{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "FeatureCreation.ipynb",
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "zyycU3DFlecK"
},
"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",
"metadata": {
"id": "gehKp2rySVf8"
},
"source": [
"# Import libraries use for visualization and analysis\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"%matplotlib inline\n",
"import matplotlib\n",
"import matplotlib.pyplot as plt\n",
"\n",
"from pandas import Series,DataFrame\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from sklearn.preprocessing import scale\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
"from scipy import stats\n",
"from IPython.display import display, HTML"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "tkuBlbCXSsdP",
"outputId": "2b3ef633-a851-4c53-80eb-6b1bf4ffcc1c"
},
"source": [
"from google.colab import drive\n",
"drive.mount('/gdrive')"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Drive already mounted at /gdrive; to attempt to forcibly remount, call drive.mount(\"/gdrive\", force_remount=True).\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "wZXe8D88S-6R"
},
"source": [
"# **Loading the Data**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "KiDSpl37Sy39"
},
"source": [
"df_Ellis = pd.read_csv(\"/gdrive/MyDrive/LFN Anuket/Analysis/data/Final/Final.csv\")\n",
"#df_Bono = pd.read_csv(\"/gdrive/MyDrive/LFN Anuket/Analysis/data/matrices/df_Bono.csv\", error_bad_lines=False)\n",
"#df_Sprout = pd.read_csv(\"/gdrive/MyDrive/LFN Anuket/Analysis/data/matrices/df_Sprout.csv\", error_bad_lines=False)\n",
"#df_Homer = pd.read_csv(\"/gdrive/MyDrive/LFN Anuket/Analysis/data/matrices/df_Homer.csv\", error_bad_lines=False)\n",
"#df_Homestead = pd.read_csv(\"/gdrive/MyDrive/LFN Anuket/Analysis/data/matrices/df_Homestead.csv\", error_bad_lines=False)\n",
"#df_Ralf = pd.read_csv(\"/gdrive/MyDrive/LFN Anuket/Analysis/data/matrices/df_Ralf.csv\", error_bad_lines=False)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 204
},
"id": "dpy8jAm-TsCs",
"outputId": "d8ad2072-1fa3-4b3c-fb55-b5128767b349"
},
"source": [
"df_Ellis.head()"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Timestamp | \n",
" ellis-cpu.system_perc | \n",
" ellis-cpu.wait_perc | \n",
" ellis-load.avg_1_min | \n",
" ellis-mem.free_mb | \n",
" ellis-net.in_bytes_sec | \n",
" ellis-net.out_packets_sec | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 14/09/2016 0:00 | \n",
" 0.5 | \n",
" 12.9 | \n",
" 1.73 | \n",
" 3949 | \n",
" 5413.200 | \n",
" 62.067 | \n",
"
\n",
" \n",
" 1 | \n",
" 14/09/2016 0:00 | \n",
" 0.4 | \n",
" 10.3 | \n",
" 1.79 | \n",
" 3950 | \n",
" 5201.667 | \n",
" 59.567 | \n",
"
\n",
" \n",
" 2 | \n",
" 14/09/2016 0:01 | \n",
" 0.4 | \n",
" 11.8 | \n",
" 1.52 | \n",
" 3950 | \n",
" 5370.733 | \n",
" 61.200 | \n",
"
\n",
" \n",
" 3 | \n",
" 14/09/2016 0:01 | \n",
" 0.4 | \n",
" 12.9 | \n",
" 1.43 | \n",
" 3949 | \n",
" 5292.467 | \n",
" 60.400 | \n",
"
\n",
" \n",
" 4 | \n",
" 14/09/2016 0:02 | \n",
" 0.5 | \n",
" 12.1 | \n",
" 1.44 | \n",
" 3950 | \n",
" 5318.167 | \n",
" 61.700 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Timestamp ... ellis-net.out_packets_sec\n",
"0 14/09/2016 0:00 ... 62.067\n",
"1 14/09/2016 0:00 ... 59.567\n",
"2 14/09/2016 0:01 ... 61.200\n",
"3 14/09/2016 0:01 ... 60.400\n",
"4 14/09/2016 0:02 ... 61.700\n",
"\n",
"[5 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 264
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 297
},
"id": "dJa9FgJNgqpI",
"outputId": "54d6c43d-489f-4347-93e5-12e4a4da2066"
},
"source": [
"df_Ellis.describe()"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" ellis-cpu.system_perc | \n",
" ellis-cpu.wait_perc | \n",
" ellis-load.avg_1_min | \n",
" ellis-mem.free_mb | \n",
" ellis-net.in_bytes_sec | \n",
" ellis-net.out_packets_sec | \n",
"
\n",
" \n",
" \n",
" \n",
" count | \n",
" 177000.000000 | \n",
" 177000.000000 | \n",
" 177000.000000 | \n",
" 177000.000000 | \n",
" 1.770000e+05 | \n",
" 177000.000000 | \n",
"
\n",
" \n",
" mean | \n",
" 2.315540 | \n",
" 1.024163 | \n",
" 0.198842 | \n",
" 4206.847232 | \n",
" 1.855987e+07 | \n",
" 1336.694851 | \n",
"
\n",
" \n",
" std | \n",
" 1.170977 | \n",
" 3.127178 | \n",
" 0.262227 | \n",
" 173.364297 | \n",
" 5.612164e+06 | \n",
" 2220.146124 | \n",
"
\n",
" \n",
" min | \n",
" 0.100000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 2320.000000 | \n",
" 0.000000e+00 | \n",
" 0.000000 | \n",
"
\n",
" \n",
" 25% | \n",
" 1.500000 | \n",
" 0.200000 | \n",
" 0.095000 | \n",
" 4095.000000 | \n",
" 1.797602e+07 | \n",
" 182.033000 | \n",
"
\n",
" \n",
" 50% | \n",
" 1.700000 | \n",
" 0.200000 | \n",
" 0.140000 | \n",
" 4214.000000 | \n",
" 2.087674e+07 | \n",
" 200.067000 | \n",
"
\n",
" \n",
" 75% | \n",
" 3.500000 | \n",
" 0.400000 | \n",
" 0.198000 | \n",
" 4331.000000 | \n",
" 2.160859e+07 | \n",
" 1069.667000 | \n",
"
\n",
" \n",
" max | \n",
" 16.700000 | \n",
" 22.400000 | \n",
" 2.580000 | \n",
" 4633.000000 | \n",
" 2.339041e+07 | \n",
" 7887.552000 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" ellis-cpu.system_perc ... ellis-net.out_packets_sec\n",
"count 177000.000000 ... 177000.000000\n",
"mean 2.315540 ... 1336.694851\n",
"std 1.170977 ... 2220.146124\n",
"min 0.100000 ... 0.000000\n",
"25% 1.500000 ... 182.033000\n",
"50% 1.700000 ... 200.067000\n",
"75% 3.500000 ... 1069.667000\n",
"max 16.700000 ... 7887.552000\n",
"\n",
"[8 rows x 6 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 265
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "xGVleQbnhRm6"
},
"source": [
"#df_Ellis['SLO1'] = 0\n",
"#print('Column names are: ',list(df_Ellis.columns))"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "b-F_gA61xowR",
"outputId": "f9bd6232-2603-40ad-ccff-18887839e2da"
},
"source": [
"df4 = df_Ellis[\"ellis-load.avg_1_min\"] > 2.45\n",
"df4\n",
"df4.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/Final/EllisLoadAvgLabel_lessthan0198.csv')\n",
"df4.head(50)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0 False\n",
"1 False\n",
"2 False\n",
"3 False\n",
"4 False\n",
"5 False\n",
"6 False\n",
"7 False\n",
"8 False\n",
"9 False\n",
"10 False\n",
"11 False\n",
"12 False\n",
"13 False\n",
"14 False\n",
"15 False\n",
"16 False\n",
"17 False\n",
"18 False\n",
"19 False\n",
"20 False\n",
"21 False\n",
"22 False\n",
"23 False\n",
"24 False\n",
"25 False\n",
"26 False\n",
"27 False\n",
"28 False\n",
"29 False\n",
"30 False\n",
"31 False\n",
"32 False\n",
"33 False\n",
"34 False\n",
"35 False\n",
"36 False\n",
"37 False\n",
"38 False\n",
"39 False\n",
"40 False\n",
"41 False\n",
"42 False\n",
"43 False\n",
"44 False\n",
"45 False\n",
"46 False\n",
"47 False\n",
"48 False\n",
"49 False\n",
"Name: ellis-load.avg_1_min, dtype: bool"
]
},
"metadata": {
"tags": []
},
"execution_count": 267
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "8xcPRerCz8nA",
"outputId": "fb66f20e-7365-40ec-857a-9dd9a8072401"
},
"source": [
"df3 = df_Ellis[\"ellis-cpu.wait_perc\"] > 5\n",
"df3\n",
"df3.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/Final/ellis-cpu>5.csv')\n",
"df3.head(50)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0 True\n",
"1 True\n",
"2 True\n",
"3 True\n",
"4 True\n",
"5 True\n",
"6 True\n",
"7 True\n",
"8 True\n",
"9 True\n",
"10 True\n",
"11 True\n",
"12 True\n",
"13 True\n",
"14 True\n",
"15 True\n",
"16 True\n",
"17 True\n",
"18 True\n",
"19 True\n",
"20 True\n",
"21 True\n",
"22 True\n",
"23 True\n",
"24 True\n",
"25 True\n",
"26 True\n",
"27 True\n",
"28 True\n",
"29 True\n",
"30 True\n",
"31 True\n",
"32 True\n",
"33 True\n",
"34 True\n",
"35 True\n",
"36 True\n",
"37 True\n",
"38 True\n",
"39 True\n",
"40 True\n",
"41 True\n",
"42 True\n",
"43 True\n",
"44 True\n",
"45 True\n",
"46 True\n",
"47 True\n",
"48 True\n",
"49 True\n",
"Name: ellis-cpu.wait_perc, dtype: bool"
]
},
"metadata": {
"tags": []
},
"execution_count": 268
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "EED56Wiq_NjM",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "20b06258-c5ba-457b-a022-cf5823217cbf"
},
"source": [
"df5 = df_Ellis[\"ellis-net.out_packets_sec\"] > 1000\n",
"df5\n",
"df5.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/Final/ellis-net.in_bytes_sec21139.csv')\n",
"df5.head(50)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0 False\n",
"1 False\n",
"2 False\n",
"3 False\n",
"4 False\n",
"5 False\n",
"6 False\n",
"7 False\n",
"8 False\n",
"9 False\n",
"10 False\n",
"11 False\n",
"12 False\n",
"13 False\n",
"14 False\n",
"15 False\n",
"16 False\n",
"17 False\n",
"18 False\n",
"19 False\n",
"20 False\n",
"21 False\n",
"22 False\n",
"23 False\n",
"24 False\n",
"25 False\n",
"26 False\n",
"27 False\n",
"28 False\n",
"29 False\n",
"30 False\n",
"31 False\n",
"32 False\n",
"33 False\n",
"34 False\n",
"35 False\n",
"36 False\n",
"37 False\n",
"38 False\n",
"39 False\n",
"40 False\n",
"41 False\n",
"42 False\n",
"43 False\n",
"44 False\n",
"45 False\n",
"46 False\n",
"47 False\n",
"48 False\n",
"49 False\n",
"Name: ellis-net.out_packets_sec, dtype: bool"
]
},
"metadata": {
"tags": []
},
"execution_count": 269
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "phlI40_y0mug",
"outputId": "7fa177b9-bf9a-4b96-db65-7402f7f6cf32"
},
"source": [
"# We are applying Logical OR Operator between df4 and df3\n",
"df6 = (df4[0:176999]) | (df3[0:176999])\n",
"df6.head(50)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0 True\n",
"1 True\n",
"2 True\n",
"3 True\n",
"4 True\n",
"5 True\n",
"6 True\n",
"7 True\n",
"8 True\n",
"9 True\n",
"10 True\n",
"11 True\n",
"12 True\n",
"13 True\n",
"14 True\n",
"15 True\n",
"16 True\n",
"17 True\n",
"18 True\n",
"19 True\n",
"20 True\n",
"21 True\n",
"22 True\n",
"23 True\n",
"24 True\n",
"25 True\n",
"26 True\n",
"27 True\n",
"28 True\n",
"29 True\n",
"30 True\n",
"31 True\n",
"32 True\n",
"33 True\n",
"34 True\n",
"35 True\n",
"36 True\n",
"37 True\n",
"38 True\n",
"39 True\n",
"40 True\n",
"41 True\n",
"42 True\n",
"43 True\n",
"44 True\n",
"45 True\n",
"46 True\n",
"47 True\n",
"48 True\n",
"49 True\n",
"dtype: bool"
]
},
"metadata": {
"tags": []
},
"execution_count": 270
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "9xKYzZcLAZGy",
"outputId": "bc15e547-c791-4104-8bb2-8ed4d3288ac1"
},
"source": [
"df6.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/Final/OR_TwoCondition(2).csv')\n",
"df6.head(50)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0 True\n",
"1 True\n",
"2 True\n",
"3 True\n",
"4 True\n",
"5 True\n",
"6 True\n",
"7 True\n",
"8 True\n",
"9 True\n",
"10 True\n",
"11 True\n",
"12 True\n",
"13 True\n",
"14 True\n",
"15 True\n",
"16 True\n",
"17 True\n",
"18 True\n",
"19 True\n",
"20 True\n",
"21 True\n",
"22 True\n",
"23 True\n",
"24 True\n",
"25 True\n",
"26 True\n",
"27 True\n",
"28 True\n",
"29 True\n",
"30 True\n",
"31 True\n",
"32 True\n",
"33 True\n",
"34 True\n",
"35 True\n",
"36 True\n",
"37 True\n",
"38 True\n",
"39 True\n",
"40 True\n",
"41 True\n",
"42 True\n",
"43 True\n",
"44 True\n",
"45 True\n",
"46 True\n",
"47 True\n",
"48 True\n",
"49 True\n",
"dtype: bool"
]
},
"metadata": {
"tags": []
},
"execution_count": 271
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "wRADpDibBZo5",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "dfc6dc79-3d9f-4979-8210-e62e77b1aa6e"
},
"source": [
"df7 = (df6[0:176999]) | (df5[0:176999])\n",
"df7.head(50)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0 True\n",
"1 True\n",
"2 True\n",
"3 True\n",
"4 True\n",
"5 True\n",
"6 True\n",
"7 True\n",
"8 True\n",
"9 True\n",
"10 True\n",
"11 True\n",
"12 True\n",
"13 True\n",
"14 True\n",
"15 True\n",
"16 True\n",
"17 True\n",
"18 True\n",
"19 True\n",
"20 True\n",
"21 True\n",
"22 True\n",
"23 True\n",
"24 True\n",
"25 True\n",
"26 True\n",
"27 True\n",
"28 True\n",
"29 True\n",
"30 True\n",
"31 True\n",
"32 True\n",
"33 True\n",
"34 True\n",
"35 True\n",
"36 True\n",
"37 True\n",
"38 True\n",
"39 True\n",
"40 True\n",
"41 True\n",
"42 True\n",
"43 True\n",
"44 True\n",
"45 True\n",
"46 True\n",
"47 True\n",
"48 True\n",
"49 True\n",
"dtype: bool"
]
},
"metadata": {
"tags": []
},
"execution_count": 272
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "w6BrDjX4CODn",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "a6c956e7-6aed-4bdd-f37f-505a994de51a"
},
"source": [
"df7.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/Final/FinalORLabel8.5.csv')\n",
"df7.head(50)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0 True\n",
"1 True\n",
"2 True\n",
"3 True\n",
"4 True\n",
"5 True\n",
"6 True\n",
"7 True\n",
"8 True\n",
"9 True\n",
"10 True\n",
"11 True\n",
"12 True\n",
"13 True\n",
"14 True\n",
"15 True\n",
"16 True\n",
"17 True\n",
"18 True\n",
"19 True\n",
"20 True\n",
"21 True\n",
"22 True\n",
"23 True\n",
"24 True\n",
"25 True\n",
"26 True\n",
"27 True\n",
"28 True\n",
"29 True\n",
"30 True\n",
"31 True\n",
"32 True\n",
"33 True\n",
"34 True\n",
"35 True\n",
"36 True\n",
"37 True\n",
"38 True\n",
"39 True\n",
"40 True\n",
"41 True\n",
"42 True\n",
"43 True\n",
"44 True\n",
"45 True\n",
"46 True\n",
"47 True\n",
"48 True\n",
"49 True\n",
"dtype: bool"
]
},
"metadata": {
"tags": []
},
"execution_count": 273
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "wwv2cjFAIFHL"
},
"source": [
"df_Ellis.insert (7, \"Label\", df7)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "hrPqpjd96I1x"
},
"source": [
"#df_Ellis.insert (8, \"Label\", df7)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "_zKkQLOz6qPY"
},
"source": [
"# We applied Logical OR operator in two features only known as and df3 and df4 and stored result in df6 which is known as Final Label after applying OR condition\n",
"df_Ellis\n",
"df_Ellis.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/Final/Ellis_FinalTwoConditionwithOR.csv')"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "3rEy1vtp67M9",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 606
},
"outputId": "4e2175cc-dccb-4aaf-a152-e2452de241b0"
},
"source": [
"df_Ellis.head(100)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Timestamp | \n",
" ellis-cpu.system_perc | \n",
" ellis-cpu.wait_perc | \n",
" ellis-load.avg_1_min | \n",
" ellis-mem.free_mb | \n",
" ellis-net.in_bytes_sec | \n",
" ellis-net.out_packets_sec | \n",
" Label | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 14/09/2016 0:00 | \n",
" 0.5 | \n",
" 12.9 | \n",
" 1.73 | \n",
" 3949 | \n",
" 5413.200 | \n",
" 62.067 | \n",
" True | \n",
"
\n",
" \n",
" 1 | \n",
" 14/09/2016 0:00 | \n",
" 0.4 | \n",
" 10.3 | \n",
" 1.79 | \n",
" 3950 | \n",
" 5201.667 | \n",
" 59.567 | \n",
" True | \n",
"
\n",
" \n",
" 2 | \n",
" 14/09/2016 0:01 | \n",
" 0.4 | \n",
" 11.8 | \n",
" 1.52 | \n",
" 3950 | \n",
" 5370.733 | \n",
" 61.200 | \n",
" True | \n",
"
\n",
" \n",
" 3 | \n",
" 14/09/2016 0:01 | \n",
" 0.4 | \n",
" 12.9 | \n",
" 1.43 | \n",
" 3949 | \n",
" 5292.467 | \n",
" 60.400 | \n",
" True | \n",
"
\n",
" \n",
" 4 | \n",
" 14/09/2016 0:02 | \n",
" 0.5 | \n",
" 12.1 | \n",
" 1.44 | \n",
" 3950 | \n",
" 5318.167 | \n",
" 61.700 | \n",
" True | \n",
"
\n",
" \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
"
\n",
" \n",
" 95 | \n",
" 14/09/2016 0:47 | \n",
" 0.5 | \n",
" 10.8 | \n",
" 0.45 | \n",
" 3948 | \n",
" 5187.133 | \n",
" 60.100 | \n",
" True | \n",
"
\n",
" \n",
" 96 | \n",
" 14/09/2016 0:48 | \n",
" 0.5 | \n",
" 10.4 | \n",
" 0.42 | \n",
" 3949 | \n",
" 5223.100 | \n",
" 60.233 | \n",
" True | \n",
"
\n",
" \n",
" 97 | \n",
" 14/09/2016 0:48 | \n",
" 0.6 | \n",
" 13.0 | \n",
" 0.56 | \n",
" 3947 | \n",
" 5335.200 | \n",
" 60.667 | \n",
" True | \n",
"
\n",
" \n",
" 98 | \n",
" 14/09/2016 0:49 | \n",
" 0.6 | \n",
" 10.1 | \n",
" 0.47 | \n",
" 3948 | \n",
" 5185.733 | \n",
" 60.367 | \n",
" True | \n",
"
\n",
" \n",
" 99 | \n",
" 14/09/2016 0:49 | \n",
" 0.6 | \n",
" 10.8 | \n",
" 0.28 | \n",
" 3948 | \n",
" 5204.233 | \n",
" 59.600 | \n",
" True | \n",
"
\n",
" \n",
"
\n",
"
100 rows × 8 columns
\n",
"
"
],
"text/plain": [
" Timestamp ellis-cpu.system_perc ... ellis-net.out_packets_sec Label\n",
"0 14/09/2016 0:00 0.5 ... 62.067 True\n",
"1 14/09/2016 0:00 0.4 ... 59.567 True\n",
"2 14/09/2016 0:01 0.4 ... 61.200 True\n",
"3 14/09/2016 0:01 0.4 ... 60.400 True\n",
"4 14/09/2016 0:02 0.5 ... 61.700 True\n",
".. ... ... ... ... ...\n",
"95 14/09/2016 0:47 0.5 ... 60.100 True\n",
"96 14/09/2016 0:48 0.5 ... 60.233 True\n",
"97 14/09/2016 0:48 0.6 ... 60.667 True\n",
"98 14/09/2016 0:49 0.6 ... 60.367 True\n",
"99 14/09/2016 0:49 0.6 ... 59.600 True\n",
"\n",
"[100 rows x 8 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 277
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "11Qu45RY0HNG",
"outputId": "305c5dd5-ec61-48a8-abb6-e29bbc4b9e42"
},
"source": [
"# pandas count distinct values in column\n",
"df_Ellis['Label'].value_counts()"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"False 112145\n",
"True 64854\n",
"Name: Label, dtype: int64"
]
},
"metadata": {
"tags": []
},
"execution_count": 278
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "0sB-W_Ny4eHk"
},
"source": [
"#final.to_csv('/gdrive/MyDrive/LFN Anuket/Analysis/data/New/FinalLabel.csv')"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "ERsufys7wcSg"
},
"source": [
"#df_Ellis.loc[(df_Ellis[\"ellis-cpu.wait_perc\"] > 5) & (df_Ellis[\"ellis-load.avg_1_min\"] > 2)]"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "9le7MwnDhlnH"
},
"source": [
"# **Creating New Features**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "090QXGpPlEF6"
},
"source": [
""
],
"execution_count": null,
"outputs": []
}
]
}