def fit_fisk(data, mode=1):
prob = np.sum(data == 1.0) / float(data.shape[0])
num_one = np.sum(data == 1.0)
trunc_data = data[data != 1.0]
fisk_params = [np.nan, 0.0, np.nan]
if len(trunc_data) > 0:
if mode == 0:
fisk_params = fisk.fit(trunc_data, floc=0.0)
else:
fisk_params = fisk.fit(trunc_data)
return [prob, fisk_params]
def fit_fisk(signal, tag):
mu, loc, std = fisk.fit(signal["mean"].values)
confidence_interval = fisk.interval(CONFIDENCE, mu, loc=loc, scale=std)
if PLOTTING:
# Plot the histogram.
plt.subplots()
plt.hist(signal["mean"].values,
bins=25,
density=True,
alpha=0.6,
color="g")
# Plot the PDF.
xmin, xmax = plt.xlim()
x = np.linspace(xmin, xmax, 100)
p = fisk.pdf(x, mu, loc, std)
plt.plot(x, p, "k", linewidth=1)
title = "Fit results fisk: a=%2f loc = %.2f, std = %.2f" % (mu, loc,
std)
plt.title(title)
plt.axvline(x=confidence_interval[0])
plt.axvline(x=confidence_interval[1])
# Plot the confidence interval
plt.savefig(f"analysis/images/{slugify(tag)}_fit_fisk_histogram.png",
format="png")
return {
"distribution": "fisk",
"params": [{
"a": mu,
"loc": loc,
"std": std
}],
"confidence": [confidence_interval],
}
def run_Parametric(story_id, data):
print "[" + str(story_id) + "]Fitting Fisk"
fisk_params = fisk.fit(data, floc=0)
fisk_nll = fisk.nnlf(fisk_params, data)
fisk_rvs = fisk.rvs(*fisk_params, size=data.shape[0])
ks_fisk = ks_2samp(data, fisk_rvs)
bic_fisk = compute_BIC(data, len(fisk_params), fisk_nll)
print "[" + str(story_id) + "]Fitting IG"
ig_params = invgauss.fit(data, floc=0)
ig_nll = invgauss.nnlf(ig_params, data)
ig_rvs = invgauss.rvs(*ig_params, size=data.shape[0])
ks_ig = ks_2samp(data, ig_rvs)
bic_ig = compute_BIC(data, len(ig_params), ig_nll)
print "[" + str(story_id) + "]Fitting LN"
ln_params = lognorm.fit(data, floc=0)
ln_nll = lognorm.nnlf(ln_params, data)
ln_rvs = lognorm.rvs(*ln_params, size=data.shape[0])
ks_ln = ks_2samp(data, ln_rvs)
bic_ln = compute_BIC(data, len(ln_params), ln_nll)
print "[" + str(story_id) + "]Fitting Weibull"
weib_params = weibull_min.fit(data, floc=0)
weib_nll = weibull_min.nnlf(weib_params, data)
weib_rvs = weibull_min.rvs(*weib_params, size=data.shape[0])
ks_weib = ks_2samp(data, weib_rvs)
bic_weib = compute_BIC(data, len(weib_params), weib_nll)
print "[" + str(story_id) + "]Fitting Gamma"
gamma_params = gamma.fit(data, floc=0)
gamma_nll = gamma.nnlf(gamma_params, data)
gamma_rvs = gamma.rvs(*gamma_params, size=data.shape[0])
ks_gamma = ks_2samp(data, gamma_rvs)
bic_gamma = compute_BIC(data, len(gamma_params), gamma_nll)
return [
fisk_nll, ig_nll, ln_nll, weib_nll, gamma_nll, ks_fisk, ks_ig, ks_ln,
ks_weib, ks_gamma, bic_fisk, bic_ig, bic_ln, bic_weib, bic_gamma,
fisk_params, ig_params, ln_params, weib_params, gamma_params
]
def fit_fisk_loop(data):
loop_false = (data > 0)
loop_true = (data < 0)
data_false = data[loop_false]
data_true = data[loop_true]
loop_prob = np.sum(loop_false) / float(data.shape[0])
fisk_trunc_fit = np.array([np.nan, 0.0, np.nan])
nll_false = 0
nll_true = 0
if np.sum(loop_false) > 0:
trunc_data = data_false[data_false < 1.0]
prior = (len(data_false) - len(trunc_data)) / float(len(data_false))
if trunc_data.shape[0] > 0:
distribution = TruncatedFisk_Prior
rv_fisk_false = distribution(trunc_data)
res_fisk_false = rv_fisk_false.fit()
fisk_trunc_fit = np.array(
[prior, res_fisk_false.params[0], res_fisk_false.params[1]])
nll_false = np.sum(rv_fisk_false.nloglikeobs(
res_fisk_false.params))
if np.sum(loop_true) > 0:
fisk_trueloop_fit = fisk.fit(np.abs(data_true), floc=0.0)
nll_true = -np.sum(
np.log(
lognorm.pdf(np.abs(data_true), fisk_trueloop_fit[0],
fisk_trueloop_fit[1], fisk_trueloop_fit[2]) +
1e-200))
else:
fisk_trueloop_fit = np.array([np.nan, 0.0, np.nan])
nll = nll_false + nll_true
return [loop_prob, fisk_trunc_fit, fisk_trueloop_fit, nll]