/
eval.py
46 lines (39 loc) · 1.57 KB
/
eval.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
import sys
import os
import json
import pandas
import numpy
import optparse
from keras.models import Sequential, load_model
from keras.preprocessing import sequence
from keras.preprocessing.text import Tokenizer
from collections import OrderedDict
def predict(csv_file, log_entry):
# Loading processed word dictionary into keras Tokenizer would be better
dataframe = pandas.read_csv(csv_file, engine='python', quotechar='|', header=None)
dataset = dataframe.values
# Preprocess dataset
X = dataset[:,0]
for index, item in enumerate(X):
reqJson = json.loads(item, object_pairs_hook=OrderedDict, strict=False)
X[index] = json.dumps(reqJson, separators=(',', ':'))
tokenizer = Tokenizer(filters='\t\n', char_level=True)
tokenizer.fit_on_texts(X)
seq = tokenizer.texts_to_sequences([log_entry])
max_log_length = 1024
log_entry_processed = sequence.pad_sequences(seq, maxlen=max_log_length)
model = load_model('malicious-requests-model.h5')
model.load_weights('malicious-requests-weights.h5')
model.compile(loss = 'binary_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
prediction = model.predict(log_entry_processed)
print(prediction[0])
if __name__ == '__main__':
parser = optparse.OptionParser()
parser.add_option('-f', '--file', action="store", dest="file", help="data file")
options, args = parser.parse_args()
if options.file is not None:
csv_file = options.file
else:
csv_file = 'data/training.csv'
if args[0] is not None:
predict(csv_file, args[0])