Untitled

Grouping Messages by Time Intervals
def time_deltas(infile):
entries = (line.split() for line in open(INFILE, "r"))
ts = {}
for e in entries:
    if " ".join(e[2:5]) == "T out: [O]":
        ts[e[8]] = e[0]
    elif " ".join(e[2:5]) == "T in: [A]":
        in_ts, ref_id = e[0], e[7]
        out_ts = ts.pop(ref_id, None)
        yield (float(out_ts),ref_id[1:-1],(float(in_ts)*1000 - float(out_ts)*1000))

INFILE = 'C:/Users/klee/Documents/test.txt'
import csv

with open('test.csv', 'w') as f:
csv.writer(f).writerows(time_deltas(INFILE))

import datetime
import bisect
import collections

data=[ (datetime.datetime(2010, 2, 26, 12, 8, 17), 5594813L),
  (datetime.datetime(2010, 2, 26, 12, 7, 31), 5594810L),
  (datetime.datetime(2010, 2, 26, 12, 6, 4) , 5594807L),
]
interval=datetime.timedelta(seconds=50)
start=datetime.datetime(2010, 2, 26, 12, 6, 4)
grid=[start+n*interval for n in range(10)]
bins=collections.defaultdict(list)
for date,num in data:
idx=bisect.bisect(grid,date)
   bins[idx].append(num)
for idx,nums in bins.iteritems():
print('{0} --- {1}'.format(grid[idx],len(nums)))

082438.577652 - T in: [A] accepted. ordID [F25Q6] timestamp [082438.575880] RefNumber [6018786] State [L]

from itertools import groupby

data = get_time_deltas(INFILE)
get_key = lambda x: int(x[0])  # function to get group key from data
bins = [(k, list(g)) for k, g in groupby(data, get_key)]

# print out the number of messages for each second
for sec, data in bins:
    print('{0} --- {1}'.format(sec, len(data)))

# write (sec, msg_per_sec) out to CSV file
import csv
with open("test.csv", "w") as f:
    csv.writer(f).writerows((s, len(d)) for s, d in bins)

# get average message per second
message_counts = [len(d) for s, d in bins]
avg_msg_per_second = float(sum(message_count)) / len(message_count)

get_key = lambda x: int(x[0] / 60)  # truncate timestamp to the minute

def map_time_to_interval_number( epoch, times )
    for t in times:
        delta= (t - epoch)
        delta_t= delta.days*60*60*24 + delta.seconds + delta.microseconds/1000000.0
        interval = delta_t / 50
        yield interval, t

counts = defaultdict( int )
epoch = min( data )
for interval, time in map_time_to_interval_number( epoch, data ):
    counts[interval] += 1