sp2014 / android-malware-detector Goto Github PK

Error while running ad_db.py

[!] Error occured with ./files/benign/sample_goodware.apk, 'NoneType' object does not support item assignment

• about feature_vector_new = model.transform(feature_vector),i don't understand what Dimensionality reduction way did you use？

• it always generate ERROR ：https://stackoverflow.com/questions/53147529/about-machine-learning-reshape-your-data-either-using-array-reshape-1-1

can you suggest step by step? how to start with prerequisites?

PS D:\Android-Malware-Detector-master> python feature_selection.py data.csv
Traceback (most recent call last):
File "feature_selection.py", line 30, in
lsvc = LinearSVC(C=0.01, penalty="l1", dual=False).fit(dataX, dataY)
File "C:\Users\Ali Al-Zaabi\Anaconda2\lib\site-packages\sklearn\svm\classes.py", line 237, in fit
self.loss, sample_weight=sample_weight)
File "C:\Users\Ali Al-Zaabi\Anaconda2\lib\site-packages\sklearn\svm\base.py", line 881, in fit_liblinear
" class: %r" % classes[0])
ValueError: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0

I am getting the following error, even after running add_db.py on both malware and goodware samples. Then i use create_data.py to create the data.csv table, finally when i run the feature_selection.py on data.csv I get the error qouted above, which to my understanding means that I only have 1 class (goodware) and it doesnt take into consideration (malware)