def main(args):
# Next, we build a very simple model.
bests = []
worsts = []
averages = []
for i in range(args.n):
print("Training and evaluating iteration: ", i)
# SARSA does not require a memory.
agent = get_agent(args.agent, args.model, args.lr)
agent.fit(env, nb_steps=args.train_steps, visualize=False, verbose=2)
# After training is done, we save the final weights.
# sarsa.save_weights('sarsa_{}_weights.h5f'.format(ENV_NAME), overwrite=True)
# Finally, evaluate our algorithm for 5 episodes.
callback = EvaluationCallback(verbose=True)
agent.test(env,
nb_episodes=args.test_episodes,
callbacks=[callback],
verbose=0,
visualize=False)
best, worst, average = callback.get_result()
bests.append(best)
worsts.append(worst)
averages.append(average)
bests_mvs = bayes_mvs(bests)
worsts_mvs = bayes_mvs(worsts)
average_mvs = bayes_mvs(averages)
print("Best Performance: {:.2f} +- {:.2f}".format(
bests_mvs[0][0], bests_mvs[0][0] - bests_mvs[0][1][0]))
print("Worst Performance: {:.2f} +- {:.2f}".format(
worsts_mvs[0][0], worsts_mvs[0][0] - worsts_mvs[0][1][0]))
print("Average Performance: {:.2f} +- {:.2f}".format(
average_mvs[0][0], average_mvs[0][0] - average_mvs[0][1][0]))
def smith_cost(df, debug=False):
ire = df[df["effect"] == "Item repetition effect"]["contrast"]
cre1 = df[df["effect"] == "Context repetition, 1st target"]["contrast"]
cre2 = df[df["effect"] == "Context repetition, 2nd target"]["contrast"]
ire_mvs = bayes_mvs(ire)
cre1_mvs = bayes_mvs(cre1)
cre2_mvs = bayes_mvs(cre2)
if debug:
print(f"ire_mvs: {ire_mvs}")
print(f"cre1_mvs: {cre1_mvs}")
print(f"cre2_mvs: {cre2_mvs}")
ratio_top = cre1_mvs[0][0]
ratio_bottom = ire_mvs[0][0]
if np.isnan(ratio_top):
ratio_top = 0
if np.isnan(ratio_bottom):
ratio_bottom = 0.00001
ratio = ratio_top / ratio_bottom
ratio_cost = abs(ratio - 0.744) # cost = 0 if ratio is an exact match
# add 1 if ire and cre1 CIs don't overlap
# ire_cre1_overlap_cost = 1 - (
# (cre1_mvs[0][1][0] < ire_mvs[0][1][0]) and
# (cre1_mvs[0][1][1] < ire_mvs[0][1][1]) and
# (cre1_mvs[0][1][1] > ire_mvs[0][1][0])
# )
# add 1 if zero is in cre1 CI
cre1_ci_lo = cre1_mvs[0][1][0]
cre1_ci_hi = cre1_mvs[0][1][1]
if np.isnan(cre1_ci_lo) or np.isnan(cre1_ci_hi):
cre1_zero_cost = 1
else:
cre1_zero_cost = int(cre1_ci_lo < 0 < cre1_ci_hi)
# add 1 if zero is not in cre2 CI
cre2_ci_lo = cre2_mvs[0][1][0]
cre2_ci_hi = cre2_mvs[0][1][1]
if np.isnan(cre2_ci_lo) or np.isnan(cre2_ci_hi):
if np.isclose(cre2.mean(), 0):
cre2_zero_cost = 0
else:
cre2_zero_cost = 1
else:
cre2_zero_cost = 1 - int(cre2_ci_lo <= 0 <= cre2_ci_hi)
cost = ratio_cost + cre1_zero_cost + cre2_zero_cost
if debug:
print(f"Ratio cost: {ratio_cost}")
print(f"CRE1 zero cost: {cre1_zero_cost}")
print(f"CRE2 zero cost: {cre2_zero_cost}")
print(f"Total cost: {cost}")
return cost
def IntervalEstimation(the_list, ci=0.95):
"""
constrct a 95% C.I for the ...
"""
stats.bayes_mvs(the_list, ci)
#mean = np.mean(the_list)
#stdDeviation = np.std(the_list, ddof=1)
lower, upper = stats.bayes_mvs(the_list, ci)[0][1]
__printBlock(('constrct a ' + str(ci), '$(' + str(lower.round(3)) + ', ' + str(upper.round(3)) + ')'))
def plot_distribution_summaries(output_arrays, ax):
m = 1
low_lim, high_lim = [], []
for output_array in output_arrays:
mean, var, std = bayes_mvs(output_array)
low_lim.append(mean[0] - 1.96 * std[0])
high_lim.append(mean[0] + 1.96 * std[0])
markers, caps, bars = ax.errorbar([m - 0.5], [mean[0]],
yerr=[std[0] * 1.96],
fmt='o',
c='#000000',
capsize=3,
elinewidth=1,
markeredgewidth=1)
[bar.set_alpha(0.5) for bar in bars]
[cap.set_alpha(0.5) for cap in caps]
ax.scatter([m for _ in range(len(output_array))],
output_array,
marker='+',
s=1,
c=PLOT_COLORS[m - 1],
alpha=0.25)
m += 1
low_lim = np.max([np.min(low_lim), 0])
high_lim = np.max(high_lim)
span_lim = high_lim - low_lim
low_lim = low_lim - 2 * span_lim / 10
high_lim = high_lim + 3 * span_lim / 10
ax.set_ylim(low_lim, high_lim)
ax.set_xticks([m + 0.75 for m in range(len(output_arrays))])
ax.set_xticklabels(['obs.', 'gan', 'knn', 'mice'])
[lab.set_fontsize(6.5) for lab in ax.get_xticklabels()]
[lab.set_fontsize(6.5) for lab in ax.get_yticklabels()]
m = 1
for output_array in output_arrays:
mean, var, std = bayes_mvs(output_array)
y1, y2 = ax.get_ylim()
ax.annotate('%.2f ± %.2f' % (mean[0], std[0]),
xy=(m - 0.5, mean[0] + 1.96 * std[0] + (y2 - y1) / 10),
fontsize=6)
m += 1
def run(self):
"""
Resets env. Loop env.step and agent.step() until number of steps have been made.
If an env is done before the number of steps have been reached, the env is reset.
@return the total reward divided by the total number of episodes
"""
steps = 0
episodeCount = 0
totalReward = 0
episodeRewards = []
while steps < self._maxSteps:
self._env.seed(self._getSeed())
obs = self._env.reset()
episode = Episode(self._agent, self._env, obs, self._render,
self._renderDelay)
episode.addListener(self)
episodeSteps, episodeReward = episode.run()
logging.info("New episode")
steps += episodeSteps
totalReward += episodeReward
episodeRewards.append(episodeReward)
logging.info("Episode reward: " + str(episodeReward))
episodeCount += 1
try:
return stats.describe(episodeRewards), stats.bayes_mvs(
episodeRewards)
except ValueError as err:
print(err)
def estimator_boostrap_bayes(
err,
alpha=0.05,
):
from scipy.stats import bayes_mvs
mean, var, std = bayes_mvs(err, alpha=alpha)
return mean, var, std
def bayes_mvs_wrapper(sequence, alpha):
if max(sequence) == min(sequence):
return (np.mean(sequence), (np.mean(sequence), np.mean(sequence))), (0, (0,0)), (0, (0,0))
else:
return stats.bayes_mvs(sequence, alpha)
def getStatistics(list):
df = pd.DataFrame(list)
statsm = {}
mean, var, std = stats.bayes_mvs(df, alpha=0.95)
if math.isnan(mean[0]):
statsm['mean'] = 0
else:
statsm['mean'] = int(mean[0])
if math.isnan(var[0]):
statsm['var'] = 0
else:
statsm['var'] = int(var[0])
if math.isnan(std[0]):
statsm['std'] = 0
else:
statsm['std'] = int(std[0])
out = grubbs.max_test_outliers(list, alpha=0.05)
if out:
statsm['outlier'] = numpy.amax(out)
else:
statsm['outlier'] = 0
return statsm
def test_result_attributes(self):
x = np.arange(15)
attributes = ('statistic', 'minmax')
res = stats.bayes_mvs(x)
for i in res:
check_named_results(i, attributes)
def calculateMeans(df):
calcVectors = {}
calcVectors["_ids"] = df["_id"].tolist()
calcVectors["totals"] = df["total"].tolist()
calcVectors["region"] = df["region"][0]
calcVectors["hour"] = df["hour"][0]
calcVectors["region"] = df["region"][0]
calcVectors["weekday"] = df["weekday"][0]
mean, var, std = stats.bayes_mvs(df["total"].tolist())
if math.isnan(mean[0]):
calcVectors["mean"] = 0
else:
calcVectors["mean"] = int(mean[0])
if math.isnan(var[0]):
calcVectors["var"] = 0
else:
calcVectors["var"] = int(var[0])
if math.isnan(std[0]):
calcVectors["std"] = 0
else:
calcVectors["std"] = int(std[0])
calcVectors["outliers"] = outliersTest(df["total"].tolist())
out = []
for v in calcVectors["outliers"]:
q = df.query(df["total"] == v)["_id"].tolist()
out.append(q)
calcVectors["vector_ids"] = out
return calcVectors
def train_all(self, architecture, data,
seed=None, save_params=False, augment_fn=augment):
"""
Runs all training splits for a given architecture and caches trained
networks in a list.
"""
net_list = [] # initialize list
if seed:
np.random.seed(seed) # set random seed if provided
starttime = time.time() # set start time
num_splits = len(data[2])
for split in range(num_splits):
net = self.run_split(architecture, data, split, augment_fn)
net_list.append(net)
mvs = bayes_mvs([n.test_err for n in net_list ], alpha=.95) # get mean test performance after all splits complete
time_elapsed = time.time() - starttime # check total elapsed time
print("\n\nOVERALL RESULTS")
print("\tAverage NLL:\t\t{:.3f}".format(mvs[0][0]))
print("\tCred. Interval:\t\t[{:.3f}, {:.3f}]".format(mvs[0][1][0], mvs[0][1][1]))
print("\tTotal time:\t\t{:.2f}".format(time_elapsed))
return net_list
def test_result_attributes(self):
x = np.arange(15)
attributes = ('statistic', 'minmax')
res = stats.bayes_mvs(x)
for i in res:
check_named_results(i, attributes)
def fooof_channel_rejection(eeg, psds, freqs, f_low, f_high, participant,
session_name):
from scipy.stats import bayes_mvs
n_bads = 0
fooof_group = FOOOFGroup(max_n_peaks=6,
min_peak_amplitude=0.1,
peak_width_limits=[1, 12],
background_mode='knee')
fooof_group.fit(freqs, psds, freq_range=[f_low, f_high / 2], n_jobs=-1)
fooof_group_fig = fooof_group.plot(save_fig=True,
file_name='FOOOF_group_' + participant +
'_' + session_name,
file_path=data_dir + '/results/')
bg_slope = fooof_group.get_all_data('background_params', col='slope')
mean_cntr, var_cntr, std_cntr = bayes_mvs(bg_slope, alpha=0.9)
lower_slope = mean_cntr[1][0] - std_cntr[1][1]
upper_slope = mean_cntr[1][1] + std_cntr[1][1]
print('upper and lower slope range (mean, std)', lower_slope, upper_slope,
np.mean(bg_slope), np.std(bg_slope))
for channel_idx, slope in enumerate(bg_slope):
if slope < lower_slope or slope > upper_slope:
eeg.info['bads'].append(eeg.ch_names[channel_idx])
n_bads += 1
eeg.interpolate_bads(reset_bads=True)
return eeg, n_bads
def __init__(self, metric_name, measurements):
self._metric_name = metric_name
self._measurements = measurements
print("measurements:", self._measurements)
array = np.array(self._measurements)
self._stats = stats.describe(array)
self._bayes_mvs = stats.bayes_mvs(array)
def get_data(column, np_values, alpha):
mvs = bayes_mvs(np_values, alpha)
#report these metrics
output = [
present("Column", column),
present("Length", len(np_values)),
present("Unique", len(np.unique(np_values))),
present("Min", np_values.min()),
present("Max", np_values.max()),
present("Mid-Range", (np_values.max() - np_values.min()) / 2),
present("Range",
np_values.max() - np_values.min()),
present("Mean", np_values.mean()),
present("Mean-%s-CI" % alpha, tupleToString(mvs[0][1])),
present("Variance", mvs[1][0]),
present("Var-%s-CI" % alpha, tupleToString(mvs[1][1])),
present("StdDev", mvs[2][0]),
present("Std-%s-CI" % alpha, tupleToString(mvs[2][1])),
present("Mode",
stats.mode(np_values)[0][0]),
present("Q1", stats.scoreatpercentile(np_values, 25)),
present("Q2", stats.scoreatpercentile(np_values, 50)),
present("Q3", stats.scoreatpercentile(np_values, 75)),
present("Trimean", trimean(np_values)),
present("Minhinge", midhinge(np_values)),
present("Skewness", stats.skew(np_values)),
present("Kurtosis", stats.kurtosis(np_values)),
present("StdErr", sem(np_values)),
present("Normal-P-value",
normaltest(np_values)[1])
]
return output
def get_data(column, np_values, alpha):
mvs = bayes_mvs(np_values, alpha)
#report these metrics
output = [
present("Column", column),
present("Length", len(np_values)),
present("Unique", len(np.unique(np_values))),
present("Min", np_values.min()),
present("Max", np_values.max()),
present("Mid-Range", (np_values.max() - np_values.min())/2),
present("Range", np_values.max() - np_values.min()),
present("Mean", np_values.mean()),
present("Mean-%s-CI" % alpha, tupleToString(mvs[0][1])),
present("Variance", mvs[1][0]),
present("Var-%s-CI" % alpha, tupleToString(mvs[1][1])),
present("StdDev", mvs[2][0]),
present("Std-%s-CI" % alpha, tupleToString(mvs[2][1])),
present("Mode", stats.mode(np_values)[0][0]),
present("Q1", stats.scoreatpercentile(np_values, 25)),
present("Q2", stats.scoreatpercentile(np_values, 50)),
present("Q3", stats.scoreatpercentile(np_values, 75)),
present("Trimean", trimean(np_values)),
present("Minhinge", midhinge(np_values)),
present("Skewness", stats.skew(np_values)),
present("Kurtosis", stats.kurtosis(np_values)),
present("StdErr", sem(np_values)),
present("Normal-P-value", normaltest(np_values)[1])
]
return output
def evaluate(x, fp):
results_df = pd.DataFrame(columns=[
'Fingerprint', 'Average Precision', 'low_ap', 'high_ap',
'Training Set Size', 'Estimator'
])
count = 0
for size in x:
f = h5py.File(
'../../processed_data/' + fp + '_' + str(8192) + '_' + str(size) +
'_' + estimator_name + '.hdf5', 'r')
nranks = list()
aps = list()
for _ in range(5):
proba = f[f'repeat{_}']['prediction'][:].copy()
test_idx = f[f'repeat{_}']['test_idx'][:].copy()[~np.isinf(proba)]
cutoff = np.percentile(true_scores[test_idx], 0.3)
aps.append(
average_precision_score(true_scores[test_idx] < cutoff,
proba[~np.isinf(proba)]))
mean = expit(np.mean(logit(aps)))
cr = bayes_mvs(logit(aps))[0][1]
f.close()
results_df.loc[count] = [
fp, mean,
expit(cr[0]),
expit(cr[1]), size, estimator_name
]
count += 1
return results_df
def rmse_ci(attack, num_colluders):
print("{} colluders under attack {}".format(num_colluders, attack))
rms_errors = [
attack_rmse(attack, num_colluders)
for i in range(num_iterations_per_attack_size)
]
mean_ci, variance_ci, stddev_ci = bayes_mvs(rms_errors)
return mean_ci
def bayes_scale(s):
"""
Remove mean and divide by standard deviation, using bayes_kvm statistics.
"""
if sum(~np.isnan(s)) > 1:
bm, bv, bs = bayes_mvs(s[~np.isnan(s)])
return (s - bm.statistic) / bs.statistic
else:
return np.full(s.shape, np.nan)
def rm_outlier3(points, threshold=0.9):
try:
confidence = bayes_mvs(rm_outlier2(points), threshold)
return [
points[i] for i in range(0, len(points))
if confidence[i][0] != float('inf')
]
except:
return points
def __call__(self, alpha, df):
with warnings.catch_warnings():
warnings.simplefilter('error', RuntimeWarning)
try:
(mean, *_) = bayes_mvs(df, alpha=alpha)
except RuntimeWarning:
raise ValueError()
(_, (lower, upper)) = mean
return Band(lower, upper)
def part_b(fname=fname):
fname += '_b'
nsamps = int(1e5)
thetaA = np.zeros(nsamps)
thetaB = np.zeros(nsamps)
yA = np.zeros(nsamps)
yB = np.zeros(nsamps)
for i in range(nsamps): # do Monte Carlo
thetaA[i] = gamma.rvs(56, scale=1.0/59)
yA[i] = poisson.rvs(thetaA[i])
thetaB[i] = gamma.rvs(307, scale=1.0/219)
yB[i] = poisson.rvs(thetaB[i])
thetaBA = thetaB - thetaA
yBA = yB - yA
plt.figure()
plt.hist(thetaBA, bins=16, normed=True)
plt.xlabel(r'$\theta_B-\theta_A$',fontsize=labelFontSize)
plt.ylabel(r'$p(\theta_B-\theta_A)$',fontsize=labelFontSize)
plt.title(r"4.8b $\theta_B-\theta_A$",fontsize=titleFontSize)
plt.xticks(fontsize=tickFontSize)
plt.yticks(fontsize=tickFontSize)
plt.savefig(fname+'thetaBA.'+imgFmt, format=imgFmt)
plt.figure()
plt.hist(yBA, bins=16, normed=True)
plt.xlabel(r'$\tilde{Y}_B-\tilde{Y}_A$',fontsize=labelFontSize)
plt.ylabel(r'$p(\tilde{Y}_B-\tilde{Y}_A)$',fontsize=labelFontSize)
plt.title(r"4.8b $\tilde{Y}_B-\tilde{Y}_A$",fontsize=titleFontSize)
plt.xticks(fontsize=tickFontSize)
plt.yticks(fontsize=tickFontSize)
plt.savefig(fname+'yBA.'+imgFmt, format=imgFmt)
thetaCI = bayes_mvs(thetaB - thetaA, alpha=0.95)
yCI = bayes_mvs(yB - yA, alpha=0.95)
print("thetaCI = {0}".format(thetaCI[0][1]))
print("yCI = {0}".format(yCI[0][1]))
thetaCI2 = (np.percentile(thetaBA, 2.5), np.percentile(thetaBA, 97.5))
yCI2 = (np.percentile(yBA, 2.5), np.percentile(yBA, 97.5))
print("thetaCI2 = {0}".format(thetaCI2))
print("yCI2 = {0}".format(yCI2))
def posterior_mean(h_loaded, param_list):
mean_dict = {}
for param in param_list:
data = h_loaded.get_distribution(t=3)[0][param]
res_mean, res_var, res_std = stats.bayes_mvs(data, alpha=0.90)
mean_dict.update({param: res_mean[0]})
return mean_dict
def posterior_mean_and_credibility_intervals(
h_loaded, param="C_lambda", rounding=4):
data = h_loaded.get_distribution(t=3)[0][param]
res_mean, res_var, res_std = stats.bayes_mvs(data, alpha=0.90)
mean_cred_dict = {'mean': res_mean[0].round(rounding),
'lower': res_mean[1][0].round(rounding),
'upper': res_mean[1][1].round(rounding),
'std/n': round(res_std[0] / SMCABC_POPULATION_SIZE, rounding)}
return mean_cred_dict
def test_confidence_interval_for_variance(self):
n = 100
sample = []
for i in range(0, n):
sample.append(random())
mean = self.stat.calculate_mean(sample)
var = self.stat.calculate_variance(sample, mean)
center, lower, upper, precision = self.stat.confidence_interval_for_variance(
var, n, 0.95)
res = bayes_mvs(sample, 0.95)
self.assertAlmostEqual(lower, res[1][1][0])
self.assertAlmostEqual(upper, res[1][1][1])
def test_iterfilter(num_honest,
num_skewing,
num_avg,
num_times,
repetitions,
collusion_value,
randseed=None):
if randseed:
random.seed(randseed)
num_pre_avg = num_honest + num_skewing
recip_rms = []
expo_rms = []
for r in range(repetitions):
honest_data = [[
random.gauss(TRUTH, VARIANCE) for j in range(num_times)
] for i in range(num_honest)]
skewed_data = [[
random.gauss(collusion_value, VARIANCE) for j in range(num_times)
] for i in range(num_skewing)]
uncolluded_data = honest_data + skewed_data
sneaky_data = [[
sum([uncolluded_data[j][i]
for j in range(num_pre_avg)]) / num_pre_avg
for i in range(num_times)
]]
final_data = uncolluded_data + sneaky_data
recip_rms += [
rms_error(iterfilter(final_data, reciprocal), [TRUTH] * num_times)
]
expo_rms += [
rms_error(iterfilter(final_data, exponential), [TRUTH] * num_times)
]
recip_rms_bayes = stats.bayes_mvs(recip_rms)
expo_rms_bayes = stats.bayes_mvs(expo_rms)
return (recip_rms_bayes[0], expo_rms_bayes[0])
def test_iterfilter(num_honest, num_skewing, num_avg, num_times, repetitions, randseed=None):
if randseed:
random.seed(randseed)
num_pre_avg = num_honest + num_skewing
recip_rms = []
expo_rms = []
for r in range(repetitions):
honest_data = [[random.gauss(TRUTH, VARIANCE) for j in range(num_times)] for i in range(num_honest)]
skewed_data = [[random.gauss(COLLUSION_VALUE, VARIANCE) for j in range(num_times)] for i in range(num_skewing)]
uncolluded_data = honest_data + skewed_data
sneaky_data = [[sum([uncolluded_data[j][i] for j in range(num_pre_avg)])/num_pre_avg for i in range(num_times)]]
final_data = uncolluded_data + sneaky_data
recip_rms += [rms_error(iterfilter(final_data, reciprocal), [TRUTH] * num_times)]
expo_rms += [rms_error(iterfilter(final_data, exponential), [TRUTH] * num_times)]
recip_rms_bayes = stats.bayes_mvs(recip_rms)
expo_rms_bayes = stats.bayes_mvs(expo_rms)
return (recip_rms_bayes[0], expo_rms_bayes[0])
def fit_glm_bootstrap(self, glm_model, n=20):
"""Fit GLM, using bootstrap resamplig to estimate parameter distributions."""
data_dict = collections.defaultdict(list)
for _ in range(n):
beta_hat_poly, nll, aic = self.bootstrap_resample().fit_glm(
glm_model)
data_dict['beta_hat_poly'].append(beta_hat_poly)
data_dict['nll'].append(nll)
data_dict['AIC'].append(aic)
stat_dict = {'AIC': {}, 'nll': {}}
for key in ['AIC', 'nll']:
fit = sps.bayes_mvs(np.array(data_dict[key]))
stat_dict[key]['mean'] = {
'statistic': fit[0].statistic,
'minmax': list(fit[0].minmax)
}
stat_dict[key]['std'] = {
'statistic': fit[2].statistic,
'minmax': list(fit[2].minmax)
}
for bi, beta_data in enumerate(zip(*data_dict['beta_hat_poly'])):
key = f'b{bi}'
if np.abs(beta_data).sum() == 0:
continue
fit = sps.bayes_mvs(beta_data)
stat_dict[key] = {}
stat_dict[key]['mean'] = {
'statistic': fit[0].statistic,
'minmax': list(fit[0].minmax)
}
stat_dict[key]['std'] = {
'statistic': fit[2].statistic,
'minmax': list(fit[2].minmax)
}
return stat_dict
def _conf_interval(x, conf_level=0.95):
# Гистограмма
hist, bins = np.histogram(x)
width = np.diff(bins)
center = (bins[:-1] + bins[1:]) / 2
fig, ax = plt.subplots(figsize=(8, 4))
ax.bar(center, hist, align='center', width=width)
plt.savefig('..\\resources\\hist.png')
plt.show()
# Мат.ожидание, дисперсия, стандартное отклонение
mean_, variance_, std_ = stats.bayes_mvs(x, conf_level)
return mean_[0], mean_[1], variance_[0], variance_[1]
def _calculate_mean_and_confidence_intervals(vector):
bundled_stats = stats.bayes_mvs(vector)
mean = np.mean(vector)
lower_bound = bundled_stats[0][1][0]
upper_bound = bundled_stats[0][1][1]
if np.isnan(lower_bound):
lower_bound = mean
upper_bound = mean
return {
'mean': mean,
'lower_bound': lower_bound,
'upper_bound': upper_bound
}
def submit_time_histogram(arr):
"""
Use Matplotlib to plot a normalized histogram of submit times
"""
from math import ceil, log
try:
import matplotlib.mlab as mlab
from prettyplotlib import plt
except ImportError:
print(
'You must have Matplotlib and Prettyplotlib installed to plot a histogram.'
)
# Use Sturges' formula for number of bins: k = ceiling(log2 n + 1)
k = ceil(log(len(arr), 2) + 1)
n, bins, patches = plt.hist(arr,
k,
normed=1,
facecolor='green',
alpha=0.75)
# throw a PDF plot on top of it
#y = mlab.normpdf(bins, np.mean(arr), np.std(arr))
#l = plt.plot(bins, y, 'r--', linewidth=1)
# Get a Bayesian confidence interval for mean, variance, standard deviation
dmean, dvar, dsd = bayes_mvs(deltas)
# drop a line in at the mean for fun
plt.axvline(dmean[0], color='blue', alpha=0.5)
plt.axvspan(dmean[1][0], dmean[1][1], color='blue', alpha=0.5)
plt.axvline(np.median(deltas), color='y', alpha=0.5)
# Caclulate a Kernel Density Estimate
density = gaussian_kde(deltas)
xs = np.arange(0., np.max(deltas), 0.1)
density.covariance_factor = lambda: .25
density._compute_covariance()
plt.plot(xs, density(xs), color='m')
#FIXME: come up with better legend names
#plt.legend(('Normal Curve', 'Mean', 'Median', 'KDE'))
plt.legend(('Mean', 'Median', 'KDE'))
plt.xlabel('Submit Times (in Seconds)')
plt.ylabel('Probability')
plt.title('Histogram of Worker submit times')
plt.grid(True)
plt.show()
def random_sample(fdist, sample_size, runs=1000):
"""
Given an nltk.FreqDist, compute frequency distributions from random
of the data.
Returns the means for type count and number of hapaxes, with
confidence intervals: ((mean (min, max)), (mean (min, max)))
"""
stats_pool = []
for x in range(0, runs):
sample = nltk.FreqDist(
random.sample(list(fdist.elements()), sample_size))
stats_pool.append((
sample.B(), #number of types, realized productivity
len(sample.hapaxes()), # number of hapax legomena
))
stats_pool = np.array(stats_pool)
mean_types = st.bayes_mvs(stats_pool[:, 0])
mean_hapaxes = st.bayes_mvs(stats_pool[:, 1])
return mean_types, mean_hapaxes
def basicStats(x):
return pd.Series([
x.count(),
x.isna().sum(),
x.min(),
x.max(),
round(x.quantile(.25), 6),
round(x.quantile(.75), 6),
round(x.mean(), 6),
round(x.median(), 6),
round(x.sum(), 6),
round(x.sem(), 6),
round(stat.bayes_mvs(x, alpha=0.95)[0].minmax[0], 6),
round(stat.bayes_mvs(x, alpha=0.95)[0].minmax[1], 6),
round(x.var(), 6),
round(x.std(), 6),
round(x.skew(), 6),
round(x.kurt(), 6)
],
index=[
'總計', 'NAs', '最小值', '最大值', '25%分位數', '75%分位數', '均值',
'中位數', '總和', '平均值標準誤差', "LCL Mean", "UCL Mean", '方差',
'標準差', '偏度', '超額峰度'
])
def generate_plots(self, mcmc, map_fit=None, pdf_filename=None):
"""
Generate interactive or PDF plots from MCMC trace.
Parameters
----------
mcmc : pymc.MCMC
MCMC samples to plot
map_fit : pymc.MAP, optional, default=None
Plot the maximum a posteriori (MAP) estimate if provided.
pdf_filename : str, optional, default=None
If specified, generate a PDF containing plots.
"""
alpha = 0.95 # confidence interval width
print('')
print('Generating plots...')
from scipy.stats import bayes_mvs
with PdfPages(pdf_filename) as pdf:
for group in self.parameter_names:
print(group)
for name in self.parameter_names[group]:
try:
if map_fit:
mle = getattr(map_fit, name).value
else:
mle = getattr(mcmc, name).trace().mean()
trace = getattr(mcmc, name).trace()
mean_cntr, var_cntr, std_cntr = bayes_mvs(trace, alpha=alpha)
(center, (lower, upper)) = mean_cntr
if trace.std() == 0.0:
lower = upper = trace[0]
plt.figure(figsize=(12, 8))
plt.hold(True)
niterations = len(trace)
plt.plot([0, niterations], [mle, mle], 'r-')
plt.plot(trace, 'k.')
plt.xlabel('iteration')
plt.ylabel(name)
plt.title(name)
pdf.savefig()
plt.close()
except AttributeError as e:
pass
def test_basic(self):
# Expected values in this test simply taken from the function. For
# some checks regarding correctness of implementation, see review in
# gh-674
data = [6, 9, 12, 7, 8, 8, 13]
mean, var, std = stats.bayes_mvs(data)
assert_almost_equal(mean.statistic, 9.0)
assert_allclose(mean.minmax, (7.1036502226125329, 10.896349777387467),
rtol=1e-14)
assert_almost_equal(var.statistic, 10.0)
assert_allclose(var.minmax, (3.1767242068607087, 24.45910381334018),
rtol=1e-09)
assert_almost_equal(std.statistic, 2.9724954732045084, decimal=14)
assert_allclose(std.minmax, (1.7823367265645145, 4.9456146050146312),
rtol=1e-14)
def test_basic(self):
# Expected values in this test simply taken from the function. For
# some checks regarding correctness of implementation, see review in
# gh-674
data = [6, 9, 12, 7, 8, 8, 13]
mean, var, std = stats.bayes_mvs(data)
assert_almost_equal(mean.statistic, 9.0)
assert_allclose(mean.minmax, (7.1036502226125329, 10.896349777387467),
rtol=1e-14)
assert_almost_equal(var.statistic, 10.0)
assert_allclose(var.minmax, (3.1767242068607087, 24.45910381334018),
rtol=1e-09)
assert_almost_equal(std.statistic, 2.9724954732045084, decimal=14)
assert_allclose(std.minmax, (1.7823367265645145, 4.9456146050146312),
rtol=1e-14)
def dados():
clf = AdaBoostClassifier(n_estimators=50, learning_rate=1, random_state=0)
x, y = questao1()
modelo = clf.fit(x, y)
k = 10
scores = cross_val_score(modelo, x, y, cv=k)
cont = 0
for score in scores:
cont += 1
print("score " + str(cont) + ": ", score)
taxa_de_acerto = np.mean(scores)
print("Taxa de Acerto: ", taxa_de_acerto)
desvio = scores.std()
print("Desvio", desvio)
print(bayes_mvs(scores, 0.95))
def update_figure8(n_clicks, value, start_date, end_date, my_ticker_symbol,
confidence):
month = [
"January", "February", "March", "April", "May", "June", "July",
"August", "September", "October", "November", "December"
]
dataOpen = pdr.DataReader(value, 'yahoo', start_date, end_date)["Open"]
dataClose = pdr.DataReader(value, 'yahoo', start_date, end_date)["Close"]
dataLogReturns = np.log(dataClose) - np.log(dataOpen)
for i in value:
dataLogReturns = dataLogReturns.rename(columns={i: i + "_returns"})
dataLogReturns = dataLogReturns.assign(DateTime=dataLogReturns.index)
filter1 = dataLogReturns["DateTime"].dt.day_name()
dataLogReturns = dataLogReturns.assign(Day=filter1)
filter2 = dataLogReturns["DateTime"].dt.month_name()
dataLogReturns = dataLogReturns.assign(Month=filter2)
filter3 = dataLogReturns["DateTime"].dt.year
dataLogReturns = dataLogReturns.assign(Year=filter3)
i = my_ticker_symbol + "_returns"
res_mean, res_var, res_std = stats.bayes_mvs(dataLogReturns[i],
alpha=confidence)
res_mean1 = list(res_mean.minmax)
res_var1 = list(res_var.minmax)
table_header = [
html.Thead(
html.Tr([
html.Th("Stock"),
html.Th("Mean Range (Min,Max)"),
html.Th("Variance Range (Min,Max)")
]))
]
row1 = html.Tr([
html.Td(my_ticker_symbol),
html.Td("Min:" + str(res_mean1[0]) + " Max:" + str(res_mean1[1])),
html.Td("Min:" + str(res_var1[0]) + " Max:" + str(res_var1[1]))
])
table_body = [html.Tbody([row1])]
table = dbc.Table(table_header + table_body,
bordered=True,
dark=True,
hover=True)
return table
def show_summary(self, mcmc, map_fit=None):
"""
Show summary statistics of MCMC and (optionally) MAP estimates.
Parameters
----------
mcmc : pymc.MCMC
MCMC samples
map_fit : pymc.MAP, optional, default=None
The MAP fit.
TODO
----
* Automatically determine appropriate number of decimal places from statistical uncertainty.
* Automatically adjust concentration units (e.g. pM, nM, uM) depending on estimated affinity.
"""
# Compute summary statistics
alpha = 0.95 # confidence interval width
from scipy.stats import bayes_mvs
for group in self.parameter_names:
print(group)
for name in self.parameter_names[group]:
try:
if map_fit:
mle = getattr(map_fit, name).value
else:
mle = getattr(mcmc, name).trace().mean()
trace = getattr(mcmc, name).trace()
mean_cntr, var_cntr, std_cntr = bayes_mvs(trace, alpha=alpha)
(center, (lower, upper)) = mean_cntr
if trace.std() == 0.0:
lower = upper = trace[0]
if ('concentration' in name) or ('volume' in name):
print("%-64s : initial %7.1e final %7.1e : %7.1e [%7.1e, %7.1e]" % (name, trace[0], trace[-1], mle, lower, upper))
else:
print("%-64s : initial %7.1f final %7.1f : %7.1f [%7.1f, %7.1f]" % (name, trace[0], trace[-1], mle, lower, upper))
except AttributeError as e:
# Skip observed stochastics
pass
print('')
def confianca(self):
'''
funcao que realiza intervalo de confianca de cada serie de amostra
'''
self.juntaMesmoTipo()
for download in self.dadosOrganizados:
for serie in self.dadosOrganizados[download]:
interador = 0
confianca = []
for i in self.dadosOrganizados[download][serie][0]:
vetor = []
for numero in self.dadosOrganizados[download][serie]:
vetor.append(numero[interador])
if (len(list(set(vetor))) > 1):
confianca.append(stats.bayes_mvs(vetor,alpha=0.95)[0])
else:
confianca.append((vetor[0],(0,0)))
interador += 1
self.dadosOrganizados[download][serie].append({'confianca':confianca})
return self.dadosOrganizados, self.quantidade
def mean_intervals(dataset, column_label="irony", alpha=0.05):
""" Confidence confidence intervals for the mean of a bunch of samples
(1 for each different label).
Args:
DataFrame:: dataset
str::column_label: cloumn containing sample labels
float::alpha: first order risk
Return:
DataFrame
"""
intervals = []
for feature in dataset.columns:
if feature!=column_label:
temp = {}
for label, group in dataset.groupby(column_label):
mean, (inf, sup) = stats.bayes_mvs(group[feature], alpha=1-alpha)[0]
temp[label] = {"inf":inf, "mean":mean, "sup":sup}
intervals.append(DataFrame(temp).T)
return concat(intervals, keys=dataset.columns)
num_sensors = 20
biases = array([0.3 * sensor for sensor in range(num_sensors)])
compensated_biases = biases - array([mean(biases)] * num_sensors)
variances = array([(num_sensors - sensor + 1) / 2 for sensor in range(num_sensors)])
num_times = 10
true_value = lambda t: (t - num_times / 2) ** 4
num_readings = 500
reading_sampling = [readings_generator.readings(compensated_biases, variances, num_times, true_value) for i in
range(num_readings)]
bias_estimates = array([linear_solution_bias_estimate(r) for r in reading_sampling])
variance_estimates_with_estimated_biases = array(
[linear_solution_variance_estimate(r, b) for r, b in zip(reading_sampling, bias_estimates)])
alpha = 0.95
#variance_estimates[i,s] gives the estimate of sensor s in reading i.
#variance_estimates.transpose()[s, i] gives the same.
variance_cis = [stats.bayes_mvs(v_est, alpha) for v_est in variance_estimates_with_estimated_biases.transpose()]
v_mean_cis, v_var_cis, v_std_cis = zip(*variance_cis)
v_mean_cntrs, v_mean_bounds = zip(*v_mean_cis)
v_mean_lo, v_mean_hi = zip(*v_mean_bounds)
v_mean_lo_diff = array(v_mean_cntrs) - array(v_mean_lo)
v_mean_hi_diff = array(v_mean_hi) - array(v_mean_cntrs)
fig = pyplot.figure()
axes = fig.add_subplot(1, 1, 1)
axes.set_title('Variance Estimation (p={}, n={})'.format(alpha, num_readings))
axes.plot(variances)
axes.errorbar(range(num_sensors), v_mean_cntrs, vstack((v_mean_lo_diff, v_mean_hi_diff)))
reading_sampling = [readings_generator.readings(compensated_biases, variances, num_times, true_value) for i in
range(num_readings)]
variance_estimates_with_true_biases = array(
variance = 1
bias = 0
truth = 0
times = 10
num_sensors = 10
variances = [variance] * num_sensors
biases = [bias] * num_sensors
iter_rms_errors = []
mle_rms_errors = []
def truth_fn(t):
return truth
for i in range(repeats):
print ('{}/{}'.format(i, repeats))
readings = readings_generator.readings(biases, variances, times, truth_fn)
estimate = robust_aggregate.estimate(readings, exponential)
iter_rms_errors += [rms_error(estimate, [0]*num_sensors)]
mle_estiamte = mle.estimate(readings, variances, biases)
mle_rms_errors += [rms_error(mle_estiamte, [0]*num_sensors)]
iter_mvs = bayes_mvs(iter_rms_errors)
mle_mvs = bayes_mvs(mle_rms_errors)
pp.bar([0, 1], [iter_mvs[0][0], mle_mvs[0][0]], yerr=[iter_mvs[0][0]-iter_mvs[0][1][0], mle_mvs[0][0]-mle_mvs[0][1][0]])
pp.show()
for line in tt:
target_taxa.append(line.rstrip())
tt.close()
#now read in a collection of trees, calc branch lengths over sample, summarise and print out
branch_lengths = defaultdict(list) #key = taxa, value = list of brlens
treefile = open(sys.argv[3])
for line in treefile:
curr_tree = Tree(line.rstrip())
root_node = curr_tree.get_common_ancestor(outgroups)
if curr_tree != root_node:
curr_tree.set_outgroup(root_node)
print curr_tree
#bundle = curr_tree.check_monophyly(values=outgroups,target_attr='name')
#print bundle
#if bundle[0] == False:
# continue
#find common ancestor of the target taxa, and use this as the reference node for calculating branch lengths. This might not always be the measure you want!
reference_node = curr_tree.get_common_ancestor(target_taxa)
#if reference_node != curr_tree:
# curr_tree.set_outgroup(reference_node)
#calc distance from root to each branch of interest
for taxon in target_taxa:
dist = curr_tree.get_distance(taxon, reference_node)
branch_lengths[taxon].append(dist)
#now compute the credible intervals of the branch length for each of the target taxa
for taxon in branch_lengths:
mean, var, std = stats.bayes_mvs(branch_lengths[taxon], alpha=0.95)
print taxon + "\t" + str(mean[0]) + "\t" + str(mean[1][0]) + "\t" + str(mean[1][1])
def rmse_ci(attack, num_colluders):
print("{} colluders under attack {}".format(num_colluders, attack))
rms_errors = [attack_rmse(attack, num_colluders) for i in range(num_iterations_per_attack_size)]
mean_ci, variance_ci, stddev_ci = bayes_mvs(rms_errors)
return mean_ci
def intervaloConfianca(cop,limiteTempo,coeficientes,confidence = 0.99):
"""
Calcula o intervalo de confianca a partir da simulação usando a funcao e seus parametros
A simulação para no tempoLimite = distancia entre o primeiro e último evento
"""
qtdeSimulacoes = 100
serieSimulacao = []
serieIntervaloEntreChegadas = []
serieQtdeIntervalo = []
serieProbIntervalo = []
for simulacao in range(0,qtdeSimulacoes):
serieSimulacao.append([])
serieIntervaloEntreChegadas.append([])
serieQtdeIntervalo.append([])
serieProbIntervalo.append([])
tempoSimulacao = 0
# controlando por tempo
while tempoSimulacao < limiteTempo:
#tempoSimulacao = tempoSimulacao + invFuncWeibull(np.random.uniform(0,1),*coeficientes)
#serieSimulacao[simulacao].append(tempoSimulacao)
randomNumber = random.uniform(0,1)
ts = 0
while ts < 60:
if(funcWeibull(ts,*coeficientes)>randomNumber):
tempoSimulacao = tempoSimulacao + ts
serieSimulacao[simulacao].append(tempoSimulacao)
ts = 61
ts = ts + 1
"""
# por qtde
for item in range(0,limiteTempo+1):
serieSimulacao[simulacao].append(invFuncWeibull(np.random.uniform(0,1),*coeficientes))
"""
# calculo do intervalo entre chegadas
for i in range(0,len(serieSimulacao[simulacao])-1):
serieIntervaloEntreChegadas[simulacao].append(serieSimulacao[simulacao][i+1] - serieSimulacao[simulacao][i])
print 'QTDE======= ',len(serieIntervaloEntreChegadas[simulacao])
#calculo da qtde de chegadas em cada intervalo
for t in np.arange(0,61,1):
serieQtdeIntervalo[simulacao].append(float(len([q for q in serieIntervaloEntreChegadas[simulacao] if (q <= t)])))
#transformando qtde em porcentagem
for t in np.arange(0,61,1):
serieProbIntervalo[simulacao] = [q/float(serieQtdeIntervalo[simulacao][-1]) for q in serieQtdeIntervalo[simulacao]]
# calculo do IC para cada ponto da distribuicao
media = []
upper = []
lower = []
valoresPorInstante = []
for tempo in np.arange(0,61,1):
valoresPorInstante.append([])
for simulacao in range(0,qtdeSimulacoes):
#valoresPorInstante[tempo].append(serieQtdeIntervalo[simulacao][tempo])
valoresPorInstante[tempo].append(serieProbIntervalo[simulacao][tempo])
# gerando media e limites do IC
icmedia = str(bayes_mvs(valoresPorInstante[tempo],confidence)).split(')),')[0]
icmedia = icmedia.replace(" ","")
icmedia = icmedia.replace("(","")
icmedia = icmedia.replace(")","")
m,l,u = icmedia.split(',')
#dados da populacao
sizeData, (minimum,maximum),arithmeticMean,variance,skeness,kurtosis = stats.describe(valoresPorInstante[tempo])
#l,u = norm.interval(confidence, loc=arithmeticMean, scale=sqrt(variance))
#media.append(m)
tmp = 2.58 * sqrt(variance)/sqrt(len(valoresPorInstante[tempo]))
l = arithmeticMean - tmp
u = arithmeticMean + tmp
media.append(arithmeticMean)
lower.append(l)
upper.append(u)
return serieProbIntervalo, media,lower,upper
if __name__ == '__main__':
repeats = 1000
variance = 1
bias = 0
truth = 0
times = 10
num_sensors = 10
variances = [variance] * num_sensors
biases = [bias] * num_sensors
time_errors = [[] for t in range(times)]
def truth_fn(t):
return truth
for i in range(repeats):
print ('{}/{}'.format(i, repeats))
readings = readings_generator.readings(biases, variances, times, truth_fn)
estimate = robust_aggregate.estimate(readings, exponential)
for t in range(times):
time_errors[t] += [estimate[t]]
mvs = [bayes_mvs(t) for t in time_errors]
pp.errorbar(range(times), [m[0][0] for m in mvs], yerr=[m[0][0]-m[0][1][0] for m in mvs])
pp.show()
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--infile", required=True, help="Tabular file.")
parser.add_argument("-o", "--outfile", required=True, help="Path to the output file.")
parser.add_argument("--sample_one_cols", help="Input format, like smi, sdf, inchi")
parser.add_argument("--sample_two_cols", help="Input format, like smi, sdf, inchi")
parser.add_argument("--sample_cols", help="Input format, like smi, sdf, inchi,separate arrays using ;")
parser.add_argument("--test_id", help="statistical test method")
parser.add_argument(
"--mwu_use_continuity",
action="store_true",
default=False,
help="Whether a continuity correction (1/2.) should be taken into account.",
)
parser.add_argument(
"--equal_var",
action="store_true",
default=False,
help="If set perform a standard independent 2 sample test that assumes equal population variances. If not set, perform Welch's t-test, which does not assume equal population variance.",
)
parser.add_argument(
"--reta", action="store_true", default=False, help="Whether or not to return the internally computed a values."
)
parser.add_argument("--fisher", action="store_true", default=False, help="if true then Fisher definition is used")
parser.add_argument(
"--bias",
action="store_true",
default=False,
help="if false,then the calculations are corrected for statistical bias",
)
parser.add_argument("--inclusive1", action="store_true", default=False, help="if false,lower_limit will be ignored")
parser.add_argument(
"--inclusive2", action="store_true", default=False, help="if false,higher_limit will be ignored"
)
parser.add_argument("--inclusive", action="store_true", default=False, help="if false,limit will be ignored")
parser.add_argument(
"--printextras",
action="store_true",
default=False,
help="If True, if there are extra points a warning is raised saying how many of those points there are",
)
parser.add_argument(
"--initial_lexsort",
action="store_true",
default="False",
help="Whether to use lexsort or quicksort as the sorting method for the initial sort of the inputs.",
)
parser.add_argument("--correction", action="store_true", default=False, help="continuity correction ")
parser.add_argument(
"--axis",
type=int,
default=0,
help="Axis can equal None (ravel array first), or an integer (the axis over which to operate on a and b)",
)
parser.add_argument(
"--n",
type=int,
default=0,
help="the number of trials. This is ignored if x gives both the number of successes and failures",
)
parser.add_argument("--b", type=int, default=0, help="The number of bins to use for the histogram")
parser.add_argument("--N", type=int, default=0, help="Score that is compared to the elements in a.")
parser.add_argument("--ddof", type=int, default=0, help="Degrees of freedom correction")
parser.add_argument("--score", type=int, default=0, help="Score that is compared to the elements in a.")
parser.add_argument("--m", type=float, default=0.0, help="limits")
parser.add_argument("--mf", type=float, default=2.0, help="lower limit")
parser.add_argument("--nf", type=float, default=99.9, help="higher_limit")
parser.add_argument(
"--p",
type=float,
default=0.5,
help="The hypothesized probability of success. 0 <= p <= 1. The default value is p = 0.5",
)
parser.add_argument("--alpha", type=float, default=0.9, help="probability")
parser.add_argument("--new", type=float, default=0.0, help="Value to put in place of values in a outside of bounds")
parser.add_argument(
"--proportiontocut",
type=float,
default=0.0,
help="Proportion (in range 0-1) of total data set to trim of each end.",
)
parser.add_argument(
"--lambda_",
type=float,
default=1.0,
help="lambda_ gives the power in the Cressie-Read power divergence statistic",
)
parser.add_argument(
"--imbda",
type=float,
default=0,
help="If lmbda is not None, do the transformation for that value.If lmbda is None, find the lambda that maximizes the log-likelihood function and return it as the second output argument.",
)
parser.add_argument("--base", type=float, default=1.6, help="The logarithmic base to use, defaults to e")
parser.add_argument("--dtype", help="dtype")
parser.add_argument("--med", help="med")
parser.add_argument("--cdf", help="cdf")
parser.add_argument("--zero_method", help="zero_method options")
parser.add_argument("--dist", help="dist options")
parser.add_argument("--ties", help="ties options")
parser.add_argument("--alternative", help="alternative options")
parser.add_argument("--mode", help="mode options")
parser.add_argument("--method", help="method options")
parser.add_argument("--md", help="md options")
parser.add_argument("--center", help="center options")
parser.add_argument("--kind", help="kind options")
parser.add_argument("--tail", help="tail options")
parser.add_argument("--interpolation", help="interpolation options")
parser.add_argument("--statistic", help="statistic options")
args = parser.parse_args()
infile = args.infile
outfile = open(args.outfile, "w+")
test_id = args.test_id
nf = args.nf
mf = args.mf
imbda = args.imbda
inclusive1 = args.inclusive1
inclusive2 = args.inclusive2
sample0 = 0
sample1 = 0
sample2 = 0
if args.sample_cols != None:
sample0 = 1
barlett_samples = []
for sample in args.sample_cols.split(";"):
barlett_samples.append(map(int, sample.split(",")))
if args.sample_one_cols != None:
sample1 = 1
sample_one_cols = args.sample_one_cols.split(",")
if args.sample_two_cols != None:
sample_two_cols = args.sample_two_cols.split(",")
sample2 = 1
for line in open(infile):
sample_one = []
sample_two = []
cols = line.strip().split("\t")
if sample0 == 1:
b_samples = columns_to_values(barlett_samples, line)
if sample1 == 1:
for index in sample_one_cols:
sample_one.append(cols[int(index) - 1])
if sample2 == 1:
for index in sample_two_cols:
sample_two.append(cols[int(index) - 1])
if test_id.strip() == "describe":
size, min_max, mean, uv, bs, bk = stats.describe(map(float, sample_one))
cols.append(size)
cols.append(min_max)
cols.append(mean)
cols.append(uv)
cols.append(bs)
cols.append(bk)
elif test_id.strip() == "mode":
vals, counts = stats.mode(map(float, sample_one))
cols.append(vals)
cols.append(counts)
elif test_id.strip() == "nanmean":
m = stats.nanmean(map(float, sample_one))
cols.append(m)
elif test_id.strip() == "nanmedian":
m = stats.nanmedian(map(float, sample_one))
cols.append(m)
elif test_id.strip() == "kurtosistest":
z_value, p_value = stats.kurtosistest(map(float, sample_one))
cols.append(z_value)
cols.append(p_value)
elif test_id.strip() == "variation":
ra = stats.variation(map(float, sample_one))
cols.append(ra)
elif test_id.strip() == "itemfreq":
freq = stats.itemfreq(map(float, sample_one))
for list in freq:
elements = ",".join(map(str, list))
cols.append(elements)
elif test_id.strip() == "nanmedian":
m = stats.nanmedian(map(float, sample_one))
cols.append(m)
elif test_id.strip() == "variation":
ra = stats.variation(map(float, sample_one))
cols.append(ra)
elif test_id.strip() == "boxcox_llf":
IIf = stats.boxcox_llf(imbda, map(float, sample_one))
cols.append(IIf)
elif test_id.strip() == "tiecorrect":
fa = stats.tiecorrect(map(float, sample_one))
cols.append(fa)
elif test_id.strip() == "rankdata":
r = stats.rankdata(map(float, sample_one), method=args.md)
cols.append(r)
elif test_id.strip() == "nanstd":
s = stats.nanstd(map(float, sample_one), bias=args.bias)
cols.append(s)
elif test_id.strip() == "anderson":
A2, critical, sig = stats.anderson(map(float, sample_one), dist=args.dist)
cols.append(A2)
for list in critical:
cols.append(list)
cols.append(",")
for list in sig:
cols.append(list)
elif test_id.strip() == "binom_test":
p_value = stats.binom_test(map(float, sample_one), n=args.n, p=args.p)
cols.append(p_value)
elif test_id.strip() == "gmean":
gm = stats.gmean(map(float, sample_one), dtype=args.dtype)
cols.append(gm)
elif test_id.strip() == "hmean":
hm = stats.hmean(map(float, sample_one), dtype=args.dtype)
cols.append(hm)
elif test_id.strip() == "kurtosis":
k = stats.kurtosis(map(float, sample_one), axis=args.axis, fisher=args.fisher, bias=args.bias)
cols.append(k)
elif test_id.strip() == "moment":
n_moment = stats.moment(map(float, sample_one), n=args.n)
cols.append(n_moment)
elif test_id.strip() == "normaltest":
k2, p_value = stats.normaltest(map(float, sample_one))
cols.append(k2)
cols.append(p_value)
elif test_id.strip() == "skew":
skewness = stats.skew(map(float, sample_one), bias=args.bias)
cols.append(skewness)
elif test_id.strip() == "skewtest":
z_value, p_value = stats.skewtest(map(float, sample_one))
cols.append(z_value)
cols.append(p_value)
elif test_id.strip() == "sem":
s = stats.sem(map(float, sample_one), ddof=args.ddof)
cols.append(s)
elif test_id.strip() == "zscore":
z = stats.zscore(map(float, sample_one), ddof=args.ddof)
for list in z:
cols.append(list)
elif test_id.strip() == "signaltonoise":
s2n = stats.signaltonoise(map(float, sample_one), ddof=args.ddof)
cols.append(s2n)
elif test_id.strip() == "percentileofscore":
p = stats.percentileofscore(map(float, sample_one), score=args.score, kind=args.kind)
cols.append(p)
elif test_id.strip() == "bayes_mvs":
c_mean, c_var, c_std = stats.bayes_mvs(map(float, sample_one), alpha=args.alpha)
cols.append(c_mean)
cols.append(c_var)
cols.append(c_std)
elif test_id.strip() == "sigmaclip":
c, c_low, c_up = stats.sigmaclip(map(float, sample_one), low=args.m, high=args.n)
cols.append(c)
cols.append(c_low)
cols.append(c_up)
elif test_id.strip() == "kstest":
d, p_value = stats.kstest(
map(float, sample_one), cdf=args.cdf, N=args.N, alternative=args.alternative, mode=args.mode
)
cols.append(d)
cols.append(p_value)
elif test_id.strip() == "chi2_contingency":
chi2, p, dof, ex = stats.chi2_contingency(
map(float, sample_one), correction=args.correction, lambda_=args.lambda_
)
cols.append(chi2)
cols.append(p)
cols.append(dof)
cols.append(ex)
elif test_id.strip() == "tmean":
if nf is 0 and mf is 0:
mean = stats.tmean(map(float, sample_one))
else:
mean = stats.tmean(map(float, sample_one), (mf, nf), (inclusive1, inclusive2))
cols.append(mean)
elif test_id.strip() == "tmin":
if mf is 0:
min = stats.tmin(map(float, sample_one))
else:
min = stats.tmin(map(float, sample_one), lowerlimit=mf, inclusive=args.inclusive)
cols.append(min)
elif test_id.strip() == "tmax":
if nf is 0:
max = stats.tmax(map(float, sample_one))
else:
max = stats.tmax(map(float, sample_one), upperlimit=nf, inclusive=args.inclusive)
cols.append(max)
elif test_id.strip() == "tvar":
if nf is 0 and mf is 0:
var = stats.tvar(map(float, sample_one))
else:
var = stats.tvar(map(float, sample_one), (mf, nf), (inclusive1, inclusive2))
cols.append(var)
elif test_id.strip() == "tstd":
if nf is 0 and mf is 0:
std = stats.tstd(map(float, sample_one))
else:
std = stats.tstd(map(float, sample_one), (mf, nf), (inclusive1, inclusive2))
cols.append(std)
elif test_id.strip() == "tsem":
if nf is 0 and mf is 0:
s = stats.tsem(map(float, sample_one))
else:
s = stats.tsem(map(float, sample_one), (mf, nf), (inclusive1, inclusive2))
cols.append(s)
elif test_id.strip() == "scoreatpercentile":
if nf is 0 and mf is 0:
s = stats.scoreatpercentile(
map(float, sample_one), map(float, sample_two), interpolation_method=args.interpolation
)
else:
s = stats.scoreatpercentile(
map(float, sample_one), map(float, sample_two), (mf, nf), interpolation_method=args.interpolation
)
for list in s:
cols.append(list)
elif test_id.strip() == "relfreq":
if nf is 0 and mf is 0:
rel, low_range, binsize, ex = stats.relfreq(map(float, sample_one), args.b)
else:
rel, low_range, binsize, ex = stats.relfreq(map(float, sample_one), args.b, (mf, nf))
for list in rel:
cols.append(list)
cols.append(low_range)
cols.append(binsize)
cols.append(ex)
elif test_id.strip() == "binned_statistic":
if nf is 0 and mf is 0:
st, b_edge, b_n = stats.binned_statistic(
map(float, sample_one), map(float, sample_two), statistic=args.statistic, bins=args.b
)
else:
st, b_edge, b_n = stats.binned_statistic(
map(float, sample_one),
map(float, sample_two),
statistic=args.statistic,
bins=args.b,
range=(mf, nf),
)
cols.append(st)
cols.append(b_edge)
cols.append(b_n)
elif test_id.strip() == "threshold":
if nf is 0 and mf is 0:
o = stats.threshold(map(float, sample_one), newval=args.new)
else:
o = stats.threshold(map(float, sample_one), mf, nf, newval=args.new)
for list in o:
cols.append(list)
elif test_id.strip() == "trimboth":
o = stats.trimboth(map(float, sample_one), proportiontocut=args.proportiontocut)
for list in o:
cols.append(list)
elif test_id.strip() == "trim1":
t1 = stats.trim1(map(float, sample_one), proportiontocut=args.proportiontocut, tail=args.tail)
for list in t1:
cols.append(list)
elif test_id.strip() == "histogram":
if nf is 0 and mf is 0:
hi, low_range, binsize, ex = stats.histogram(map(float, sample_one), args.b)
else:
hi, low_range, binsize, ex = stats.histogram(map(float, sample_one), args.b, (mf, nf))
cols.append(hi)
cols.append(low_range)
cols.append(binsize)
cols.append(ex)
elif test_id.strip() == "cumfreq":
if nf is 0 and mf is 0:
cum, low_range, binsize, ex = stats.cumfreq(map(float, sample_one), args.b)
else:
cum, low_range, binsize, ex = stats.cumfreq(map(float, sample_one), args.b, (mf, nf))
cols.append(cum)
cols.append(low_range)
cols.append(binsize)
cols.append(ex)
elif test_id.strip() == "boxcox_normmax":
if nf is 0 and mf is 0:
ma = stats.boxcox_normmax(map(float, sample_one))
else:
ma = stats.boxcox_normmax(map(float, sample_one), (mf, nf), method=args.method)
cols.append(ma)
elif test_id.strip() == "boxcox":
if imbda is 0:
box, ma, ci = stats.boxcox(map(float, sample_one), alpha=args.alpha)
cols.append(box)
cols.append(ma)
cols.append(ci)
else:
box = stats.boxcox(map(float, sample_one), imbda, alpha=args.alpha)
cols.append(box)
elif test_id.strip() == "histogram2":
h2 = stats.histogram2(map(float, sample_one), map(float, sample_two))
for list in h2:
cols.append(list)
elif test_id.strip() == "ranksums":
z_statistic, p_value = stats.ranksums(map(float, sample_one), map(float, sample_two))
cols.append(z_statistic)
cols.append(p_value)
elif test_id.strip() == "ttest_1samp":
t, prob = stats.ttest_1samp(map(float, sample_one), map(float, sample_two))
for list in t:
cols.append(list)
for list in prob:
cols.append(list)
elif test_id.strip() == "ansari":
AB, p_value = stats.ansari(map(float, sample_one), map(float, sample_two))
cols.append(AB)
cols.append(p_value)
elif test_id.strip() == "linregress":
slope, intercept, r_value, p_value, stderr = stats.linregress(
map(float, sample_one), map(float, sample_two)
)
cols.append(slope)
cols.append(intercept)
cols.append(r_value)
cols.append(p_value)
cols.append(stderr)
elif test_id.strip() == "pearsonr":
cor, p_value = stats.pearsonr(map(float, sample_one), map(float, sample_two))
cols.append(cor)
cols.append(p_value)
elif test_id.strip() == "pointbiserialr":
r, p_value = stats.pointbiserialr(map(float, sample_one), map(float, sample_two))
cols.append(r)
cols.append(p_value)
elif test_id.strip() == "ks_2samp":
d, p_value = stats.ks_2samp(map(float, sample_one), map(float, sample_two))
cols.append(d)
cols.append(p_value)
elif test_id.strip() == "mannwhitneyu":
mw_stats_u, p_value = stats.mannwhitneyu(
map(float, sample_one), map(float, sample_two), use_continuity=args.mwu_use_continuity
)
cols.append(mw_stats_u)
cols.append(p_value)
elif test_id.strip() == "zmap":
z = stats.zmap(map(float, sample_one), map(float, sample_two), ddof=args.ddof)
for list in z:
cols.append(list)
elif test_id.strip() == "ttest_ind":
mw_stats_u, p_value = stats.ttest_ind(
map(float, sample_one), map(float, sample_two), equal_var=args.equal_var
)
cols.append(mw_stats_u)
cols.append(p_value)
elif test_id.strip() == "ttest_rel":
t, prob = stats.ttest_rel(map(float, sample_one), map(float, sample_two), axis=args.axis)
cols.append(t)
cols.append(prob)
elif test_id.strip() == "mood":
z, p_value = stats.mood(map(float, sample_one), map(float, sample_two), axis=args.axis)
cols.append(z)
cols.append(p_value)
elif test_id.strip() == "shapiro":
W, p_value, a = stats.shapiro(map(float, sample_one), map(float, sample_two), args.reta)
cols.append(W)
cols.append(p_value)
for list in a:
cols.append(list)
elif test_id.strip() == "kendalltau":
k, p_value = stats.kendalltau(
map(float, sample_one), map(float, sample_two), initial_lexsort=args.initial_lexsort
)
cols.append(k)
cols.append(p_value)
elif test_id.strip() == "entropy":
s = stats.entropy(map(float, sample_one), map(float, sample_two), base=args.base)
cols.append(s)
elif test_id.strip() == "spearmanr":
if sample2 == 1:
rho, p_value = stats.spearmanr(map(float, sample_one), map(float, sample_two))
else:
rho, p_value = stats.spearmanr(map(float, sample_one))
cols.append(rho)
cols.append(p_value)
elif test_id.strip() == "wilcoxon":
if sample2 == 1:
T, p_value = stats.wilcoxon(
map(float, sample_one),
map(float, sample_two),
zero_method=args.zero_method,
correction=args.correction,
)
else:
T, p_value = stats.wilcoxon(
map(float, sample_one), zero_method=args.zero_method, correction=args.correction
)
cols.append(T)
cols.append(p_value)
elif test_id.strip() == "chisquare":
if sample2 == 1:
rho, p_value = stats.chisquare(map(float, sample_one), map(float, sample_two), ddof=args.ddof)
else:
rho, p_value = stats.chisquare(map(float, sample_one), ddof=args.ddof)
cols.append(rho)
cols.append(p_value)
elif test_id.strip() == "power_divergence":
if sample2 == 1:
stat, p_value = stats.power_divergence(
map(float, sample_one), map(float, sample_two), ddof=args.ddof, lambda_=args.lambda_
)
else:
stat, p_value = stats.power_divergence(map(float, sample_one), ddof=args.ddof, lambda_=args.lambda_)
cols.append(stat)
cols.append(p_value)
elif test_id.strip() == "theilslopes":
if sample2 == 1:
mpe, met, lo, up = stats.theilslopes(map(float, sample_one), map(float, sample_two), alpha=args.alpha)
else:
mpe, met, lo, up = stats.theilslopes(map(float, sample_one), alpha=args.alpha)
cols.append(mpe)
cols.append(met)
cols.append(lo)
cols.append(up)
elif test_id.strip() == "combine_pvalues":
if sample2 == 1:
stat, p_value = stats.combine_pvalues(
map(float, sample_one), method=args.med, weights=map(float, sample_two)
)
else:
stat, p_value = stats.combine_pvalues(map(float, sample_one), method=args.med)
cols.append(stat)
cols.append(p_value)
elif test_id.strip() == "obrientransform":
ob = stats.obrientransform(*b_samples)
for list in ob:
elements = ",".join(map(str, list))
cols.append(elements)
elif test_id.strip() == "f_oneway":
f_value, p_value = stats.f_oneway(*b_samples)
cols.append(f_value)
cols.append(p_value)
elif test_id.strip() == "kruskal":
h, p_value = stats.kruskal(*b_samples)
cols.append(h)
cols.append(p_value)
elif test_id.strip() == "friedmanchisquare":
fr, p_value = stats.friedmanchisquare(*b_samples)
cols.append(fr)
cols.append(p_value)
elif test_id.strip() == "fligner":
xsq, p_value = stats.fligner(center=args.center, proportiontocut=args.proportiontocut, *b_samples)
cols.append(xsq)
cols.append(p_value)
elif test_id.strip() == "bartlett":
T, p_value = stats.bartlett(*b_samples)
cols.append(T)
cols.append(p_value)
elif test_id.strip() == "levene":
w, p_value = stats.levene(center=args.center, proportiontocut=args.proportiontocut, *b_samples)
cols.append(w)
cols.append(p_value)
elif test_id.strip() == "median_test":
stat, p_value, m, table = stats.median_test(
ties=args.ties, correction=args.correction, lambda_=args.lambda_, *b_samples
)
cols.append(stat)
cols.append(p_value)
cols.append(m)
cols.append(table)
for list in table:
elements = ",".join(map(str, list))
cols.append(elements)
outfile.write("%s\n" % "\t".join(map(str, cols)))
outfile.close()
def rm_outlier3(points, threshold=0.9):
try:
confidence = bayes_mvs(rm_outlier2(points), threshold)
return [points[i] for i in range(0, len(points)) if confidence[i][0] != float('inf')]
except:
return points
truth = [TRUTH * num_sensors for i in range(num_times)]
for i in range(num_repetitions):
readings = [[random.gauss(TRUTH, VARIANCE) for i in range(num_sensors)] for j in range(num_times)]
for j in range(num_times):
recip_iterative_result = iterative_filter.by_time(readings[0:j+1], iterative_filter.reciprocal)
exp_iterative_result = iterative_filter.by_time(readings[0:j+1], iterative_filter.exponential)
recip_avg_error = rms_error(recip_iterative_result[0:1], [TRUTH] * len(recip_iterative_result))
exp_avg_error = rms_error(exp_iterative_result[0:1], [TRUTH] * len(exp_iterative_result))
recip_error_calcs[j].append(recip_avg_error)
exp_error_calcs[j].append(exp_avg_error)
recip_error_bayes = [stats.bayes_mvs(x) for x in recip_error_calcs]
exp_error_bayes = [stats.bayes_mvs(x) for x in exp_error_calcs]
slice_length = range(1, num_times + 1)
recip_mids = [t[0][0] for t in recip_error_bayes]
recip_errors = [e[0][1][0]-m for (e, m) in zip(recip_error_bayes, recip_mids)]
exp_mids = [t[0][0] for t in exp_error_bayes]
exp_errors = [e[0][1][0]-m for (e, m) in zip(exp_error_bayes, exp_mids)]
pp.errorbar(slice_length, recip_mids, yerr=recip_errors, label='reciprocal discriminant')
pp.errorbar(slice_length, exp_mids, yerr=exp_errors, label='exponential discriminant')
pp.xlabel('Instants')
pp.ylabel('RMS Error')
pp.title('RMS Error using discriminant (n={})'.format(num_repetitions))
def confidence_interval(self, fun, alpha=0.95):
"will return mean, confidence interval"
return bayes_mvs(self.map_doc_scores(fun), alpha)[0]
def get_conf_interval(dataset):
if len(dataset) > 1:
return stats.bayes_mvs(dataset, alpha=.9)[0][1]
else:
return (None, None)
def gMIC(distrib):
"""
Bayesian estimates of mean, and standard deviation
"""
estimates = spp.bayes_mvs(distrib,alpha=0.95)[0]
return[estimates[0],estimates[1][0],estimates[1][1]]
iter_recip = []
iter_expo = []
robust_agg_recip = []
robust_agg_expo = []
for i in range(repeats):
print (i)
readings = readings_generator.readings(biases, variances, num_times, truth)
#iter_recip += [rms_error(iterfilter(readings, reciprocal), [0]*num_sensors)]
iter_expo += [rms_error(iterfilter(readings, exponential), [0]*num_sensors)]
#robust_agg_recip += [rms_error(estimate(readings, reciprocal), [0]*num_sensors)]
robust_agg_expo += [rms_error(estimate(readings, exponential), [0]*num_sensors)]
#iter_recip_mean = bayes_mvs(iter_recip)[0]
iter_expo_mean = bayes_mvs(iter_expo)[0]
#robust_agg_recip_mean = bayes_mvs(robust_agg_recip)[0]
robust_agg_expo_mean = bayes_mvs(robust_agg_expo)[0]
#iter_recip_means += [iter_recip_mean[0]]
iter_expo_means += [iter_expo_mean[0]]
#robust_agg_recip_means += [robust_agg_recip_mean[0]]
robust_agg_expo_means += [robust_agg_expo_mean[0]]
#iter_recip_errors += [iter_recip_mean[0] - iter_recip_mean[1][0]]
iter_expo_errors += [iter_expo_mean[0] - iter_expo_mean[1][0]]
#robust_agg_recip_errors += [robust_agg_recip_mean[0] - robust_agg_recip_mean[1][0]]
robust_agg_expo_errors += [robust_agg_expo_mean[0] - robust_agg_expo_mean[1][0]]
#pp.errorbar(x_values, iter_recip_means, yerr=iter_recip_errors, label='Iterative Filtering - reciprocal')
pp.errorbar(x_values, iter_expo_means, yerr=iter_expo_errors, label='Iterative Filtering - exponential')
