def discretize_gdp(self, N=3):
Σ = self.Σ
ρ = self.ρ
n_nodes = N
n_std = 2.5
n_integration_nodes = 5
try:
assert Σ.shape[0] == 1
except:
raise Exception("Not implemented.")
try:
assert ρ.shape[0] == ρ.shape[1] == 1
except:
raise Exception("Not implemented.")
ρ = ρ[0, 0]
σ = np.sqrt(Σ[0, 0])
from dolo.numeric.discretization import gauss_hermite_nodes
epsilons, weights = gauss_hermite_nodes([n_integration_nodes], Σ)
min = -n_std * (σ / (np.sqrt(1 - ρ**2)))
max = n_std * (σ / (np.sqrt(1 - ρ**2)))
from .grids import CartesianGrid
grid = CartesianGrid([min], [max], [n_nodes])
nodes = np.linspace(min, max, n_nodes)[:, None]
iweights = weights[None, :].repeat(n_nodes, axis=0)
integration_nodes = np.zeros((n_nodes, n_integration_nodes))[:, :,
None]
for i in range(n_nodes):
for j in range(n_integration_nodes):
integration_nodes[i, j, :] = ρ * nodes[i, :] + epsilons[j]
return GDP(nodes, integration_nodes, iweights, grid=grid)
def evaluate_policy(model, dr, tol=1e-8, grid={}, distribution={}, maxit=2000, verbose=False, hook=None,
integration_orders=None):
'''
Compute value function corresponding to policy ``dr``
Parameters:
-----------
model:
"dtcscc" model. Must contain a 'value' function.
dr:
decision rule to evaluate
Returns:
--------
decision rule:
value function (a function of the space similar to a decision rule
object)
'''
assert (model.model_type == 'dtcscc')
vfun = model.functions["value"]
gfun = model.functions['transition']
parms = model.calibration['parameters']
n_vals = len(model.symbols['values'])
t1 = time.time()
err = 1.0
it = 0
approx = model.get_grid(**grid)
interp_type = approx.interpolation
distrib = model.get_distribution(**distribution)
sigma = distrib.sigma
drv = create_interpolator(approx, approx.interpolation)
grid = drv.grid
N = drv.grid.shape[0]
controls = dr(grid)
guess_0 = model.calibration['values']
guess_0 = guess_0[None, :].repeat(N, axis=0)
if not integration_orders:
integration_orders = [3] * sigma.shape[0]
[nodes, weights] = gauss_hermite_nodes(integration_orders, sigma)
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} |'.format('N', ' Error', 'Gain', 'Time')
stars = '-' * len(headline)
print(stars)
print(headline)
print(stars)
err_0 = 1.0
while err > tol and it < maxit:
if hook:
hook()
t_start = time.time()
it += 1
# update spline coefficients with current values
drv.set_values(guess_0)
# update the geuss of value functions
guess = update_value(gfun, vfun, grid, controls, dr, drv,
nodes, weights, parms, n_vals)
# compute error
err = abs(guess - guess_0).max()
err_SA = err / err_0
err_0 = err
# update guess
guess_0[:] = guess.copy()
# print update to user, if verbose
t_end = time.time()
elapsed = t_end - t_start
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format(
it, err, err_SA, elapsed))
if it == maxit:
warnings.warn(UserWarning("Maximum number of iterations reached"))
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
return drv
def solve_policy(model, tol=1e-6, grid={}, distribution={}, integration_orders=None, maxit=500, maxit_howard=500, verbose=False, hook=None, initial_dr=None, pert_order=1):
'''
Solve for the value function and associated decision rule by iterating over
the value function.
Parameters
-----------
model :
``dtcscc`` model. Must contain a ``felicity`` function.
Returns
--------
dr : Markov decision rule
The solved decision rule/policy function
drv : decision rule
The solved value function
'''
assert (model.model_type == 'dtcscc')
def vprint(t):
if verbose:
print(t)
# transition(s, x, e, p, out), felicity(s, x, p, out)
transition = model.functions['transition']
felicity = model.functions['felicity']
controls_lb = model.functions['controls_lb']
controls_ub = model.functions['controls_ub']
parms = model.calibration['parameters']
discount = model.calibration['beta']
x0 = model.calibration['controls']
s0 = model.calibration['states']
r0 = felicity(s0, x0, parms)
approx = model.get_grid(**grid)
# a = approx.a
# b = approx.b
# orders = approx.orders
distrib = model.get_distribution(**distribution)
sigma = distrib.sigma
# Possibly use the approximation orders?
if integration_orders is None:
integration_orders = [3] * sigma.shape[0]
[nodes, weights] = gauss_hermite_nodes(integration_orders, sigma)
interp_type = approx.interpolation
drv = create_interpolator(approx, interp_type)
if initial_dr is None:
if pert_order == 1:
dr = approximate_controls(model)
if pert_order > 1:
raise Exception("Perturbation order > 1 not supported (yet).")
else:
dr = initial_dr
grid = drv.grid
N = grid.shape[0] # Number of states
n_x = grid.shape[1] # Number of controls
controls = dr(grid)
controls_0 = np.zeros((N, n_x))
controls_0[:, :] = model.calibration['controls'][None, :]
values_0 = np.zeros((N, 1))
values_0[:, :] = r0/(1-discount)
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} |'.format('N', ' Error','Gain', 'Time')
stars = '-' * len(headline)
print(stars)
print(headline)
print(stars)
t1 = time.time()
# FIRST: value function iterations, 10 iterations to start
it = 0
err_v = 100
err_v_0 = 0.0
gain_v = 0.0
err_x = 100
err_x_0 = 100
if verbose:
print(stars)
print('Starting value function iteration')
print(stars)
while err_v > tol and it < 10:
t_start = time.time()
it += 1
# update interpolation object with current values
drv.set_values(values_0)
values = values_0.copy()
controls = controls_0.copy()
for n in range(N):
s = grid[n, :]
x = controls[n, :]
lb = controls_lb(s, parms)
ub = controls_ub(s, parms)
bnds = [e for e in zip(lb, ub)]
def valfun(xx):
return -choice_value(transition, felicity, s, xx, drv, nodes,
weights, parms, discount)[0]
res = minimize(valfun, x, bounds=bnds, tol=1e-4)
controls[n, :] = res.x
values[n, 0] = -valfun(res.x)
# compute error, update value and dr
err_x = abs(controls - controls_0).max()
err_v = abs(values - values_0).max()
t_end = time.time()
elapsed = t_end - t_start
values_0 = values
controls_0 = controls
gain_x = err_x / err_x_0
gain_v = err_v / err_v_0
err_x_0 = err_x
err_v_0 = err_v
# print update to user, if verbose
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format(
it, err_v, gain_v, elapsed))
# SECOND: Howard improvement step, 10-20 iterations
it = 0
err_v = 100
err_v_0 = 0.0
gain_v = 0.0
if verbose:
print(stars)
print('Starting Howard improvement step')
print(stars)
while err_v > tol and it < maxit_howard:
t_start = time.time()
it += 1
# update interpolation object with current values
drv.set_values(values_0)
values = values_0.copy()
controls = controls_0.copy()
# controls = controls_0.copy() # No need to keep updating
for n in range(N):
s = grid[n, :]
x = controls[n, :]
values[n, 0] = choice_value(transition, felicity, s, x, drv, nodes,
weights, parms, discount)[0]
# compute error, update value function
err_v = abs(values - values_0).max()
values_0 = values
t_end = time.time()
elapsed = t_end - t_start
gain_v = err_v / err_v_0
err_v_0 = err_v
# print update to user, if verbose
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format(
it, err_v, gain_v, elapsed))
# THIRD: Back to value function iteration until convergence.
it = 0
err_v = 100
err_v_0 = 0.0
gain_v = 0.0
err_x = 100
err_x_0 = 100
if verbose:
print(stars)
print('Starting value function iteration')
print(stars)
while err_v > tol and it < maxit:
t_start = time.time()
it += 1
# update interpolation object with current values
drv.set_values(values_0)
values = values_0.copy()
controls = controls_0.copy()
for n in range(N):
s = grid[n, :]
x = controls[n, :]
lb = controls_lb(s, parms)
ub = controls_ub(s, parms)
bnds = [e for e in zip(lb, ub)]
def valfun(xx):
return -choice_value(transition, felicity, s, xx, drv, nodes,
weights, parms, discount)[0]
res = minimize(valfun, x, bounds=bnds, tol=1e-4)
controls[n, :] = res.x
values[n, 0] = -valfun(res.x)
# compute error, update value and dr
err_x = abs(controls - controls_0).max()
err_v = abs(values - values_0).max()
t_end = time.time()
elapsed = t_end - t_start
values_0 = values
controls_0 = controls
gain_x = err_x / err_x_0
gain_v = err_v / err_v_0
err_x_0 = err_x
err_v_0 = err_v
# print update to user, if verbose
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format(
it, err_v, gain_v, elapsed))
if it == maxit:
warnings.warn(UserWarning("Maximum number of iterations reached"))
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
# final value function and decision rule
drv.set_values(values_0)
dr = create_interpolator(approx, interp_type)
dr.set_values(controls_0)
return dr, drv
def pea(model, maxit=100, tol=1e-8, initial_dr=None, verbose=False):
t1 = time.time()
g = model.functions['transition']
d = model.functions['direct_response']
h = model.functions['expectation']
p = model.calibration['parameters']
if initial_dr is None:
drp = approximate_controls(model)
else:
drp = approximate_controls(model)
nodes, weights = gauss_hermite_nodes([5], model.covariances)
ap = model.options['approximation_space']
a = ap['a']
b = ap['b']
orders = ap['orders']
grid = mlinspace(a,b,orders)
dr = MultivariateCubicSplines(a,b,orders)
N = grid.shape[0]
z = np.zeros((N,len(model.symbols['expectations'])))
x_0 = drp(grid)
it = 0
err = 10
err_0 = 10
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} |'
headline = headline.format('N', ' Error', 'Gain', 'Time')
stars = '-'*len(headline)
print(stars)
print(headline)
print(stars)
# format string for within loop
fmt_str = '|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'
while err>tol and it<=maxit:
t_start = time.time()
dr.set_values(x_0)
z[...] = 0
for i in range(weights.shape[0]):
e = nodes[i,:]
S = g(grid, x_0, e, p)
# evaluate future controls
X = dr(S)
z += weights[i]*h(S,X,p)
# TODO: check that control is admissible
new_x = d(grid, z, p)
# check whether they differ from the preceding guess
err = (abs(new_x - x_0).max())
x_0 = new_x
if verbose:
# update error and print if `verbose`
err_SA = err/err_0
err_0 = err
t_finish = time.time()
elapsed = t_finish - t_start
if verbose:
print(fmt_str.format(it, err, err_SA, elapsed))
if it == maxit:
import warnings
warnings.warn(UserWarning("Maximum number of iterations reached"))
# compute final fime and do final printout if `verbose`
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
return dr
def test_simulations():
from dolo import yaml_import, approximate_controls
model = yaml_import('../../examples/models/rbc.yaml')
dr = approximate_controls(model)
parms = model.calibration['parameters']
sigma = model.covariances
import numpy
s0 = dr.S_bar
horizon = 50
import time
t1 = time.time()
simul = simulate(model, dr, s0, sigma, n_exp=1000, parms=parms, seed=1, horizon=horizon)
t2 = time.time()
print("Took: {}".format(t2-t1))
from dolo.numeric.discretization import gauss_hermite_nodes
N = 80
[x,w] = gauss_hermite_nodes(N, sigma)
t3 = time.time()
simul_2 = simulate(model, dr, s0, sigma, n_exp=1000, parms=parms, horizon=horizon, seed=1, solve_expectations=True, nodes=x, weights=w)
t4 = time.time()
print("Took: {}".format(t4-t3))
from matplotlib.pyplot import hist, show, figure, plot, title
timevec = numpy.array(range(simul.shape[2]))
figure()
for k in range(10):
plot(simul[:,k,0] - simul_2[:,k,0])
title("Productivity")
show()
figure()
for k in range(10):
plot(simul[:,k,1] - simul_2[:,k,1])
title("Investment")
show()
#
# figure()
# plot(simul[0,0,:])
# plot(simul_2[0,0,:])
# show()
figure()
for i in range( horizon ):
hist( simul[i,:,0], bins=50 )
show()
def time_iteration(model, bounds=None, verbose=False, initial_dr=None,
pert_order=1, with_complementarities=True,
interp_type='smolyak', smolyak_order=3, interp_orders=None,
maxit=500, tol=1e-8, inner_maxit=10,
integration='gauss-hermite', integration_orders=None,
T=200, n_s=3, hook=None):
'''
Finds a global solution for ``model`` using backward time-iteration.
This algorithm iterates on the residuals of the arbitrage equations
Parameters
----------
model : NumericModel
"fg" or "fga" model to be solved
bounds : ndarray
boundaries for approximations. First row contains minimum values.
Second row contains maximum values.
verbose : boolean
if True, display iterations
initial_dr : decision rule
initial guess for the decision rule
pert_order : {1}
if no initial guess is supplied, the perturbation solution at order
``pert_order`` is used as initial guess
with_complementarities : boolean (True)
if False, complementarity conditions are ignored
interp_type : {`smolyak`, `spline`}
type of interpolation to use for future controls
smolyak_orders : int
parameter ``l`` for Smolyak interpolation
interp_orders : 1d array-like
list of integers specifying the number of nodes in each dimension if
``interp_type="spline" ``
Returns
-------
decision rule :
approximated solution
'''
def vprint(t):
if verbose:
print(t)
parms = model.calibration['parameters']
sigma = model.covariances
if initial_dr is None:
if pert_order == 1:
initial_dr = approximate_controls(model)
if pert_order > 1:
raise Exception("Perturbation order > 1 not supported (yet).")
if interp_type == 'perturbations':
return initial_dr
if bounds is not None:
pass
elif model.options and 'approximation_space' in model.options:
vprint('Using bounds specified by model')
approx = model.options['approximation_space']
a = approx['a']
b = approx['b']
bounds = np.row_stack([a, b])
bounds = np.array(bounds, dtype=float)
if interp_orders is None:
interp_orders = approx.get('orders', [5] * bounds.shape[1])
else:
vprint('Using asymptotic bounds given by first order solution.')
from dolo.numeric.timeseries import asymptotic_variance
# this will work only if initial_dr is a Taylor expansion
Q = asymptotic_variance(initial_dr.A.real, initial_dr.B.real,
initial_dr.sigma, T=T)
devs = np.sqrt(np.diag(Q))
bounds = np.row_stack([
initial_dr.S_bar - devs * n_s,
initial_dr.S_bar + devs * n_s,
])
if interp_orders is None:
interp_orders = [5] * bounds.shape[1]
if interp_type == 'smolyak':
from dolo.numeric.interpolation.smolyak import SmolyakGrid
dr = SmolyakGrid(bounds[0, :], bounds[1, :], smolyak_order)
elif interp_type == 'spline':
from dolo.numeric.interpolation.splines import MultivariateSplines
dr = MultivariateSplines(bounds[0, :], bounds[1, :], interp_orders)
if integration == 'optimal_quantization':
from dolo.numeric.discretization import quantization_nodes
# number of shocks
[epsilons, weights] = quantization_nodes(N_e, sigma)
elif integration == 'gauss-hermite':
from dolo.numeric.discretization import gauss_hermite_nodes
if not integration_orders:
integration_orders = [3] * sigma.shape[0]
[epsilons, weights] = gauss_hermite_nodes(integration_orders, sigma)
vprint('Starting time iteration')
# TODO: transpose
grid = dr.grid
xinit = initial_dr(grid)
xinit = xinit.real # just in case...
f = model.functions['arbitrage']
g = model.functions['transition']
# define objective function (residuals of arbitrage equations)
def fun(x):
return step_residual(grid, x, dr, f, g, parms, epsilons, weights)
##
t1 = time.time()
err = 1
x0 = xinit
it = 0
verbit = True if verbose == 'full' else False
if with_complementarities:
lbfun = model.functions['controls_lb']
ubfun = model.functions['controls_ub']
lb = lbfun(grid, parms)
ub = ubfun(grid, parms)
else:
lb = None
ub = None
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} | {4:3} |'
headline = headline.format('N', ' Error', 'Gain', 'Time', 'nit')
stars = '-'*len(headline)
print(stars)
print(headline)
print(stars)
# format string for within loop
fmt_str = '|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} | {4:3} |'
err_0 = 1
while err > tol and it < maxit:
# update counters
t_start = time.time()
it += 1
# update interpolation coefficients (NOTE: filters through `fun`)
dr.set_values(x0)
# Derivative of objective function
sdfun = SerialDifferentiableFunction(fun)
# Apply solver with current decision rule for controls
if with_complementarities:
[x, nit] = ncpsolve(sdfun, lb, ub, x0, verbose=verbit,
maxit=inner_maxit)
else:
[x, nit] = serial_newton(sdfun, x0, verbose=verbit)
# update error and print if `verbose`
err = abs(x-x0).max()
err_SA = err/err_0
err_0 = err
t_finish = time.time()
elapsed = t_finish - t_start
if verbose:
print(fmt_str.format(it, err, err_SA, elapsed, nit))
# Update control vector
x0[:] = x # x0 = x0 + (x-x0)
# call user supplied hook, if any
if hook:
hook(dr, it, err)
# warn and bail if we get inf
if False in np.isfinite(x0):
print('iteration {} failed : non finite value')
return [x0, x]
if it == maxit:
import warnings
warnings.warn(UserWarning("Maximum number of iterations reached"))
# compute final fime and do final printout if `verbose`
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
return dr
def evaluate_policy(model, dr, tol=1e-8, maxit=2000, verbose=False, hook=None, integration_orders=None):
"""Compute value function corresponding to policy ``dr``
Parameters:
-----------
model:
"fg" or "fga" model. Must contain a 'value' function.
dr:
decision rule to evaluate
Returns:
--------
decision rule:
value function (a function of the space similar to a decision rule object)
"""
assert(model.model_spec=='fga')
vfun = model.functions["value"]
gfun = model.functions['transition']
afun = model.functions['auxiliary']
parms = model.calibration['parameters']
n_vals = len(model.symbols['values'])
import time
t1 = time.time()
err = 1
it = 0
approx = model.options['approximation_space']
a = approx['a']
b = approx['b']
orders = approx['orders']
from dolo.numeric.interpolation.splines import MultivariateSplines
drv = MultivariateSplines(a,b,orders)
grid = drv.grid
N = drv.grid.shape[0]
controls = dr(grid)
auxiliaries = model.functions['auxiliary'](grid, controls, parms)
guess_0 = model.calibration['values']
guess_0 = guess_0[None,:].repeat(N, axis=0)
sigma = model.covariances
from dolo.numeric.discretization import gauss_hermite_nodes
if not integration_orders:
integration_orders = [3] * sigma.shape[0]
[epsilons, weights] = gauss_hermite_nodes(integration_orders, sigma)
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} |'.format( 'N',' Error', 'Gain','Time')
stars = '-'*len(headline)
print(stars)
print(headline)
print(stars)
err_0 = 1
while err > tol and it < maxit:
if hook:
hook()
t_start = time.time()
it +=1
drv.set_values(guess_0)
guess = update_value(gfun, afun, vfun, grid, controls, auxiliaries, dr, drv, epsilons, weights, parms, n_vals)
err = abs(guess-guess_0).max()
err_SA = err/err_0
err_0 = err
guess_0 = guess
t_finish = time.time()
elapsed = t_finish - t_start
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format( it, err, err_SA, elapsed))
if it == maxit:
import warnings
warnings.warn(UserWarning("Maximum number of iterations reached"))
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
return drv
def evaluate_policy(model,
dr,
tol=1e-8,
maxit=2000,
verbose=False,
hook=None,
integration_orders=None):
"""Compute value function corresponding to policy ``dr``
Parameters:
-----------
model:
"fg" or "fga" model. Must contain a 'value' function.
dr:
decision rule to evaluate
Returns:
--------
decision rule:
value function (a function of the space similar to a decision rule
object)
"""
assert (model.model_type == 'dtcscc')
vfun = model.functions["value"]
gfun = model.functions['transition']
afun = model.functions['auxiliary']
parms = model.calibration['parameters']
n_vals = len(model.symbols['values'])
t1 = time.time()
err = 1.0
it = 0
approx = model.options['approximation_space']
a = approx['a']
b = approx['b']
orders = approx['orders']
drv = MultivariateSplines(a, b, orders)
grid = drv.grid
N = drv.grid.shape[0]
controls = dr(grid)
auxiliaries = afun(grid, controls, parms)
guess_0 = model.calibration['values']
guess_0 = guess_0[None, :].repeat(N, axis=0)
sigma = model.covariances
if not integration_orders:
integration_orders = [3] * sigma.shape[0]
[epsilons, weights] = gauss_hermite_nodes(integration_orders, sigma)
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} |'.format(
'N', ' Error', 'Gain', 'Time')
stars = '-' * len(headline)
print(stars)
print(headline)
print(stars)
err_0 = 1.0
while err > tol and it < maxit:
if hook:
hook()
t_start = time.time()
it += 1
# update spline coefficients with current values
drv.set_values(guess_0)
# update the geuss of value functions
guess = update_value(gfun, afun, vfun, grid, controls, dr, drv,
epsilons, weights, parms, n_vals)
# compute error
err = abs(guess - guess_0).max()
err_SA = err / err_0
err_0 = err
# update guess
guess_0[:] = guess.copy()
# print update to user, if verbose
t_finish = time.time()
elapsed = t_finish - t_start
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format(
it, err, err_SA, elapsed))
if it == maxit:
warnings.warn(UserWarning("Maximum number of iterations reached"))
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
return drv
def pea(model, maxit=100, tol=1e-8, initial_dr=None, verbose=False):
t1 = time.time()
g = model.functions['transition']
d = model.functions['direct_response']
h = model.functions['expectation']
p = model.calibration['parameters']
if initial_dr is None:
drp = approximate_controls(model)
else:
drp = approximate_controls(model)
nodes, weights = gauss_hermite_nodes([5], model.covariances)
ap = model.options['approximation_space']
a = ap['a']
b = ap['b']
orders = ap['orders']
grid = mlinspace(a, b, orders)
dr = MultivariateCubicSplines(a, b, orders)
N = grid.shape[0]
z = np.zeros((N, len(model.symbols['expectations'])))
x_0 = drp(grid)
it = 0
err = 10
err_0 = 10
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} |'
headline = headline.format('N', ' Error', 'Gain', 'Time')
stars = '-' * len(headline)
print(stars)
print(headline)
print(stars)
# format string for within loop
fmt_str = '|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'
while err > tol and it <= maxit:
t_start = time.time()
dr.set_values(x_0)
z[...] = 0
for i in range(weights.shape[0]):
e = nodes[i, :]
S = g(grid, x_0, e, p)
# evaluate future controls
X = dr(S)
z += weights[i] * h(S, X, p)
# TODO: check that control is admissible
new_x = d(grid, z, p)
# check whether they differ from the preceding guess
err = (abs(new_x - x_0).max())
x_0 = new_x
if verbose:
# update error and print if `verbose`
err_SA = err / err_0
err_0 = err
t_finish = time.time()
elapsed = t_finish - t_start
if verbose:
print(fmt_str.format(it, err, err_SA, elapsed))
if it == maxit:
import warnings
warnings.warn(UserWarning("Maximum number of iterations reached"))
# compute final fime and do final printout if `verbose`
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
return dr
def evaluate_policy(model,
dr,
tol=1e-8,
grid={},
distribution={},
maxit=2000,
verbose=False,
hook=None,
integration_orders=None):
'''
Compute value function corresponding to policy ``dr``
Parameters:
-----------
model:
"dtcscc" model. Must contain a 'value' function.
dr:
decision rule to evaluate
Returns:
--------
decision rule:
value function (a function of the space similar to a decision rule
object)
'''
assert (model.model_type == 'dtcscc')
vfun = model.functions["value"]
gfun = model.functions['transition']
parms = model.calibration['parameters']
n_vals = len(model.symbols['values'])
t1 = time.time()
err = 1.0
it = 0
approx = model.get_grid(**grid)
interp_type = approx.interpolation
distrib = model.get_distribution(**distribution)
sigma = distrib.sigma
drv = create_interpolator(approx, approx.interpolation)
grid = drv.grid
N = drv.grid.shape[0]
controls = dr(grid)
guess_0 = model.calibration['values']
guess_0 = guess_0[None, :].repeat(N, axis=0)
if not integration_orders:
integration_orders = [3] * sigma.shape[0]
[nodes, weights] = gauss_hermite_nodes(integration_orders, sigma)
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} |'.format(
'N', ' Error', 'Gain', 'Time')
stars = '-' * len(headline)
print(stars)
print(headline)
print(stars)
err_0 = 1.0
while err > tol and it < maxit:
if hook:
hook()
t_start = time.time()
it += 1
# update spline coefficients with current values
drv.set_values(guess_0)
# update the geuss of value functions
guess = update_value(gfun, vfun, grid, controls, dr, drv, nodes,
weights, parms, n_vals)
# compute error
err = abs(guess - guess_0).max()
err_SA = err / err_0
err_0 = err
# update guess
guess_0[:] = guess.copy()
# print update to user, if verbose
t_end = time.time()
elapsed = t_end - t_start
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format(
it, err, err_SA, elapsed))
if it == maxit:
warnings.warn(UserWarning("Maximum number of iterations reached"))
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
return drv
def solve_policy(model,
tol=1e-6,
grid={},
distribution={},
integration_orders=None,
maxit=500,
maxit_howard=500,
verbose=False,
hook=None,
initial_dr=None,
pert_order=1):
'''
Solve for the value function and associated decision rule by iterating over
the value function.
Parameters
-----------
model :
``dtcscc`` model. Must contain a ``felicity`` function.
Returns
--------
dr : Markov decision rule
The solved decision rule/policy function
drv : decision rule
The solved value function
'''
assert (model.model_type == 'dtcscc')
def vprint(t):
if verbose:
print(t)
# transition(s, x, e, p, out), felicity(s, x, p, out)
transition = model.functions['transition']
felicity = model.functions['felicity']
controls_lb = model.functions['controls_lb']
controls_ub = model.functions['controls_ub']
parms = model.calibration['parameters']
discount = model.calibration['beta']
x0 = model.calibration['controls']
s0 = model.calibration['states']
r0 = felicity(s0, x0, parms)
approx = model.get_grid(**grid)
# a = approx.a
# b = approx.b
# orders = approx.orders
distrib = model.get_distribution(**distribution)
sigma = distrib.sigma
# Possibly use the approximation orders?
if integration_orders is None:
integration_orders = [3] * sigma.shape[0]
[nodes, weights] = gauss_hermite_nodes(integration_orders, sigma)
interp_type = approx.interpolation
drv = create_interpolator(approx, interp_type)
if initial_dr is None:
if pert_order == 1:
dr = approximate_controls(model)
if pert_order > 1:
raise Exception("Perturbation order > 1 not supported (yet).")
else:
dr = initial_dr
grid = drv.grid
N = grid.shape[0] # Number of states
n_x = grid.shape[1] # Number of controls
controls = dr(grid)
controls_0 = np.zeros((N, n_x))
controls_0[:, :] = model.calibration['controls'][None, :]
values_0 = np.zeros((N, 1))
values_0[:, :] = r0 / (1 - discount)
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} |'.format(
'N', ' Error', 'Gain', 'Time')
stars = '-' * len(headline)
print(stars)
print(headline)
print(stars)
t1 = time.time()
# FIRST: value function iterations, 10 iterations to start
it = 0
err_v = 100
err_v_0 = 0.0
gain_v = 0.0
err_x = 100
err_x_0 = 100
if verbose:
print(stars)
print('Starting value function iteration')
print(stars)
while err_v > tol and it < 10:
t_start = time.time()
it += 1
# update interpolation object with current values
drv.set_values(values_0)
values = values_0.copy()
controls = controls_0.copy()
for n in range(N):
s = grid[n, :]
x = controls[n, :]
lb = controls_lb(s, parms)
ub = controls_ub(s, parms)
bnds = [e for e in zip(lb, ub)]
def valfun(xx):
return -choice_value(transition, felicity, s, xx, drv, nodes,
weights, parms, discount)[0]
res = minimize(valfun, x, bounds=bnds, tol=1e-4)
controls[n, :] = res.x
values[n, 0] = -valfun(res.x)
# compute error, update value and dr
err_x = abs(controls - controls_0).max()
err_v = abs(values - values_0).max()
t_end = time.time()
elapsed = t_end - t_start
values_0 = values
controls_0 = controls
gain_x = err_x / err_x_0
gain_v = err_v / err_v_0
err_x_0 = err_x
err_v_0 = err_v
# print update to user, if verbose
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format(
it, err_v, gain_v, elapsed))
# SECOND: Howard improvement step, 10-20 iterations
it = 0
err_v = 100
err_v_0 = 0.0
gain_v = 0.0
if verbose:
print(stars)
print('Starting Howard improvement step')
print(stars)
while err_v > tol and it < maxit_howard:
t_start = time.time()
it += 1
# update interpolation object with current values
drv.set_values(values_0)
values = values_0.copy()
controls = controls_0.copy()
# controls = controls_0.copy() # No need to keep updating
for n in range(N):
s = grid[n, :]
x = controls[n, :]
values[n, 0] = choice_value(transition, felicity, s, x, drv, nodes,
weights, parms, discount)[0]
# compute error, update value function
err_v = abs(values - values_0).max()
values_0 = values
t_end = time.time()
elapsed = t_end - t_start
gain_v = err_v / err_v_0
err_v_0 = err_v
# print update to user, if verbose
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format(
it, err_v, gain_v, elapsed))
# THIRD: Back to value function iteration until convergence.
it = 0
err_v = 100
err_v_0 = 0.0
gain_v = 0.0
err_x = 100
err_x_0 = 100
if verbose:
print(stars)
print('Starting value function iteration')
print(stars)
while err_v > tol and it < maxit:
t_start = time.time()
it += 1
# update interpolation object with current values
drv.set_values(values_0)
values = values_0.copy()
controls = controls_0.copy()
for n in range(N):
s = grid[n, :]
x = controls[n, :]
lb = controls_lb(s, parms)
ub = controls_ub(s, parms)
bnds = [e for e in zip(lb, ub)]
def valfun(xx):
return -choice_value(transition, felicity, s, xx, drv, nodes,
weights, parms, discount)[0]
res = minimize(valfun, x, bounds=bnds, tol=1e-4)
controls[n, :] = res.x
values[n, 0] = -valfun(res.x)
# compute error, update value and dr
err_x = abs(controls - controls_0).max()
err_v = abs(values - values_0).max()
t_end = time.time()
elapsed = t_end - t_start
values_0 = values
controls_0 = controls
gain_x = err_x / err_x_0
gain_v = err_v / err_v_0
err_x_0 = err_x
err_v_0 = err_v
# print update to user, if verbose
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'.format(
it, err_v, gain_v, elapsed))
if it == maxit:
warnings.warn(UserWarning("Maximum number of iterations reached"))
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
# final value function and decision rule
drv.set_values(values_0)
dr = create_interpolator(approx, interp_type)
dr.set_values(controls_0)
return dr, drv
def test_simulations():
import time
from matplotlib.pyplot import hist, show, figure, plot, title
from dolo import yaml_import, approximate_controls
from dolo.numeric.discretization import gauss_hermite_nodes
model = yaml_import('../../examples/models/rbc.yaml')
dr = approximate_controls(model)
parms = model.calibration['parameters']
sigma = model.get_calibration().sigma
s0 = dr.S_bar
horizon = 50
t1 = time.time()
simul = simulate(model,
dr,
s0,
sigma,
n_exp=1000,
parms=parms,
seed=1,
horizon=horizon)
t2 = time.time()
print("Took: {}".format(t2 - t1))
N = 80
[x, w] = gauss_hermite_nodes(N, sigma)
t3 = time.time()
simul_2 = simulate(model,
dr,
s0,
sigma,
n_exp=1000,
parms=parms,
horizon=horizon,
seed=1,
solve_expectations=True,
nodes=x,
weights=w)
t4 = time.time()
print("Took: {}".format(t4 - t3))
timevec = numpy.array(range(simul.shape[2]))
figure()
for k in range(10):
plot(simul[:, k, 0] - simul_2[:, k, 0])
title("Productivity")
show()
figure()
for k in range(10):
plot(simul[:, k, 1] - simul_2[:, k, 1])
title("Investment")
show()
#
# figure()
# plot(simul[0,0,:])
# plot(simul_2[0,0,:])
# show()
figure()
for i in range(horizon):
hist(simul[i, :, 0], bins=50)
show()
def time_iteration(model,
bounds=None,
verbose=False,
initial_dr=None,
pert_order=1,
with_complementarities=True,
interp_type='smolyak',
smolyak_order=3,
interp_orders=None,
maxit=500,
tol=1e-8,
integration='gauss-hermite',
integration_orders=None,
T=200,
n_s=3,
hook=None):
"""Finds a global solution for ``model`` using backward time-iteration.
Parameters:
-----------
model: NumericModel
"fg" or "fga" model to be solved
bounds: ndarray
boundaries for approximations. First row contains minimum values. Second row contains maximum values.
verbose: boolean
if True, display iterations
initial_dr: decision rule
initial guess for the decision rule
pert_order: {1}
if no initial guess is supplied, the perturbation solution at order ``pert_order`` is used as initial guess
with_complementarities: boolean (True)
if False, complementarity conditions are ignored
interp_type: {`smolyak`, `spline`}
type of interpolation to use for future controls
smolyak_orders: int
parameter ``l`` for Smolyak interpolation
interp_orders: 1d array-like
list of integers specifying the number of nods in each dimension if ``interp_type="spline" ``
Returns:
--------
decision rule object (SmolyakGrid or MultivariateSplines)
"""
def vprint(t):
if verbose:
print(t)
parms = model.calibration['parameters']
sigma = model.covariances
if initial_dr == None:
if pert_order == 1:
from dolo.algos.perturbations import approximate_controls
initial_dr = approximate_controls(model)
if pert_order > 1:
raise Exception("Perturbation order > 1 not supported (yet).")
if interp_type == 'perturbations':
return initial_dr
if bounds is not None:
pass
elif model.options and 'approximation_space' in model.options:
vprint('Using bounds specified by model')
approx = model.options['approximation_space']
a = approx['a']
b = approx['b']
bounds = numpy.row_stack([a, b])
bounds = numpy.array(bounds, dtype=float)
else:
vprint('Using asymptotic bounds given by first order solution.')
from dolo.numeric.timeseries import asymptotic_variance
# this will work only if initial_dr is a Taylor expansion
Q = asymptotic_variance(initial_dr.A.real,
initial_dr.B.real,
initial_dr.sigma,
T=T)
devs = numpy.sqrt(numpy.diag(Q))
bounds = numpy.row_stack([
initial_dr.S_bar - devs * n_s,
initial_dr.S_bar + devs * n_s,
])
if interp_orders == None:
interp_orders = [5] * bounds.shape[1]
if interp_type == 'smolyak':
from dolo.numeric.interpolation.smolyak import SmolyakGrid
dr = SmolyakGrid(bounds[0, :], bounds[1, :], smolyak_order)
elif interp_type == 'spline':
from dolo.numeric.interpolation.splines import MultivariateSplines
dr = MultivariateSplines(bounds[0, :], bounds[1, :], interp_orders)
elif interp_type == 'multilinear':
from dolo.numeric.interpolation.multilinear import MultilinearInterpolator
dr = MultilinearInterpolator(bounds[0, :], bounds[1, :], interp_orders)
if integration == 'optimal_quantization':
from dolo.numeric.discretization import quantization_nodes
# number of shocks
[epsilons, weights] = quantization_nodes(N_e, sigma)
elif integration == 'gauss-hermite':
from dolo.numeric.discretization import gauss_hermite_nodes
if not integration_orders:
integration_orders = [3] * sigma.shape[0]
[epsilons, weights] = gauss_hermite_nodes(integration_orders, sigma)
vprint('Starting time iteration')
# TODO: transpose
grid = dr.grid
xinit = initial_dr(grid)
xinit = xinit.real # just in case...
from dolo.algos.convert import get_fg_functions
f, g = get_fg_functions(model)
import time
fun = lambda x: step_residual(grid, x, dr, f, g, parms, epsilons, weights)
##
t1 = time.time()
err = 1
x0 = xinit
it = 0
verbit = True if verbose == 'full' else False
if with_complementarities:
lbfun = model.functions['arbitrage_lb']
ubfun = model.functions['arbitrage_ub']
lb = lbfun(grid, parms)
ub = ubfun(grid, parms)
else:
lb = None
ub = None
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} | {4:3} |'.format(
'N', ' Error', 'Gain', 'Time', 'nit')
stars = '-' * len(headline)
print(stars)
print(headline)
print(stars)
err_0 = 1
while err > tol and it < maxit:
t_start = time.time()
it += 1
dr.set_values(x0)
from dolo.numeric.optimize.newton import serial_newton, SerialDifferentiableFunction
from dolo.numeric.optimize.ncpsolve import ncpsolve
sdfun = SerialDifferentiableFunction(fun)
if with_complementarities:
[x, nit] = ncpsolve(sdfun, lb, ub, x0, verbose=verbit)
else:
[x, nit] = serial_newton(sdfun, x0, verbose=verbit)
err = abs(x - x0).max()
err_SA = err / err_0
err_0 = err
t_finish = time.time()
elapsed = t_finish - t_start
if verbose:
print('|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} | {4:3} |'.format(
it, err, err_SA, elapsed, nit))
x0 = x0 + (x - x0)
if hook:
hook(dr, it, err)
if False in np.isfinite(x0):
print('iteration {} failed : non finite value')
return [x0, x]
if it == maxit:
import warnings
warnings.warn(UserWarning("Maximum number of iterations reached"))
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
return dr
def gssa(model, maxit=100, tol=1e-8, initial_dr=None, verbose=False,
n_sim=10000, deg=3, damp=0.1, seed=42):
"""
Sketch of algorithm:
0. Choose levels for the initial states and the simulation length (n_sim)
1. Obtain an initial decision rule -- here using first order perturbation
2. Draw a sequence of innovations epsilon
3. Iterate on the following steps:
- Use the epsilons, initial states, and proposed decision rule to
simulate model forward. Will leave us with time series of states and
controls
- Evaluate expectations using quadrature
- Use direct response to get alternative proposal for controls
- Regress updated controls on the simulated states to get proposal
coefficients. New coefficients are convex combination of previous
coefficients and proposal coefficients. Weights controlled by damp,
where damp is the weight on the old coefficients. This should be
fairly low to increase chances of convergence.
- Check difference between the simulated series of controls and the
direct response version of controls
"""
# verify input arguments
if deg < 0 or deg > 5:
raise ValueError("deg must be in [1, 5]")
if damp < 0 or damp > 1:
raise ValueError("damp must be in [0, 1]")
t1 = time.time()
# extract model functions and parameters
g = model.__original_functions__['transition']
g_gu = model.__original_gufunctions__['transition']
h_gu = model.__original_gufunctions__['expectation']
d_gu = model.__original_gufunctions__['direct_response']
p = model.calibration['parameters']
n_s = len(model.symbols["states"])
n_x = len(model.symbols["controls"])
n_z = len(model.symbols["expectations"])
n_eps = len(model.symbols["shocks"])
s0 = model.calibration["states"]
x0 = model.calibration["controls"]
# construct initial decision rule if not supplied
if initial_dr is None:
drp = approximate_controls(model)
else:
drp = initial_dr
# set up quadrature weights and nodes
sigma = model.covariances
nodes, weights = gauss_hermite_nodes([5], model.covariances)
# draw sequence of innovations
np.random.seed(seed)
epsilon = numpy.random.multivariate_normal(np.zeros(n_eps), sigma, n_sim)
# simulate initial decision rule and do initial regression for coefs
init_sim = simulate(model, drp, horizon=n_sim, return_array=True,
forcing_shocks=epsilon)
s_sim = init_sim[:, 0, 0:n_s]
x_sim = init_sim[:, 0, n_s:n_s + n_x]
Phi_sim = complete_polynomial(s_sim.T, deg).T
coefs = np.ascontiguousarray(lstsq(Phi_sim, x_sim)[0])
# NOTE: the ascontiguousarray above was needed for numba to compile the
# `np.dot` in the simulation function in no python mode. Appearantly
# the array returned from lstsq is not C-contiguous
# allocate for simulated series of expectations and next period states
z_sim = np.empty((n_sim, n_z))
S = np.empty_like(s_sim)
X = np.empty_like(x_sim)
H = np.empty_like(z_sim)
new_x = np.empty_like(x_sim)
# set initial states and controls
s_sim[0, :] = s0
x_sim[0, :] = x0
Phi_t = np.empty(n_complete(n_s, deg)) # buffer array for simulation
# create jitted function that will simulate states and controls, using
# the epsilon shocks from above (define here as closure over all data
# above).
@jit(nopython=True)
def simulate_states_controls(s, x, Phi_t, coefs):
for t in range(1, n_sim):
g(s[t - 1, :], x[t - 1, :], epsilon[t, :], p, s[t, :])
# fill Phi_t with new complete poly version of s[t, :]
_complete_poly_impl_vec(s[t, :], deg, Phi_t)
# do inner product to get new controls
x[t, :] = Phi_t @coefs
it = 0
err = 10.0
err_0 = 10
if verbose:
headline = '|{0:^4} | {1:10} | {2:8} | {3:8} |'
headline = headline.format('N', ' Error', 'Gain', 'Time')
stars = '-' * len(headline)
print(stars)
print(headline)
print(stars)
# format string for within loop
fmt_str = '|{0:4} | {1:10.3e} | {2:8.3f} | {3:8.3f} |'
while err > tol and it <= maxit:
t_start = time.time()
# simulate with new coefficients
simulate_states_controls(s_sim, x_sim, Phi_t, coefs)
# update expectations of z
# update_expectations(s_sim, x_sim, z_sim, Phi_sim)
z_sim[:, :] = 0.0
for i in range(weights.shape[0]):
e = nodes[i, :] # extract nodes
# evaluate future states at each node (stores in S)
g_gu(s_sim, x_sim, e, p, S)
# evaluate future controls at each future state
_complete_poly_impl(S.T, deg, Phi_sim.T)
np.dot(Phi_sim, coefs, out=X)
# compute expectation (stores in H)
h_gu(S, X, p, H)
z_sim += weights[i] * H
# get controls on the simulated points from direct_resposne
# (stores in new_x)
d_gu(s_sim, z_sim, p, new_x)
# update basis matrix and do regression of new_x on s_sim to get
# updated coefficients
_complete_poly_impl(s_sim.T, deg, Phi_sim.T)
new_coefs = np.ascontiguousarray(lstsq(Phi_sim, new_x)[0])
# check whether they differ from the preceding guess
err = (abs(new_x - x_sim).max())
# update the series of controls and coefficients
x_sim[:, :] = new_x
coefs = (1 - damp) * new_coefs + damp * coefs
if verbose:
# update error and print if `verbose`
err_SA = err / err_0
err_0 = err
t_finish = time.time()
elapsed = t_finish - t_start
if verbose:
print(fmt_str.format(it, err, err_SA, elapsed))
it += 1
if it == maxit:
warnings.warn(UserWarning("Maximum number of iterations reached"))
# compute final fime and do final printout if `verbose`
t2 = time.time()
if verbose:
print(stars)
print('Elapsed: {} seconds.'.format(t2 - t1))
print(stars)
return coefs