def prob_3():
data_x, data_y = hw3_data.evap()
sigma = pymc.Uniform('sigma', lower=0., upper=500., value=1.)
# Covariates:
# max gr temp, min gr temp, ave gr temp index, max air temp, min air temp, ave air temp index
beta = pymc.Normal(
'beta',
mu=[0, 0, 0, 0, 0, 0, 0],
tau=[10**-6, 10**-6, 10**-6, 10**-6, 10**-6, 10**-6, 10**-6],
value=[0, 0, 0, 0, 0, 0, 0])
@deterministic
def y_mean(beta=beta, data=data_x):
return np.dot(data_x, beta)
y_obs = pymc.Normal('y_obs',
value=data_y,
mu=y_mean,
tau=sigma**-2,
observed=True)
evap_sim = pymc.Normal('evap_sim', mu=y_mean, tau=sigma**-2)
return vars()
def prob_3():
data_x, data_y = hw3_data.evap()
sigma = pymc.Uniform('sigma', lower=0., upper=500., value=1.)
# Covariates:
# max gr temp, min gr temp, ave gr temp index, max air temp, min air temp, ave air temp index
beta = pymc.Normal('beta', mu = [0,0,0,0,0,0,0], tau=[10**-6,10**-6,10**-6,10**-6,10**-6,10**-6,10**-6] , value=[0,0,0,0,0,0,0])
@deterministic
def y_mean(beta=beta, data=data_x):
return np.dot(data_x,beta)
y_obs = pymc.Normal('y_obs', value=data_y, mu=y_mean, tau=sigma**-2, observed=True)
evap_sim = pymc.Normal('evap_sim', mu=y_mean, tau=sigma**-2)
return vars()
from numpy import arange,array,ones,linalg import hw3_data data_x, data_y = hw3_data.evap() # print data_y print data_x w = linalg.lstsq(data_x,data_y)[0] # obtaining the parameters print w
from numpy import arange, array, ones, linalg import hw3_data data_x, data_y = hw3_data.evap() # print data_y print data_x w = linalg.lstsq(data_x, data_y)[0] # obtaining the parameters print w