def displacements(self,
select='all',
deltas=None,
srange=None,
sample_size=100,
corr=None,
stats=None):
I = self.select(select)
s = Sampler(*srange) if srange else Sampler(self.start, self.stop)
if deltas is None:
deltas = get_exponential_deltas(s.start, s.stop)
if corr is None:
corr = correlator
if stats is None:
stats = mean_var
data = [[
stats(data) for data in zip(*[
iterable(corr(*self.get_rand_pair(s, delta), I))
for _ in range(sample_size)
])
] for delta in deltas]
results = [
list(zip(*[dat[j] for dat in data])) for j in range(len(data[0]))
]
return deltas, results
def chan_stats(x,m,v,s,k):
xptr = x.ctypes.data_as(ctypes.POINTER(ctypes.c_float))
stats_out = stats.stats(xptr, len(z), ctypes.byref(m),ctypes.byref(v), ctypes.byref(s), ctypes.byref(k))
#print 'mean = %f, variance = %f, skew = %f, kurtosis = %f' %(m.value, v.value, s.value, k.value)
#print 'expected values: %f, %f, %f, %f' %(mu, sig, scipy.stats.skew(x), scipy.stats.kurtosis(x))
#norm_kurt = scipy.stats.kurtosistest(x)
#print norm_kurt
#count, bins, ignored = plt.hist(x, 500, normed=True)
#plt.plot(bins, 1/(sig * np.sqrt(2 * np.pi)) * np.exp(-(bins-mu)**2 / (2*sig**2)))
#plt.show()
return np.array([m.value, v.value, s.value, k.value])
import numpy as np
import ctypes
import matplotlib.pyplot as plt
import scipy.stats
n = 1000000
mu = 0
sig = np.sqrt(0.1)
x = np.random.normal(mu,sig,n).astype(np.float32)
print x
m = ctypes.c_double()
v = ctypes.c_double()
s = ctypes.c_double()
k = ctypes.c_double()
stats = ctypes.cdll.LoadLibrary("./stats.so")
xptr = x.ctypes.data_as(ctypes.POINTER(ctypes.c_float))
stats.stats(xptr, n, ctypes.byref(m),ctypes.byref(v), ctypes.byref(s), ctypes.byref(k))
print 'mean = %f, variance = %f, skew = %f, kurtosis = %f' %(m.value, v.value, s.value, k.value)
print 'expected values: %f, %f, %f, %f' %(mu, sig, scipy.stats.skew(x), scipy.stats.kurtosis(x))
norm_kurt = scipy.stats.kurtosistest(x)
print norm_kurt
count, bins, ignored = plt.hist(x, 500, normed=True)
plt.plot(bins, 1/(sig * np.sqrt(2 * np.pi)) * np.exp(-(bins-mu)**2 / (2*sig**2)))
plt.show()
import ctypes
import matplotlib.pyplot as plt
import scipy.stats
n = 1000000
mu = 0
sig = np.sqrt(0.1)
x = np.random.normal(mu, sig, n).astype(np.float32)
print x
m = ctypes.c_double()
v = ctypes.c_double()
s = ctypes.c_double()
k = ctypes.c_double()
stats = ctypes.cdll.LoadLibrary("./stats.so")
xptr = x.ctypes.data_as(ctypes.POINTER(ctypes.c_float))
stats.stats(xptr, n, ctypes.byref(m), ctypes.byref(v), ctypes.byref(s),
ctypes.byref(k))
print 'mean = %f, variance = %f, skew = %f, kurtosis = %f' % (m.value, v.value,
s.value, k.value)
print 'expected values: %f, %f, %f, %f' % (mu, sig, scipy.stats.skew(x),
scipy.stats.kurtosis(x))
norm_kurt = scipy.stats.kurtosistest(x)
print norm_kurt
count, bins, ignored = plt.hist(x, 500, normed=True)
plt.plot(
bins,
1 / (sig * np.sqrt(2 * np.pi)) * np.exp(-(bins - mu)**2 / (2 * sig**2)))
plt.show()
def ave_vol(self, srange=None, sample_size=100, stats=None):
s = Sampler(*srange) if srange else Sampler(self.start, self.stop)
if stats is None:
stats = mean_var
v = stats([self[s.sample()].get_volume() for _ in range(sample_size)])
return v