def get_confidence_interval_for_mean(self,X=[]):
"""
Calculates the confidence interval for each datapoint, given a model fit
This is the confidence interval of the model, not the prediction interval
"""
if isinstance(X,pd.core.frame.DataFrame):
X=X[self.independent_]
df_results=pd.DataFrame({'y_hat':numpy.zeros(X.shape[0])})
y_hat=self.predict(X)
w=numpy.matrix(X)
# XT_X=numpy.matrix(X).T*\
# numpy.matrix(X)
#print "X_XT"
#print X_XT
# print "w"
# print numpy.shape(w)
# print "XT_T"
# print numpy.shape(XT_X)
#logging.debug(numpy.shape(s_2*inv(XT_X)))
s_c_2=numpy.array(w*numpy.power(self.s_y,2)*inv(self.X_dash_X)*w.T)
#logging.debug("s_c_2: {}".format(s_c_2))
#we only want the diagonal
s_c_2=numpy.diagonal(s_c_2)
#logging.debug("s_c_2 diag: {}".format(s_c_2))
#tau=df_new.apply(lambda x:numpy.matrix(x[est.params.index.values].values),axis=1)
# X_XT*numpy.matrix(x[est.params.index.values].values).T)
# tau=numpy.matrix(df_new[est.params.index.values].values[])*X_XT*\
# numpy.matrix(df_new[est.params.index.values].values).T
#print "tau"
#print numpy.shape(numpy.squeeze(tau))
#95% confidence interval so alpha =0.95
alpha=0.05
t_val=stats.t.ppf(1-alpha/2,self.df_resid+1)
upper=y_hat+t_val*numpy.sqrt(s_c_2)
lower=y_hat-t_val*numpy.sqrt(s_c_2)
# df_orig['s_c_2']=s_c_2
# #df_orig['sigma_tilde']=sigma_tilde
# df_orig['t']=t_val
# df_orig['upper_y_hat']=upper
# df_orig['lower_y_hat']=lower
df=pd.DataFrame({'y_hat':y_hat,'upper_mean':upper,'lower_mean':lower})
return (df)
def gen_simplemodel_data(n=1000,k=1):
numpy.random.seed(10)
df_x=pd.DataFrame({'alpha':numpy.ones(n)})
coefs=numpy.random.rand(k+1)
for ii in range(k):
#draw from normal distribution and scale it randomly
df_x['X{}'.format(ii)]=numpy.random.normal(0,1,n)
# logging.debug(df_x.head())
# logging.debug("coefs: {}. df_x: {}. disturb: {}".format(\
# numpy.shape(numpy.matrix(coefs)),\
# numpy.shape(numpy.matrix(df_x)),\
# numpy.shape(numpy.matrix(numpy.random.normal(0,1,n)*numpy.random.rand(1)).T)))
data=numpy.array(numpy.matrix(df_x)*numpy.matrix(coefs).T+numpy.matrix(numpy.random.normal(0,1,n)*numpy.random.rand(1)).T)
df_x['y']=data
return (coefs,df_x)
