Skip to content

Commit 4dac778

Browse files
yasakramiyasakrami
committed
upload
0 parents  commit 4dac778

5 files changed

+1579
-0
lines changed

‎AttackDivision.ipynb

+227
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,227 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 3,
6+
"id": "61949a39",
7+
"metadata": {},
8+
"outputs": [
9+
{
10+
"name": "stdout",
11+
"output_type": "stream",
12+
"text": [
13+
"Saved Bot_vs_BENIGN.csv\n",
14+
"Saved DDoS_vs_BENIGN.csv\n",
15+
"Saved DoS GoldenEye_vs_BENIGN.csv\n",
16+
"Saved DoS Hulk_vs_BENIGN.csv\n",
17+
"Saved DoS Slowhttptest_vs_BENIGN.csv\n",
18+
"Saved DoS slowloris_vs_BENIGN.csv\n",
19+
"Saved FTP-Patator_vs_BENIGN.csv\n",
20+
"Saved Heartbleed_vs_BENIGN.csv\n",
21+
"Saved Infiltration_vs_BENIGN.csv\n",
22+
"Saved PortScan_vs_BENIGN.csv\n",
23+
"Saved SSH-Patator_vs_BENIGN.csv\n",
24+
"Saved Web Attack – Brute Force_vs_BENIGN.csv\n",
25+
"Saved Web Attack – Sql Injection_vs_BENIGN.csv\n",
26+
"Saved Web Attack – XSS_vs_BENIGN.csv\n",
27+
"Execution time: 736.30 seconds\n"
28+
]
29+
}
30+
],
31+
"source": [
32+
"# Importing the libraries\n",
33+
"import pandas as pd\n",
34+
"import numpy as np\n",
35+
"import time\n",
36+
"from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
37+
"from sklearn.utils import resample\n",
38+
"from sklearn import preprocessing\n",
39+
"from warnings import simplefilter\n",
40+
"from imblearn.under_sampling import RandomUnderSampler\n",
41+
"\n",
42+
"# Suppress FutureWarning messages\n",
43+
"simplefilter(action='ignore', category=FutureWarning)\n",
44+
"\n",
45+
"# Record start time\n",
46+
"start_time = time.time()\n",
47+
"\n",
48+
"# Load the main dataset (all_data.csv)\n",
49+
"main_dataset = pd.read_csv(\"combined_data.csv\")\n",
50+
"\n",
51+
"# List of attack types and BENIGN\n",
52+
"attack_types = [\"Bot\", \"DDoS\", \"DoS GoldenEye\", \"DoS Hulk\", \"DoS Slowhttptest\", \"DoS slowloris\", \"FTP-Patator\",\n",
53+
" \"Heartbleed\", \"Infiltration\", \"PortScan\", \"SSH-Patator\", \"Web Attack – Brute Force\",\n",
54+
" \"Web Attack – Sql Injection\", \"Web Attack – XSS\"]\n",
55+
"benign_type = \"BENIGN\"\n",
56+
"\n",
57+
"# Loop through each attack type\n",
58+
"for attack_type in attack_types:\n",
59+
" # Create a DataFrame for the current attack type\n",
60+
" attack_data = main_dataset[main_dataset[\" Label\"] == attack_type]\n",
61+
" \n",
62+
" # Create a DataFrame for BENIGN data\n",
63+
" benign_data = main_dataset[main_dataset[\" Label\"] == benign_type]\n",
64+
" \n",
65+
" # Concatenate the attack and benign data\n",
66+
" combined_data = pd.concat([attack_data, benign_data], axis=0)\n",
67+
" \n",
68+
" # Shuffle the combined data\n",
69+
" combined_data = combined_data.sample(frac=1, random_state=42)\n",
70+
" \n",
71+
" # Save the combined data to a CSV file\n",
72+
" output_filename = f\"{attack_type}_vs_{benign_type}.csv\"\n",
73+
" combined_data.to_csv(output_filename, index=False)\n",
74+
" print(f\"Saved {output_filename}\")\n",
75+
"\n",
76+
"# Calculate and print the execution time\n",
77+
"end_time = time.time()\n",
78+
"execution_time = end_time - start_time\n",
79+
"print(f\"Execution time: {execution_time:.2f} seconds\")\n"
80+
]
81+
},
82+
{
83+
"cell_type": "code",
84+
"execution_count": 2,
85+
"id": "a456a074",
86+
"metadata": {},
87+
"outputs": [
88+
{
89+
"name": "stdout",
90+
"output_type": "stream",
91+
"text": [
92+
"File: Bot_vs_BENIGN.csv\n",
93+
"Number of Benign instances: 1741839\n",
94+
"Number of Attack instances: 1956\n",
95+
"Shape of the dataset: (1743795, 85)\n",
96+
"-----------------------------\n",
97+
"File: DDoS_vs_BENIGN.csv\n",
98+
"Number of Benign instances: 1741839\n",
99+
"Number of Attack instances: 128025\n",
100+
"Shape of the dataset: (1869864, 85)\n",
101+
"-----------------------------\n",
102+
"File: DoS GoldenEye_vs_BENIGN.csv\n",
103+
"Number of Benign instances: 1741839\n",
104+
"Number of Attack instances: 10293\n",
105+
"Shape of the dataset: (1752132, 85)\n",
106+
"-----------------------------\n",
107+
"File: DoS Hulk_vs_BENIGN.csv\n",
108+
"Number of Benign instances: 1741839\n",
109+
"Number of Attack instances: 230124\n",
110+
"Shape of the dataset: (1971963, 85)\n",
111+
"-----------------------------\n",
112+
"File: DoS Slowhttptest_vs_BENIGN.csv\n",
113+
"Number of Benign instances: 1741839\n",
114+
"Number of Attack instances: 5499\n",
115+
"Shape of the dataset: (1747338, 85)\n",
116+
"-----------------------------\n",
117+
"File: DoS slowloris_vs_BENIGN.csv\n",
118+
"Number of Benign instances: 1741839\n",
119+
"Number of Attack instances: 5796\n",
120+
"Shape of the dataset: (1747635, 85)\n",
121+
"-----------------------------\n",
122+
"File: FTP-Patator_vs_BENIGN.csv\n",
123+
"Number of Benign instances: 1741839\n",
124+
"Number of Attack instances: 7935\n",
125+
"Shape of the dataset: (1749774, 85)\n",
126+
"-----------------------------\n",
127+
"File: Heartbleed_vs_BENIGN.csv\n",
128+
"Number of Benign instances: 1741839\n",
129+
"Number of Attack instances: 11\n",
130+
"Shape of the dataset: (1741850, 85)\n",
131+
"-----------------------------\n",
132+
"File: Infiltration_vs_BENIGN.csv\n",
133+
"Number of Benign instances: 1741839\n",
134+
"Number of Attack instances: 36\n",
135+
"Shape of the dataset: (1741875, 85)\n",
136+
"-----------------------------\n",
137+
"File: PortScan_vs_BENIGN.csv\n",
138+
"Number of Benign instances: 1741839\n",
139+
"Number of Attack instances: 158804\n",
140+
"Shape of the dataset: (1900643, 85)\n",
141+
"-----------------------------\n",
142+
"File: SSH-Patator_vs_BENIGN.csv\n",
143+
"Number of Benign instances: 1741839\n",
144+
"Number of Attack instances: 5897\n",
145+
"Shape of the dataset: (1747736, 85)\n",
146+
"-----------------------------\n",
147+
"File: Web Attack – Brute Force_vs_BENIGN.csv\n",
148+
"Number of Benign instances: 1741839\n",
149+
"Number of Attack instances: 1507\n",
150+
"Shape of the dataset: (1743346, 85)\n",
151+
"-----------------------------\n",
152+
"File: Web Attack – Sql Injection_vs_BENIGN.csv\n",
153+
"Number of Benign instances: 1741839\n",
154+
"Number of Attack instances: 21\n",
155+
"Shape of the dataset: (1741860, 85)\n",
156+
"-----------------------------\n",
157+
"File: Web Attack – XSS_vs_BENIGN.csv\n",
158+
"Number of Benign instances: 1741839\n",
159+
"Number of Attack instances: 652\n",
160+
"Shape of the dataset: (1742491, 85)\n",
161+
"-----------------------------\n"
162+
]
163+
}
164+
],
165+
"source": [
166+
"import pandas as pd\n",
167+
"import glob\n",
168+
"\n",
169+
"# List of file names\n",
170+
"file_names = [\n",
171+
" 'Bot_vs_BENIGN.csv', 'DDoS_vs_BENIGN.csv', 'DoS GoldenEye_vs_BENIGN.csv',\n",
172+
" 'DoS Hulk_vs_BENIGN.csv', 'DoS Slowhttptest_vs_BENIGN.csv',\n",
173+
" 'DoS slowloris_vs_BENIGN.csv', 'FTP-Patator_vs_BENIGN.csv',\n",
174+
" 'Heartbleed_vs_BENIGN.csv', 'Infiltration_vs_BENIGN.csv',\n",
175+
" 'PortScan_vs_BENIGN.csv', 'SSH-Patator_vs_BENIGN.csv',\n",
176+
" 'Web Attack – Brute Force_vs_BENIGN.csv',\n",
177+
" 'Web Attack – Sql Injection_vs_BENIGN.csv', 'Web Attack – XSS_vs_BENIGN.csv'\n",
178+
"]\n",
179+
"\n",
180+
"# Loop through each file\n",
181+
"for file_name in file_names:\n",
182+
" # Read the file using pandas\n",
183+
" data = pd.read_csv(file_name)\n",
184+
" \n",
185+
" # Count the number of benign and attack instances\n",
186+
" num_benign = (data[' Label'] == 'BENIGN').sum()\n",
187+
" num_attack = (data[' Label'] != 'BENIGN').sum()\n",
188+
" \n",
189+
" # Print information\n",
190+
" print(f\"File: {file_name}\")\n",
191+
" print(f\"Number of Benign instances: {num_benign}\")\n",
192+
" print(f\"Number of Attack instances: {num_attack}\")\n",
193+
" print(\"Shape of the dataset:\", data.shape)\n",
194+
" print(\"-----------------------------\")\n"
195+
]
196+
},
197+
{
198+
"cell_type": "code",
199+
"execution_count": null,
200+
"id": "b48fcc8f",
201+
"metadata": {},
202+
"outputs": [],
203+
"source": []
204+
}
205+
],
206+
"metadata": {
207+
"kernelspec": {
208+
"display_name": "Python 3 (ipykernel)",
209+
"language": "python",
210+
"name": "python3"
211+
},
212+
"language_info": {
213+
"codemirror_mode": {
214+
"name": "ipython",
215+
"version": 3
216+
},
217+
"file_extension": ".py",
218+
"mimetype": "text/x-python",
219+
"name": "python",
220+
"nbconvert_exporter": "python",
221+
"pygments_lexer": "ipython3",
222+
"version": "3.11.4"
223+
}
224+
},
225+
"nbformat": 4,
226+
"nbformat_minor": 5
227+
}

‎FeatureSelection.ipynb

+678
Large diffs are not rendered by default.

0 commit comments

Comments
 (0)