Malware_Classifier_For_PE_Files/01_data_preprocessing.py at master · Harsh-06/Malware_Classifier_For_PE_Files · GitHub

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
import operator
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.preprocessing import StandardScaler

def getXY(path):
    # getting unimp features
    unimp_features = {
     'AddressOfEntryPoint': 0,
     'BaseOfCode': 0,
     'BaseOfData': 0,
     'Characteristics': 1032.206797186472,
     'CheckSum': 0,
     'DllCharacteristics': 1478.4954869782816,
     'ExportNb': 0,
     'FileAlignment': 0,
     # 'ImageBase': 530.5361006533311,
     'ImageBase': 0,
     'ImportsNb': 0,
     'ImportsNbDLL': 0,
     'ImportsNbOrdinal': 0,
     'LoadConfigurationSize': 0,
     'LoaderFlags': 0,
     'Machine': 1082.9256010888016,
     'MajorImageVersion': 0,
     'MajorLinkerVersion': 0,
     'MajorOperatingSystemVersion': 236.61647685302975,
     'MajorSubsystemVersion': 487.3898733331374,
     'MinorImageVersion': 0,
     'MinorLinkerVersion': 0,
     'MinorOperatingSystemVersion': 0,
     'MinorSubsystemVersion': 0,
     'Name': 0,
     'NumberOfRvaAndSizes': 0,
     'ResourcesMaxEntropy': 441.8248905853912,
     'ResourcesMaxSize': 0,
     'ResourcesMeanEntropy': 0,
     'ResourcesMeanSize': 0,
     'ResourcesMinEntropy': 353.224684768646,
     'ResourcesMinSize': 8.160597671881105,
     'ResourcesNb': 0,
     'SectionAlignment': 0,
     'SectionMaxRawsize': 0,
     'SectionMaxVirtualsize': 0,
     'SectionsMaxEntropy': 580.740479410044,
     'SectionsMeanEntropy': 72.19620856510386,
     'SectionsMeanRawsize': 0,
     'SectionsMeanVirtualsize': 0,
     'SectionsMinEntropy': 158.0840575679675,
     'SectionsMinRawsize': 0,
     'SectionsMinVirtualsize': 0,
     'SectionsNb': 7.795926354766131,
     'SizeOfCode': 0,
     'SizeOfHeaders': 0,
     'SizeOfHeapCommit': 0,
     'SizeOfHeapReserve': 0,
     'SizeOfImage': 0,
     'SizeOfInitializedData': 0,
     'SizeOfOptionalHeader': 393.1119115064255,
     'SizeOfStackCommit': 0,
     'SizeOfStackReserve': 93.14759692294628,
     'SizeOfUninitializedData': 0,
     'Subsystem': 590.0487097835594,
     'VersionInformationSize': 648.0362688739431,
     'md5': 0}
    unimp_features = sorted(unimp_features.items(), key=operator.itemgetter(1))
    unimp_features.reverse()
    unimp_features = unimp_features[16:]
    for i in range(len(unimp_features)):
        unimp_features[i] = unimp_features[i][0]

    # reading data
    dataset = pd.read_csv(path)
    dataset = dataset[dataset.columns.difference(unimp_features)]
    X = dataset.iloc[:,:-1].values
    y = dataset.iloc[:,-1].values

    # one-hot encoding (Categorical Data)
    from sklearn.preprocessing import LabelEncoder, OneHotEncoder
    labelencoder_X = LabelEncoder()

    # Label encoding
    X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
    X[:, 1] = labelencoder_X.fit_transform(X[:, 1])
    X[:, 2] = labelencoder_X.fit_transform(X[:, 2])
    X[:, 3] = labelencoder_X.fit_transform(X[:, 3])
    X[:, 4] = labelencoder_X.fit_transform(X[:, 4])
    X[:, 14] = labelencoder_X.fit_transform(X[:, 14])

    for i in range(len(X[:, 14])):
        X[i, 14], X[i, 5] = X[i, 5], X[i, 14]

    onehotencoder = OneHotEncoder()
    Z = onehotencoder.fit_transform(X[:, :1]).toarray()
    Z = Z[:, 1:]
    X = X[:, 1:]

    W = onehotencoder.fit_transform(X[:, :1]).toarray()
    W = W[:, 1:]
    X = X[:, 1:]
    Z = np.concatenate((Z, W), 1)

    W = onehotencoder.fit_transform(X[:, :1]).toarray()
    W = W[:, 1:]
    X = X[:, 1:]
    Z = np.concatenate((Z, W), 1)

    W = onehotencoder.fit_transform(X[:, :1]).toarray()
    W = W[:, 1:]
    X = X[:, 1:]
    Z = np.concatenate((Z, W), 1)

    W = onehotencoder.fit_transform(X[:, :1]).toarray()
    W = W[:, 1:]
    X = X[:, 1:]
    Z = np.concatenate((Z, W), 1)

    W = onehotencoder.fit_transform(X[:, :1]).toarray()
    W = W[:, 1:]
    X = X[:, 1:]
    Z = np.concatenate((Z, W), 1)

    X = np.concatenate((Z, X), 1)

    # Scaling
    sc_X = StandardScaler()
    X = sc_X.fit_transform(X)

    return X, y

X, y = getXY('/home/yash/Documents/Malware_Classifier_For_PE_Files/cleaned_data.csv')

# train test split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

### ----------------- RF -------------------- ###
from Models.Logistic import Logistic
model = Logistic(X_train, y_train)

y_pred = model.predict(X_test)

count = 0
for i in range(len(y_pred)):
    if y_pred[i] == y_test[i]:
        count += 1

acc = (count / len(y_pred)) * 100
print('Logistic Reg: {}'.format(acc))

### ----------------------------------------- ###