def d_param(self, diff):
'''function takes different values for difference step, and returns true or false flag if acf and pacf values
lie into the threshold area'''
THRESHOLD = 0.08
if diff == 0:
acf = tss.acf(self.val)
pacf = tss.pacf(self.val)
# acf and pacf plots
fig = plt.figure(figsize = (12,8))
ax1 = fig.add_subplot(121)
fig = plot_acf(self.val,lags =40 ,ax=ax1)
ax2 = fig.add_subplot(122, sharey=ax1)
fig= plot_pacf(self.val, lags = 40, ax =ax2)
plt.savefig('ACF_vs_PACF.jpg')
plt.close()
# check if most acf and pacf are lie in the accepted region for diff0
acf_percent = len(acf[np.abs(acf) <= THRESHOLD])/float(len(acf))
pacf_percent = len(pacf[np.abs(pacf) <= THRESHOLD])/float(len(pacf))
return (acf_percent >= .65) and (pacf_percent >= 0.65)
elif diff == 1:
diff1_acf = tss.acf(self.diff1_val.dropna())
diff1_pacf = tss.pacf(self.diff1_val.dropna())
# for acf and pacf plots
fig = plt.figure(figsize = (12,8))
ax1 = fig.add_subplot(121)
fig = plot_acf(self.diff1_val.dropna(),lags =40 ,ax=ax1)
ax2 = fig.add_subplot(122, sharey=ax1)
fig= plot_pacf(self.diff1_val.dropna(), lags = 40, ax =ax2)
plt.savefig('ACF_vs_PACF_diff1.jpg')
plt.close()
# check if most acf and pacf are lie in the accepted region for diff1
acf_percent = len(diff1_acf[np.abs(diff1_acf) <= THRESHOLD])/float(len(diff1_acf))
pacf_percent = len(diff1_pacf[np.abs(diff1_pacf) <= THRESHOLD])/float(len(diff1_pacf))
return (acf_percent >= .65) and (pacf_percent >= 0.65)
elif diff == 2:
diff2_acf = tss.acf(self.diff2_val.dropna())
diff2_pacf = tss.pacf(self.diff2_val.dropna())
# check save fig for acf and pacf plots
fig = plt.figure(figsize = (12,8))
ax1 = fig.add_subplot(121)
fig = plot_acf(self.diff2_val.dropna(),lags =40 ,ax=ax1)
ax2 = fig.add_subplot(122, sharey=ax1)
fig = plot_pacf(self.diff2_val.dropna(), lags = 40, ax =ax2)
plt.savefig('ACF_vs_PACF_diff2.jpg')
plt.close()
# check if most acf and pacf are lie in the accepted region for diff2
acf_percent = len(diff2_acf[np.abs(diff2_acf) <= THRESHOLD])/float(len(diff2_acf))
pacf_percent = len(diff2_pacf[np.abs(diff2_pacf) <= THRESHOLD])/float(len(diff2_pacf))
return (acf_percent >= .65) and (pacf_percent >= 0.65)
else:
raise InvalidParamError
def plot_acf_multiple(ys, lags=20):
"""
"""
from scikits.statsmodels.tsa.stattools import acf
# hack
old_size = mpl.rcParams['font.size']
mpl.rcParams['font.size'] = 8
plt.figure(figsize=(10, 10))
xs = np.arange(lags + 1)
acorr = np.apply_along_axis(lambda x: acf(x, nlags=lags), 0, ys)
k = acorr.shape[1]
for i in range(k):
ax = plt.subplot(k, 1, i + 1)
ax.vlines(xs, [0], acorr[:, i])
ax.axhline(0, color='k')
ax.set_ylim([-1, 1])
# hack?
ax.set_xlim([-1, xs[-1] + 1])
mpl.rcParams['font.size'] = old_size
def plot_acf_multiple(ys, lags=20):
"""
"""
from scikits.statsmodels.tsa.stattools import acf
# hack
old_size = mpl.rcParams['font.size']
mpl.rcParams['font.size'] = 8
plt.figure(figsize=(10, 10))
xs = np.arange(lags + 1)
acorr = np.apply_along_axis(lambda x: acf(x, nlags=lags), 0, ys)
k = acorr.shape[1]
for i in range(k):
ax = plt.subplot(k, 1, i + 1)
ax.vlines(xs, [0], acorr[:, i])
ax.axhline(0, color='k')
ax.set_ylim([-1, 1])
# hack?
ax.set_xlim([-1, xs[-1] + 1])
mpl.rcParams['font.size'] = old_size
def plot_acf(y, lags=100, partial=False, ax=None):
from scikits.statsmodels.tsa.stattools import acf, pacf
if partial:
the_acf = pacf(y, nlags=lags)
else:
the_acf = acf(y, nlags=lags)
if ax is None:
fig = plt.figure(figsize=(10, 5))
ax = fig.add_subplot(111)
ax.vlines(np.arange(lags + 1), [0], the_acf)
ax.axhline(0, color='k')
def plot_acf(y, lags=100, partial=False, ax=None):
from scikits.statsmodels.tsa.stattools import acf, pacf
if partial:
the_acf = pacf(y, nlags=lags)
else:
the_acf = acf(y, nlags=lags)
if ax is None:
fig = plt.figure(figsize=(10, 5))
ax = fig.add_subplot(111)
ax.vlines(np.arange(lags+1), [0], the_acf)
ax.axhline(0, color='k')
def __init__(self):
self.acf = self.results['acvarfft']
self.qstat = self.results['Q1']
self.res1 = acf(self.x, nlags=40, qstat=True, fft=True)
def __init__(self):
self.acf = self.results['acvar']
#self.acf = np.concatenate(([1.], self.acf))
self.qstat = self.results['Q1']
self.res1 = acf(self.x, nlags=40, qstat=True)
def __init__(self):
self.acf = self.results['acvarfft']
self.qstat = self.results['Q1']
self.res1 = acf(self.x, nlags=40, qstat=True, fft=True)
def __init__(self):
self.acf = self.results['acvar']
#self.acf = np.concatenate(([1.], self.acf))
self.qstat = self.results['Q1']
self.res1 = acf(self.x, nlags=40, qstat=True)
def acorr_ljungbox(x, lags=None, boxpierce=False):
'''Ljung-Box test for no autocorrelation
Parameters
----------
x : array_like, 1d
data series, regression residuals when used as diagnostic test
lags : None, int or array_like
If lags is an integer then this is taken to be the largest lag
that is included, the test result is reported for all smaller lag length.
If lags is a list or array, then all lags are included up to the largest
lag in the list, however only the tests for the lags in the list are
reported.
If lags is None, then the default maxlag is 12*(nobs/100)^{1/4}
boxpierce : {False, True}
If true, then additional to the results of the Ljung-Box test also the
Box-Pierce test results are returned
Returns
-------
lbvalue : float or array
test statistic
pvalue : float or array
p-value based on chi-square distribution
bpvalue : (optionsal), float or array
test statistic for Box-Pierce test
bppvalue : (optional), float or array
p-value based for Box-Pierce test on chi-square distribution
Notes
-----
Ljung-Box and Box-Pierce statistic differ in their scaling of the
autocorrelation function. Ljung-Box test is reported to have better
small sample properties.
could be extended to work with more than one series
1d or nd ? axis ? ravel ?
needs more testing
''Verification''
Looks correctly sized in Monte Carlo studies.
not yet compared to verified values
Examples
--------
see example script
References
----------
Greene
Wikipedia
'''
x = np.asarray(x)
nobs = x.shape[0]
if lags is None:
lags = range(1, 41) #TODO: check default; SS: changed to 40
elif isinstance(lags, int):
lags = range(1, lags + 1)
maxlag = max(lags)
lags = np.asarray(lags)
acfx = acf(x, nlags=maxlag) # normalize by nobs not (nobs-nlags)
# SS: unbiased=False is default now
# acf2norm = acfx[1:maxlag+1]**2 / (nobs - np.arange(1,maxlag+1))
acf2norm = acfx[1:maxlag + 1]**2 / (nobs - np.arange(1, maxlag + 1))
qljungbox = nobs * (nobs + 2) * np.cumsum(acf2norm)[lags - 1]
pval = stats.chi2.sf(qljungbox, lags)
if not boxpierce:
return qljungbox, pval
else:
qboxpierce = nobs * np.cumsum(acfx[1:maxlag + 1]**2)[lags]
pvalbp = stats.chi2.sf(qboxpierce, lags)
return qljungbox, pval, qboxpierce, pvalbp
# plt.show()
# print adfuller(x_diff_1, regression="c") #The Augmented Dickey-Fuller test
x_fit, res, lag = create_ar_modex(x)
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.plot(x[lag:])
ax.plot(x_fit[lag:])
plt.legend(labels=['X', 'AR model'])
plt.show()
plt.bar(range(len(res)), res)
plt.show()
# check auto correlation
acf = stattools.acf(res, nlags=100)
plt.bar(range(len(acf)), acf)
plt.show()
# lbs = stattools.q_stat(acf, len(res[lag:]))
# plt.bar(range(len(lbs[1])), lbs[1])
# plt.show()
# print adfuller(res, regression="c") # The Augmented Dickey-Fuller test
# y_fit, res = create_ar_modex(y)
# fig = plt.figure()
# ax = fig.add_subplot(1,1,1)
# ax.plot(y)
# ax.plot(y_fit)
# plt.legend(labels=['Y', 'AR model'])
from scikits.statsmodels.tsa.arima_process import arma_generate_sample, arma_impulse_response
from scikits.statsmodels.tsa.arima_process import arma_acovf, arma_acf, ARIMA
# from movstat import acf, acovf
# from scikits.statsmodels.sandbox.tsa import acf, acovf, pacf
from scikits.statsmodels.tsa.stattools import acf, acovf, pacf
ar = [1.0, -0.6]
# ar = [1., 0.]
ma = [1.0, 0.4]
# ma = [1., 0.4, 0.6]
# ma = [1., 0.]
mod = "" #'ma2'
x = arma_generate_sample(ar, ma, 5000)
x_acf = acf(x)[:10]
x_ir = arma_impulse_response(ar, ma)
# print x_acf[:10]
# print x_ir[:10]
# irc2 = np.correlate(x_ir,x_ir,'full')[len(x_ir)-1:]
# print irc2[:10]
# print irc2[:10]/irc2[0]
# print irc2[:10-1] / irc2[1:10]
# print x_acf[:10-1] / x_acf[1:10]
# detrend helper from matplotlib.mlab
def detrend(x, key=None):
if key is None or key == "constant":
return detrend_mean(x)
elif key == "linear":
def acorr_ljungbox(x, lags=None, boxpierce=False):
'''Ljung-Box test for no autocorrelation
Parameters
----------
x : array_like, 1d
data series, regression residuals when used as diagnostic test
lags : None, int or array_like
If lags is an integer then this is taken to be the largest lag
that is included, the test result is reported for all smaller lag length.
If lags is a list or array, then all lags are included up to the largest
lag in the list, however only the tests for the lags in the list are
reported.
If lags is None, then the default maxlag is 12*(nobs/100)^{1/4}
boxpierce : {False, True}
If true, then additional to the results of the Ljung-Box test also the
Box-Pierce test results are returned
Returns
-------
lbvalue : float or array
test statistic
pvalue : float or array
p-value based on chi-square distribution
bpvalue : (optionsal), float or array
test statistic for Box-Pierce test
bppvalue : (optional), float or array
p-value based for Box-Pierce test on chi-square distribution
Notes
-----
Ljung-Box and Box-Pierce statistic differ in their scaling of the
autocorrelation function. Ljung-Box test is reported to have better
small sample properties.
could be extended to work with more than one series
1d or nd ? axis ? ravel ?
needs more testing
''Verification''
Looks correctly sized in Monte Carlo studies.
not yet compared to verified values
Examples
--------
see example script
References
----------
Greene
Wikipedia
'''
x = np.asarray(x)
nobs = x.shape[0]
if lags is None:
lags = range(1,41) #TODO: check default; SS: changed to 40
elif isinstance(lags, int):
lags = range(1,lags+1)
maxlag = max(lags)
lags = np.asarray(lags)
acfx = acf(x, nlags=maxlag) # normalize by nobs not (nobs-nlags)
# SS: unbiased=False is default now
# acf2norm = acfx[1:maxlag+1]**2 / (nobs - np.arange(1,maxlag+1))
acf2norm = acfx[1:maxlag+1]**2 / (nobs - np.arange(1,maxlag+1))
qljungbox = nobs * (nobs+2) * np.cumsum(acf2norm)[lags-1]
pval = stats.chi2.sf(qljungbox, lags)
if not boxpierce:
return qljungbox, pval
else:
qboxpierce = nobs * np.cumsum(acfx[1:maxlag+1]**2)[lags]
pvalbp = stats.chi2.sf(qboxpierce, lags)
return qljungbox, pval, qboxpierce, pvalbp
import matplotlib.mlab as mlab
from scikits.statsmodels.tsa.arima_process import arma_generate_sample, arma_impulse_response
from scikits.statsmodels.tsa.arima_process import arma_acovf, arma_acf, ARIMA
#from movstat import acf, acovf
#from scikits.statsmodels.sandbox.tsa import acf, acovf, pacf
from scikits.statsmodels.tsa.stattools import acf, acovf, pacf
ar = [1., -0.6]
#ar = [1., 0.]
ma = [1., 0.4]
#ma = [1., 0.4, 0.6]
#ma = [1., 0.]
mod = '' #'ma2'
x = arma_generate_sample(ar, ma, 5000)
x_acf = acf(x)[:10]
x_ir = arma_impulse_response(ar, ma)
#print x_acf[:10]
#print x_ir[:10]
#irc2 = np.correlate(x_ir,x_ir,'full')[len(x_ir)-1:]
#print irc2[:10]
#print irc2[:10]/irc2[0]
#print irc2[:10-1] / irc2[1:10]
#print x_acf[:10-1] / x_acf[1:10]
# detrend helper from matplotlib.mlab
def detrend(x, key=None):
if key is None or key == 'constant':
return detrend_mean(x)
xhat5, err5 = VARMA(x,B,C)
#print err5
#in differences
#VARMA(np.diff(x,axis=0),B,C)
#Note:
# * signal correlate applies same filter to all columns if kernel.shape[1]<K
# e.g. signal.correlate(x0,np.ones((3,1)),'valid')
# * if kernel.shape[1]==K, then `valid` produces a single column
# -> possible to run signal.correlate K times with different filters,
# see the following example, which replicates VAR filter
x0 = np.column_stack([np.arange(T), 2*np.arange(T)])
B[:,:,0] = np.ones((P,K))
B[:,:,1] = np.ones((P,K))
B[1,1,1] = 0
xhat0 = VAR(x0,B)
xcorr00 = signal.correlate(x0,B[:,:,0])#[:,0]
xcorr01 = signal.correlate(x0,B[:,:,1])
print np.all(signal.correlate(x0,B[:,:,0],'valid')[:-1,0]==xhat0[P:,0])
print np.all(signal.correlate(x0,B[:,:,1],'valid')[:-1,0]==xhat0[P:,1])
#import error
#from movstat import acovf, acf
from scikits.statsmodels.tsa.stattools import acovf, acf
aav = acovf(x[:,0])
print aav[0] == np.var(x[:,0])
aac = acf(x[:,0])
def test_acf():
acf_x = tsa.acf(x100, unbiased=False)[:21]
assert_array_almost_equal(mlacf.acf100.ravel(), acf_x, 8) #why only dec=8
acf_x = tsa.acf(x1000, unbiased=False)[:21]
assert_array_almost_equal(mlacf.acf1000.ravel(), acf_x, 8) #why only dec=9
