mem.usable_perc', 'homestead-net.in_bytes_sec', 'homestead-net.in_errors_sec', 'homestead-net.in_packets_dropped_sec', 'homestead-net.in_packets_sec', 'homestead-net.out_bytes_sec', 'homestead-net.out_errors_sec', 'homestead-net.out_packets_sec']\n",
    "df_Homestead = select_columns(dframesorted, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 241
    },
    "id": "Qc5vd1CVNas2",
    "outputId": "8b6ab0c1-d15d-4545-e69b-dd39facc5915"
   },
   "outputs": [],
   "source": [
    "df_Homestead.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "U5e-23VDNgjS"
   },
   "outputs": [],
   "source": [
    "selected_columns= ['homestead-load.avg_1_min', 'homestead-cpu.wait_perc', 'homestead-net.out_packets_sec', 'homestead-cpu.system_perc', 'homestead-net.in_bytes_sec', 'homestead-mem.free_mb']\n",
    "df_Homestead_7 = select_columns(df_Homestead, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 221
    },
    "id": "03Y_KhJVNuOC",
    "outputId": "ab3eef43-6a18-4c61-926a-43afac19d7a5"
   },
   "outputs": [],
   "source": [
    "df_Homestead_7.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/homestead/df_Homestead.csv')\n",
    "df_Homestead_7.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "CVdMWcneN7ix",
    "outputId": "f3e00de9-f60d-44d0-ae5b-9c4eda033687"
   },
   "outputs": [],
   "source": [
    "df_Homestead_7.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_kw5-s7hOFN3"
   },
   "source": [
    "# **Ralf**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "v6xYItZWOANR"
   },
   "outputs": [],
   "source": [
    "# this function select column from the global df and create a new df with them\n",
    "def select_columns(data_frame, column_names):\n",
    "    new_frame = data_frame.loc[:, column_names]\n",
    "    return new_frame\n",
    "\n",
    "selected_columns = ['ralf-cpu.idle_perc', 'ralf-cpu.stolen_perc', 'ralf-cpu.system_perc', 'ralf-cpu.wait_perc', 'ralf-disk.inode_used_perc', 'ralf-disk.space_used_perc', 'ralf-io.read_kbytes_sec', 'ralf-io.read_req_sec', 'ralf-io.read_time_sec', 'ralf-io.write_kbytes_sec', 'ralf-io.write_req_sec', 'ralf-io.write_time_sec', 'ralf-load.avg_15_min', 'ralf-load.avg_1_min', 'ralf-load.avg_5_min', 'ralf-mem.free_mb', 'ralf-mem.total_mb', 'ralf-mem.usable_mb', 'ralf-mem.usable_perc', 'ralf-net.in_bytes_sec', 'ralf-net.in_errors_sec', 'ralf-net.in_packets_dropped_sec', 'ralf-net.in_packets_sec', 'ralf-net.out_bytes_sec', 'ralf-net.out_errors_sec', 'ralf-net.out_packets_sec']\n",
    "df_Ralf = select_columns(dframesorted, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 241
    },
    "id": "XlYi3QBlORiI",
    "outputId": "6a4740f0-b2c8-4e48-9067-c17c7a267b0d"
   },
   "outputs": [],
   "source": [
    "df_Ralf.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "6l88CRqDOVs-"
   },
   "outputs": [],
   "source": [
    "selected_columns= ['ralf-load.avg_1_min', 'ralf-cpu.wait_perc', 'ralf-net.out_packets_sec', 'ralf-cpu.system_perc', 'ralf-net.in_bytes_sec', 'ralf-mem.free_mb']\n",
    "df_Ralf_7 = select_columns(df_Ralf, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "u3v26LoiOi5L",
    "outputId": "441d54ec-a644-446e-dc5b-e7ad5ec58456"
   },
   "outputs": [],
   "source": [
    "df_Ralf_7.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/ralf/df_Ralf.csv')\n",
    "df_Ralf_7.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "mR7Fg1w8OtnU",
    "outputId": "141c6b09-3c69-45cc-e723-728e1f0e8e68"
   },
   "outputs": [],
   "source": [
    "df_Ralf_7.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2-udEbTHO-HS"
   },
   "source": [
    "# **Homer**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "vVpG5lJiOyYw"
   },
   "outputs": [],
   "source": [
    "# this function select column from the global df and create a new df with them\n",
    "def select_columns(data_frame, column_names):\n",
    "    new_frame = data_frame.loc[:, column_names]\n",
    "    return new_frame\n",
    "\n",
    "selected_columns = ['homer-cpu.idle_perc', 'homer-cpu.stolen_perc', 'homer-cpu.system_perc', 'homer-cpu.wait_perc', 'homer-disk.inode_used_perc', 'homer-disk.space_used_perc', 'homer-io.read_kbytes_sec', 'homer-io.read_req_sec', 'homer-io.read_time_sec', 'homer-io.write_kbytes_sec', 'homer-io.write_req_sec', 'homer-io.write_time_sec', 'homer-load.avg_15_min', 'homer-load.avg_1_min', 'homer-load.avg_5_min', 'homer-mem.free_mb', 'homer-mem.total_mb', 'homer-mem.usable_mb', 'homer-mem.usable_perc', 'homer-net.in_bytes_sec', 'homer-net.in_errors_sec', 'homer-net.in_packets_dropped_sec', 'homer-net.in_packets_sec', 'homer-net.out_bytes_sec', 'homer-net.out_errors_sec', 'homer-net.out_packets_sec']\n",
    "df_Homer = select_columns(dframesorted, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 241
    },
    "id": "cwMKYQWUPKpl",
    "outputId": "ca108468-0c41-4f44-aef0-8c63239c9fd5"
   },
   "outputs": [],
   "source": [
    "df_Homer.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "rsUb47imPOyE"
   },
   "outputs": [],
   "source": [
    "selected_columns= ['homer-load.avg_1_min', 'homer-cpu.wait_perc', 'homer-net.out_packets_sec', 'homer-cpu.system_perc', 'homer-net.in_bytes_sec', 'homer-mem.free_mb']\n",
    "df_Homer_7 = select_columns(df_Homer, selected_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "VZw7WV7tPd9i",
    "outputId": "39dc88dd-eb89-45b0-a0d3-f261aab6bbd1"
   },
   "outputs": [],
   "source": [
    "df_Homer_7.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/homer/df_Homer.csv')\n",
    "df_Homer_7.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "E1Cqq8V3PnEv",
    "outputId": "9a80be17-5bb5-4f8d-a61c-d3206e730309"
   },
   "outputs": [],
   "source": [
    "df_Homer_7.info()"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "vIMS_Visualization.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}