SSH-Master-Thesis/ethan_data_processing_scripts/runtests.py

#!/usr/bin/python3
import sys
import Vector
import sample
import nearestneighbors


# test classifications on a pickled file of samples and denoting active features with
# sample codes, ex: high.total_packets
# Usage: main.py pickled_sample_file high.total_packets high.time_spent...
def main():
    i = 0
    sampleList = Vector.readPickledData(sys.argv[1])
    featureList = []
    classifications = []
    for s in sampleList:
        v = Vector.FeatureVector(s)
        featureList.append(v)
        classifications.append(v.classification)
    activeFeatureStrings = []
    for i in range(2, len(sys.argv)):
        activeFeatureStrings.append(sys.argv[i])
    for f in featureList:
        f.set_features(activeFeatureStrings)
    # perform classification on f here
    nearestneighbors.kNearestNeighbors(featureList[:8 * len(featureList)//10], classifications[:8 * len(classifications)//10], featureList[8 * len(featureList)//10:])


if __name__ == '__main__':
    main()