def _bootstrap(self, block_size):
"""
Description
----
Stationary bootstrap for different block sizes
Inputs
----
:block_size: Number of points per block
Outputs
----
List containing mean, standard error
"""
bs = StationaryBootstrap(block_size, self._data)
try:
bs_results = eval('bs.apply(' + self._custom_func +
', nbootstrap)')
except TypeError:
bs_results = bs.apply(np.mean, self._nbootstrap)
mn = np.mean(bs_results, axis=0)
se = np.std(bs_results, ddof=1, axis=0)
return list(np.hstack((mn, se)))
def bootstrap(block_size, data, nbootstrap, sig_level=0.05, custom_func=None):
"""
Description
----
Stationary bootstrap for different block sizes
Inputs
----
:block_size: Number of points per block
:nbootstrap: Number of bootstrap samples
:data: Data to find confidence intervals for
Outputs
----
List containing mean, standard error
"""
bs = StationaryBootstrap(block_size, data)
try:
bs_results = eval('bs.apply(' + custom_func + ', nbootstrap)')
except TypeError:
bs_results = bs.apply(np.mean, nbootstrap)
mn = np.mean(bs_results, axis=0)
se = np.std(bs_results, ddof=1, axis=0)
return list(np.hstack((mn, se)))
def block_bootstrap(series, n_samples, bs_type='Stationary', block_size=10):
'''
Computes bootstrapped samples of series.
Inputs:
series: pandas Series indexed by time
n_samples: # bootstrapped samples to output
bs_type ('Stationary'): type of bootstrapping to perform.
Options include ['Stationary', 'Circular']
block_size: # size of resampling blocks. Should be big enough to
capture important frequencies in the series
Ouput:
DataFrame indexed by sample number and time
'''
# Set up list for sampled time-series
list_samples = []
# Stationary bootstrapping
if bs_type == 'Stationary':
bs = StationaryBootstrap(block_size, series)
# Count for sample number
count = 1
for data in bs.bootstrap(n_samples):
df_temp = pd.DataFrame({
'sample': count,
'time': series.index.values,
'x': data[0][0]
})
list_samples.append(df_temp)
count += 1
if bs_type == 'Circular':
bs = CircularBlockBootstrap(block_size, series)
# Count for sample number
count = 1
for data in bs.bootstrap(n_samples):
df_temp = pd.DataFrame({
'sample': count,
'time': series.index.values,
'x': data[0][0]
})
list_samples.append(df_temp)
count += 1
# Concatenate list of samples
df_samples = pd.concat(list_samples)
df_samples.set_index(['sample', 'time'], inplace=True)
# Output DataFrame of samples
return df_samples
def stationary_boostrap_method(X, Y, block_size=50, n_samples=50):
boot_samples = []
bs = StationaryBootstrap(block_size, X, y=Y)
for samp in bs.bootstrap(n_samples):
boot_samples.append((samp[0][0], samp[1]['y']))
return boot_samples
def test_str(self):
bs = IIDBootstrap(self.y_series)
expected = 'IID Bootstrap(no. pos. inputs: 1, no. keyword inputs: 0)'
assert_equal(str(bs), expected)
expected = expected[:-1] + ', ID: ' + hex(id(bs)) + ')'
assert_equal(bs.__repr__(), expected)
expected = '<strong>IID Bootstrap</strong>(' + \
'<strong>no. pos. inputs</strong>: 1, ' + \
'<strong>no. keyword inputs</strong>: 0, ' + \
'<strong>ID</strong>: ' + hex(id(bs)) + ')'
assert_equal(bs._repr_html(), expected)
bs = StationaryBootstrap(10, self.y_series, self.x_df)
expected = 'Stationary Bootstrap(block size: 10, no. pos. inputs: 2, no. keyword inputs: 0)'
assert_equal(str(bs), expected)
expected = expected[:-1] + ', ID: ' + hex(id(bs)) + ')'
assert_equal(bs.__repr__(), expected)
bs = CircularBlockBootstrap(block_size=20,
y=self.y_series,
x=self.x_df)
expected = 'Circular Block Bootstrap(block size: 20, no. pos. inputs: 0, no. keyword inputs: 2)'
assert_equal(str(bs), expected)
expected = expected[:-1] + ', ID: ' + hex(id(bs)) + ')'
assert_equal(bs.__repr__(), expected)
expected = '<strong>Circular Block Bootstrap</strong>' + \
'(<strong>block size</strong>: 20, ' \
+ '<strong>no. pos. inputs</strong>: 0, ' + \
'<strong>no. keyword inputs</strong>: 2,' + \
' <strong>ID</strong>: ' + hex(id(bs)) + ')'
assert_equal(bs._repr_html(), expected)
def test_smoke(self):
num_bootstrap = 20
def func(y):
return y.mean(axis=0)
bs = StationaryBootstrap(13, self.y)
cov = bs.cov(func, reps=num_bootstrap)
bs = MovingBlockBootstrap(13, self.y)
cov = bs.cov(func, reps=num_bootstrap)
bs = CircularBlockBootstrap(13, self.y)
cov = bs.cov(func, reps=num_bootstrap)
bs = MovingBlockBootstrap(10, self.y)
cov = bs.cov(func, reps=num_bootstrap)
bs = CircularBlockBootstrap(10, self.y)
cov = bs.cov(func, reps=num_bootstrap)
def get_TheilSen(_x, what, _nboot, _y):
import numpy as np
import pandas as pd
#the x y are weird, it appears that apply passes the dataframe column as last element
from arch.bootstrap import StationaryBootstrap, IIDBootstrap
from scipy.stats import mstats, mannwhitneyu, t, kendalltau
from statsmodels.distributions.empirical_distribution import ECDF
try:
if what=="slope":
return mstats.theilslopes(np.ma.masked_invalid(_y.values), _x)[0]*86400*365*1000000000
elif what=="pval_tau":
return kendalltau(_x, _y)[1]/2
elif what=="pval_autocorr":
res0=mstats.theilslopes(_y, _x, alpha=0.95)[0]
bs=StationaryBootstrap(3, np.array(range(len(_y))))
bs_slopes=[]
for data in bs.bootstrap(_nboot):
ind=data[0][0]
res=mstats.theilslopes(_y[ind], _x, alpha=0.95)
bs_slopes=bs_slopes+[res[0]]
ecdf=ECDF(bs_slopes)
pvalue=ecdf(res0)
if pvalue>0.5:
pvalue=1-pvalue
# print pvalue
return pvalue
elif what=="pval":
bs=IIDBootstrap(np.array(range(len(_y))))
bs_slopes=[]
for data in bs.bootstrap(_nboot):
ind=data[0][0]
res=mstats.theilslopes(_y[ind], _x, alpha=0.95)
bs_slopes=bs_slopes+[res[0]]
ecdf=ECDF(bs_slopes)
pvalue=ecdf(0)
if pvalue>0.5:
pvalue=1-pvalue
# print pvalue
return pvalue
except:
return np.nan
def fit(self, df_portfolios, df_factors):
""" Fit the estimator
Parameters
-----------
df_portfolios : DataFrame
Time series of portfolios (test assets)
df_factors : DataFrame or Series
Time series of the factors
"""
tsres, _, loadings = _fmb(df_portfolios, df_factors, self.intercept)
self._tsres = tsres
self.loadings = loadings
if self.alpha is None:
self.alpha = _get_alpha(self._tsres)
self._xsres = _penfmb(loadings, self.alpha, self.d, self.tol,
self.maxiter)
self._xsres.name = 'coef'
sbs = StationaryBootstrap(self.block_length, df_portfolios, df_factors)
bsxsres = []
for data in sbs.bootstrap(self.nboot):
tsres, _, bloadings = _fmb(data[0][0].reset_index(drop=True),
data[0][1].reset_index(drop=True),
self.intercept)
bsxsres.append(
_penfmb(bloadings, _get_alpha(tsres), self.d, self.tol,
self.maxiter))
bsxsres = pd.DataFrame(bsxsres)
self._srate = 1.0 * (bsxsres == 0).sum(axis=0) / bsxsres.shape[0]
self._srate.name = 'shrinkage rate'
# self._se = bsxsres.std(axis=0)
# self._se.name = 'standard error'
return self
def test_str(bs_setup):
bs = IIDBootstrap(bs_setup.y_series)
expected = "IID Bootstrap(no. pos. inputs: 1, no. keyword inputs: 0)"
assert_equal(str(bs), expected)
expected = expected[:-1] + ", ID: " + hex(id(bs)) + ")"
assert_equal(bs.__repr__(), expected)
expected = ("<strong>IID Bootstrap</strong>(" +
"<strong>no. pos. inputs</strong>: 1, " +
"<strong>no. keyword inputs</strong>: 0, " +
"<strong>ID</strong>: " + hex(id(bs)) + ")")
assert_equal(bs._repr_html(), expected)
bs = StationaryBootstrap(10, bs_setup.y_series, bs_setup.x_df)
expected = ("Stationary Bootstrap(block size: 10, no. pos. "
"inputs: 2, no. keyword inputs: 0)")
assert_equal(str(bs), expected)
expected = expected[:-1] + ", ID: " + hex(id(bs)) + ")"
assert_equal(bs.__repr__(), expected)
bs = CircularBlockBootstrap(block_size=20,
y=bs_setup.y_series,
x=bs_setup.x_df)
expected = ("Circular Block Bootstrap(block size: 20, no. pos. "
"inputs: 0, no. keyword inputs: 2)")
assert_equal(str(bs), expected)
expected = expected[:-1] + ", ID: " + hex(id(bs)) + ")"
assert_equal(bs.__repr__(), expected)
expected = ("<strong>Circular Block Bootstrap</strong>" +
"(<strong>block size</strong>: 20, " +
"<strong>no. pos. inputs</strong>: 0, " +
"<strong>no. keyword inputs</strong>: 2," +
" <strong>ID</strong>: " + hex(id(bs)) + ")")
assert_equal(bs._repr_html(), expected)
bs = MovingBlockBootstrap(block_size=20,
y=bs_setup.y_series,
x=bs_setup.x_df)
expected = ("Moving Block Bootstrap(block size: 20, no. pos. "
"inputs: 0, no. keyword inputs: 2)")
assert_equal(str(bs), expected)
expected = expected[:-1] + ", ID: " + hex(id(bs)) + ")"
assert_equal(bs.__repr__(), expected)
expected = ("<strong>Moving Block Bootstrap</strong>" +
"(<strong>block size</strong>: 20, " +
"<strong>no. pos. inputs</strong>: 0, " +
"<strong>no. keyword inputs</strong>: 2," +
" <strong>ID</strong>: " + hex(id(bs)) + ")")
assert_equal(bs._repr_html(), expected)
def calibrate(volume_duration, strikes, reps):
volume_duration = volume_duration.unstack(['Half-spread', 'Strike'])
arrival_rate = volume_duration.groupby('Class').apply(
lambda c: compute_arrival_rate(c.loc[c.name, 'Volume'], c.loc[
c.name, 'Duration'], strikes[c.name]))
arrival_rate.name = 'Arrival rate'
arrival_rate.index = arrival_rate.index.reorder_levels(
['Class', 'Strike', 'Half-spread'])
sbs = volume_duration.groupby('Class').apply(lambda c: StationaryBootstrap(
25, volume=c.loc[c.name, 'Volume'], duration=c.loc[c.name, 'Duration'])
)
conf_int = sbs.groupby('Class').apply(lambda c: pd.DataFrame(
c[c.name].conf_int(lambda volume, duration: compute_arrival_rate(
volume, duration, strikes[c.name]),
reps=reps), ['2.5%', '97.5%'], arrival_rate.loc[
c.name].index))
conf_int = conf_int.T.stack('Class')
conf_int.index = conf_int.index.reorder_levels(
['Class', 'Strike', 'Half-spread'])
sigma = sbs.groupby('Class').apply(lambda c: pd.DataFrame(
c[c.name].cov(lambda volume, duration: compute_arrival_rate(
volume, duration, strikes[c.name]),
reps=reps), arrival_rate.loc[c.name].index, arrival_rate.
loc[c.name].index))
sigma = sigma.groupby('Strike').apply(
lambda k: k.xs(k.name, level='Strike', axis=1))
sigma.dropna(how='all', inplace=True)
gls = arrival_rate.loc[sigma.index].groupby(
['Class', 'Strike']).apply(lambda k: sm.GLS(
k.values,
sm.add_constant(k.index.get_level_values('Half-spread')),
sigma=sigma.xs(k.name, level=['Class', 'Strike']).dropna(axis=1)).
fit())
params = gls.apply(lambda g: pd.Series([np.exp(g.params[0]), -g.params[1]],
['A', '$\\kappa$']))
base_conf_int = gls.apply(lambda g: pd.Series(
np.exp(g.conf_int(alpha=.1)[0]), ['A 5%', 'A 95%']))
decay_conf_int = gls.apply(lambda g: pd.Series(
-g.conf_int(alpha=.1)[1, ::-1], ['$\\kappa$ 5%', '$\\kappa$ 95%']))
params = pd.concat([params, base_conf_int, decay_conf_int], axis=1)
arrival_rate = np.exp(pd.concat([arrival_rate, conf_int], axis=1))
return arrival_rate, params
def sb_bootstrap(self):
"""
return paths simulated using the stationary bootstrap
params:
-------
- self: see above
return:
-------
- none
"""
print("\nSTATIONARY BOOTSTRAP \n")
bs = StationaryBootstrap(self.blocksize, self.data)
out_sbb = boot(N_paths=self.n_paths,
method=bs,
obs_path=self.data,
add_noise=self.add_noise)
if self.store_sim:
self.simulated_paths['SB'] = out_sbb.iloc[:, :out_sbb.
shape[1] if out_sbb.
shape[1] < 100 else 100]
self.store_output = investment_horizons(
observed_path=self.data,
sims=out_sbb,
investment_horizons=self.ih,
freq=self.frequency,
sum_stats=self.stats,
perf_functions=self.perf_functions,
store_output_dic=self.store_output,
simulation_tech='SB',
plotting=self.plotting)
return None
def test_smoke(self):
num_bootstrap = 20
def func(y):
return y.mean(axis=0)
bs = StationaryBootstrap(13, self.y)
cov = bs.cov(func, reps=num_bootstrap)
bs = MovingBlockBootstrap(13, self.y)
cov = bs.cov(func, reps=num_bootstrap)
bs = CircularBlockBootstrap(13, self.y)
cov = bs.cov(func, reps=num_bootstrap)
bs = MovingBlockBootstrap(10, self.y)
cov = bs.cov(func, reps=num_bootstrap)
bs = CircularBlockBootstrap(10, self.y)
cov = bs.cov(func, reps=num_bootstrap)
def bootstrap(x, f):
if len(x) == 0:
return np.nan
from arch.bootstrap import StationaryBootstrap
bs = StationaryBootstrap(50, x)
return bs.apply(f,100).mean()
def bootstrap(x, f):
if len(x) == 0:
return np.nan
from arch.bootstrap import StationaryBootstrap
bs = StationaryBootstrap(50, x)
return bs.apply(f, 100).mean()
from read_data import import_data
def sharpe_ratio(x):
mu, sigma = x.mean(), np.sqrt(x.var())
values = np.array([x.sum(), sigma, mu / sigma]).squeeze()
index = ['CR', 'sigma', 'SR']
return pd.Series(values, index=index)
R = import_data('results/Yearly_portfolio/yearly_portfolio_returns_CDAX_mp')
R1 = R.iloc[:, 2]
params = sharpe_ratio(R1)
bs = StationaryBootstrap(12, R1)
results = bs.apply(sharpe_ratio, 100000)
delta_CR = results[:, 0] - params[0]
delta_sigma = results[:, 1] - params[1]
delta_SR = results[:, 2] - params[2]
def CI(delta, q=0.95):
delta.sort()
abs_sorted = np.abs(delta)
bound = abs_sorted[int(q * 100000)]
return bound
CR_bound = CI(delta_CR)
sigma_bound = CI(delta_sigma)
def block_bootstrap(series,
n_samples,
bs_type = 'Stationary',
block_size = 10
):
'''
Computes block-bootstrap samples of series.
Args
----
series: pd.Series
Time-series data in the form of a Pandas Series indexed by time
n_samples: int
Number of bootstrapped samples to output.
bs_type: {'Stationary', 'Circular'}
Type of block-bootstrapping to perform.
block_size: int
Size of resampling blocks. Should be big enough to
capture important frequencies in the series.
Returns
-------
pd.DataFrame:
DataFrame containing the block-bootstrapped samples of series.
Indexed by sample number, then time.
'''
# Set up list for sampled time-series
list_samples = []
# Stationary bootstrapping
if bs_type == 'Stationary':
bs = StationaryBootstrap(block_size, series)
# Count for sample number
count = 1
for data in bs.bootstrap(n_samples):
df_temp = pd.DataFrame({'sample': count,
'time': series.index.values,
'x': data[0][0]})
list_samples.append(df_temp)
count += 1
if bs_type == 'Circular':
bs = CircularBlockBootstrap(block_size, series)
# Count for sample number
count = 1
for data in bs.bootstrap(n_samples):
df_temp = pd.DataFrame({'sample': count,
'time': series.index.values,
'x': data[0][0]})
list_samples.append(df_temp)
count += 1
# Concatenate list of samples
df_samples = pd.concat(list_samples)
df_samples.set_index(['sample','time'], inplace=True)
# Output DataFrame of samples
return df_samples
def trend_CI(x_var, y_var, n_boot=1000, ci=95, trendtype="linreg", q=0.5, frac=0.6, it=3, autocorr=None, CItype="bootstrap"):
"""calculates bootstrap confidence interval and significance level for trend, ignoring autocorrelation or accounting for it
Parameters
----------
x_var : list
independent variable
y_var : list
dependent variable, same length as x_var
q : int, optional, only if trendtype==quantreg
quantile for which regression is to be calculated
n : int, optional
number of bootstrap samples
ci : int, optional
confidence level. Default is for 95% confidence interval
frac : int, optional, only if trendtype==lowess
lowess parameter (fraction of time period length used in local regression)
it : int, optional, only if trendtype==lowess
lowess parameter (numbre of iterations)
autocorr : str, optional
way of accounting for autocorrelation, possible values: None, "bootstrap"
trendtype : str, optional
method of trend derivation, possible values: lowess, linreg, quantreg, TheilSen
CItype : str, optional
method of CI derivation, possible values: "analytical" and "bootstrap".
if trendtype is "lowess", CItype will be set to None
if CItype is "analytical": autocorrelation will be set to None
Results
-------
returns library with following elements:
slope - slope of the trend
CI_high - CI on the slope value
CI_low - as above
pvalue - trend's significance level
trend - trend line, or rather its y values for all x_var
trendCI_high - confidence interval for each value of y
trendCI_low - as above
Remarks
-------
the fit function ocassionally crashes on resampled data. The workaround is to use try statement
"""
import numpy as np
import pandas as pd
#for linreg
import statsmodels.api as sm
from statsmodels.regression.linear_model import OLS
#for arima
import statsmodels.tsa as tsa
#for quantreg
import statsmodels.formula.api as smf
from statsmodels.regression.quantile_regression import QuantReg
#for lowess
import statsmodels.nonparametric.api as npsm
#other
from statsmodels.distributions.empirical_distribution import ECDF
from scipy.stats import mstats, mannwhitneyu, t, kendalltau
from arch.bootstrap import StationaryBootstrap, IIDBootstrap
#preparing data
if CItype=="analytical" and trendtype=="TheilSen":
CItype="bootstrap"
x_var=np.array(x_var)
y_var=np.ma.masked_invalid(y_var)
n_data=len(y_var)
ci_low=(100-ci)/2
ci_high=100-ci_low
#setting bootstrapping function
if autocorr=="bootstrap":
bs=StationaryBootstrap(3, np.array(range(len(y_var))))
else:
bs=IIDBootstrap(np.array(range(len(y_var))))
if trendtype=="quantreg":
print "Quantile regression, CI type: "+CItype+", autocorrelation adjustment: "+str(autocorr)+"\n"
xydata=pd.DataFrame(np.column_stack([x_var, y_var]), columns=['X', 'Y'])
model=smf.quantreg('Y ~ X', xydata)
res=model.fit(q=q)
intcpt=res.params.Intercept
slope=res.params.X
pvalue=res.pvalues[1]
CI_low=res.conf_int()[0]['X']
CI_high=res.conf_int()[1]['X']
y_pred=res.predict(xydata)
#calculating residuals
resids=y_var-y_pred
#calculate autocorrelation indices
autocorr_test(x_var, resids)
if CItype=="bootstrap":
#bootstrapping
bs_trends=np.copy(y_pred).reshape(-1,1)
bs_slopes=[]
bs_intcpts=[]
for data in bs.bootstrap(n_boot):
ind=data[0][0]
model = smf.quantreg('Y ~ X', xydata.ix[ind,:])
try:
res = model.fit(q=q)
bs_slopes=bs_slopes+[res.params.X]
bs_intcpts=bs_intcpts+[res.params.Intercept]
bs_trends=np.append(bs_trends,res.predict(xydata).reshape(-1,1), 1)
except:
goingdownquietly=1
if trendtype=="linreg":
print "Linear regression, CI type: "+CItype+", autocorrelation adjustment: "+str(autocorr)+"\n"
x_varOLS = sm.add_constant(x_var)
model = sm.OLS(y_var, x_varOLS, hasconst=True, missing='drop')
res = model.fit()
intcpt,slope=res.params
pvalue=res.pvalues[1]
CI_low,CI_high=res.conf_int()[1]
y_pred=res.predict(x_varOLS)
#calculating residuals
resids=y_var-y_pred
#calculate autocorrelation indices
autocorr_test(x_var, resids)
if CItype=="bootstrap":
#bootstrapping for confidence intervals
bs_slopes=[]
bs_intcpts=[]
bs_trends=np.copy(y_pred).reshape(-1,1)
for data in bs.bootstrap(n_boot):
ind=data[0][0]
model = sm.OLS(y_var[ind], x_varOLS[ind,:], hasconst=True, missing='drop')
try:
res = model.fit()
bs_slopes=bs_slopes+[res.params[1]]
bs_intcpts=bs_intcpts+[res.params[0]]
bs_trends=np.append(bs_trends,res.predict(x_varOLS).reshape(-1,1), 1)
except:
goingdownquietly=1
if trendtype=="TheilSen":
# print "Theil-Sen slope, CI type: "+CItype+", autocorrelation adjustment: "+str(autocorr)+"\n"
#significance of MK tau
tau,pvalue=kendalltau(x_var, y_var)
# print "raw MK tau:", tau, "raw MK pvalue:", pvalue
#TS slope and confidence intervals
slope,intercept,CI_low,CI_high=mstats.theilslopes(y_var, x_var, alpha=0.95)
#getting slope line's y values
y_pred=intercept+slope*x_var
#calculating residuals
resids=y_var-y_pred
#calculate autocorrelation indices
autocorr_test(x_var, resids)
if CItype=="bootstrap":
#bootstrapping for confidence intervals
bs_slopes=[]
bs_intcpts=[]
bs_trends=np.copy(y_pred).reshape(-1,1)
for data in bs.bootstrap(n_boot):
ind=data[0][0]
res=mstats.theilslopes(y_var[ind], x_var[ind], alpha=0.95)
bs_slopes=bs_slopes+[res[0]]
bs_intcpts=bs_intcpts+[res[1]]
bs_trends=np.append(bs_trends, (res[1]+res[0]*x_var).reshape(-1,1), 1)
if trendtype=="lowess":
print "Lowess\n"
temp=dict(npsm.lowess(y_var, x_var, frac=frac, it=it, missing="drop"))
y_pred=np.array(map(temp.get, x_var)).astype("float").reshape(-1,1)
bs_trends=np.copy(y_pred)
for data in bs.bootstrap(n_boot):
ind=data[0][0]
try:
temp = dict(npsm.lowess(y_var[ind], x_var[ind], frac=frac, it=it, missing="drop"))
temp=np.array(map(temp.get, x_var)).astype("float").reshape(-1,1)
pred=pd.DataFrame(temp, index=x_var)
temp_interp=pred.interpolate().values
bs_trends=np.append(bs_trends, temp_interp, 1)
except:
goingdownquietly=1
#calculating final values of CI and p-value
#skipping when lowess
if trendtype=="lowess":
CI_low=np.nan
CI_high=np.nan
slope=np.nan
intcpt=np.nan
pvalue=np.nan
confint=np.nanpercentile(bs_trends, [ci_low,ci_high], 1)
trendCI_low=confint[:,0]
trendCI_high=confint[:,1]
else:
if CItype=="bootstrap":
#values for slope, intercept and trend can be obtained as medians of bootstrap distributions, but normally analytical parameters are used instead
# it the bootstrap bias (difference between analytical values and bootstap median) is strong, it might be better to use bootstrap values.
# These three lines would need to be uncommented then
# slope=np.median(bs_slopes)
# intcpt=np.median(bs_intcpts)
# trend=intcpt+slope*x_var
#these are from bootstrap too, but needs to be used for this accounts for autocorrelation, which is the point of this script
CI_low,CI_high=np.percentile(bs_slopes, [5, 95])
ecdf=ECDF(bs_slopes)
pvalue=ecdf(0)
#this makes sure we are calculating p-value on the correct side of the distribution. That will be one-sided pvalue
if pvalue>0.5:
pvalue=1-pvalue
confint=np.nanpercentile(bs_trends, [ci_low,ci_high], 1)
print "bs_trends:", bs_trends.shape, confint.shape
trendCI_low=confint[:,0]
trendCI_high=confint[:,1]
else:
#this is for analytical calculation of trend confidence interval
#it happens in the same way for each of the trend types, thus it is done here, not under the trendtype subroutines
#making sure x are floats
xtemp=np.array(x_var)*1.0
#squared anomaly
squanom=(xtemp-np.mean(xtemp))**2
temp=((1./len(x_var))+(squanom/sum(squanom)))**0.5
#standard error of estmation
see=(np.nansum((np.array(y_var)-np.nanmean(y_pred))**2)/len(x_var))**0.5
#adjusting ci
ci_adj=1-((1-ci/100.)/2)
#accounting for uncertainty in mean through student's t
tcomp=t.ppf(ci_adj, len(x_var)-2)
#confidence interval
cint=tcomp*see*temp
#for trend only
trendCI_high=y_pred+cint
trendCI_low=y_pred-cint
print trendtype, "slope:",slope, "pvalue (one sided):", pvalue, "conf interval:", CI_low, CI_high, "autocorrelation adjustment:", autocorr, "\n"
output={"slope":slope, "CI_high":CI_high, "CI_low":CI_high, "pvalue":pvalue, "trend": y_pred, "trendCI_low":trendCI_low, "trendCI_high":trendCI_high}
return output
with open('lyapunov_exponents_both_297.dat', 'rb') as f:
lyap_coupled = numpy.fromfile(f, dtype='float64').reshape([-1, 36])
with open('lyapunov_exponents_ocn_297.dat', 'rb') as f:
lyap_ocn = numpy.fromfile(f, dtype='float64').reshape([-1, 36])[:, 20:36]
lyap_coupled *= 86400 * 1.032e-4
lyap_ocn *= 86400 * 1.032e-4
block_length_coupled = numpy.array(block_length(lyap_coupled))[:, 0]
all_ci = []
for var in range(36):
bootstrap = StationaryBootstrap(block_length_coupled[var],
lyap_coupled[:, var])
ci = bootstrap.conf_int(mean, 1000)
all_ci.append(ci)
ci_coupled = numpy.hstack(all_ci)
block_length_ocn = numpy.array(block_length(lyap_ocn))[:, 0]
all_ci = []
for var in range(16):
bootstrap = StationaryBootstrap(block_length_ocn[var], lyap_ocn[:, var])
ci = bootstrap.conf_int(mean, 1000)
all_ci.append(ci)
