Torrent_uploads_ascii_graphing

# more info here:
# http://raspberrypibeginner.wordpress.com/

import time
start_time = time.time()

import re
print time.time() - start_time, "seconds after regex load"
import scitools.aplotter
print time.time() - start_time, "seconds after plot load"
import csv
print time.time() - start_time, "seconds after csv load"
import datetime
print time.time() - start_time, "seconds after datetime load"


data_input_path = '/media/USBHDD/PythonStudy/torrent_data_collection/data_one.csv'
# later add: /media/USBHDD/PythonStudy/torrent_data_collection/

time_string_axis = []
upload_bytes_axis = []
# Constant
current_time_obj = datetime.datetime.now()

# Gathering data simply
with open(data_input_path, 'rb') as csvfile:
        raw_torrenting_data = csv.reader(csvfile, delimiter=',')
        # print time.time() - start_time, "seconds before regex"
        for data_array in raw_torrenting_data:
                for each_entry in data_array:
                        parse_data_point = re.search(r'(\d+-\d\d-\d\d\s\d\d:\d\d:\d\d)\$(\d+)', each_entry)

                        # time = parse_data_point.group(1)
                        # uploaded_bytes = parse_data_point.group(2)
                        # print type(parse_data_point)
                        if str(type(parse_data_point)) == "<type '_sre.SRE_Match'>":
                                time_string_axis.append(parse_data_point.group(1))
                                upload_bytes_axis.append(parse_data_point.group(2))
        # print time.time() - start_time, "seconds after regex"

def make_time_obj(string_a):
        # turn each string in time_string_axis into a time object
        return datetime.datetime.strptime(string_a, '%Y-%m-%d %X')

def convert_timestrings_to_hours_ago(array_of_strings):
        difference_array = []
        for time_string in array_of_strings:
                diff_obj = current_time_obj - make_time_obj(time_string)
                # plus 4 because of UTC, other object was created
                # with incompattible gmtime, this is the easiest conversion
                hour_difference = (4 + diff_obj.days * 24 + (diff_obj.seconds/3600.))
                difference_array.append(float('%.2f' % hour_difference))
        return difference_array

# print sorted(time_string_axis) == time_string_axis
# print convert_timestrings_to_hours_ago(time_string_axis)

# for ea in convert_timestrings_to_hours_ago(time_string_axis):
#       print type(ea)

def convert_bytes_to_mb(string_number):
        return float(string_number) / 1048676.0

def upload_derivative_mb(array_of_string_nums):
        # print time.time() - start_time, "seconds before list subtraction"
        derivative_mb = []
        original_data = array_of_string_nums[1:]
        offset_data = array_of_string_nums[:-1]

        for index in xrange(0,len(original_data)):
                change = float(original_data[index]) - float(offset_data[index])
                derivative_mb.append(convert_bytes_to_mb(change))
        derivative_mb.insert(0, 0.0)
        # print len(original_data), len(offset_data)
        return derivative_mb
        # print time.time() - start_time, "seconds after list subtraction"

# print upload_derivative_mb(upload_bytes_axis)

def sizeof_fmt(num):
    """
    from:
    http://stackoverflow.com/questions/1094841/reusable-
    library-to-get-human-readable-version-of-file-size
        """
    for x in ['bytes','KB','MB','GB','TB']:
        if num < 1024.0:
            return "%3.1f %s" % (num, x)
        num /= 1024.0

def last_xhours_total(num):
        return sizeof_fmt(int(upload_bytes_axis[-1]) - int(upload_bytes_axis[-(num*6 + 1)]))

# print len(upload_derivative_mb(upload_bytes_axis)), len(convert_timestrings_to_hours_ago(time_string_axis))
# print len(time_string_axis), len(upload_bytes_axis)

def graph_last_day():
        y_axis = upload_derivative_mb(upload_bytes_axis)
        x_axis = convert_timestrings_to_hours_ago(time_string_axis)

        x = x_axis[-145:-1]
        y = y_axis[-145:-1]

        scitools.aplotter.plot(x, y)

print graph_last_day()

print last_xhours_total(24) + " uploaded in the last 24 hours"
print "computation time:"
print time.time() - start_time, "seconds"