def summarize_all(self):
if len(self.independent) == 1:
dependent = self.dependent
independent = self.independent[0]
params = self.result.params
result = self.result
k = params[1]
b = params[0]
conf = result.conf_int()
cadf = adfuller(result.resid)
if cadf[0] <= cadf[4]['5%']:
boolean = 'likely'
else:
boolean = 'unlikely'
print
print("{:^40}".format("{} vs {}".format(dependent.upper(),
independent.upper())))
print("%20s %s = %.4f * %s + %.4f" %
("Model:", dependent, k, independent, b))
print("%20s %.4f" % ("R square:", result.rsquared))
print("%20s [%.4f, %.4f]" %
("Confidence interval:", conf.iloc[1, 0], conf.iloc[1, 1]))
print("%20s %.4f" % ("Model error:", result.resid.std()))
print("%20s %s" % ("Mean reverting:", boolean))
print("%20s %d" % ("Half life:", half_life(result.resid)))
else:
dependent = self.dependent
independent = self.independent # list
params = self.result.params
result = self.result
b = params[0]
conf = result.conf_int() # pandas
cadf = adfuller(result.resid)
if cadf[0] <= cadf[4]['5%']:
boolean = 'likely'
else:
boolean = 'unlikely'
print
print("{:^40}".format("{} vs {}".format(
dependent.upper(), (', '.join(independent)).upper())))
string = []
for i in range(len(independent)):
string.append("%.4f * %s" %
(params[independent[i]], independent[i]))
print("%20s %s = %s + %.4f" %
("Model:", dependent, ' + '.join(string), b))
print("%20s %.4f" % ("R square:", result.rsquared))
string = []
for i in range(len(independent)):
string.append(
"[%.4f, %.4f]" %
(conf.loc[independent[i], 0], conf.loc[independent[i], 1]))
print("%20s %s" % ("Confidence interval:", ' , '.join(string)))
print("%20s %.4f" % ("Model error:", result.resid.std()))
print("%20s %s" % ("Mean reverting:", boolean))
print("%20s %d" % ("Half life:", half_life(result.resid)))
def summarize_all(self):
if len(self.independent) == 1:
dependent = self.dependent
independent = self.independent[0]
params = self.result.params
result = self.result
k = params[1]
b = params[0]
conf = result.conf_int()
cadf = adfuller(result.resid)
if cadf[0] <= cadf[4]['5%']:
boolean = 'likely'
else:
boolean = 'unlikely'
print
print ("{:^40}".format("{} vs {}".format(dependent.upper(), independent.upper())))
print ("%20s %s = %.4f * %s + %.4f" % ("Model:", dependent, k, independent, b))
print ("%20s %.4f" % ("R square:", result.rsquared))
print ("%20s [%.4f, %.4f]" % ("Confidence interval:", conf.iloc[1, 0], conf.iloc[1, 1]))
print ("%20s %.4f" % ("Model error:", result.resid.std()))
print ("%20s %s" % ("Mean reverting:", boolean))
print ("%20s %d" % ("Half life:", half_life(result.resid)))
else:
dependent = self.dependent
independent = self.independent # list
params = self.result.params
result = self.result
b = params[0]
conf = result.conf_int() # pandas
cadf = adfuller(result.resid)
if cadf[0] <= cadf[4]['5%']:
boolean = 'likely'
else:
boolean = 'unlikely'
print
print ("{:^40}".format("{} vs {}".format(dependent.upper(), (', '.join(independent)).upper())))
string = []
for i in range(len(independent)):
string.append("%.4f * %s" % (params[independent[i]], independent[i]))
print ("%20s %s = %s + %.4f" % ("Model:", dependent, ' + '.join(string), b))
print ("%20s %.4f" % ("R square:", result.rsquared))
string = []
for i in range(len(independent)):
string.append("[%.4f, %.4f]" % (conf.loc[independent[i], 0], conf.loc[independent[i], 1]))
print ("%20s %s" % ("Confidence interval:", ' , '.join(string)))
print ("%20s %.4f" % ("Model error:", result.resid.std()))
print ("%20s %s" % ("Mean reverting:", boolean))
print ("%20s %d" % ("Half life:", half_life(result.resid)))
def run_all(self):
"""
Lazy ass's ultimate solution. Run all available analysis
Pre-condition:
There should be only one independent variable
"""
_2D = len(self.independent) == 1
print
self.plot_all()
print
print self.summary()
if _2D:
self.plot2D()
print
print 'Error statistics'
print self.residual().describe()
print
self.residual_vs_fit()
self.residual_plot()
residual = self.residual()
test_mean_reverting(residual)
print
print 'Halflife = ', half_life(residual)