def parse_result_file(filename):
result = []
with open(filename) as f:
data ={}
timeInNextLine = False
for line in f:
if "round" in line:
data['round'] = get_round(line)
elif "elapsed" in line:
timeInNextLine = True
elif "iterations" in line:
data['iterations'] = get_iterations(line)
elif "totalcost" in line:
data['totalcost'] = get_totalcost(line)
data['converged'] = True
result.append(data)
data = {}
elif timeInNextLine:
timeInNextLine = False
data['time'] = get_time(line)
f.close()
df = pd.DataFrame(result)
stats.compute_stats(df)
def slave_job(myrank):
# define the slave
slave = mns.Slave(myrank, verbose=False)
# master defines the tasks
tasks, keys = mns.bcast(None)
bb = mns.bcast(None)
slave.barrier(0)
#pd.read_pickle(file_tiles_to_stats)
done = False
#print('slave #%3i is ready to go' % (slave.islave))
# do_stats_task(slave.islave)
while not (done):
itask = slave.get_async_task()
# itask = slave.islave
if itask > -1:
tile = keys[itask]
print('** slave #%3i processes task %i / tile %s' %
(slave.islave, itask, tile))
stats.compute_stats(bb, tile)
else:
done = True
# slaves work
slave.barrier(1)
# master gathers the dataframes
slave.barrier(2)
def monoproc_job():
tasks, keys = define_tasks(resume=True)
bb = tiles.read_tiles()
for itask in tasks:
tile = keys[itask]
print('** processes tile %s' % tile)
stats.compute_stats(bb, tile)
def main():
#build the list of test words
f = open(TESTFILE, 'r')
segments = map(lambda f: f.strip('\n'), f.readlines())
f.close()
#build dictionary of words vs segments
for word in segments:
tmp = word.split('\t')
STANDARD[tmp[0]] = tmp[1] #put the kv pairing
WORDS[tmp[0]] = 0
#print WORDS
get_segments()
prune(11)
discover_new_morphemes()
segment_words()
print "Statistics for Dejean algorithm segmentation"
print "********************************************"
print compute_stats(CUTS, CORRECT_CUTS, TRUE_BOUNDARIES)
print
def main():
#build the list of test words
f = open(TESTFILE, 'r')
segments = map(lambda f: f.strip('\n'), f.readlines())
f.close()
#build dictionary of words vs segments
for word in segments:
tmp = word.split('\t')
WORDS[tmp[0]] = tmp[1] #put the kv pairing
#RTRIE.pretty_print()
successor_segmentor()
print "Successor Stats"
print "****************"
print compute_stats(CUTS, CORRECT_CUTS, TRUE_BOUNDARIES)
print
predecessor_segmentor()
print "Predecessor Stats"
print "****************"
print compute_stats(CUTS, CORRECT_CUTS, TRUE_BOUNDARIES)
print
# 1. Combine multi line messages
# 4. Map phone numbers to users
# 2. Extract emojis
# 5. Sentiment analysis
# FILES AND LOCATIONS # of images, videos, voicemessages and locations
# GIF omitted
# image omitted
# video omitted
# audio omitted
# Contact card omitted
# Location: https://maps.google.com/?q=-13.523442,-71.950256
# TIMESPAN: how long did the chat go
# TIMELINE: when and how much you where messaging
# TOTAL NUMBERS days you are chatting, message/word/letter count
# TOPS most active day
if __name__ == "__main__":
with time_it('Reading'):
with open('_chat.txt', 'r') as f:
chat = f.readlines()
with open('numbers.json', 'r') as f:
user_number_map = json.load(f)
with time_it('Parsing'):
grouped_messages = Message.parse_chat(chat, user_number_map)
with time_it('Stats'):
stats = compute_stats(grouped_messages)
pprint(stats)
#!/usr/bin/env python
import numpy as np
from stats import Statistics, compute_stats
n = 10
data = np.empty(n)
my_stats = Statistics()
for i in range(n):
value = 0.3 * i
my_stats.add(value)
data[i] = value
print(my_stats.mean())
my_stats = compute_stats(data)
print(my_stats.mean())
