def generate_weibull(size):
k1 = 0.5
scale1 = 0.3
dat1 = exponweib.rvs(a=1, c=k1, scale=scale1, size=size)
k2 = 1.1
scale2 = 0.1
dat2 = exponweib.rvs(a=1, c=k2, scale=scale2, size=size)
dat = np.concatenate([dat1, dat2])
return dat
def samples(self, size=1000):
'''
Generates samples from current Weibull distribution.
args:
size: The number of samples to be generated.
'''
return exponweib.rvs(a=1, c=self.k, scale=self.lmb, size=size)
def time_to_failure():
"""Return time until next failure for a machine."""
if not useWeibull:
nextFailure = int(random.expovariate(BREAK_MEAN))
else:
# The Weibull distr. generates many errors.
#nextFailure = int(np.random.weibull(WEIBULL_K)*98.0) # Gives MTBF to be 200
nextFailure = int(exponweib.rvs(1.0, WEIBULL_SHAPE, scale=WEIBULL_SCALE))
return nextFailure
def fit_weib2():
# 生成韦伯分布数据
sample = exponweib.rvs(a=10, c=1, scale=3, loc=0, size=1000)
x = np.linspace(0, np.max(sample), 100)
#拟合
a, c, loc, scale = exponweib.fit(sample, floc=0, fa=1)
print(a, c, loc, scale)
y = exponweib.pdf(x, a, c, loc, scale)
for x1, y1 in zip(x, y):
print(x1, y1)
plt.plot(x, y)
plt.show()
def example_4():
a, c = 3, 1
data = exponweib.rvs(a, c, size=1000)
pf = lambda ah, ch=c, d=data: -np.sum(np.log(exponweib.pdf(data, ah, ch)))
x0 = 2
sols = {}
methods = ["nelder-mead", "powell", "Anneal", "BFGS", "TNC", "L-BFGS-B", "SLSQP"]
for method in sorted(methods):
th = {'success': False}
while not th['success']:
th = minimizer(x0, pf, method)
print '{0} ({1}): {2}'.format(method, x0, th['message'])
x0 = np.random.uniform(0, 10)
sols[method] = th['x']
for i, (method, sol) in enumerate(sols.iteritems()):
print '{0}: {1}'.format(method, sol)
def example_2():
a, c = 3, 1
data = exponweib.rvs(a, c, size=1000)
l = round(max(data) - min(data))
pf = lambda ah, ch=c, d=data: np.sum(np.log(exponweib.pdf(data, ah, ch)))
e = 1 # step size of random-walk
qrf = lambda x, e=e: norm.rvs(x, e)
x0 = 2
ahs0 = metropolis_hastings(x0, 100000, pf, qrf)
# ahs = ahs0
ahs = prune(ahs0, l, e)
print 'Generated {0} samples after pruning from {1}.'.format(len(ahs), len(ahs0))
print min(ahs), max(ahs)
plt.axvline(a, label='theta', color='b', linestyle='--')
plt.hist(ahs, 100, normed=True, label='pruned m-h samples')
plt.legend()
# plt.savefig('../img/example-2.png')
plt.show()
def example_3():
a, c = 3, 1
data = exponweib.rvs(a, c, size=1000)
l = round(max(data) - min(data))
pf = lambda ah, ch=c, d=data: np.sum(np.log(exponweib.pdf(data, ah, ch)))
d = 1.0
Tf = lambda i: d/np.log(i+2) # cooling function
e = 1 # step size of random-walk
qrf = lambda x, e=e: norm.rvs(x, e)
x0 = 2
ahs0 = simulated_annealing(x0, 100000, pf, qrf, Tf)
print 'Generated {0} samples. MAP estimate is {1}'.format(len(ahs0), ahs0[-1])
plt.hist(ahs0, 100, normed=True, label='samples')
plt.axvline(a, label='theta', color='b', linestyle='--')
plt.axvline(ahs0[-1], label='theta-hat', color='c', linestyle='--')
plt.xlim([2.8, 3.4])
plt.legend()
# plt.savefig('../img/example-3.png')
plt.show()
def next_ttr(final_downtime_model, CRN=None):
dist = final_downtime_model[0]
params = final_downtime_model[1]
if dist == "uniform":
return uniform.rvs(*params, random_state=CRN)
elif dist == "expon":
return expon.rvs(*params, random_state=CRN)
elif dist == "rayleigh":
return rayleigh.rvs(*params, random_state=CRN)
elif dist == "weibull_min":
return weibull_min.rvs(*params, random_state=CRN)
elif dist == "gamma":
return gamma.rvs(*params, random_state=CRN)
elif dist == "gengamma":
return gengamma.rvs(*params, random_state=CRN)
elif dist == "invgamma":
return invgamma.rvs(*params, random_state=CRN)
elif dist == "gompertz":
return gompertz.rvs(*params, random_state=CRN)
elif dist == "lognorm":
return lognorm.rvs(*params, random_state=CRN)
elif dist == "exponweib":
return exponweib.rvs(*params, random_state=CRN)
# # # # plt.matshow(upper); # plt.colorbar(); # plt.show() # plt.matshow(lower); # plt.colorbar(); # plt.show(); # plt.matshow(median); # plt.colorbar(); # plt.show(); exit(); r = exponweib.rvs(1.0,2.0,loc=0.0,scale=1.0,size=10); interv = exponweib.interval(0.99,1.0,2.0,loc=0.0,scale=1.0) print(interv); binned,edges = np.histogram(r,bins, normed=True); fit = exponweib.fit(r); DF = bins - len(fit); print(DF) x = np.linspace(np.min(r),np.max(r),bins); y = exponweib.pdf(x,*fit); kern = scipy.stats.gaussian_kde(r)
def adult(frame, tpgroup, weibull, day):
# empexclude = False;
# if frame['empcode'] > -1:
# empexclude = True;
#revisit later
actlist = []
t = np.floor(exponweib.rvs(1.0, 1.8, scale=90)) + 120
act = 10101
locx = frame['addrx']
locy = frame['addry']
actlist += [(t, act, locx, locy)]
ct = t
while ct < 1440.0:
hour = np.floor(ct / 60.0)
g = tpgroup.get_group((day, hour))
#act = np.random.choice(g['dest'],p=(g['count']/np.sum(g['count'])) );
act = np.random.choice(g['dest'], p=g['prob'])
#handle movement
if act <= 189999 and act >= 180000:
#if we're travelling, we know we start at the current location
#so locx and locy remain the same
#but then we have to pick the next item
wb = weibull.ix[act]
t = np.floor(exponweib.rvs(1.0, wb['c'], scale=wb['scale'])) + 1
ct += t
actlist += [(t, act, locx, locy)]
#pick based on the type of travel and consider where we currently are
#determine maximum range based on travel time
#we assume an average speed of 60 kph using taxicab movement
#60 kph is 1000 m/min
dist = np.floor(800.0 * t)
#if we are working and we are NOT at work, go to work
#if we are at work, go home
if frame['empcode'] > -1 and act >= 180501 and act <= 180599:
if locx != frame['empx'] and locy != frame['empy']:
locx = frame['empx']
locy = frame['empy']
else:
locx = frame['addrx']
locy = frame['addry']
#if we are not travelling related to work, then
#we we are travelling somewhere else
#but, we might not travel directly home
else:
if locx == frame['addrx'] and locy == frame['addry']:
locx = np.random.randint(-dist, dist) + locx
locy = np.random.randint(-dist, dist) + locy
#after 4 PM 50% probability of going home
elif t > 720 and (np.random.rand() > 0.5):
locx = frame['addrx']
locy = frame['addry']
#after 8 PM 75% probability of going home
elif t > 960 and (np.random.rand() > 0.25):
locx = frame['addrx']
locy = frame['addry']
else:
locx = np.random.randint(-dist, dist) + frame['addrx']
locy = np.random.randint(-dist, dist) + frame['addry']
g = tpgroup.get_group((day, hour))
#act = np.random.choice(g['dest'],p=(g['count']/np.sum(g['count'])));
act = np.random.choice(g['dest'], p=g['prob'])
#teleport home if its after midnight
if t > 1200 and locx != frame['addrx'] and locy != frame['addry']:
locx = frame['addrx']
locy = frame['addry']
wb = weibull.ix[act]
t = np.floor(exponweib.rvs(1.0, wb['c'], scale=wb['scale'])) + 1
ct += t
actlist += [(t, act, locx, locy)]
return actlist
def rollweibull(act, tab):
wb = tab.ix[act]
return np.floor(exponweib.rvs(1.0, wb['c'], scale=wb['scale'])) + 1
def indchild(frame, tpgroup, weibull, day):
#we assume that school happens around 8:30 on a weekday for 6.5 hours
school = False
if day > 1 and day < 7:
school = True
if school:
if frame['age'] > 12: grid = 4000.0
elif frame['age'] > 10: grid = 2000.0
else: grid = 1000.0
actlist = []
t = np.floor(exponweib.rvs(1.0, 1.8, scale=90)) + 120
act = 10101
locx = frame['addrx']
locy = frame['addry']
actlist += [(t, act, locx, locy)]
ct = t
while ct < 1440.0:
#force school time
if school and t > (4.5 * 60.0 - 15) and t < (11.0 * 60.0 +
15) and act != 60101:
act = 180601
t = np.floor(exponweib.rvs(1.0, 1.5, scale=15)) + 1
ct += t
locx = frame['addrx']
locy = frame['addry']
actlist += [(t, act, locx, locy)]
t = (11.0 * 60.0) - ct
ct += t
act = 60101
locx = np.round(frame['addrx'] / grid, 0) * grid
locy = np.round(frame['addry'] / grid, 0) * grid
actlist += [(t, act, locx, locy)]
else:
hour = np.floor(ct / 60.0)
g = tpgroup.get_group((day, hour))
#act = np.random.choice(g['dest'],p=(g['count']/np.sum(g['count'])));
act = np.random.choice(g['dest'], p=g['prob'])
#handle movement
if act <= 189999 and act >= 180000:
#if we're travelling, we know we start at the current location
#so locx and locy remain the same
#but then we have to pick the next item
wb = weibull.ix[act]
t = np.floor(exponweib.rvs(1.0, wb['c'],
scale=wb['scale'])) + 1
ct += t
actlist += [(t, act, locx, locy)]
#pick based on the type of travel and consider where we currently are
#determine maximum range based on travel time
#we assume an average speed of 60 kph using taxicab movement
#30 mph is 800 m/min
dist = np.floor(800.0 * t)
#if we are working and we are NOT at work, go to work
#if we are at work, go home
if frame['empcode'] > -1 and act >= 180501 and act <= 180599:
if locx != frame['empx'] and locy != frame['empy']:
locx = frame['empx']
locy = frame['empy']
else:
locx = frame['addrx']
locy = frame['addry']
#if we are not travelling related to work, then
#we we are travelling somewhere else
#but, we might not travel directly home
else:
if locx == frame['addrx'] and locy == frame['addry']:
locx = np.random.randint(-dist, dist) + locx
locy = np.random.randint(-dist, dist) + locy
#after 4 PM 50% probability of going home
elif t > 720 and (np.random.rand() > 0.5):
locx = frame['addrx']
locy = frame['addry']
#after 8 PM 75% probability of going home
elif t > 960 and (np.random.rand() > 0.25):
locx = frame['addrx']
locy = frame['addry']
else:
locx = np.random.randint(-dist, dist) + frame['addrx']
locy = np.random.randint(-dist, dist) + frame['addry']
g = tpgroup.get_group((day, hour))
#act = np.random.choice(g['dest'],p=(g['count']/np.sum(g['count'])));
act = np.random.choice(g['dest'], p=g['prob'])
#teleport home if its after midnight
if t > 1200 and locx != frame['addrx'] and locy != frame['addry']:
locx = frame['addrx']
locy = frame['addry']
wb = weibull.ix[act]
t = np.floor(exponweib.rvs(1.0, wb['c'], scale=wb['scale'])) + 1
ct += t
actlist += [(t, act, locx, locy)]
return actlist
def samples(self, size = 1000):
return exponweib.rvs(a=1,c=self.k,scale=self.lmb,size=size)
exponweib.pdf(x, a, c),
'r-',
lw=5,
alpha=0.6,
label='exponweib pdf')
# Alternatively, the distribution object can be called (as a function)
# to fix the shape, location and scale parameters. This returns a "frozen"
# RV object holding the given parameters fixed.
# Freeze the distribution and display the frozen ``pdf``:
rv = exponweib(a, c)
ax.plot(x, rv.pdf(x), 'k-', lw=2, label='frozen pdf')
# Check accuracy of ``cdf`` and ``ppf``:
vals = exponweib.ppf([0.001, 0.5, 0.999], a, c)
np.allclose([0.001, 0.5, 0.999], exponweib.cdf(vals, a, c))
# True
# Generate random numbers:
r = exponweib.rvs(a, c, size=1000)
# And compare the histogram:
ax.hist(r, density=True, histtype='stepfilled', alpha=0.2)
ax.legend(loc='best', frameon=False)
plt.show()
def samples_(k, lmb, size=1000):
return exponweib.rvs(a=1, c=k, scale=lmb, size=size)
