def _aggregate(self):
if not self._modified:
return
functions = defaultdict(lambda: defaultdict(list))
for profile in filter(self._validate_profile, self._profiles.values()):
for function, values in profile["functions"].items():
functions[function]["num_calls"].append(values["num_calls"])
functions[function]["total_time"].append(values["total_time"])
functions[function]["cum_time"].append(values["cum_time"])
for function, lists in functions.items():
self._results[function] = Aggregator.Result(
num_calls_median = int(median(lists["num_calls"])),
total_time_mean = mean(lists["total_time"]),
total_time_stdev = stdev(lists["total_time"]),
cum_time_mean = mean(lists["cum_time"]),
cum_time_stdev = stdev(lists["cum_time"]))
run_times = lambda: (p["run_time"] for p in self._profiles.values())
self._summary = Aggregator.Summary(
run_time_mean = mean(run_times()),
run_time_stdev = stdev(run_times()))
self._modified = False
def process_result(self, t_frame, r_frame):
print(t_frame, r_frame)
try:
stat_const = float(2.776)
res2 = [] # frame transmission
res3 = [] # throughput
for i in range(int(self.T[0])):
# frame transmission
res2.append(t_frame[i]/r_frame[i])
res3.append(self.F * r_frame[i] / self.R)
# print(res2, res3)
avg_res2 = statistics.mean(res2)
sd2 = statistics.stdev(res2)
dif2 = sd2/math.sqrt(int(self.T[0]))*stat_const
upper_bound2 = avg_res2 + dif2
lower_bound2 = avg_res2 - dif2
avg_res3 = statistics.mean(res3)
sd3 = statistics.stdev(res3)
dif3 = sd3/math.sqrt(int(self.T[0]))*stat_const
upper_bound3 = avg_res3 + dif3
lower_bound3 = avg_res3 - dif3
except ZeroDivisionError:
return float("inf"), float("inf"), float("inf"), 0, 0, 0
return avg_res2, lower_bound2, upper_bound2, avg_res3, lower_bound3, upper_bound3
def display_histogram_scipy(args, result):
import boltons.statsutils
import matplotlib.pyplot as plt
import pylab
import scipy.stats as stats
samples = result.get_samples()
samples.sort()
samples_stats = boltons.statsutils.Stats(samples)
median = statistics.median(samples)
# median +- MAD
fit = stats.norm.pdf(samples, median, samples_stats.median_abs_dev)
pylab.plot(samples, fit, '-o', label='median-mad')
# median +- std dev
fit2 = stats.norm.pdf(samples, median, statistics.stdev(samples, median))
pylab.plot(samples, fit2, '-v', label='median-stdev')
# mean + std dev
fit3 = stats.norm.pdf(samples, statistics.mean(samples), statistics.stdev(samples))
pylab.plot(samples, fit3, '-+', label='mean-stdev')
legend = plt.legend(loc='upper right', shadow=True, fontsize='x-large')
pylab.hist(samples, bins=25, normed=True)
pylab.show()
def test():
n = [random.random() for _ in range(20)]
bag = Bag()
for i in n:
bag.add(i)
print(bag)
for i in bag:
print(i)
total = 0
for item in bag:
total += item
mean = total / bag.size()
total = 0
for item in bag:
total += (item - mean)**2
std = math.sqrt(total / (bag.size() - 1))
print('calculated mean is {}'.format(mean))
print('calculated stdev is {}'.format(std))
print('stdlib mean is {}'.format(statistics.mean(n)))
print('stdlib stdev is {}'.format(statistics.stdev(n)))
assert(round(mean, 10) == round(statistics.mean(n), 10))
assert(round(std, 10) == round(statistics.stdev(n), 10))
def calc_evalmetrics(self):
"""Calculate evaluation metrics:
Tour Recall, Tour Precision, Tour F1-score, RMSE of POI visit duration
Tour Popularity, Tour Interest, Popularity and Interest Rank
"""
assert(len(self.recommendSeqs) > 0)
# calculate intersection size of recommended POI set and real POI set
intersize = dict()
for k, v in self.recommendSeqs.items():
intersize[k] = len(set(v) & set(self.sequences[k]))
# calculate tour recall
recalls = []
for k, v in intersize.items():
recalls.append(v / len(self.sequences[k]))
# calculate tour precision
precisions = []
for k, v in intersize.items():
precisions.append(v / len(self.recommendSeqs[k]))
# calculate F1-score
f1scores = []
assert(len(recalls) == len(precisions))
for i in range(len(recalls)):
f1scores.append(2 * precisions[i] * recalls[i] / (precisions[i] + recalls[i]))
print('Recall: ', stat.mean(recalls), stat.stdev(recalls))
print('Precision:', stat.mean(precisions), stat.stdev(precisions))
print('F1-score: ', stat.mean(f1scores), stat.stdev(f1scores))
def bootstrap_test(self, nsamples=100, noise=0.2):
"""Returns mean and std. dev. of successful recognitions."""
boot = {}
for vec, pat in zip(self.pattern_vectors, self.patterns):
boot[pat] = {"closest": [], "iterations": [], "full_matches": [], "accuracy": []}
for sample in range(nsamples):
recalled, noisy, iterations = self.recall_noisy(vec, noise=noise)
self.show_pattern(noisy, "{}_{}_noisy_{}".format(
noise, pat, sample))
self.show_pattern(recalled, "{}_{}_recalled_{}".format(
noise, pat, sample))
# equal to any patterns?
matches = {}
full_match = None
for vec2, pat2 in zip(self.pattern_vectors, self.patterns):
matches[pat2] = list( \
vec2[0] == recalled[0]).count(True)
if matches[pat2] == vec2.size:
full_match = pat2
boot[pat]["iterations"].append(iterations)
boot[pat]["full_matches"].append(full_match)
boot[pat]["closest"].append(pat == max(matches, key=matches.get))
boot[pat]["accuracy"].append(matches[pat] / vec.size)
boot[pat]["iterations"] = (mean(boot[pat]["iterations"]), stdev(boot[pat]["iterations"]))
boot[pat]["accuracy"] = (mean(boot[pat]["accuracy"]), stdev(boot[pat]["accuracy"]))
count_matches = lambda l: len(list(filter(lambda f: not f is None, l)))
boot[pat]["full_matches"] = count_matches(boot[pat]["full_matches"])
boot[pat]["closest"] = count_matches(boot[pat]["closest"])
return boot
def main(total_rolls=20000):
rolls_list = rolls(total_rolls, 1, 6)
sliced_sum20 = sliced_sums(20, rolls_list)
sums20 = sums(sliced_sum20, -20)
roll_count20 = lens(sliced_sum20)
sliced_sum10k = sliced_sums(10000, rolls_list)
sums10k = sums(sliced_sum10k, -10000)
roll_count10k = lens(sliced_sum10k)
paired_sums = [(20, sums20), (10000, sums10k)]
paired_rolls = [(20, roll_count20), (10000, roll_count10k)]
answers("Mean of the sum - {0} when M is {0}:",
paired_sums, lambda s: statistics.mean(s))
answers("Mean of the number of rolls when M is {0}:",
paired_rolls, lambda s: statistics.mean(s))
answers("Standard deviation of the sum - {0} when M is {0}:",
paired_sums, lambda s: statistics.stdev(s))
answers("Standard deviation of the number of rolls when M is {0}:",
paired_rolls, lambda s: statistics.stdev(s))
answers("\nView of the rolls summing to {0}\n" +
format("Count", ">7") + " " + format("Sum", ">7") + " Rolls\n",
[(20, sliced_sum20), (10000, sliced_sum10k)],
lambda ss: ''.join(
format(len(s[1]), ">7") + " " + format(s[0], ">7") + " " +
format(s[1]) + "\n" for s in ss)
, sep=''
)
def main():
dailymotion = acquire_dailymotion()
print "Dailymotion"
print "total videos: " + str(len(dailymotion[0]))
print "mean views: " + str(statistics.mean(dailymotion[0]))
print "median views: " + str(statistics.median(dailymotion[0]))
print "STD views: " + str(statistics.stdev(dailymotion[0]))
print "Average Date: " + str(convert_to_datetime(statistics.mean(dailymotion[1])))
print "Median Date: " + str(convert_to_datetime(statistics.median(dailymotion[1])))
print "Average Lengths: " + str(statistics.mean(dailymotion[2]))
print "Median Lengths: " + str(statistics.median(dailymotion[2]))
print "STD Lengths: " + str(statistics.stdev(dailymotion[2]))
print "Top 20 most used word in title: "
word_count_dailymotion("title")
print "Top 20 most used word in description:"
word_count_dailymotion("description")
youtube = acquire_youtube()
print "YouTube"
print "total videos: " + str(len(youtube[0]))
print "mean views: " + str(statistics.mean(youtube[0]))
print "median views: " + str(statistics.median(youtube[0]))
print "STD views: " + str(statistics.stdev(youtube[0]))
print "Average Date: " + str(convert_to_datetime(statistics.mean(youtube[1])))
print "Median Date: " + str(convert_to_datetime(statistics.median(youtube[1])))
print "Video Definition: " , str(statistics.mode(youtube[2])) , " - " , str(youtube[2].count(statistics.mode(youtube[2]))) ,"/" , str(len(youtube[2]))
print "Average Lengths: " + str(statistics.mean(youtube[3]))
print "Median Lengths: " + str(statistics.median(youtube[3]))
print "STD Lengths: " + str(statistics.stdev(youtube[3]))
print "Top 20 most used word in title: "
word_count_yt("title")
print "Top 20 most used words in description: "
word_count_yt("description")
client.close()
def mean_dev(training_set):
'''
Calculates and returns the mean and standard deviation to the classes yes and no of a given training set
'''
class_yes = []
class_no = []
mean_yes = {}
mean_no = {}
dev_yes = {}
dev_no = {}
for key in training_set[0]:
for i in range(len(training_set)):
if training_set[i]['DiabetesClass'] == 'yes':
class_yes.append(training_set[i][key])
else:
class_no.append(training_set[i][key])
if not key == 'DiabetesClass':
mean_yes[key] = statistics.mean(class_yes)
mean_no[key] = statistics.mean(class_no)
dev_yes[key] = statistics.stdev(class_yes)
dev_no[key] = statistics.stdev(class_no)
else:
prob_yes = float(len(class_yes) / len(training_set))
prob_no = float(len(class_no) / len(training_set))
class_yes = []
class_no = []
return mean_yes, mean_no, dev_yes, dev_no, prob_yes, prob_no
def good_stdev(self, current_offer):
if self.counter < 5:
return False
# array of utilities the opponent would get for their offer
past_utils = [self.utility_for(x) for x in self.opponent_offers]
old_stdev = statistics.stdev(past_utils)
old_mean = statistics.mean(past_utils)
if past_utils[-1] < self.penalty:
return False
new_utils = []
# filter outliers (2 standard deviations above or below)
for u in past_utils:
if old_mean - 2*old_stdev < u < old_mean + 2*old_stdev:
new_utils.append(u)
if len(new_utils) < 2:
return False
# if the utility we get for the offer is greater than the mean + 1 std dev, then return True
offer_utility = self.utility_for(current_offer)
new_stdev = statistics.stdev(new_utils)
new_mean = statistics.mean(new_utils)
return offer_utility > new_mean + new_stdev
def run_simulation(init_duration, init_stake, samples, player):
""" Run simulation, print the result to stdout
"""
wheel = create_wheel()
table = Table(wheel)
game = RouletteGame(wheel, table)
simulator = Simulator(game, player,
init_duration=init_duration, samples=samples,
init_stake=init_stake)
simulator.gather()
durations = simulator.durations
maxima = simulator.maxima
print(player)
print()
print("Durations")
print(" min :", min(durations))
print(" max :", max(durations))
print(" mean: %.2f" % statistics.mean(durations))
print(" dev : %.2f" % statistics.stdev(durations))
print("Maxima")
print(" min :", min(maxima))
print(" max :", max(maxima))
print(" mean: %.2f" % statistics.mean(maxima))
print(" dev : %.2f" % statistics.stdev(maxima))
def replacePearsonPvalueWithZscore():
all_sample_data={}
for tissue in tissue_comparison_scores:
for (r,p,sample) in tissue_comparison_scores[tissue]:
all_sample_data[sample] = [] ### populate this dictionary and create sub-dictionaries
break
for tissue in tissue_comparison_scores:
for (r,p,sample) in tissue_comparison_scores[tissue]:
all_sample_data[sample].append(r)
sample_stats={}
all_dataset_rho_values=[]
### Get average and standard deviation for all sample rho's
for sample in all_sample_data:
all_dataset_rho_values+=all_sample_data[sample]
avg=statistics.avg(all_sample_data[sample])
stdev=statistics.stdev(all_sample_data[sample])
sample_stats[sample]=avg,stdev
global_rho_avg = statistics.avg(all_dataset_rho_values)
global_rho_stdev = statistics.stdev(all_dataset_rho_values)
### Replace the p-value for each rho
for tissue in tissue_comparison_scores:
scores = []
for (r,p,sample) in tissue_comparison_scores[tissue]:
#u,s=sample_stats[sample]
#z = (r-u)/s
z = (r-global_rho_avg)/global_rho_stdev ### Instead of doing this for the sample background, do it relative to all analyzed samples
scores.append([r,z,sample])
tissue_comparison_scores[tissue] = scores
def pCalc (movMat, movNumber, n, reviewers):
xVals = [int(x) for i,x in enumerate(movMat[movNumber][1].split(';')) if i in reviewers]
yVals = [int(x) for i,x in enumerate(movMat[n][1].split(';')) if i in reviewers]
xi = sum(xVals) #get first movie values
average1 = xi/len(reviewers)
stdDev1 = statistics.stdev(xVals)
yi = sum(yVals) #get second movie values
average2 = yi/len(yVals)
stdDev2 = statistics.stdev(yVals)
r = 0 #get r value
newSum = [((x - average1) / stdDev1) * ((y-average2)/stdDev2) for x,y in zip(xVals, yVals)]
r = (1/(len(reviewers)-1))*sum(newSum)
review = [] #append all values to the list
review.append(r)
review.append(average1)
review.append(average2)
review.append(stdDev1)
review.append(stdDev2)
review.append(n)
review.append(len(reviewers))
return review
def extract_results(input, out):
header = ['fft_type', 'n_threads', 'n_points', 'n_iterations',
'Throughput', 'Stdev']
records = []
for dirs, subdirs, files in os.walk(input):
for file in files:
if ('.stderr' not in file):
continue
l = []
threads = string_between(file, 'n_thr', '.')
points = string_between(file, 'n_p', 'n_i')
iters = string_between(file, 'n_i', 'n_thr')
exe = string_between(file, '', '-bench')
#implementation = dirs.split('/')[-2]
for line in open(os.path.join(dirs, file), 'r'):
if 'Throughput' in line:
temp = string_between(line, ':', 'M')
l.append(float(temp.strip()))
if l:
records.append([exe, threads, points, iters,
stat.mean(l), stat.stdev(l)])
print file
percent = 100.0 * stat.stdev(l) / stat.mean(l)
if percent > 10:
print "The previous file has %.2f %% error" % percent
else:
print "I found an empty file called %s" % file
records.sort(key=lambda a: (a[0], int(a[1]), int(a[2]), int(a[3])))
t = PrettyTable(header)
t.align = 'l'
t.border = False
for r in records:
t.add_row(r)
with open(out, 'w') as f:
f.writelines(str(t) + '\n')
def main(y):
print("Give me",y,"numbers")
r = int(input())
numbers =[]
while len(numbers) < y:
numbers.append(r)
if len(numbers) < y:
r = int(input("Give me another number"))
print (numbers)
#sum of the 10 numbers
def function(x):
name = x
var = 0
for i in numbers:
var += i
result = var/len(numbers)
if name == 1:
return var
else:
return result
#Paul´s blog idea -->https://pololarinette.wordpress.com/2015/10/15/wsq10-lists/
#Standar deviation
import statistics
statistics.stdev(numbers)
print("The sum of the",y,"numbers is",function(1))
print("The average of the",y,"numbers is",function(2))
print("The stardart deviation is",statistics.stdev(numbers))
def bench_throughput_latency(samples=3, max_rsd=0.1,
*args, **kwargs):
while True:
throughputs = []
latencies = []
iteration = 1
errors = 0
while iteration <= samples:
sys.stdout.write(' [*] Iteration %d/%d\r' % (iteration,samples))
sys.stdout.flush()
try:
bench = Benchmark(*args, **kwargs)
bench.run()
throughputs.append(bench.throughput)
latencies.append(bench.latency)
iteration += 1
except Exception as e:
errors += 1
if errors >= samples:
raise
print(' [!] Iteration %d failed: %s\n%s' % \
(iteration, str(type(e)), str(e)))
mean_throughput = statistics.mean(throughputs)
mean_latency = statistics.mean(latencies)
stdev_throughput = statistics.stdev(throughputs)
stdev_latency = statistics.stdev(latencies)
rsd_throughput = stdev_throughput/mean_throughput
rsd_latency = stdev_latency/mean_latency
if rsd_throughput > max_rsd or rsd_latency > max_rsd:
sys.stderr.write(' [!] Discarding experiment: '+\
'throughput RSD %.2f %%, latency RSD %.2f %%\n' %\
(rsd_throughput*100, rsd_latency*100))
continue
return (mean_throughput, mean_latency,
rsd_throughput, rsd_latency)
def addDataToPlt(fig, ax, dates, diff, c = 'c', label="raw", isMultiple=True):
assert len(dates) == len(diff), "Plot and data are of different lenght"
label1 = "average of 3"
label2 = "average of 7"
med3 = [i for i in diff]
med7 = [i for i in diff]
for i in range(3, len(diff) - 4):
if i > 2 and i < len(diff) - 4:
med7[i] = stats.median(diff[i-3:i+3])
if i > 0 and i < len(diff) - 2:
med3[i] = stats.median(diff[i-1:i+2])
marker = "o"
if len(diff) > 200:
marker = "."
if not isMultiple:
if len(diff) > 1 and stats.stdev(diff) > 0.1:
logger.error("Why do you have a high stdev?" + str(stats.stdev(diff)))
marker = "x"
ax.plot_date(dates, diff, c, xdate=True, marker = marker, linestyle="", label=label)
if isMultiple:
ax.plot_date(dates, med3, 'b', xdate=True, marker = ".", linestyle="", label=label1)
ax.plot_date(dates, med7, 'r', xdate=True, marker = ".", linestyle="", label=label2)
ax.xaxis.set_major_locator(matplotlib.dates.HourLocator())
ax.xaxis.set_major_formatter(matplotlib.dates.DateFormatter("%H:00"))
ax.xaxis.set_minor_locator(matplotlib.dates.MinuteLocator())
ax.autoscale_view()
fig.autofmt_xdate()
ax.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.)
def cmp(tweet1_counts1, tweet2_counts2):
(tweet1, counts1) = tweet1_counts1
(tweet2, counts2) = tweet2_counts2
"1. Из твитов с разным количеством элементов списков более информативен тот, в котором элементов больше"
if sum(counts1) > sum(counts2):
return -1
elif sum(counts2) > sum(counts1):
return 1
"""
2. Из твитов с одинаковой суммой количеств элементов список выбираем тот, где количества элементов более
сбалансированы (например, [1, 1] лучше, чем [2, 0])
"""
std1 = statistics.stdev(counts1)
std2 = statistics.stdev(counts2)
if std1 < std2:
return -1
elif std2 < std1:
return 1
"И, наконец, наиболее информативен твит большей длины"
if len(tweet1) > len(tweet2):
return -1
elif len(tweet2) > len(tweet1):
return 1
return 0
def model_analysis(x, x_matrix, y, line, y_hat, b):
n = len(x) # number of samples
s_x = stats.stdev(x) # standard deviation of x values
s_y = stats.stdev(y) # standard deviation of y values
s2_x = stats.variance(x) # variance of x values
s2_y = stats.variance(y) # variance of y values
s_xy = b * s2_x # covariance of VM
mad_temp = 0
SSE = 0
for i in range(len(y)):
temp = abs(y[i] - y_hat[i])
mad_temp += temp
SSE += temp**2 # sum of squares for error
MAD = mad_temp / n
s_err = math.sqrt(SSE / (n - 2)) # standard error of estimate
s_b = s_err / math.sqrt((n - 1) * s2_x)
r = s_xy / (s_x * s_y) # sample coefficient of correlation
R_2 = line.score(x_matrix, y) # coefficient of determination
R_2calc = s_xy**2 / (s2_x * s2_y)
t = b / s_b # t-value for slope assuming true slope = 0
f1.write('\nSkew = ' + str(b) + '\n')
f1.write('Coefficient of correlation (r) = ' + str(r) + '\n')
#f1.write('Coefficient of determination (R^2) via scikit = ' + str(R_2) + '\n')
f1.write('Coefficient of determination (R^2) calculate = ' + str(R_2calc) + '\n')
f1.write('Test statistic for clock skew (t) = ' + str(t) + '\n')
f1.write('Mean Absolute Deviation (MAD) = ' + str(MAD) + '\n')
f1.write('Sum of Squares for Forecast Error (SSE) = ' + str(SSE) + '\n')
return
def get_result(self, raw_fname):
node_flow_num_vs_performance = {}
in_file = open(raw_fname, 'r')
lines = in_file.readlines()
in_file.close()
for line in lines:
#get each value
line = line[1:-2]
#print(line)
items = line.split(', ')
if len(items) != 9:
continue
num_nodes = int(items[0])
num_tasks = int(items[1])
num_candidate_pair = int(items[2])
max_node_flows = int(items[3])
num_pairs = int(items[4])
latency = int(items[5])
flow_avg_latency = int(items[7])
max_flow_latency = int(items[8])
if max_node_flows not in node_flow_num_vs_performance:
node_flow_num_vs_performance[max_node_flows] = []
node_flow_num_vs_performance[max_node_flows].append(
(num_nodes, num_tasks, num_candidate_pair, num_pairs, latency, flow_avg_latency, max_flow_latency)
)
#statistics results
for max_node_flows, tuples in sorted(node_flow_num_vs_performance.items(), key=lambda item: item[0]):
list_num_tasks = []
list_num_candidate_pair = []
list_num_pairs = []
list_latency = []
list_flow_avg_latency = []
all_rounds_max_flow_latency = 0
for one_tuple in tuples:
list_num_tasks.append(one_tuple[1])
list_num_candidate_pair.append(one_tuple[2])
list_num_pairs.append(one_tuple[3])
list_latency.append(one_tuple[4])
list_flow_avg_latency.append(one_tuple[5])
all_rounds_max_flow_latency = max(all_rounds_max_flow_latency, int(one_tuple[6]))
avg_num_tasks = statistics.mean(list_num_tasks)
avg_num_candidate_pair = statistics.mean(list_num_candidate_pair)
avg_num_pairs = statistics.mean(list_num_pairs)
avg_latency = statistics.mean(list_latency)
avg_flow_avg_latency = statistics.mean(list_flow_avg_latency)
stdv_num_tasks = 0
stdv_num_candidate_pair = 0
stdv_num_pairs = 0
stdv_latency = 0
stdv_flow_avg_latency = 0
if len(tuples) > 1:
stdv_num_tasks = statistics.stdev(list_num_tasks)
stdv_num_candidate_pair = statistics.stdev(list_num_candidate_pair)
stdv_num_pairs = statistics.stdev(list_num_pairs)
stdv_latency = statistics.stdev(list_latency)
stdv_flow_avg_latency = statistics.stdev(list_flow_avg_latency)
print(max_node_flows, avg_num_tasks, stdv_num_tasks, avg_num_candidate_pair, stdv_num_candidate_pair, avg_num_pairs, stdv_num_pairs, avg_latency, stdv_latency, avg_flow_avg_latency, stdv_flow_avg_latency, all_rounds_max_flow_latency)
def csv_dict_reader(file_obj):
"""
Read a CSV file using csv.DictReader
"""
reader = csv.DictReader(file_obj, delimiter=',')
num_likes = []
num_comments = []
num_shares = []
for line in reader:
p = int(line["num_likes"])
q = int(line["first_page_comment"])
r = int(line["comments_beyond_pageone"])
num_likes.append(p)
num_comments.append(q)
num_shares.append(r)
mean_num_likes = statistics.mean(num_likes)
stdev_num_likes = statistics.stdev(num_likes)
mean_num_comments = statistics.mean(num_comments)
stdev_num_comments = statistics.stdev(num_comments)
mean_num_shares = statistics.mean(num_shares)
stdev_num_shares = statistics.stdev(num_shares)
covariance_likes = stdev_num_likes / mean_num_likes
covariance_comments = stdev_num_comments / mean_num_comments
covariance_shares = stdev_num_shares / mean_num_shares
w = csv.writer(open("svm_dataset.csv","a"),delimiter=',',quoting=csv.QUOTE_ALL)
w.writerow([mean_num_likes,stdev_num_likes,covariance_likes,mean_num_comments,stdev_num_comments,covariance_comments,mean_num_shares,stdev_num_shares,covariance_shares])
def calculate_switches_one_setting_result(self, switches_rounds_result, avg_switches_result_one_setting):
#switches_rounds_result
#pair: key-switch_id, value-{{sec, switch_one_round_result_c},{sec, switch_one_round_result_c}}
switches_avg_real_targetflow_num = []
for switch_id, rounds_result_map in switches_rounds_result.items():
avg_switch_one_setting = avg_switch_result_one_setting_c()
avg_switches_result_one_setting[switch_id] = avg_switch_one_setting
#avg_switch_one_setting.condition_map_size = self.switches_condition_map_size[switch_id]
fn_list = []
fp_list = []
accuracy_list = []
all_volume_list = []
all_flow_num_list = []
real_target_flow_num_list = []
fn_num_list = []
fn_num_not_targetflow_list = []
fn_num_not_captured_list = []
condition_pkt_num_list = []
for sec, one_round_result in rounds_result_map.items():
#print("fn-fp-accuracy:{0}-{1}-{2}" .format(one_round_result.fn, one_round_result.fp, one_round_result.accuracy))
fn_list.append(one_round_result.fn)
fp_list.append(one_round_result.fp)
accuracy_list.append(one_round_result.accuracy)
all_volume_list.append(one_round_result.all_volume_one_interval)
all_flow_num_list.append(one_round_result.all_flow_num_one_interval)
real_target_flow_num_list.append(one_round_result.real_target_flow_num)
fn_num_list.append(one_round_result.fn_num)
fn_num_not_targetflow_list.append(one_round_result.fn_num_not_targetflow)
fn_num_not_captured_list.append(one_round_result.fn_num_not_captured)
condition_pkt_num_list.append(one_round_result.condition_pkt_num)
avg_switch_one_setting.avg_fn = statistics.mean(fn_list)
avg_switch_one_setting.avg_fp = statistics.mean(fp_list)
avg_switch_one_setting.avg_accuracy = statistics.mean(accuracy_list)
avg_switch_one_setting.avg_real_target_flow_num = statistics.mean(real_target_flow_num_list)
switches_avg_real_targetflow_num.append(round(avg_switch_one_setting.avg_real_target_flow_num, 1))
avg_switch_one_setting.avg_fn_num = statistics.mean(fn_num_list)
avg_switch_one_setting.avg_fn_num_not_targetflow = statistics.mean(fn_num_not_targetflow_list)
avg_switch_one_setting.avg_fn_num_not_captured = statistics.mean(fn_num_not_captured_list)
avg_switch_one_setting.avg_condition_pkt_num = statistics.mean(condition_pkt_num_list)
if len(rounds_result_map) > 1:
avg_switch_one_setting.stdv_fn =statistics.stdev(fn_list)
avg_switch_one_setting.stdv_fp =statistics.stdev(fp_list)
avg_switch_one_setting.stdv_accuracy =statistics.stdev(accuracy_list)
avg_switch_one_setting.stdv_condition_pkt_num = statistics.stdev(condition_pkt_num_list)
print("switch_id:{switch_id}, #interval:{num_interval}, traffic:{all_volume}Mbyte, #flow:{all_flow_num}, #target_flow:{target_flow_num}, #buckets:{avg_sample_map_size}, avg_fn:{fn}(stdv:{fn_stdv}), avg_accuracy:{accuracy}(stdv:{acc_stdv})" \
.format( \
switch_id=switch_id, \
num_interval = len(rounds_result_map), \
all_volume = int(sum(all_volume_list)/1000000), \
all_flow_num = sum(all_flow_num_list), \
target_flow_num = round(avg_switch_one_setting.avg_real_target_flow_num, 1), \
avg_sample_map_size = avg_switch_one_setting.avg_sample_map_size, \
fn=round(avg_switch_one_setting.avg_fn, 4), \
fn_stdv = round(avg_switch_one_setting.stdv_fn, 4), \
accuracy=round(avg_switch_one_setting.avg_accuracy, 4), \
acc_stdv = round(avg_switch_one_setting.stdv_accuracy, 4) \
))
def get_precision_recall_fscore_overall(results, k):
precision, recall, fscore = [], [], []
for res in results:
precision.append(res[0])
recall.append(res[1])
fscore.append(res[2])
return stat.mean(precision), stat.stdev(precision),stat.mean(recall), \
stat.stdev(recall), stat.mean(fscore), stat.stdev(fscore)
def userStDev(user1, user2):
ratingDictionary = buildRatingDictionary(int(user1), int(user2))
userOneRatings = []
userTwoRatings = []
for dictionary in ratingDictionary:
userOneRatings.append(ratingDictionary[dictionary][0])
userTwoRatings.append(ratingDictionary[dictionary][1])
return [statistics.stdev(userOneRatings), statistics.stdev(userTwoRatings)]
def get_test_results(self, guess_tags, correct_tags):
tag_score_dict = {}
correct_tag_type ={}
wrong_tag_type = {}
conf_right = []
conf_wrong = []
total_tags = 0
total_wrong_tags = 0
total_sentences = len(guess_tags)
total_wrong_sent = 0
for sent_num, correct_sentence in enumerate(correct_tags):
perfect_sentence = True
for word_idx, correct_token in enumerate(correct_sentence.get_tokens()):
guess_token = guess_tags[sent_num].get_token_at(word_idx)
assert correct_token.orig == guess_token.orig
for i, (feature, guess) in enumerate(guess_token.get_testable_attr_list()):
tag_score_dict[feature] = tag_score_dict.get(feature, 0) + (guess==correct_token.get_testable_attr_list()[i][1])
tag_guess = guess_token.pos_tag
guess_confidence = guess_token.conf
total_tags +=1
if(correct_token.pos_tag != tag_guess):
total_wrong_tags +=1
conf_wrong.append(guess_confidence)
perfect_sentence = False
error_tuple = (correct_token.pos_tag, tag_guess)
wrong_tag_type[error_tuple] = wrong_tag_type.get(error_tuple, 0) + 1
else:
correct_tag_type[tag_guess] = correct_tag_type.get(tag_guess, 0) + 1
conf_right.append(guess_confidence)
if not perfect_sentence:
total_wrong_sent+= 1
if(len(conf_right) >0 and len(conf_wrong)>0):
print "average confidence of right tag= " + str(s.mean(conf_right))
print "average confidence of wrong tag= " + str(s.mean(conf_wrong))
print "stdev confidence of right tag= " + str(s.stdev(conf_right))
print "stdev confidence of wrong tag= " + str(s.stdev(conf_wrong))
tag_word_acc = (100.00*(total_tags-total_wrong_tags))/total_tags
tag_sentence_acc = (100.00*(total_sentences-total_wrong_sent))/total_sentences
print "tag token accuracy: " + str(tag_word_acc) + "%"
print "tag sentence accuracy: " + str(tag_sentence_acc) + "%"
print "have not written tests for parse yet"
for feature, correct_count in tag_score_dict.iteritems():
print feature, "accuracy:", (100.0*correct_count)/total_tags
def coplot_node_density_and_total_wire_length(trials):
fig = plt.figure()
plot = plt.subplot()
fig.suptitle('Node Density & Total Wire Length vs. Wire Count')
plt.xlabel('Wire Count')
plt.ylabel('Node Density (node/unit^2)')
xs = [r.wire_count for r in trials[0]]
trial_count = len(trials)
data_points = len(trials[0])
#if not all()
large_set = [ [t[n].average_shortest_path_length / 60 for t in trials] for n in range(data_points)]
largest = [s.mean(x) for x in large_set]
discon_set = [ [t[n].total_wire_length for t in trials] for n in range(data_points)]
disconnected = [s.mean(y) for y in discon_set]
# There's a bug in errorbar() when called without fmt=None that
# causes connecting lines to be drawn between data points. This creates
# a significant amount of visual noise. The page below says it was
# supposed to be fixed in 1.4 and higher, but this doesn't seem to be
# the cases or I haven't configured the module import correctly.
# An alternate solution is to draw the data points and the errorbars
# separately as is done below. The error bars seems to be slightly off
# center, but it's better than the alternative.
# See: http://stackoverflow.com/questions/18498742/how-do-you-make-an-errorbar-plot-in-matplotlib-using-linestyle-none-in-rcparams
h1, = plot.plot(xs, largest, "ok", label="Density")
# Calculate the standard error for each x's seqence of
# y values. There must be at least two data points or exceptions
# are thrown.
# See: https://en.wikipedia.org/wiki/Standard_error
if trial_count >= 2:
data_points_root = sqrt(trial_count)
stdev = [s.stdev(value) for value in large_set]
stderr = [x / data_points_root for x in stdev]
plt.errorbar(xs, largest, yerr=stderr, color="black", fmt=None)
twin = plot.twinx()
twin.yaxis.label.set_text('Total Wire Length (units)')
h2, = twin.plot(xs, disconnected, "*r", label="Total")
plt.legend(handles=[h1,h2])
if trial_count >= 2:
data_points_root = sqrt(trial_count)
stdev = [s.stdev(value) for value in discon_set]
stderr = [x / data_points_root for x in stdev]
plt.errorbar(xs, disconnected, yerr=stderr, color="black", fmt=None)
#plt.plot(xs, ys, 'o')
plt.savefig('density_vs_total.png')
plt.show()
def analiza(self):
"""
Media y desviación de todos los datos
"""
self.mediaTotal['C'] = sum(self.propC)/float(len(self.propC))
self.desvTotal['C'] = statistics.stdev(self.propC)
self.mediaTotal['H'] = sum(self.propH)/float(len(self.propH))
self.desvTotal['H'] = statistics.stdev(self.propH)
self.mediaTotal['R'] = sum(self.propR)/float(len(self.propR))
self.desvTotal['R'] = statistics.stdev(self.propR)
def compute_sharpe(returns, risk_free):
""" Compute annualized Sharpe Ratio based on daily returns (252 trading days / year)"""
adj_returns = []
for i in range(len(returns)):
adj_returns += [returns[i] - (risk_free / 252)]
if statistics.stdev(adj_returns) == 0:
return 0
sharpe = math.sqrt(252) * statistics.mean(adj_returns) / statistics.stdev(adj_returns)
return sharpe
def save_load_benchmark():
from relstorage.cache import LocalClientBucket
from io import BytesIO
bucket = LocalClientBucket(10*1024*1024)
i = 1
j = 0
while bucket.size < bucket.limit - i:
val = (str(j) * i).encode('ascii')
if len(val) > bucket.limit or bucket.size + len(val) > bucket.limit:
break
bucket[str(i)] = val
if i < 1096:
i += 50
j += 1
else:
j += 1
i += 1
print("Len", len(bucket), "size",bucket.size, "i", i)
print("Len", len(bucket), "size", bucket.size)
number = 50
import timeit
import statistics
import cProfile
import pstats
def write():
io = BytesIO()
bucket.write_to_file(io)
bio = BytesIO()
bucket.write_to_file(bio)
def load():
bio.seek(0)
b2 = LocalClientBucket(bucket.limit)
b2.load_from_file(bio)
write_timer = timeit.Timer(write)
write_times = write_timer.repeat(number=number)
print("write average", statistics.mean(write_times), "stddev", statistics.stdev(write_times))
#pr = cProfile.Profile()
#pr.enable()
read_timer = timeit.Timer(load)
read_times = read_timer.repeat(number=number)
#pr.disable()
#ps = pstats.Stats(pr).sort_stats('cumulative')
#ps.print_stats()
print("read average", statistics.mean(read_times), "stddev", statistics.stdev(read_times))
def __init__(): for param1 in params: for param2 in params: print print 'Step Size 1: ' + str(param1) print 'Step Size 2: ' + str(param2) lvlOptimism = RMAX numSeeds = 2000 numIterations = 1000 #Variables that will store the results for all methods res_MAX = [] res_SARSA = [] '''Already pull all the arms and store them, this way one can easily reproduce the results and come back to see other possibilities''' b = [] for s in xrange(1, numSeeds+1): b.append(Bandits(s, numIterations)) #Run the experiment x times, where x is the number of seeds for s in xrange(1, numSeeds + 1): seed = s r.seed(seed) res_MAX.append([]) res_SARSA.append([]) maxReturn = 0 '''First I just calculate the max return one could've get.''' for i in xrange(numIterations): maxReturn += max(b[s-1].pullArm(0), b[s-1].pullArm(1)) res_MAX[s-1].append(maxReturn) b[s-1].resetEnv() '''Agent following the SARSA(0) with two value functions.''' r.seed(seed) res_SARSA[s-1].append(SARSA_SPLIT(b[s-1], numIterations, param1, param2, lvlOptimism)) b[s-1].resetEnv() '''Now we can take the average return of each method:''' res_MAX_avg = [] res_SARSA_avg = [] for i in xrange(numSeeds): res_MAX_avg.append(stat.mean(res_MAX[i])) res_SARSA_avg.append(stat.mean(res_SARSA[i])) print 'Max return :', stat.mean(res_MAX_avg), ',', stat.stdev(res_MAX_avg) print 'SARSA(0) :', stat.mean(res_SARSA_avg), ',', stat.stdev(res_SARSA_avg)
#print(GIMap)
curMap = fill(curMap)
#print(curMap)
curSSD = findSSD(curMap, GIMap)
SSD.append(curSSD)
SSDList.append([curSSD, image[1]])
if (count == runs):
print("----------------FULL------------------")
fullList.append([curSSD, image[1]])
print(curSSD)
length.append(findLength(visited))
mean = statistics.mean(means)
sd = statistics.stdev(means)
meanSSD = statistics.mean(SSD)
sdSSD = statistics.stdev(SSD)
SSDList.sort()
for item in SSDList:
print(item)
print("-------------------------FULL LIST--------------------------------")
for item in fullList:
print(item)
print("-------------------------LENGTH------------------------------------")
for item in length:
import plotly.figure_factory as ff
import plotly.graph_objects as go
import statistics
import csv
import random
import pandas as pd
df = pd.read_csv("studentMarks.csv")
data = df["Math_score"].to_list()
fig = ff.create_distplot([data], ["Math Scores"], show_hist=False)
#fig.show()
datamean = statistics.mean(data)
datamedian = statistics.median(data)
datamode = statistics.mode(data)
datastdDev = statistics.stdev(data)
print("Mean, Median, Mode of the data is {} {} {} respectively".format(
datamean, datamedian, datamode))
print("Standard Deviation of the data is {}".format(datastdDev))
def randomSetOfMean(counter):
dataSet = []
for i in range(0, counter):
randomIndex = random.randint(0, len(data) - 1)
value = data[randomIndex]
dataSet.append(value)
mean = statistics.mean(dataSet)
return mean
meanlist = []
for i in range(0, 1000):
with open('Auto.csv', newline='') as csvfile:
Auto = csv.reader(csvfile, quotechar='|')
for row in Auto:
if count > 0:
mpg.append(float(row[0]))
cylinders.append(int(row[1]))
displacement.append(float(row[2]))
if row[3] != '?':
horsepower.append(int(row[3])) #some ?
weight.append(int(row[4]))
acceleration.append((float(row[5])))
year.append(int(row[6]))
count += 1
print("Range of mpg: ", min(mpg), '~', max(mpg), '/ mean: ',
sum(mpg) / count, '/ standard deviation: ', statistics.stdev(mpg))
print("Range of cylinders: ", min(cylinders), '~', max(cylinders), '/ mean: ',
sum(cylinders) / count, '/ standard deviation: ',
statistics.stdev(cylinders))
print("Range of displacement: ", min(displacement), '~', max(displacement),
'/ mean: ',
sum(displacement) / count, '/ standard deviation: ',
statistics.stdev(displacement))
print("Range of horsepower: ", min(horsepower), '~', max(horsepower),
'/ mean: ',
sum(horsepower) / len(horsepower), '/ standard deviation: ',
statistics.stdev(horsepower))
print("Range of weight: ", min(weight), '~', max(weight), '/ mean: ',
sum(weight) / count, '/ standard deviation: ', statistics.stdev(weight))
print("Range of acceleration: ", min(acceleration), '~', max(acceleration),
'/ mean: ',
# expovariate - used to simulate arrival times # distribution centers around reciprical of argument # so expovariate(20) centers around .05 (1/20) expovariate(20) ### 0.11416353263962384 expovariate(20) ### 0.0523532783809665 # triangular mean is centered sharply around midpoint # (smaller stdev) from statistics import mean, stdev data = [triangular(1000, 1100) for i in range(1000)] mean(data) ### 1048.7593107346681 stdev(data) ### 20.13510622686606 # uniform mean is still centered around midpoint # but larger stdev data = [uniform(1000, 1100) for i in range(1000)] mean(data) ### 1051.0406593043674 stdev(data) ### 28.545863280007982 # gauss gives us very close to mean and stdev # provided in the arguments data = [gauss(100, 15) for i in range(1000)] mean(data) ### 100.05158436289322
total += freq_abs[x]
print(x, " ", total)
print("FREQ ACUMULADA")
total = 0
for x in range(0, len(freq_abs)):
total += freq_abs[x]
print(x, " ", (total / 36) * 100)
print('SEGUNDA QUESTAO')
print()
print('Altura: ', altura)
print('MEDIA DE ALTURA = ', mean(altura))
print("MEDIANA DE ALTURA = ", median(altura))
print("MODA DE ALTURA = ", mode(altura))
print('DESVIO PADRAO DE ALTURA = ', stdev(altura))
print("COEFICIENTE DE VARIACAO DE ALTURA = ", stdev(altura) / mean(altura))
print()
print('Peso: ', peso)
print('MEDIA DE PESO = ', mean(peso))
print("MEDIANA DE PESO = ", median(peso))
print("MODA DE PESO = ", mode(peso))
print('DESVIO PADRAO DE PESO = ', stdev(peso))
print("COEFICIENTE DE VARIACAO DE PESO = ", stdev(peso) / mean(peso))
print()
imc = list(imc.values())
print('Imc: ', imc)
print('MEDIA DE IMC = ', mean(imc))
print("MEDIANA DE IMC = ", median(imc))
print("MODA DE IMC = ", mode(imc))
print('DESVIO PADRAO DE IMC = ', stdev(imc))
def process_stats(arr, precision=2, empty=''):
'''Returns the statistics for the given array'''
arr_mean = round(mean(arr), precision) if len(arr) > 0 else empty
arr_median = round(median(arr), precision) if len(arr) > 0 else empty
arr_stdev = round(stdev(arr), precision) if len(arr) > 1 else empty
return arr_mean, arr_median, arr_stdev
import numpy
from scipy import stats
rent_list = [
425, 430, 430, 435, 435, 435, 435, 435, 440, 440, 440, 440, 440, 445, 445,
445, 445, 445, 450, 450, 450, 450, 450, 450, 450, 460, 460, 460, 465, 465,
465, 470, 470, 472, 475, 475, 475, 480, 480, 480, 480, 485, 490, 490, 490,
500, 500, 500, 500, 510, 510, 515, 525, 525, 525, 535, 549, 550, 570, 570,
575, 575, 580, 590, 600, 600, 600, 600, 615, 615
]
rent_list_np = numpy.array(rent_list)
median = statistics.median(rent_list)
mean = statistics.mean(rent_list)
mode = statistics.mode(rent_list)
variance = statistics.variance(rent_list)
coefficient_of_variance = (statistics.stdev(rent_list) / mean) * 100
twenty_fifth_percentile = numpy.percentile(rent_list_np, 25)
fifty_percentile = numpy.percentile(rent_list_np, 50)
seventy_fifth_percentile = numpy.percentile(rent_list_np, 75)
print("The mean is : ", mean)
print("The median is : ", median)
print("The mode is : ", mode)
res = stats.relfreq(rent_list, numbins=9)
start = res.lowerlimit
gap = res.binsize
cumilative_frequency = res.frequency[0]
print(" Range Frequency CF")
for i in range(len(res.frequency)):
print(
"plot.py"
from statistics import mean, median, stdev
from matplotlib import pyplot as plt
file = open("packages_time.txt", "r")
pack_times = []
for val in file.read().split():
pack_times.append(int(val))
file.close()
mean_value = mean(pack_times)
min_value = min(pack_times)
max_value = max(pack_times)
median_value = median(pack_times)
std_dev = stdev(pack_times)
print("Mean value : %f \nMin value : %f\nMax value : %f\nMedian value : %f" %
(mean_value, min_value, max_value, median_value))
print("Standard deviation : %f" % std_dev)
plt.scatter(list(range(0, len(pack_times))), pack_times)
plt.xlabel('No of package')
plt.ylabel('Time received package in us')
plt.text(
1,
min_value + 120,
"Duration: 7200 sec\nInterval: 0.1 sec\nBMean value: %f us\nMin value: %f us\nMax value: %f us\nMedian value: %f us"
% (mean_value, min_value, max_value, median_value),
bbox=dict(facecolor='green', alpha=0.1))
plt.show()
print ("Wektor: ",numbers)
minimum = min(numbers)
maximum = max(numbers)
print ("Min: ", minimum)
print ("Max: ", maximum)
newNumbers = sorted(numbers)
print ("Posortowany wektor: ",newNumbers)
srednia = np.average(newNumbers)
print ("Średnia: ",srednia)
odchylenieStandardowe = statistics.stdev(numbers)
print("Odchylenie standardowe: ",odchylenieStandardowe)
#wektorZnormalizowany
wektorZnormalizowany = []
for x in range(0, 29):
wZ = (newNumbers[x]-minimum)/(minimum-maximum)
wektorZnormalizowany.append(wZ)
#Wektor standaryzowany
for x in range(0, 29):
wS = (newNumbers[x]-srednia)/odchylenieStandardowe
wektorZnormalizowany.append(wS)
print("Wektor znormalizowany: ", wZ)
print("Wektor standaryzowany: ", wS)
def process(self, number_of_parts, width, height, crf_value, idr_interval, model):
"""Do the necessary crf encodings and assessments
:param number_of_parts: Number of part/segment for the analysis
:type number_of_parts: int
:param width: Width of the CRF encode
:type width: int
:param height: Height of the CRF encode
:type height: int
:param crf_value: Constant Rate Factor: this is a constant quality factor, see ffmpeg.org for more documentation on this parameter
:type crf_value: int
:param idr_interval: IDR interval in seconds
:type idr_interval: int
:param model: linear (True) or for each (False)
:type model: bool
"""
# Start by probing the input video file
input_probe = Probe(self.input_file_path)
input_probe.execute()
crf_bitrate_list = []
part_duration = input_probe.duration/number_of_parts
idr_interval_frames = idr_interval*input_probe.framerate #rcl: An IDR frame is a special type of I-frame in H.264. An IDR frame specifies that no frame after the IDR frame can reference any frame before it. This makes seeking the H.264 file easier and more responsive in the player.
#As I have an IDR_FRAME every 2 seconds, I can find out the number of frame between two IDR using framerate !
# Start Analysis
for i in range(0,number_of_parts):
part_start_time = i*part_duration #select extracts to encode
# Do a CRF encode for the input file
crf_encode = CrfEncode(self.input_file_path, width, height, crf_value, idr_interval_frames, part_start_time, part_duration)
crf_encode.execute()
# Get the Bitrate from the CRF encoded file
crf_probe = Probe(crf_encode.output_file_path)
crf_probe.execute()
# Remove temporary CRF encoded file
os.remove(crf_encode.output_file_path)
# Set the crf bitrate
crf_bitrate_list.append(crf_probe.bitrate)
# Calculate the average bitrate for all CRF encodings
self.average_bitrate = statistics.mean(crf_bitrate_list)
self.peak_bitrate = max(crf_bitrate_list)
if number_of_parts > 1:
# Calculate the the standard deviation of crf bitrate values
self.standard_deviation = statistics.stdev(crf_bitrate_list)
weight = 1
weighted_bitrate_sum = 0
weighted_bitrate_len = 0
# Giving weight for each bitrate based on the standard deviation
for bitrate in crf_bitrate_list:
if bitrate > (self.average_bitrate + self.standard_deviation):
weight = 4
elif bitrate > (self.average_bitrate + self.standard_deviation/2):
weight = 2
elif bitrate < (self.average_bitrate - self.standard_deviation/2):
weight = 0.5
elif bitrate < (self.average_bitrate - self.standard_deviation):
weight = 0
else:
weight = 1
weighted_bitrate_sum += weight*bitrate
weighted_bitrate_len += weight
# Set the optimal bitrate from the weighted bitrate of all crf encoded parts
self.optimal_bitrate = weighted_bitrate_sum/weighted_bitrate_len
else:
# Set the optimal bitrate from the only one crf result
self.optimal_bitrate = self.average_bitrate
if not model:
print(' ',width,'x',height,' ',self.optimal_bitrate*1e-3,'kbps encode_for_each','/ nbr part:',number_of_parts,' ')
if model:
# We calculate optimal bitrate of the the remaining profiles using bitrate factor
self.set_bitrate(number_of_parts)
# Adding results to json
result = {}
result['processing_date'] = str(datetime.datetime.now())
result['parameters'] = {}
result['parameters']['method'] = "CRF"
result['parameters']['width'] = width
result['parameters']['height'] = height
result['parameters']['crf_value'] = crf_value
result['parameters']['idr_interval'] = idr_interval
result['parameters']['number_of_parts'] = number_of_parts
result['parameters']['part_duration'] = part_duration
result['bitrate'] = {}
result['bitrate']['optimal'] = self.optimal_bitrate
result['bitrate']['average'] = self.average_bitrate
result['bitrate']['peak'] = self.average_bitrate
result['bitrate']['standard_deviation'] = self.standard_deviation
result['optimized_encoding_ladder'] = {}
if model == "True":
result['optimized_encoding_ladder']['model'] = "linear"
if model == "False":
result['optimized_encoding_ladder']['model'] = "encode_for_each"
self.json['analyses'].append(result)
import random
import plotly.express as px
import plotly.figure_factory as ff
import statistics
import plotly.graph_objects as go
count = []
diceresult = []
for i in range(0, 100):
dice1 = random.randint(1, 6)
dice2 = random.randint(1, 6)
diceresult.append(dice1 + dice2)
count.append(i)
#fig=px.bar(x=diceresult,y=count)
mean = sum(diceresult) / len(diceresult)
stdevation = statistics.stdev(diceresult)
median = statistics.median(diceresult)
mode = statistics.mode(diceresult)
print(mean)
print(stdevation)
print(mode)
print(median)
fig = ff.create_distplot([diceresult], ['result'], show_hist=False)
#fig.show()
fsds, fsde = mean - stdevation, mean + stdevation
ssds, ssde = mean - (2 * stdevation), mean + (2 * stdevation)
tsds, tsde = mean - (3 * stdevation), mean + (3 * stdevation)
listofdatawithin1standarddevation = [
result for result in diceresult if result > fsds and result < fsde
]
listofdatawithin2ndstandarddevation = [
current_linear_plus_merge_io = []
current_linear_plus_merge_t = []
for i in x_range:
current_binary_io.append(binary_dict[str(t)][str(i)]["I/Os"])
current_binary_t.append(binary_dict[str(t)][str(i)]["time"])
current_indexed_io.append(indexed_dict[str(t)][str(i)]["I/Os"])
current_indexed_t.append(indexed_dict[str(t)][str(i)]["time"])
current_linear_io.append(linear_dict[str(t)][str(i)]["I/Os"])
current_linear_t.append(linear_dict[str(t)][str(i)]["time"])
current_linear_plus_binary_io.append(linear_plus_binary_dict[str(t)][str(i)]["I/Os"])
current_linear_plus_binary_t.append(linear_plus_binary_dict[str(t)][str(i)]["time"])
current_linear_plus_merge_io.append(linear_plus_merge_dict[str(t)][str(i)]["I/Os"])
current_linear_plus_merge_t.append(linear_plus_merge_dict[str(t)][str(i)]["time"])
y_binary_io.append(statistics.mean(current_binary_io)/div)
y_binary_io_std.append(statistics.stdev(current_binary_io))
y_binary_t.append(statistics.mean(current_binary_t))
y_binary_t_std.append(statistics.stdev(current_binary_t))
y_indexed_io.append(statistics.mean(current_indexed_io)/div)
y_indexed_io_std.append(statistics.stdev(current_indexed_io))
y_indexed_t.append(statistics.mean(current_indexed_t))
y_indexed_t_std.append(statistics.mean(current_indexed_t))
y_linear_io.append(statistics.mean(current_linear_io)/div)
y_linear_io_std.append(statistics.stdev(current_linear_io))
y_linear_t.append(statistics.mean(current_linear_t))
y_linear_t_std.append(statistics.stdev(current_linear_t))
y_linear_plus_binary_io.append(statistics.mean(current_linear_plus_binary_io))
y_linear_plus_binary_io_std.append(statistics.stdev(current_linear_plus_binary_io))
def problem4_2(ran_list):
""" Compute the mean and standard deviation of a list of floats """
print(statistics.mean(ran_list))
print(statistics.stdev(ran_list))
# === 母集団の標準偏差: === # statistics.pstdev() pstdev = statistics.pstdev(l) print(pstdev) """母集団の標準偏差は母分散の平方根である""" print(math.sqrt(pvariance)) # === 不偏分散・標本分散: === # statistics.variance() variance = statistics.variance(l) print(variance) """組み込み関数 sum() と len() を使って算出することもできる""" my_variance = sum((x - sum(l) / len(l))**2 for x in l) / (len(l) - 1) print(my_variance) # === 標本標準偏差: === # statistics.stdev() stdev = statistics.stdev(l) print(stdev) """ 標本標準偏差と呼ばれたり不偏標準偏差と呼ばれたりするが、 statistics.stdev() で取得できるのは上述の不偏分散の平方根 """ print(math.sqrt(variance))
def main(commandline_arguments):
comm_args = create_and_parse_argument_options(commandline_arguments)
aln_name = str(comm_args.alignment_file).split("/")[-1].replace(
".fasta", "").replace(".fas", "")
if comm_args.indelible_tree_file:
indeli_trees = read_indeli_trees_file(comm_args.indelible_tree_file)
for name, tree in indeli_trees.items():
alignIO_out = read_align(comm_args.alignment_file +
'INDELI_TRUE_' + name + '.fas')
deepest_anc = find_deepest_ancestors(tree)
gapped_sliced_alns = slice_by_anc(alignIO_out, deepest_anc)
print(name, gapped_sliced_alns)
with open(comm_args.alignment_file + 'tg_' + name + '.fas',
"w") as tagged_aln_file:
for aln_group_name, alignment in gapped_sliced_alns.items():
for entry in alignment:
tagged_aln_file.write(
str(">" + str(aln_group_name) + "_" +
str(entry.id) + "\n" + entry.seq + "\n"))
sys.exit()
alignIO_out = read_align(comm_args.alignment_file)
if comm_args.nucleotide_alignments:
for sequence in alignIO_out:
sequence.seq = sequence.seq.back_transcribe()
tree = tree_construct(alignIO_out, nucl=True)
else:
tree = tree_construct(alignIO_out)
if comm_args.split_by_tree:
deepestanc_to_child = find_deepest_ancestors(tree)
sliced_dict = slice_by_anc(alignIO_out, deepestanc_to_child)
if comm_args.save_split_alignments:
output_split_alignments(sliced_dict,
comm_args.save_split_alignments,
comm_args.alignment_file)
sys.exit()
else:
sliced_dict = slice_by_name(alignIO_out)
if comm_args.dhat:
# #D hat here figure out why it always ranges between 0.4-0.7
seq_names = list()
group_names = list()
for group in sliced_dict:
if group[-1] == 'b':
continue
group_names.append(group)
seq_names.append([x.id for x in sliced_dict[group]])
dhat = calc_d_hat(tree, seq_names[0], seq_names[1])
named_intra1, intra1 = pairwise_dist(tree, seq_names[0])
named_intra2, intra2 = pairwise_dist(tree, seq_names[1])
print(aln_name, "\t", ' '.join(group_names), dhat)
print(named_intra1, intra1)
print(named_intra2, intra2)
sys.exit()
wei_vr_dict, pairwise_dict, pairwise_lists = {}, {}, {}
for alngroup_name in sliced_dict:
tree = tree_construct(sliced_dict[alngroup_name])
seq_names = tree.get_terminals()
pairwise_dict[alngroup_name], pairwise_lists[
alngroup_name] = pairwise_dist(tree, seq_names)
wei_vr_dict[alngroup_name] = generate_weight_vectors(tree)
print(aln_name, end="\t")
for group in pairwise_lists:
print(group,
mean(pairwise_lists[group]),
stdev(pairwise_lists[group]),
end="\t")
#print(group, [x for x in pairwise_lists[group]])
print()
def generateRooflinePoints(kernelMetrics):
"""
Generates roofline points from a set of kernel metrics
The flops type is automatically selected to be the one
with the highest throughput
"""
rooflines = dict()
memRooflines = dict()
# one point for each kernel
# runs are averaged
for kernel in kernelMetrics:
logging.debug("Starting roofline generation for kernel {}".format(kernel))
# figure out which flops is highest
flops = dict()
for flopsMetric in rooflineMetricsFlops:
if flopsMetric in kernelMetrics[kernel]:
flops[flopsMetric] = statistics.mean(kernelMetrics[kernel][flopsMetric]) * flopsMultipliers[flopsMetric]
if len(flops) == 0:
logging.debug("flops for {} empty skipping".format(kernel))
continue
flopsMetric = max(flops, key=flops.get)
# figure out which throughput is highest
throughput = dict()
for memMetric in rooflineMetricsMem:
if memMetric in kernelMetrics[kernel]:
throughput[memMetric] = statistics.mean(kernelMetrics[kernel][flopsMetric])
if len(throughput) == 0:
logging.debug("Throughput for {} empty skipping".format(kernel))
continue
memMetric = max(throughput, key=throughput.get)
durationList = kernelMetrics[kernel]["Duration"]
flopsList = kernelMetrics[kernel][flopsMetric]
memList = kernelMetrics[kernel][memMetric]
# really should use numpy for this but some systems don't have it installed
flopsPerSecList = [flops / duration if duration > 0 else 0 for flops, duration in zip(flopsList, durationList)]
throughputList = [mem / duration if duration > 0 else 0 for mem, duration in zip(flopsList, memList)]
#[flops / duration for flops, duration in zip
# calculate intensity for each memory type
# and add it to the list
for memMetric in rooflineMetricsMem:
logging.debug("Working on memory metric {}".format(memMetric))
if memMetric in kernelMetrics[kernel]:
#intensity = flops / statistics.mean(kernelMetrics[kernel][memMetric])
intensityList = [flops / data if data > 0 else 0 for flops, data in zip (flopsList, kernelMetrics[kernel][memMetric])]
invIntensityList = [data / flops if flops > 0 else 0 for flops, data in zip(flopsList, kernelMetrics[kernel][memMetric])]
#intensityList = flopsList / np.array(kernelMetrics[kernel][memMetric])
flopsInfo = abbrMetricNames[memMetric] + " " + abbrMetricNames[flopsMetric] + "/" + kernel
#print("kernel info {}".format(flopsInfo))
intensityStdDev = 0
flopsPerSecStdDev = 0
if len(intensityList) > 1:
intensityStdDev = statistics.stdev(intensityList)
invIntensityStdDev = statistics.stdev(invIntensityList)
flopsPerSecStdDev = statistics.stdev(flopsPerSecList)
throughputStdDev = statistics.stdev(kernelMetrics[kernel][memMetric])
rooflines[flopsInfo] = [statistics.mean(intensityList), statistics.mean(flopsPerSecList),
intensityStdDev, flopsPerSecStdDev]
memRooflines[flopsInfo] = [statistics.mean(invIntensityList), statistics.mean(kernelMetrics[kernel][memMetric]),
invIntensityStdDev, throughputStdDev]
return rooflines, memRooflines
from statistics import mean, median, mode, stdev, variance
pointers = [4, 5, 10, 2, 3, 5, 4, 3, 2, 5, 1, 0]
print('Mean: {0}'.format(mean(pointers)))
print('Median: {0}'.format(median(pointers)))
print('Mode: {0}'.format(mode(pointers)))
print('Std: {0}'.format(stdev(pointers)))
print('Variance: {0}'.format(variance(pointers)))
def simul_with_err2_vecchia(N1=100, N2=100, p=0.33, t=10000, rip=10):
from one_simulation import R_one_simulation, N_one_simulation
import my_print as my
import math
#import time
import statistics
#start = time.time()
S1 = int(math.sqrt(N1))
S2 = int(math.sqrt(N2))
print("S1 = {}".format(S1))
print("S2 = {}".format(S2), '\n')
dir_name = repr(N1) + '-' + repr(N2) + '-b'
eps = 1
R_S_list = ([], [])
R_m_Pn1 = [[] for x in range(0, N1)]
R_m_Pn2 = [[] for x in range(0, N2)]
R_mean_Pn1 = []
R_mean_Pn2 = []
N_S_list = ([], [])
N_m_Pn1 = [[] for x in range(0, N1)]
N_m_Pn2 = [[] for x in range(0, N2)]
N_mean_Pn1 = []
N_mean_Pn2 = []
for i in range(0, rip):
(R_S_mean1, R_S_mean2, R_Pn1, R_Pn2,
simulation_t) = R_one_simulation(N1,
N2,
S1,
S2,
eps,
p,
t,
dir_name,
i + 1,
flag=True)
(N_S_mean1, N_S_mean2, N_Pn1, N_Pn2,
simulation_t) = N_one_simulation(N1,
N2,
S1,
S2,
eps,
p,
t,
dir_name,
i + 1,
flag=True)
for k in range(len(N_Pn1)):
N_m_Pn1[k].append(N_Pn1[k])
for k in range(len(N_Pn2)):
N_m_Pn2[k].append(N_Pn2[k])
N_S_list[0].append(N_S_mean1)
N_S_list[1].append(N_S_mean2)
for k in range(len(R_Pn1)):
R_m_Pn1[k].append(R_Pn1[k])
for k in range(len(R_Pn2)):
R_m_Pn2[k].append(R_Pn2[k])
R_S_list[0].append(R_S_mean1)
R_S_list[1].append(R_S_mean2)
N_info_hist = {
'xlab': 'Numero individui n',
'ylab_1': 'Densità di prob P1',
'tit1': 'PDF specie I gruppo nested con eps = ' + repr(eps),
'ylab_2': 'Densità di prob P2',
'tit2': 'PDF specie II gruppo nested con eps = ' + repr(eps)
}
R_info_hist = {
'xlab': 'Numero individui n',
'ylab_1': 'Densità di prob P1',
'tit1': 'PDF specie I gruppo random con eps = ' + repr(eps),
'ylab_2': 'Densità di prob P2',
'tit2': 'PDF specie II gruppo random con eps = ' + repr(eps)
}
for k in range(N1):
N_mean_Pn1.append(statistics.mean(N_m_Pn1[k]))
for k in range(N2):
N_mean_Pn2.append(statistics.mean(N_m_Pn2[k]))
my.plot_hist(N_mean_Pn1, N_mean_Pn2, 'N', dir_name, N_info_hist)
N_S_mean_1 = statistics.mean(N_S_list[0])
N_S_dev_1 = statistics.stdev(N_S_list[0])
if N_S_dev_1 == 0:
N_S_dev_1 = 0.001
N_S_mean_2 = statistics.mean(N_S_list[1])
N_S_dev_2 = statistics.stdev(N_S_list[1])
if N_S_dev_2 == 0:
N_S_dev_2 = 0.001
for k in range(N1):
R_mean_Pn1.append(statistics.mean(R_m_Pn1[k]))
for k in range(N2):
R_mean_Pn2.append(statistics.mean(R_m_Pn2[k]))
my.plot_hist(R_mean_Pn1, R_mean_Pn2, 'R', dir_name, R_info_hist)
R_S_mean_1 = statistics.mean(R_S_list[0])
R_S_dev_1 = statistics.stdev(R_S_list[0])
if R_S_dev_1 == 0:
R_S_dev_1 = 0.001
R_S_mean_2 = statistics.mean(R_S_list[1])
R_S_dev_2 = statistics.stdev(R_S_list[1])
if R_S_dev_2 == 0:
R_S_dev_2 = 0.001
N_eps_S = (eps, N_S_mean_1, N_S_dev_1, N_S_mean_2, N_S_dev_2)
R_eps_S = (eps, R_S_mean_1, R_S_dev_1, R_S_mean_2, R_S_dev_2)
return (N_eps_S, R_eps_S)
def polynomial(request):
print("polynomial was called")
if request.method == 'POST':
form = FileForm(request.POST, request.FILES)
if form.is_valid():
sampleCsvFile = form.cleaned_data['sampleCsvFile']
dataframe = pd.read_csv("media/" +
str(form.cleaned_data['sampleCsvFile']))
dataset = dataframe.values
labels = dataframe.columns.values.tolist()
data_json = dataframe.to_json()
dataList = []
factorList = []
label_num = []
labels_str = []
for i in range(0, dataset.shape[1]):
if (not isinstance(dataset[0][i], str)):
label_num.append(labels[i])
sitenum = 0
max, min = 0, 0
sum = 0
datavec = []
for j in range(0, dataset.shape[0]):
datavec.append(dataset[j][i])
if (sitenum == 0):
max, mean, min = dataset[j][i], dataset[j][
i], dataset[j][i]
else:
if (dataset[j][i] > max):
max = dataset[j][i]
if (dataset[j][i] < min):
min = dataset[j][i]
sum = sum + dataset[j][i]
sitenum = sitenum + 1
dataList.append({
"parameter": labels[i],
"datavec": datavec,
"median": statistics.median(datavec),
"mean": statistics.mean(datavec),
"stdev": statistics.stdev(datavec),
"max": max,
"min": min,
"points": len(datavec),
"P99": np.percentile(datavec, 99),
"P95": np.percentile(datavec, 95),
"P75": np.percentile(datavec, 75),
"P25": np.percentile(datavec, 25),
"P05": np.percentile(datavec, 5),
"P01": np.percentile(datavec, 1),
})
else:
labels_str.append(labels[i])
datavec = []
for j in range(0, dataset.shape[0]):
datavec.append(dataset[j][i])
factorList.append({
"parameter": labels[i],
"datavec": datavec
})
return render(
request, 'data_model/polynomial.html', {
'form': form,
'dataList': dataList,
'factorList': factorList,
'data_json': data_json,
'dataset': dataset,
'labels_all': labels,
'labels': label_num,
'labels_str': labels_str,
'range': range(dataset.shape[1])
})
else:
print("form is not valid!")
return render(request, 'data_model/polynomial.html',
{'form': form})
else:
form = FileForm()
return render(request, 'data_model/polynomial.html', {'form': form})
scalingCoef = 0.15660133 / 7.0
spanTest = []
for i in range(200):
spanTest.append(span_data[i] - (1.06 / 7) * span_data[i])
finalCorrelation.append(correlationCoefTest[i][99] -
scalingCoef * span_data[i])
#Scaling coefficient
coef100 = 74.71029758
coef0 = 26.79919337
#Correlation process from correlation coeficients
for i in range(200):
correlationTest.append(
np.correlate(pressure_data[i], pressure_data[0]) * (10**(-9)) /
statistics.stdev(pressure_data[0]) *
statistics.stdev(pressure_data[i]) / 1.35200046)
#Plot properties
plt.style.use(["ggplot"])
plt.figure(figsize=(16, 9))
plt.ylim(bottom=0, top=1)
plt.xlim(left=0, right=8)
plt.xlabel('Z/D', fontsize=18)
plt.ylabel('R', fontsize=18)
plt.tick_params(labelsize=18)
#Experimental data plot
plt.scatter(span_data_blue,
correlation_blue,
s=100,
import statistics
i = [1, 2, 5, 6, 12, 19, 21, 27, 45, 75, 150]
AVG = sum(i) / len(i)
dev = statistics.stdev(i)
print(AVG)
print(dev)
l = []
for I in i:
l.append((I - AVG) / dev + 10)
norm = [float(i) / sum(l) * 100 for i in l]
print(l)
def getstdev(arg):
if len(arg) == 0:
return 0
else:
return round(statistics.stdev(arg),2)
gamma=gamma)
svmLib.clear_folds()
print 'fitting parameters...'
parameters = svmLib.fit_polynomial_parameters()
print 'parameters fitted', parameters
print 'testing model...'
errors = svmLib.test_polynomial_model(parameters["c"], parameters["g"],
parameters["d"])
print 'model tested', errors
mean = statistics.mean(errors)
standard_deviation = statistics.stdev(errors)
print 'mean', mean
print 'standard deviation', standard_deviation
f = open('svm_polynomial_kernel_results.txt', 'w')
f.write('C: ' + str(parameters['c']) + '\n')
f.write('gamma: ' + str(parameters['g']) + '\n')
f.write('degree: ' + str(parameters['d']) + '\n')
f.write('Mean: ' + str(mean) + '\n')
f.write('Standard deviation: ' + str(standard_deviation) + '\n')
f.close()
case: Series = case.T
control = control.T
dev_sum = case.std() + control.std()
query_signature = (case.mean() - control.mean()) / dev_sum
query_signature.loc[isinf(query_signature)] = nan
return query_signature.T
@jit
def signal_to_noise(case, control):
"""Calculates SNR as ratio of means difference and deviation sum.
Case and control has to be tuples or other hashable iterable.
Assumes that there are:
- at least two samples in both case and control
- the samples have non-zero variation
"""
dev_sum = (stdev(case) + stdev(control))
return ((mean(case) - mean(control)) / dev_sum) if dev_sum else nan
@jit()
def fold_change(case, control):
return mean(case) / mean(control)
@jit()
def signed_fold_change(case, control):
return abs(mean(case) / mean(control)) * sign(mean(case))
def game():
random.seed()
timeout = 3 # Set timeout for each action
total_moves = 0
total_score = 0
time.sleep(1)
os.system('mpg321 Audio/startgame.mp3')
time.sleep(1)
while total_moves < 10: # 10 moves in one game
action_num = random.randint(1,3) # generate move randomly
if action_num == 1:
action = "Shake"
os.system('mpg321 Audio/shake.mp3')
elif action_num == 2:
action = "Raise"
os.system('mpg321 Audio/raise.mp3')
else:
action = "Button"
os.system('mpg321 Audio/button.mp3')
print("Do action: "+action)
user_action = 0
start_action_time = time.time()
elapsed_action_time = time.time() - start_action_time
action_done = False
while (elapsed_action_time <= timeout) and (action_done is False):
# check if Shake or Raise moves are detected (done with accelerometer)
if (action_done is False):
x_out = []
y_out = []
z_out = []
for j in range(0,29): # take standard deviation over the past 30 readings in order to tell weather Shake or Raise actions were detected - raw readings were too inaccurate
x, y, z = accelerometer_fn.read_xyz()
x_out.append(x)
y_out.append(y)
z_out.append(z)
x_stdev = stdev(x_out)
y_stdev = stdev(y_out)
z_stdev = stdev(z_out)
if x_stdev > 10000 or y_stdev > 10000 or z_stdev > 10000:
action_done = True
user_action = "Shake"
if (x_stdev > 3000 and x_stdev < 7000) or (y_stdev > 3000 and y_stdev < 7000) or (z_stdev > 3000 and z_stdev < 7000):
action_done = True
user_action = "Raise"
# clear arrays to ensure next reading is correct
x_out.clear()
y_out.clear()
z_out.clear()
elapsed_action_time = time.time() - start_action_time
# check if Button move is detected
if (action_done is False):
input_state = GPIO.input(10)
if input_state == True:
action_done = True
user_action = "Button"
elapsed_action_time = time.time() - start_action_time
# When the button is pressed, the accelerometer detects the board moving, detecting Shake or Raise insted. So check if the botton is pressed after 0.1s of the deteced move
loopstart_time = time.time()
loop_time = time.time() - loopstart_time
if action_done is True and (user_action == "Shake" or user_action == "Raise") and loop_time < 0.1:
input_state = GPIO.input(10)
loop_time = time.time() - loopstart_time
if input_state == True:
action_done = True
user_action = "Button"
# Send game data to the database.
if action_done is False:
print("No action") # no move detected within timeout
mqtt_senddata.sendmove(action, timeout, constants_game.player, False)
elif user_action == action:
print("Right action "+str(action)) # right move is detected
total_score += 100 # 100 points for right move
if elapsed_action_time < 1:
total_score += 50 # plus 50 points for right move done within one second
print("score = "+str(total_score))
mqtt_senddata.sendmove(action, elapsed_action_time, constants_game.player, True)
else:
total_score -= 20 # -20 penalty for performing wrong action
print("Wrong action. Had to do "+str(action)+ ", done "+str(user_action)+" instead\n") # wrong move is detected
mqtt_senddata.sendmove(action, timeout, constants_game.player, False)
total_moves += 1
user_action = 0
time.sleep(2) #at the end of the move, wait before the next one
if total_score >= 1000:
mqtt_senddata.sendgame(True, total_score, constants_game.player)
else:
mqtt_senddata.sendgame(False, total_score, constants_game.player)
from pylab import axes
import matplotlib.pyplot as plt
import statistics
f_origin = open("./full_dataorigin", "r")
f_addscore = open("./full_addscore", "r")
f_scorenet = open("./full_scorenet", "r")
origin = []
for line in f_origin:
origin.append(float(line))
m = statistics.mean(origin)
sd = statistics.stdev(origin, xbar=m)
print(m)
print(sd)
addscore = []
for line in f_addscore:
addscore.append(float(line))
m = statistics.mean(addscore)
sd = statistics.stdev(addscore, xbar=m)
print(m)
print(sd)
scorenet = []
for line in f_scorenet:
scorenet.append(float(line))
m = statistics.mean(scorenet)
sd = statistics.stdev(scorenet, xbar=m)
print(m)
print(sd)
plt.boxplot([origin, addscore, scorenet])
dataset,
clasificadorSL_NB,
seed=seed)
aciertos_particion = [(1 - elem) for elem in errores_particion]
#if clasificadorSL_NB.Multinomial_flag == True:
# print("MultinomialNB")
#else:
print("GaussianNB")
#print("Errores particion: " + str(errores_particion))
#print("Media: " + str(statistics.mean(errores_particion)))
#print("Desv tipica: " + str(statistics.stdev(errores_particion)))
print("Aciertos particion: " + str(aciertos_particion))
print("Media: " + str(statistics.mean(aciertos_particion)))
print("Desv tipica: " + str(statistics.stdev(aciertos_particion)))
print("matriz confusion:\n" + str(clasificadorSL_NB.matriz_confusion))
print()
'''
# Prueba clasificador KNN
clasificadorSL_KNN = ClasificadorSL.ClasificadorKNN_SL("distance", 3)
errores_particion = clasificadorSL_KNN.validacion(val_cruzada, dataset, clasificadorSL_KNN, seed=seed)
aciertos_particion = [(1 - elem) for elem in errores_particion]
print("KNN")
#print("Errores particion: " + str(errores_particion))
#print("Media: " + str(statistics.mean(errores_particion)))
#print("Desv tipica: " + str(statistics.stdev(errores_particion)))
print("Aciertos particion: " + str(aciertos_particion))
parser.add_argument('--file', help='Input file')
parser.add_argument('--out', help='Outfile base')
parser.add_argument('--L', help='Fingerprint length')
parser.add_argument('--norm', help='Normalize')
args = parser.parse_args()
a = AnnoyIndex(int(args.L))
i = 0
names = []
with gzip.open(args.file, 'rt') as f:
for line in f:
id, statements, *v = line.split("\t")
id = re.sub('.json.gz', '', id)
id = re.sub('\.', '|', id)
names.append(id)
v = [float(j) for j in v]
if args.norm:
avg = statistics.mean(v)
std = statistics.stdev(v)
v = [(j - avg) / std for j in v]
a.add_item(i, v)
i = i + 1
a.build(-1)
a.save(args.out + '.tree')
with open(args.out + '.names', 'w') as f:
for item in names:
f.write("%s\n" % item)
def _mean_stdev(values):
mean = statistics.mean(values)
stdev = statistics.stdev(values, xbar=mean)
return (mean, stdev)
for _ in range(args.num_trials):
m = Manager()
return_dict = m.dict()
manager = Process(target=dealer_executor,
kwargs={
"f_all": f_all(),
"args_all": args_all(),
"kwargs_all": kwargs_all(),
"num_tasks": args.num_tasks,
"port": args.client_port,
"interchange": args.interchange,
"warmup": args.warmup,
"return_dict": return_dict
})
manager.start()
manager.join()
serialization_times.append(return_dict["avg_serialization_time"])
execution_times.append(return_dict["avg_execution_time"])
# Print stats
label = "[DEALER-INTERCHANGE-REP]" if args.interchange else "[DEALER-REP]"
s = stdev(serialization_times) if len(serialization_times) > 1 else 0
print("{} Avg Serialization Time\n"
"Mean = {:=10.4f} us, Stdev = {:=10.4f} us".format(
label, mean(serialization_times), s))
s = stdev(execution_times) if len(execution_times) > 1 else 0
print("{} Avg Execution Time\n"
"Mean = {:=10.4f} us, Stdev = {:=10.4f} us".format(
label, mean(execution_times), s))