samples_count_by_month.py

# -*- coding: UTF-8 -*-.
import argparse
import csv
import datetime

def params():
    parser = argparse.ArgumentParser()
    parser.add_argument('input_csv', help='Input CSV Location')
    params = parser.parse_args()
    return params.input_csv

def update_counter(counter, key):
    if key in counter:
        counter[key] += 1
    else:
        counter[key] = 1

counter_gw = {}
counter_mw = {}

# get params
input_csv = params()
with open(input_csv, 'rb') as file:
    reader = csv.DictReader(file)
    for row in reader:
        # convert timestamp
        time = datetime.datetime.fromtimestamp(float(row["Time"]))
        year = int(time.strftime('%Y'))
        if year < 2013:
            if row["Label"] == "1":
                update_counter(counter_mw, "<2013")
            else:
                update_counter(counter_gw, "<2013")
        else:
            if year > 2017:
                if row["Label"] == "1":
                    update_counter(counter_mw, ">2017")
                else:
                    update_counter(counter_gw, ">2017")
            else :
                time = time.strftime('%m.%Y')
                if row["Label"] == "1":
                    update_counter(counter_mw, time)
                else:
                    update_counter(counter_gw, time)

# write table
print "Year\tGoodware\tMalware"
print "<2013\t" + str(counter_gw["<2013"]) + "\t0"
for y in range(2013,2018):
    for m in range(1,13):
        my = str(m).zfill(2)+"."+str(y)
        if my in counter_gw:
            gw = counter_gw[my]
        else:
            gw = 0
        if my in counter_mw:
            mw = counter_mw[my]
        else:
            mw = 0
        print my + "\t" + str(gw) + "\t" + str(mw)
print ">2017\t" + str(counter_gw[">2017"]) + "\t" + str(counter_mw[">2017"])