{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "aea43308-a588-4730-a10e-48156b0d1aa5",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sdv.single_table import CTGANSynthesizer\n",
"from sdv.single_table import TVAESynthesizer \n",
"from sdv.single_table import CopulaGANSynthesizer\n",
"from sdv.metadata import SingleTableMetadata\n",
"from sdmetrics.reports.single_table import QualityReport\n",
"from sdmetrics.reports.single_table import DiagnosticReport\n",
"from table_evaluator import TableEvaluator\n",
"import matplotlib.pyplot as plt\n",
"from sdmetrics.single_column import StatisticSimilarity\n",
"import math\n",
"from sdmetrics.single_column import RangeCoverage\n",
"from sdmetrics.visualization import get_column_plot\n",
"import os\n",
"import plotly.io as py\n",
"import string"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f6e0f097-891b-42fc-9e20-85145c8d24ac",
"metadata": {},
"outputs": [],
"source": [
"#loading the preprocessed datasets \n",
"\n",
"# real_data = pd.read_csv('Datasets/Preprocessed_Datasets/benign.csv')\n",
"# real_data = pd.read_csv('Datasets/Preprocessed_Datasets/bot_attacks.csv')\n",
"# real_data = pd.read_csv('Datasets/Preprocessed_Datasets/bruteforce_attacks.csv')\n",
"# real_data = pd.read_csv('Datasets/Preprocessed_Datasets/doS_attacks.csv')\n",
"# real_data = pd.read_csv('Datasets/Preprocessed_Datasets/infilteration_attacks.csv')\n",
"\n",
"print(real_data.shape)\n",
"print(real_data.Label.unique())\n",
"\n",
"# if bruteforce_attack or dos_attacks are used then uncomment the below line and change the name of the dataset accordingly\n",
"#real_data=real_data[real_data.Label=='DoS attacks-Hulk'] # change according to the dataset\n",
"real_data = real_data.iloc[:300000, :]\n",
"print(real_data.shape)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bc6915d1-0c8a-4d7e-8b87-0c56ae9c6431",
"metadata": {},
"outputs": [],
"source": [
"# Categorical columns & Continuous columns\n",
"def get_data_info(df):\n",
" \"\"\"Crates the categorical columns, continuous columns, and metadata of a dataframe.\n",
"\n",
" Args:\n",
" df (pandas.Dataframe): The input dataframe containing continuous and categorical values.\n",
"\n",
" Returns:\n",
" list: the list of categorical column names. Specifically, columns with only 4 uniques values\n",
" list: The list of continuous column names.\n",
" metadata: The metadata of the dataframe. for more informatin visit https://docs.sdv.dev/sdv/reference/metadata-spec/single-table-metadata-json\n",
" \"\"\"\n",
" #createing \n",
" categorical_columns = ['Label']\n",
" continuous_columns = []\n",
"\n",
" for i in df.columns:\n",
" if i not in categorical_columns:\n",
" continuous_columns.append(i)\n",
" \n",
" #creating metadat\n",
" metadata = SingleTableMetadata()\n",
" metadata.detect_from_dataframe(df)\n",
" \n",
" for column in categorical_columns:\n",
" metadata.update_column(\n",
" column_name = column,\n",
" sdtype = 'categorical'\n",
" )\n",
" \n",
" for column in continuous_columns:\n",
" metadata.update_column(\n",
" column_name = column,\n",
" sdtype = 'numerical' \n",
" )\n",
" # validating metadata\n",
" metadata.validate()\n",
" metadata.validate_data(data=real_data)\n",
" \n",
" return categorical_columns, continuous_columns, metadata\n",
"\n",
"\n",
"categorical_columns, continuous_columns, metadata = get_data_info(real_data)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bd625bf1-52ed-4bda-9e69-b62009c0422f",
"metadata": {},
"outputs": [],
"source": [
"#fiting the synthesizer\n",
"# for more info check https://docs.sdv.dev/sdv/single-table-data/modeling/synthesizers\n",
"#availabel options CTGANSynthesizer, CopulaGANSynthesizer, and TVAESynthesizer\n",
"\n",
"#uncomment below for CTGANSynthesizer and CopulaGANSynthesizer\n",
"# synthesizer = CTGANSynthesizer(metadata, enforce_min_max_values=True, enforce_rounding=True, embedding_dim=128, generator_dim=(256, 256), \n",
"# discriminator_dim=(256, 256), generator_lr=0.000001, generator_decay=0.000001, epochs=500, discriminator_lr=0.000001, \n",
"# discriminator_decay=0.000001, batch_size=300, discriminator_steps=3, log_frequency=True, verbose=True, pac=10)\n",
"\n",
"\n",
"#uncommnet below for TVAESynthesizer\n",
"# synthesizer = TVAESynthesizer(metadata, enforce_min_max_values=True, enforce_rounding=True, embedding_dim=100, compress_dims=(128, 128), \n",
"# decompress_dims=(128, 128), l2scale=0.000001, batch_size=500, epochs=500, loss_factor=2, cuda=True)\n",
"\n",
"\n",
"\n",
"synthesizer.fit(real_data)\n",
"synthesizer.save(filepath='CopulaGAN_Results/Hulk/CopulaGAN.pkl') # change the path accordingly\n",
"synthetic_data = synthesizer.sample(300000) # change the instances you want to be genereated"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "60019781-cf26-4a21-a1b5-0fd099f07972",
"metadata": {},
"outputs": [],
"source": [
"# evaluating synthetic data with table_evaluator cumulative sum per features and distribution\n",
"table_evaluator = TableEvaluator(real_data, synthetic_data, cat_cols = categorical_columns)\n",
"table_evaluator.visual_evaluation()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "273ea89c-161b-4c73-ac96-412effb4e8bb",
"metadata": {},
"outputs": [],
"source": [
"#saving and visualizing column pair trend and column shapes\n",
"metadata = metadata.to_dict()\n",
"my_report = QualityReport()\n",
"my_report.generate(real_data, synthetic_data, metadata)\n",
"my_report.save(filepath='CopulaGAN_Results/Hulk/quality.pkl')\n",
"my_report.get_visualization(property_name='Column Pair Trends')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "169f33e3-f1e3-4677-b092-742db80d9aa6",
"metadata": {},
"outputs": [],
"source": [
"#saving and visualiztation data validity\n",
"my_report = DiagnosticReport()\n",
"my_report.generate(real_data, synthetic_data, metadata)\n",
"my_report.save(filepath='CopulaGAN_Results/Hulk/diagnostic.pkl')\n",
"my_report.get_visualization('Data Validity')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a46d7cdd-d907-4a49-bb8a-cac585c1776b",
"metadata": {},
"outputs": [],
"source": [
"#statistical similarity metric\n",
"sstest=[]\n",
"for i in real_data.columns:\n",
" y=StatisticSimilarity.compute(\n",
" real_data=real_data[i],\n",
" synthetic_data=synthetic_data[i],\n",
" statistic='median'\n",
" )\n",
" sstest.append(y)\n",
"\n",
"df = pd.DataFrame(sstest, columns=['SS Test'])\n",
"\n",
"print(df['SS Test'].mean())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c23e2399-5b2c-40aa-9ce7-1bc36ccbe119",
"metadata": {},
"outputs": [],
"source": [
"#range coverage metric\n",
"range_coverage=[]\n",
"for i in real_data.columns:\n",
" \n",
" y=RangeCoverage.compute(\n",
" real_data=real_data[i],\n",
" synthetic_data=synthetic_data[i]\n",
" )\n",
" range_coverage.append(y)\n",
"df = pd.DataFrame(range_coverage, columns=['Range Coverage'])\n",
"\n",
"print(df['Range Coverage'].mean())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d7e00eb7-5133-4374-a7dc-1d131ddc387f",
"metadata": {},
"outputs": [],
"source": [
"# checking the number of unique synthetic data instances\n",
"df = pd.concat([real_data, synthetic_data], axis=0)\n",
"print(df.shape)\n",
"df.dropna(inplace=True)\n",
"df.drop_duplicates(inplace=True)\n",
"print(df.shape)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "85b532bf-91f1-4cb5-8fee-7a74d71a000c",
"metadata": {},
"outputs": [],
"source": [
"#Saving the distribution of each column\n",
"def sanitize_column_name(column_name):\n",
" valid_chars = \"-_.() %s%s\" % (string.ascii_letters, string.digits)\n",
" return ''.join(c for c in column_name if c in valid_chars)\n",
"\n",
"for i in real_data.columns:\n",
" fig = get_column_plot(\n",
" real_data=real_data,\n",
" synthetic_data=synthetic_data,\n",
" column_name=i,\n",
" plot_type='bar'\n",
" )\n",
"\n",
" sanitized_column_name = sanitize_column_name(i)\n",
"\n",
" # Save the figure in the 'Pics' directory, change the location accordingly\n",
" py.write_image(fig, os.path.join('CopulaGAN_Results/Hulk/Pics', f\"{sanitized_column_name}.png\")) \n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "edf6097f-6274-4a32-8b13-c91cea49166f",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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": "3.8.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}