Internet Firewall Data Data Set - دست نوشته‌های امیر

Internet Firewall Data Data Set

github link : https://github.com/amirshnll/Internet-Firewall
dataset link : http://archive.ics.uci.edu/ml/datasets/Internet+Firewall+Data

# Author : Amir Shokri
# github link : https://github.com/amirshnll/Internet-Firewall
# dataset link : http://archive.ics.uci.edu/ml/datasets/Internet+Firewall+Data
# email : amirsh.nll@gmail.com

# Author : Amir Shokri

# github link : https://github.com/amirshnll/Internet-Firewall

# dataset link : http://archive.ics.uci.edu/ml/datasets/Internet+Firewall+Data

# email : amirsh.nll@gmail.com

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np


df = pd.read_csv('firewall.csv')
df

import pandas as pd

import seaborn as sns

import matplotlib.pyplot as plt

import numpy as np

df = pd.read_csv('firewall.csv')

df.info()

df.info()

<class ‘pandas.core.frame.DataFrame’>
RangeIndex: 65532 entries, 0 to 65531
Data columns (total 12 columns):
# Column Non-Null Count Dtype
— —— ————– —–
0 Source Port 65532 non-null int64
1 Destination Port 65532 non-null int64
2 NAT Source Port 65532 non-null int64
3 NAT Destination Port 65532 non-null int64
4 Action 65532 non-null object
5 Bytes 65532 non-null int64
6 Bytes Sent 65532 non-null int64
7 Bytes Received 65532 non-null int64
8 Packets 65532 non-null int64
9 Elapsed Time (sec) 65532 non-null int64
10 pkts_sent 65532 non-null int64
11 pkts_received 65532 non-null int64
dtypes: int64(11), object(1)
memory usage: 6.0+ MB

y = df['Action'].values
y = y.reshape(-1,1)
x_data = df.drop(['Action'],axis = 1)
print(x_data)

y = df['Action'].values

y = y.reshape(-1,1)

x_data = df.drop(['Action'],axis = 1)

print(x_data)

sns.countplot(x='Action',data=df,palette='hls')
plt.show()

1 2	sns.countplot(x='Action',data=df,palette='hls') plt.show()

Internet Firewall Data Data Set - fig 1 — Internet Firewall Data Data Set – fig 1

#normalize data

x = (x_data - np.min(x_data)) / (np.max(x_data) / np.min(x_data)).values
x.head()

#normalize data

x = (x_data - np.min(x_data)) / (np.max(x_data) / np.min(x_data)).values

x.head()

#data train & data test
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.3,random_state= 300)
print("x_train",x_train.shape)
print("x_test",x_test.shape)
print("y_train",y_train.shape)
print("y_test",y_test.shape)

#data train & data test

from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.3,random_state= 300)

print("x_train",x_train.shape)

print("x_test",x_test.shape)

print("y_train",y_train.shape)

print("y_test",y_test.shape)

x_train (45872, 11)
x_test (19660, 11)
y_train (45872, 1)
y_test (19660, 1)

#decision tree classifier

from sklearn.tree import DecisionTreeClassifier
from sklearn import metrics
from sklearn import preprocessing
from sklearn.metrics import accuracy_score

dt = DecisionTreeClassifier()
dt = dt.fit(x_train,y_train)
y_forecast=dt.predict(x_test)

from sklearn.metrics import classification_report
print(classification_report(y_test, dt.predict(x_test)))
print('accuracy:{:.4f}'.format(dt.score(x_test, y_test)))

from sklearn import tree
plt.figure(figsize=(30,30))
temp = tree.plot_tree(dt.fit(x,y), fontsize=10)
plt.show()

#decision tree classifier

from sklearn.tree import DecisionTreeClassifier

from sklearn import metrics

from sklearn import preprocessing

from sklearn.metrics import accuracy_score

dt = DecisionTreeClassifier()

dt = dt.fit(x_train,y_train)

y_forecast=dt.predict(x_test)

from sklearn.metrics import classification_report

print(classification_report(y_test, dt.predict(x_test)))

print('accuracy:{:.4f}'.format(dt.score(x_test, y_test)))

from sklearn import tree

plt.figure(figsize=(30,30))

temp = tree.plot_tree(dt.fit(x,y), fontsize=10)

plt.show()

              precision    recall  f1-score   support

       allow       0.99      0.96      0.98     11381
        deny       0.75      0.98      0.85      4456
        drop       0.88      0.67      0.76      3808
  reset-both       0.83      0.33      0.48        15

    accuracy                           0.91     19660
   macro avg       0.87      0.74      0.77     19660
weighted avg       0.92      0.91      0.91     19660

accuracy:0.9074

precision recall f1-score support

allow 0.99 0.96 0.98 11381

deny 0.75 0.98 0.85 4456

drop 0.88 0.67 0.76 3808

reset-both 0.83 0.33 0.48 15

accuracy 0.91 19660

macro avg 0.87 0.74 0.77 19660

weighted avg 0.92 0.91 0.91 19660

accuracy:0.9074

Internet Firewall Data Data Set - fig 2 — Internet Firewall Data Data Set – fig 2

#Nave Bayes Classifier

from sklearn.naive_bayes import GaussianNB

nb = GaussianNB()
nb = nb.fit(x_train, y_train.ravel())
y_forecast=nb.predict(x_test)

from sklearn.metrics import classification_report
print(classification_report(y_test, nb.predict(x_test)))
print('Nave Bayes Classifier{:.4f}'.format(nb.score(x_test, y_test)))

#Nave Bayes Classifier

from sklearn.naive_bayes import GaussianNB

nb = GaussianNB()

nb = nb.fit(x_train, y_train.ravel())

y_forecast=nb.predict(x_test)

from sklearn.metrics import classification_report

print(classification_report(y_test, nb.predict(x_test)))

print('Nave Bayes Classifier{:.4f}'.format(nb.score(x_test, y_test)))

              precision    recall  f1-score   support

       allow       1.00      0.36      0.53     11381
        deny       0.11      0.14      0.12      4456
        drop       0.37      1.00      0.54      3808
  reset-both       0.00      0.00      0.00        15

    accuracy                           0.43     19660
   macro avg       0.37      0.37      0.30     19660
weighted avg       0.68      0.43      0.44     19660

Nave Bayes Classifier0.4311

precision recall f1-score support

allow 1.00 0.36 0.53 11381

deny 0.11 0.14 0.12 4456

drop 0.37 1.00 0.54 3808

reset-both 0.00 0.00 0.00 15

accuracy 0.43 19660

macro avg 0.37 0.37 0.30 19660

weighted avg 0.68 0.43 0.44 19660

Nave Bayes Classifier0.4311

#Logistic Regreession Classifier

from sklearn.linear_model import LogisticRegression

lr = LogisticRegression(solver='lbfgs')
lr = lr.fit(x_train, y_train.ravel())
y_forecast=lr.predict(x_test)


from sklearn.metrics import classification_report
print(classification_report(y_test, lr.predict(x_test)))
print('accuracy:{:.4f}'.format(lr.score(x_test, y_test)))

#Logistic Regreession Classifier

from sklearn.linear_model import LogisticRegression

lr = LogisticRegression(solver='lbfgs')

lr = lr.fit(x_train, y_train.ravel())

y_forecast=lr.predict(x_test)

from sklearn.metrics import classification_report

print(classification_report(y_test, lr.predict(x_test)))

print('accuracy:{:.4f}'.format(lr.score(x_test, y_test)))

              precision    recall  f1-score   support

       allow       0.58      1.00      0.73     11381
        deny       0.00      0.00      0.00      4456
        drop       0.00      0.00      0.00      3808
  reset-both       0.00      0.00      0.00        15

    accuracy                           0.58     19660
   macro avg       0.14      0.25      0.18     19660
weighted avg       0.34      0.58      0.42     19660

accuracy:0.5789

precision recall f1-score support

allow 0.58 1.00 0.73 11381

deny 0.00 0.00 0.00 4456

drop 0.00 0.00 0.00 3808

reset-both 0.00 0.00 0.00 15

accuracy 0.58 19660

macro avg 0.14 0.25 0.18 19660

weighted avg 0.34 0.58 0.42 19660

accuracy:0.5789

#Knn Classifier
from sklearn.neighbors import KNeighborsClassifier
K = 1
knn = KNeighborsClassifier(n_neighbors=K)
knn = knn.fit(x_train,y_train.ravel())
print("k = {}neighbors , knn test:{}".format(K, knn.score(x_test, y_test)))
print("knn = {}neighbors , knn train:{}".format(K, knn.score(x_train, y_train)))

ran = np.arange(1,40)
train_list = []
test_list = []
for i,each in enumerate(ran):
    knn = KNeighborsClassifier(n_neighbors=each)
    knn = knn.fit(x_train, y_train.ravel())
    test_list.append(knn.score(x_test, y_test))
    train_list.append(knn.score(x_train, y_train))
    
print("best test {} , k={}".format(np.max(test_list),test_list.index(np.max(test_list))+1))
print("best train {} , k={}".format(np.max(train_list),train_list.index(np.max(train_list))+1))

#Knn Classifier

from sklearn.neighbors import KNeighborsClassifier

K = 1

knn = KNeighborsClassifier(n_neighbors=K)

knn = knn.fit(x_train,y_train.ravel())

print("k = {}neighbors , knn test:{}".format(K, knn.score(x_test, y_test)))

print("knn = {}neighbors , knn train:{}".format(K, knn.score(x_train, y_train)))

ran = np.arange(1,40)

train_list = []

test_list = []

for i,each in enumerate(ran):

knn = KNeighborsClassifier(n_neighbors=each)

knn = knn.fit(x_train, y_train.ravel())

test_list.append(knn.score(x_test, y_test))

train_list.append(knn.score(x_train, y_train))

print("best test {} , k={}".format(np.max(test_list),test_list.index(np.max(test_list))+1))

print("best train {} , k={}".format(np.max(train_list),train_list.index(np.max(train_list))+1))

k = 1neighbors , knn test:0.8978128179043744
knn = 1neighbors , knn train:0.8984129752354377

#mlp classifier
from sklearn.neural_network import MLPClassifier
clfm = MLPClassifier(hidden_layer_sizes=(5,), max_iter=1000)
clfm.fit(x_train, y_train.ravel())
y_predm = clfm.predict(x_test)
print("ACCTURACY:", metrics.accurecy_score(y_test, y_predm))
print(classification_report(y_test, clfk.predict(x_test)))
print("mlp:", clfk.score(x_test, y_test))

#mlp classifier

from sklearn.neural_network import MLPClassifier