diff --git a/TGAN/.gitkeep b/TGAN/.gitkeep
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/TGAN/TGAN.ipynb b/TGAN/TGAN.ipynb
deleted file mode 100644
index 2a6038a592fb521e58da9fcbecb216ec9be822c1..0000000000000000000000000000000000000000
--- a/TGAN/TGAN.ipynb
+++ /dev/null
@@ -1,226 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "fefebe4b",
- "metadata": {},
- "outputs": [],
- "source": [
- "#https://github.com/sdv-dev/TGAN/tree/master\n",
- "import pandas as pd\n",
- "from tgan.data import load_demo_data\n",
- "from tgan.model import TGANModel\n",
- "import tensorflow as tf\n",
- "import numpy as np"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "a345cefc",
- "metadata": {},
- "outputs": [],
- "source": [
- "#loading datasets\n",
- "def load_data(location):\n",
- " data = pd.read_csv(location)\n",
- " data_columns = data.columns\n",
- " data = preprocessing(data)\n",
- " return data, data_columns\n",
- "\n",
- "\n",
- "#Dataset preprocessing\n",
- "def preprocessing(data):\n",
- " \n",
- " \"\"\"\n",
- " dropping duplicate values\n",
- " changing timeformat to d/m/Y H:M:S and then to Unix fomrat that starts from 1970/1/ 00:00:00\n",
- " making sure that numeric columns only have numeric values and if not numeric then to NaN\n",
- " dropping all NaN values \n",
- " \"\"\"\n",
- " print(\"Shape of data before preprocessing:\", data.shape)\n",
- " data.drop_duplicates(inplace=True) #dropping duplicated\n",
- " data.replace([np.inf, -np.inf], np.nan, inplace=True)# changing inf and -inf to nan\n",
- "\n",
- " data['Timestamp'] = pd.to_datetime(data['Timestamp'], format='%d/%m/%Y %H:%M:%S', errors='coerce')\n",
- " data['Timestamp'] = (data['Timestamp'] - pd.Timestamp(\"1970-01-01\")) // pd.Timedelta('1s') \n",
- "\n",
- " for col in data.columns: #changing columns to numeric if not, then to NaN\n",
- " if data[col].dtype == 'object' and col != 'Label':\n",
- " data[col] = pd.to_numeric(data[col], errors='coerce')\n",
- " \n",
- " \n",
- " \n",
- " data.dropna(inplace=True) #droping Na\n",
- " \n",
- " print(\"Shape of data after preprocessing:\", data.shape)\n",
- " \n",
- " return data"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "41dfaeff",
- "metadata": {},
- "outputs": [],
- "source": [
- "def tGAN(data, continuous_columns,max_epoch=5, steps_per_epoch=10000, batch_size=200, z_dim=200, noise=0.2, l2norm=0.00001, \n",
- " learning_rate=0.001, num_gen_rnn=100, num_gen_feature=100, num_dis_layers=1, num_dis_hidden=100, \n",
- " optimizer='AdamOptimizer'):\n",
- " \n",
- " \"\"\"\n",
- " Required arguments to be passed:\n",
- " -data: dataframe with rows and columns\n",
- " -continuous_columns: a list containing all the columns that are continuous \n",
- " \"\"\"\n",
- "\n",
- " print(data.shape)\n",
- "\n",
- " tgan = TGANModel(continuous_columns=continuous_columns, max_epoch=max_epoch, steps_per_epoch=steps_per_epoch, \n",
- " batch_size=batch_size, z_dim=z_dim, noise=noise, l2norm=l2norm, learning_rate=learning_rate, \n",
- " num_gen_rnn=num_gen_rnn, num_gen_feature=num_gen_feature, num_dis_layers=num_dis_layers, \n",
- " num_dis_hidden=num_dis_hidden, optimizer=optimizer)\n",
- " \n",
- " tgan.fit(data)\n",
- "\n",
- " return tgan"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "07714e0c",
- "metadata": {},
- "outputs": [],
- "source": [
- "continuous_columns = [2, 3, 17, 18, 20, 21, 38, 39]\n",
- "\n",
- "data, data_columns = load_data(\"C:\\\\Users\\\\sayed\\\\Desktop\\\\Dataset\\\\02-14-2018.csv\")\n",
- "\n",
- "data = data[data[\"Label\"] == \"FTP-BruteForce\"]\n",
- "data.columns = [None] * len(data.columns) # revoming column names"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "95f316b5",
- "metadata": {},
- "outputs": [],
- "source": [
- "#fitting the TGAN model\n",
- "tgan= tGAN(data=data, continuous_columns=continuous_columns, batch_size=150, max_epoch = 15)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "d0b5a40e",
- "metadata": {},
- "outputs": [],
- "source": [
- "#Saving the model\n",
- "model_path = 'C:\\\\Users\\\\sayed\\\\Desktop\\\\Dataset\\\\models\\\\tGAN_model_firstrun.pkl'\n",
- "tgan.save(model_path)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "d7343348",
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "num_samples = 8000\n",
- "new_tgan = TGANModel.load(model_path)\n",
- "samples = new_tgan.sample(num_samples)\n",
- "samples.head()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "20667896",
- "metadata": {},
- "outputs": [],
- "source": [
- "#assinging back the column names\n",
- "samples.columns = data_columns\n",
- "data.columns = data_columns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "4bdf2761",
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "8423e0de",
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "9ae7fce1",
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "d2fd753c",
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "06a0123c",
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "ebf1c5cd",
- "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": "3.7.16"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
diff --git a/TGAN/mymodel_17_12.pkl b/TGAN/mymodel_17_12.pkl
deleted file mode 100644
index e7c968357447bb6e37c68fbe5bbad51f67447bbe..0000000000000000000000000000000000000000
Binary files a/TGAN/mymodel_17_12.pkl and /dev/null differ