-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmalware_detection.py
338 lines (208 loc) · 8.3 KB
/
malware_detection.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
# -*- coding: utf-8 -*-
"""Malware_detection_all_classifiers(with proper docstrings).ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1ur0pkOM9G0AF_iqTF2ybeCuysjMvzA8q
"""
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error
from sklearn.metrics import r2_score
from sklearn.metrics import confusion_matrix
from google.colab import files
from sklearn.metrics import ConfusionMatrixDisplay
from mlxtend.plotting import plot_confusion_matrix
import matplotlib as mlt
mlt.rcParams['figure.dpi']=300
"""**Mounting Drive**"""
from google.colab import drive
drive.mount('/content/drive',force_remount=True)
"""**Reading and storing data for work**"""
malData= pd.read_csv("/content/drive/MyDrive/datasets/dataset_malwares.csv")
display(malData.shape)
malData.head()
"""**Analysing the data and dropping the columns**"""
malData.isnull().sum()
data1=malData.dropna(how='any',axis=0)
display(data1.shape)
malData.head()
data1["classification"].value_counts()
data1["classification"]=data1.classification.map({'benign':0,'malware':1})
data1.head()
malData["classification"].value_counts().plot(kind="pie",autopct="%1.1f%%")
plt.axis("equal")
plt.savefig('CLASSIFICATION.png')
#files.download('CLASSIFICATION.png')
feature= data1.drop(["hash","classification","vm_truncate_count","shared_vm","exec_vm","nvcsw","maj_flt","utime"],axis=1)
display(feature.shape)
feature.head()
target = data1["classification"]
target
"""**Scaling data for better results and less time complexity**"""
scaler = StandardScaler()
scaler.fit(feature.values)
scaler.mean_
scaled_feature = scaler.transform(feature.values)
scaled_feature
scaled_feature_df = pd.DataFrame(scaled_feature, columns = feature.columns)
scaled_feature_df.head()
"""**Splitting the datasets into training data and testing data**"""
x_train, x_test, y_train, y_test = train_test_split(scaled_feature_df, target , test_size=0.2, random_state=42)
"""**Logistic regression method**
"""
model=LogisticRegression()
model.fit(x_train,y_train)
y_pred=model.predict(x_test)
y_pred
cm=confusion_matrix(y_test, y_pred)
cm
figure, ax = plot_confusion_matrix(conf_mat = cm,show_absolute = False,show_normed = True,colorbar = True)
plt.savefig('Logistic_cm.png')
files.download('Logistic_cm.png')
model.score(x_test,y_test)
mean_squared_error(y_test,y_pred)
r2_score(y_test, y_pred)
print(classification_report(y_test, y_pred))
"""**Naive bayes theorm**"""
model=GaussianNB()
model.fit(x_train,y_train)
y_pred=model.predict(x_test)
y_pred
cm=confusion_matrix(y_test, y_pred)
cm
figure, ax = plot_confusion_matrix(conf_mat = cm,show_absolute = False,show_normed = True,colorbar = True)
plt.savefig('Naive_cm.png')
files.download('Naive_cm.png')
model.score(x_test,y_test)
mean_squared_error(y_test,y_pred)
r2_score(y_test, y_pred)
print(classification_report(y_test, y_pred))
"""**K-Neighbours**"""
model=KNeighborsClassifier()
model.fit(x_train,y_train)
y_pred=model.predict(x_test)
y_pred
cm=confusion_matrix(y_test, y_pred)
cm
figure, ax = plot_confusion_matrix(conf_mat = cm,show_absolute = False,show_normed = True,colorbar = True)
plt.savefig('KNN_cm.png')
files.download('KNN_cm.png')
model.score(x_test,y_test)
mean_squared_error(y_test,y_pred)
r2_score(y_test, y_pred)
print(classification_report(y_test, y_pred))
"""**Gradient Boosting**"""
model=GradientBoostingClassifier()
model.fit(x_train,y_train)
y_pred=model.predict(x_test)
y_pred
cm=confusion_matrix(y_test, y_pred)
cm
figure, ax = plot_confusion_matrix(conf_mat = cm,show_absolute = False,show_normed = True,colorbar = True)
plt.savefig('Gradient_cm.png')
files.download('Gradient_cm.png')
model.score(x_test,y_test)
mean_squared_error(y_test,y_pred)
r2_score(y_test, y_pred)
print(classification_report(y_test, y_pred))
"""**ADA Boosting**"""
model=AdaBoostClassifier()
model.fit(x_train,y_train)
y_pred=model.predict(x_test)
y_pred
cm=confusion_matrix(y_test, y_pred)
cm
figure, ax = plot_confusion_matrix(conf_mat = cm,show_absolute = False,show_normed = True,colorbar = True)
plt.savefig('ADA_cm.png')
files.download('ADA_cm.png')
model.score(x_test,y_test)
mean_squared_error(y_test,y_pred)
r2_score(y_test, y_pred)
print(classification_report(y_test, y_pred))
"""**Support Vector Classifier**"""
model=SVC()
model.fit(x_train,y_train)
y_pred=model.predict(x_test)
y_pred
cm=confusion_matrix(y_test, y_pred)
cm
figure, ax = plot_confusion_matrix(conf_mat = cm,show_absolute = False,show_normed = True,colorbar = True)
plt.savefig('SVC_cm.png')
files.download('SVC_cm.png')
model.score(x_test,y_test)
mean_squared_error(y_test,y_pred)
r2_score(y_test, y_pred)
print(classification_report(y_test, y_pred))
"""**Decision Tree**"""
model=DecisionTreeClassifier()
model.fit(x_train,y_train)
y_pred=model.predict(x_test)
y_pred
cm=confusion_matrix(y_test, y_pred)
cm
figure, ax = plot_confusion_matrix(conf_mat = cm,show_absolute = False,show_normed = True,colorbar = True)
plt.savefig('DT_cm.png')
files.download('DT_cm.png')
model.score(x_test,y_test)
mean_squared_error(y_test,y_pred)
r2_score(y_test, y_pred)
print(classification_report(y_test, y_pred))
"""**Random Forest**"""
model=RandomForestClassifier()
model.fit(x_train,y_train)
y_pred=model.predict(x_test)
y_pred
cm=confusion_matrix(y_test, y_pred)
cm
figure, ax = plot_confusion_matrix(conf_mat = cm,show_absolute = False,show_normed = True,colorbar = True)
plt.savefig('RF_cm.png')
files.download('RF_cm.png')
model.score(x_test,y_test)
mean_squared_error(y_test,y_pred)
r2_score(y_test, y_pred)
print(classification_report(y_test, y_pred))
"""**GRAPH PLOTTING**"""
mycolor = ['red', 'saddlebrown', 'maroon', 'olive', 'orange', 'green', 'darkslategrey', 'royalblue']
names = ['Logistic Regression','ADA Boosting', 'Gradient Boosting', 'K-Neighbours','Support Vector Classifier','Decision Tree','Random Forest','Naive Bayes',]
values = [0.8931333333333333, 1.0, 1.0, 0.9996, 0.9935333333333334, 1.0, 1.0, 0.6464333333333333]
plt.bar(range(len(names)), values, align='edge', width=0.5,color=mycolor)
plt.xticks(range(len(values)), names, rotation='vertical')
plt.title('ACCURACY')
plt.show()
names = ['Logistic Regression','ADA Boosting', 'Gradient Boosting', 'K-Neighbours','Support Vector Classifier','Decision Tree','Random Forest','Naive Bayes',]
values = [0.10686666666666667, 0.0, 0.0, 0.0004, 0.006466666666666667, 0.0, 0.0, 0.35356666666666664]
plt.bar(range(len(names)), values, align='edge', width=0.5,color=mycolor)
plt.xticks(range(len(values)), names, rotation='vertical')
plt.title('Mean Squared Error')
plt.show()
names = ['Logistic Regression','ADA Boosting', 'Gradient Boosting', 'K-Neighbours','Support Vector Classifier','Decision Tree','Random Forest','Naive Bayes',]
values = [0.89, 1.0, 1.0, 1.0, 0.99, 1.0, 1.0, 0.62]
plt.bar(range(len(names)), values, align='edge', width=0.5,color=mycolor)
plt.xticks(range(len(values)), names, rotation='vertical')
plt.title('F1 Score')
plt.show()
names = ['Logistic Regression','ADA Boosting', 'Gradient Boosting', 'K-Neighbours','Support Vector Classifier','Decision Tree','Random Forest','Naive Bayes',]
values = [0.5725315075679056, 1.0, 1.0, 0.998399993166193, 0.974133222853454, 1.0, 1.0, -0.4142727071825403]
plt.bar(range(len(names)), values, align='edge', width=0.5,color=mycolor)
plt.xticks(range(len(values)), names, rotation='vertical')
plt.title('R2 Score')
plt.show()
names = ['Logistic Regression','ADA Boosting', 'Gradient Boosting', 'K-Neighbours','Support Vector Classifier','Decision Tree','Random Forest','Naive Bayes',]
values = [0.89, 1.0, 1.0, 1.0, 0.99, 1.0, 1.0, 0.71]
plt.bar(range(len(names)), values, align='edge', width=0.5,color=mycolor)
plt.xticks(range(len(values)), names, rotation='vertical')
plt.title('Precision')
plt.show()