def test_clone():
config = config0()
config2 = clone(config)
nodeset = set(dfs(config))
assert not any(n in nodeset for n in dfs(config2))
foo = recursive_set_rng_kwarg(config, scope.rng_from_seed(5))
r = rec_eval(foo)
print r
r2 = rec_eval(recursive_set_rng_kwarg(config2, scope.rng_from_seed(5)))
print r2
assert r == r2
def test_vectorize_multipath():
N = as_apply(15)
p0 = hp_uniform('p0', 0, 1)
loss = hp_choice('p1', [1, p0, -p0])**2
expr_idxs = scope.range(N)
vh = VectorizeHelper(loss, expr_idxs, build=True)
vloss = vh.v_expr
print vloss
full_output = as_apply([vloss, vh.idxs_by_label(), vh.vals_by_label()])
new_vc = recursive_set_rng_kwarg(
full_output,
as_apply(np.random.RandomState(1)),
)
losses, idxs, vals = rec_eval(new_vc)
print 'losses', losses
print 'idxs p0', idxs['p0']
print 'vals p0', vals['p0']
print 'idxs p1', idxs['p1']
print 'vals p1', vals['p1']
p0dct = dict(zip(idxs['p0'], vals['p0']))
p1dct = dict(zip(idxs['p1'], vals['p1']))
for ii, li in enumerate(losses):
print ii, li
if p1dct[ii] != 0:
assert li == p0dct[ii]**2
else:
assert li == 1
def test_vectorize_multipath():
N = as_apply(15)
p0 = hp_uniform('p0', 0, 1)
loss = hp_choice('p1', [1, p0, -p0]) ** 2
expr_idxs = scope.range(N)
vh = VectorizeHelper(loss, expr_idxs, build=True)
vloss = vh.v_expr
print vloss
full_output = as_apply([vloss,
vh.idxs_by_label(),
vh.vals_by_label()])
new_vc = recursive_set_rng_kwarg(
full_output,
as_apply(np.random.RandomState(1)),
)
losses, idxs, vals = rec_eval(new_vc)
print 'losses', losses
print 'idxs p0', idxs['p0']
print 'vals p0', vals['p0']
print 'idxs p1', idxs['p1']
print 'vals p1', vals['p1']
p0dct = dict(zip(idxs['p0'], vals['p0']))
p1dct = dict(zip(idxs['p1'], vals['p1']))
for ii, li in enumerate(losses):
print ii, li
if p1dct[ii] != 0:
assert li == p0dct[ii] ** 2
else:
assert li == 1
def __init__(self, bandit, seed=seed, cmd=None, workdir=None):
self.bandit = bandit
self.seed = seed
self.rng = np.random.RandomState(self.seed)
self.cmd = cmd
self.workdir = workdir
self.s_new_ids = pyll.Literal('new_ids') # -- list at eval-time
before = pyll.dfs(self.bandit.expr)
# -- raises exception if expr contains cycles
pyll.toposort(self.bandit.expr)
vh = self.vh = VectorizeHelper(self.bandit.expr, self.s_new_ids)
# -- raises exception if v_expr contains cycles
pyll.toposort(vh.v_expr)
idxs_by_label = vh.idxs_by_label()
vals_by_label = vh.vals_by_label()
after = pyll.dfs(self.bandit.expr)
# -- try to detect if VectorizeHelper screwed up anything inplace
assert before == after
assert set(idxs_by_label.keys()) == set(vals_by_label.keys())
assert set(idxs_by_label.keys()) == set(self.bandit.params.keys())
# -- make the graph runnable and SON-encodable
# N.B. operates inplace
self.s_idxs_vals = recursive_set_rng_kwarg(
scope.pos_args(idxs_by_label, vals_by_label),
pyll.as_apply(self.rng))
# -- raises an exception if no topological ordering exists
pyll.toposort(self.s_idxs_vals)
def __init__(self, bandit, seed=seed, cmd=None, workdir=None):
self.bandit = bandit
self.seed = seed
self.rng = np.random.RandomState(self.seed)
self.cmd = cmd
self.workdir = workdir
self.s_new_ids = pyll.Literal('new_ids') # -- list at eval-time
before = pyll.dfs(self.bandit.expr)
# -- raises exception if expr contains cycles
pyll.toposort(self.bandit.expr)
vh = self.vh = VectorizeHelper(self.bandit.expr, self.s_new_ids)
# -- raises exception if v_expr contains cycles
pyll.toposort(vh.v_expr)
idxs_by_label = vh.idxs_by_label()
vals_by_label = vh.vals_by_label()
after = pyll.dfs(self.bandit.expr)
# -- try to detect if VectorizeHelper screwed up anything inplace
assert before == after
assert set(idxs_by_label.keys()) == set(vals_by_label.keys())
assert set(idxs_by_label.keys()) == set(self.bandit.params.keys())
# -- make the graph runnable and SON-encodable
# N.B. operates inplace
self.s_idxs_vals = recursive_set_rng_kwarg(
scope.pos_args(idxs_by_label, vals_by_label),
pyll.as_apply(self.rng))
# -- raises an exception if no topological ordering exists
pyll.toposort(self.s_idxs_vals)
def test_vectorize_simple():
N = as_apply(15)
p0 = hp_uniform('p0', 0, 1)
loss = p0 ** 2
print loss
expr_idxs = scope.range(N)
vh = VectorizeHelper(loss, expr_idxs, build=True)
vloss = vh.v_expr
full_output = as_apply([vloss,
vh.idxs_by_label(),
vh.vals_by_label()])
fo2 = replace_repeat_stochastic(full_output)
new_vc = recursive_set_rng_kwarg(
fo2,
as_apply(np.random.RandomState(1)),
)
#print new_vc
losses, idxs, vals = rec_eval(new_vc)
print 'losses', losses
print 'idxs p0', idxs['p0']
print 'vals p0', vals['p0']
p0dct = dict(zip(idxs['p0'], vals['p0']))
for ii, li in enumerate(losses):
assert p0dct[ii] ** 2 == li
def test_vectorize_simple():
N = as_apply(15)
p0 = hp_uniform('p0', 0, 1)
loss = p0**2
print loss
expr_idxs = scope.range(N)
vh = VectorizeHelper(loss, expr_idxs, build=True)
vloss = vh.v_expr
full_output = as_apply([vloss, vh.idxs_by_label(), vh.vals_by_label()])
fo2 = replace_repeat_stochastic(full_output)
new_vc = recursive_set_rng_kwarg(
fo2,
as_apply(np.random.RandomState(1)),
)
#print new_vc
losses, idxs, vals = rec_eval(new_vc)
print 'losses', losses
print 'idxs p0', idxs['p0']
print 'vals p0', vals['p0']
p0dct = dict(zip(idxs['p0'], vals['p0']))
for ii, li in enumerate(losses):
assert p0dct[ii]**2 == li
def evaluate(self, config, ctrl):
memo = self.memo_from_config(config)
memo[self.pyll_ctrl] = ctrl
if self.init_pyll_memo:
memo = self.init_pyll_memo(memo, config=config, ctrl=ctrl)
if self.rng is not None and not self.installed_rng:
# -- N.B. this modifies the expr graph in-place
# XXX this feels wrong
self.expr = recursive_set_rng_kwarg(self.expr,
pyll.as_apply(self.rng))
self.installed_rng = True
try:
# -- the "work" of evaluating `config` can be written
# either into the pyll part (self.expr)
# or the normal Python part (self.fn)
pyll_rval = pyll.rec_eval(self.expr, memo=memo)
rval = self.fn(pyll_rval)
except Exception, e:
n_match = 0
for match, match_pair in self.exceptions:
if match(e):
rval = match_pair(e)
logger.info('Caught fn exception %s' % str(rval))
n_match += 1
break
if n_match == 0:
raise
def test_clone():
config = config0()
config2 = clone(config)
nodeset = set(dfs(config))
assert not any(n in nodeset for n in dfs(config2))
foo = recursive_set_rng_kwarg(
config,
scope.rng_from_seed(5))
r = rec_eval(foo)
print r
r2 = rec_eval(
recursive_set_rng_kwarg(
config2,
scope.rng_from_seed(5)))
print r2
assert r == r2
def evaluate(self, config, ctrl, attach_attachments=True):
memo = self.memo_from_config(config)
self.use_obj_for_literal_in_memo(ctrl, base.Ctrl, memo)
if self.rng is not None and not self.installed_rng:
# -- N.B. this modifies the expr graph in-place
# XXX this feels wrong
self.expr = recursive_set_rng_kwarg(self.expr,
pyll.as_apply(self.rng))
self.installed_rng = True
if self.pass_expr_memo_ctrl:
rval = self.fn(
expr=self.expr,
memo=memo,
ctrl=ctrl,
*self.args)
else:
# -- the "work" of evaluating `config` can be written
# either into the pyll part (self.expr)
# or the normal Python part (self.fn)
pyll_rval = pyll.rec_eval(self.expr, memo=memo,
print_node_on_error=self.rec_eval_print_node_on_error)
rval = self.fn(pyll_rval, *self.args)
if isinstance(rval, (float, int, np.number)):
dict_rval = {'loss': rval}
elif isinstance(rval, (dict,)):
dict_rval = rval
if 'loss' not in dict_rval:
raise ValueError('dictionary must have "loss" key',
dict_rval.keys())
else:
raise TypeError('invalid return type (neither number nor dict)', rval)
if dict_rval['loss'] is not None:
# -- fail if cannot be cast to float
dict_rval['loss'] = float(dict_rval['loss'])
dict_rval.setdefault('status', base.STATUS_OK)
if dict_rval['status'] not in base.STATUS_STRINGS:
raise ValueError('invalid status string', dict_rval['status'])
if attach_attachments:
attachments = dict_rval.pop('attachments', {})
for key, val in attachments.items():
ctrl.attachments[key] = val
# -- don't do this here because SON-compatibility is only a requirement
# for trials destined for a mongodb. In-memory rvals can contain
# anything.
#return base.SONify(dict_rval)
return dict_rval
def evaluate(self, config, ctrl, attach_attachments=True):
memo = self.memo_from_config(config)
self.use_obj_for_literal_in_memo(ctrl, base.Ctrl, memo)
if self.rng is not None and not self.installed_rng:
# -- N.B. this modifies the expr graph in-place
# XXX this feels wrong
self.expr = recursive_set_rng_kwarg(self.expr,
pyll.as_apply(self.rng))
self.installed_rng = True
if self.pass_expr_memo_ctrl:
rval = self.fn(expr=self.expr, memo=memo, ctrl=ctrl)
else:
# -- the "work" of evaluating `config` can be written
# either into the pyll part (self.expr)
# or the normal Python part (self.fn)
pyll_rval = pyll.rec_eval(
self.expr,
memo=memo,
print_node_on_error=self.rec_eval_print_node_on_error)
rval = self.fn(pyll_rval)
if isinstance(rval, (float, int, np.number)):
dict_rval = {'loss': rval}
elif isinstance(rval, (dict, )):
dict_rval = rval
if 'loss' not in dict_rval:
raise ValueError('dictionary must have "loss" key',
dict_rval.keys())
else:
raise TypeError('invalid return type (neither number nor dict)',
rval)
if dict_rval['loss'] is not None:
# -- fail if cannot be cast to float
dict_rval['loss'] = float(dict_rval['loss'])
dict_rval.setdefault('status', base.STATUS_OK)
if dict_rval['status'] not in base.STATUS_STRINGS:
raise ValueError('invalid status string', dict_rval['status'])
if attach_attachments:
attachments = dict_rval.pop('attachments', {})
for key, val in attachments.items():
ctrl.attachments[key] = val
# -- don't do this here because SON-compatibility is only a requirement
# for trials destined for a mongodb. In-memory rvals can contain
# anything.
#return base.SONify(dict_rval)
return dict_rval
def __init__(self,
fn,
expr,
args=[],
workdir=None,
pass_expr_memo_ctrl=None,
**bandit_kwargs):
self.cmd = ('domain_attachment', 'FMinIter_Domain')
self.fn = fn
self.expr = expr
self.args = args
if pass_expr_memo_ctrl is None:
self.pass_expr_memo_ctrl = getattr(fn, 'fmin_pass_expr_memo_ctrl',
False)
else:
self.pass_expr_memo_ctrl = pass_expr_memo_ctrl
base.Bandit.__init__(self, expr, do_checks=False, **bandit_kwargs)
# -- This code was stolen from base.BanditAlgo, a class which may soon
# be gone
self.workdir = workdir
self.s_new_ids = pyll.Literal('new_ids') # -- list at eval-time
before = pyll.dfs(self.expr)
# -- raises exception if expr contains cycles
pyll.toposort(self.expr)
vh = self.vh = VectorizeHelper(self.expr, self.s_new_ids)
# -- raises exception if v_expr contains cycles
pyll.toposort(vh.v_expr)
idxs_by_label = vh.idxs_by_label()
vals_by_label = vh.vals_by_label()
after = pyll.dfs(self.expr)
# -- try to detect if VectorizeHelper screwed up anything inplace
assert before == after
assert set(idxs_by_label.keys()) == set(vals_by_label.keys())
assert set(idxs_by_label.keys()) == set(self.params.keys())
# -- make the graph runnable and SON-encodable
# N.B. operates inplace
self.s_idxs_vals = recursive_set_rng_kwarg(
pyll.scope.pos_args(idxs_by_label, vals_by_label),
pyll.as_apply(self.rng))
# -- raises an exception if no topological ordering exists
pyll.toposort(self.s_idxs_vals)
def __init__(self, fn, expr, args=[],
workdir=None,
pass_expr_memo_ctrl=None,
**bandit_kwargs):
self.cmd = ('domain_attachment', 'FMinIter_Domain')
self.fn = fn
self.expr = expr
self.args = args
if pass_expr_memo_ctrl is None:
self.pass_expr_memo_ctrl = getattr(fn,
'fmin_pass_expr_memo_ctrl', False)
else:
self.pass_expr_memo_ctrl = pass_expr_memo_ctrl
base.Bandit.__init__(self, expr, do_checks=False, **bandit_kwargs)
# -- This code was stolen from base.BanditAlgo, a class which may soon
# be gone
self.workdir = workdir
self.s_new_ids = pyll.Literal('new_ids') # -- list at eval-time
before = pyll.dfs(self.expr)
# -- raises exception if expr contains cycles
pyll.toposort(self.expr)
vh = self.vh = VectorizeHelper(self.expr, self.s_new_ids)
# -- raises exception if v_expr contains cycles
pyll.toposort(vh.v_expr)
idxs_by_label = vh.idxs_by_label()
vals_by_label = vh.vals_by_label()
after = pyll.dfs(self.expr)
# -- try to detect if VectorizeHelper screwed up anything inplace
assert before == after
assert set(idxs_by_label.keys()) == set(vals_by_label.keys())
assert set(idxs_by_label.keys()) == set(self.params.keys())
# -- make the graph runnable and SON-encodable
# N.B. operates inplace
self.s_idxs_vals = recursive_set_rng_kwarg(
pyll.scope.pos_args(idxs_by_label, vals_by_label),
pyll.as_apply(self.rng))
# -- raises an exception if no topological ordering exists
pyll.toposort(self.s_idxs_vals)
def evaluate(self, config, ctrl):
"""Return a result document
"""
memo = self.memo_from_config(config)
self.use_obj_for_literal_in_memo(ctrl, Ctrl, memo)
if self.rng is not None and not self.installed_rng:
# -- N.B. this modifies the expr graph in-place
# XXX this feels wrong
self.expr = recursive_set_rng_kwarg(self.expr, pyll.as_apply(self.rng))
self.installed_rng = True
try:
r_dct = pyll.rec_eval(self.expr, memo=memo)
except Exception, e:
n_match = 0
for match, match_pair in self.exceptions:
if match(e):
r_dct = match_pair(e)
n_match += 1
break
if n_match == 0:
raise
def evaluate(self, config, ctrl):
"""Return a result document
"""
memo = self.memo_from_config(config)
self.use_obj_for_literal_in_memo(ctrl, Ctrl, memo)
if self.rng is not None and not self.installed_rng:
# -- N.B. this modifies the expr graph in-place
# XXX this feels wrong
self.expr = recursive_set_rng_kwarg(self.expr,
pyll.as_apply(self.rng))
self.installed_rng = True
try:
r_dct = pyll.rec_eval(self.expr, memo=memo)
except Exception, e:
n_match = 0
for match, match_pair in self.exceptions:
if match(e):
r_dct = match_pair(e)
n_match += 1
break
if n_match == 0:
raise
def test_vectorize_config0():
p0 = hp_uniform('p0', 0, 1)
p1 = hp_loguniform('p1', 2, 3)
p2 = hp_choice('p2', [-1, p0])
p3 = hp_choice('p3', [-2, p1])
p4 = 1
p5 = [3, 4, p0]
p6 = hp_choice('p6', [-3, p1])
d = locals()
d['p1'] = None # -- don't sample p1 all the time, only if p3 says so
config = as_apply(d)
N = as_apply('N:TBA')
expr = config
expr_idxs = scope.range(N)
vh = VectorizeHelper(expr, expr_idxs, build=True)
vconfig = vh.v_expr
full_output = as_apply([vconfig, vh.idxs_by_label(), vh.vals_by_label()])
if 1:
print '=' * 80
print 'VECTORIZED'
print full_output
print '\n' * 1
fo2 = replace_repeat_stochastic(full_output)
if 0:
print '=' * 80
print 'VECTORIZED STOCHASTIC'
print fo2
print '\n' * 1
new_vc = recursive_set_rng_kwarg(fo2, as_apply(np.random.RandomState(1)))
if 0:
print '=' * 80
print 'VECTORIZED STOCHASTIC WITH RNGS'
print new_vc
Nval = 10
foo, idxs, vals = rec_eval(new_vc, memo={N: Nval})
print 'foo[0]', foo[0]
print 'foo[1]', foo[1]
assert len(foo) == Nval
if 0: # XXX refresh these values to lock down sampler
assert foo[0] == {
'p0': 0.39676747423066994,
'p1': None,
'p2': 0.39676747423066994,
'p3': 2.1281244479293568,
'p4': 1,
'p5': (3, 4, 0.39676747423066994)
}
assert foo[1] != foo[2]
print idxs
print vals['p3']
print vals['p6']
print idxs['p1']
print vals['p1']
assert len(vals['p3']) == Nval
assert len(vals['p6']) == Nval
assert len(idxs['p1']) < Nval
p1d = dict(zip(idxs['p1'], vals['p1']))
for ii, (p3v, p6v) in enumerate(zip(vals['p3'], vals['p6'])):
if p3v == p6v == 0:
assert ii not in idxs['p1']
if p3v:
assert foo[ii]['p3'] == p1d[ii]
if p6v:
print 'p6', foo[ii]['p6'], p1d[ii]
assert foo[ii]['p6'] == p1d[ii]
def __init__(self, bandit, seed=seed, cmd=None, workdir=None):
self.bandit = bandit
self.seed = seed
self.rng = np.random.RandomState(self.seed)
self.cmd = cmd
self.workdir = workdir
self.new_ids = ['dummy_id']
# -- N.B. not necessarily actually a range
self.s_new_ids = pyll.Literal(self.new_ids)
self.template_clone_memo = {}
template = pyll.clone(self.bandit.template, self.template_clone_memo)
vh = self.vh = VectorizeHelper(template, self.s_new_ids)
vh.build_idxs()
vh.build_vals()
# the keys (nid) here are strings like 'node_5'
idxs_by_nid = vh.idxs_by_id()
vals_by_nid = vh.vals_by_id()
name_by_nid = vh.name_by_id()
assert set(idxs_by_nid.keys()) == set(vals_by_nid.keys())
assert set(name_by_nid.keys()) == set(vals_by_nid.keys())
# -- replace repeat(dist(...)) with vectorized versions
t_i_v = replace_repeat_stochastic(
pyll.as_apply([
vh.vals_memo[template], idxs_by_nid, vals_by_nid]))
assert t_i_v.name == 'pos_args'
template, s_idxs_by_nid, s_vals_by_nid = t_i_v.pos_args
# -- fetch the dictionaries off the top of the cloned graph
idxs_by_nid = dict(s_idxs_by_nid.named_args)
vals_by_nid = dict(s_vals_by_nid.named_args)
# -- remove non-stochastic nodes from the idxs and vals
# because
# (a) they should be irrelevant for BanditAlgo operation,
# (b) they can be reconstructed from the template and the
# stochastic choices, and
# (c) they are often annoying when printing / saving.
for node_id, name in name_by_nid.items():
if name not in pyll.stochastic.implicit_stochastic_symbols:
del name_by_nid[node_id]
del vals_by_nid[node_id]
del idxs_by_nid[node_id]
elif name == 'one_of':
# -- one_of nodes too, because they are duplicates of randint
del name_by_nid[node_id]
del vals_by_nid[node_id]
del idxs_by_nid[node_id]
# -- make the graph runnable and SON-encodable
# N.B. operates inplace
self.s_specs_idxs_vals = recursive_set_rng_kwarg(
scope.pos_args(template, idxs_by_nid, vals_by_nid),
pyll.as_apply(self.rng))
self.vtemplate = template
self.idxs_by_nid = idxs_by_nid
self.vals_by_nid = vals_by_nid
self.name_by_nid = name_by_nid
# -- compute some document coordinate strings for the node_ids
pnames = pretty_names(bandit.template, prefix=None)
doc_coords = self.doc_coords = {}
for node, pname in pnames.items():
cnode = self.template_clone_memo[node]
if cnode.name == 'one_of':
choice_node = vh.choice_memo[cnode]
assert choice_node.name == 'randint'
doc_coords[vh.node_id[choice_node]] = pname #+ '.randint'
if cnode in vh.node_id and vh.node_id[cnode] in name_by_nid:
doc_coords[vh.node_id[cnode]] = pname
else:
#print 'DROPPING', node
pass
def __init__(self, fn, expr,
workdir=None,
pass_expr_memo_ctrl=None,
name=None,
loss_target=None,
):
"""
Paramaters
----------
fn : callable
This stores the `fn` argument to `fmin`. (See `hyperopt.fmin.fmin`)
expr : hyperopt.pyll.Apply
This is the `space` argument to `fmin`. (See `hyperopt.fmin.fmin`)
workdir : string (or None)
If non-None, the current working directory will be `workdir`while
`expr` and `fn` are evaluated. (XXX Currently only respected by
jobs run via MongoWorker)
pass_expr_memo_ctrl : bool
If True, `fn` will be called like this:
`fn(self.expr, memo, ctrl)`,
where `memo` is a dictionary mapping `Apply` nodes to their
computed values, and `ctrl` is a `Ctrl` instance for communicating
with a Trials database. This lower-level calling convention is
useful if you want to call e.g. `hyperopt.pyll.rec_eval` yourself
in some customized way.
name : string (or None)
Label, used for pretty-printing.
loss_target : float (or None)
The actual or estimated minimum of `fn`.
Some optimization algorithms may behave differently if their first
objective is to find an input that achieves a certain value,
rather than the more open-ended objective of pure minimization.
XXX: Move this from Domain to be an fmin arg.
"""
self.fn = fn
if pass_expr_memo_ctrl is None:
self.pass_expr_memo_ctrl = getattr(fn,
'fmin_pass_expr_memo_ctrl',
False)
else:
self.pass_expr_memo_ctrl = pass_expr_memo_ctrl
self.expr = pyll.as_apply(expr)
self.params = {}
for node in pyll.dfs(self.expr):
if node.name == 'hyperopt_param':
label = node.arg['label'].obj
if label in self.params:
raise DuplicateLabel(label)
self.params[label] = node.arg['obj']
self.loss_target = loss_target
self.name = name
self.workdir = workdir
self.s_new_ids = pyll.Literal('new_ids') # -- list at eval-time
before = pyll.dfs(self.expr)
# -- raises exception if expr contains cycles
pyll.toposort(self.expr)
vh = self.vh = VectorizeHelper(self.expr, self.s_new_ids)
# -- raises exception if v_expr contains cycles
pyll.toposort(vh.v_expr)
idxs_by_label = vh.idxs_by_label()
vals_by_label = vh.vals_by_label()
after = pyll.dfs(self.expr)
# -- try to detect if VectorizeHelper screwed up anything inplace
assert before == after
assert set(idxs_by_label.keys()) == set(vals_by_label.keys())
assert set(idxs_by_label.keys()) == set(self.params.keys())
self.s_rng = pyll.Literal('rng-placeholder')
# -- N.B. operates inplace:
self.s_idxs_vals = recursive_set_rng_kwarg(
pyll.scope.pos_args(idxs_by_label, vals_by_label),
self.s_rng)
# -- raises an exception if no topological ordering exists
pyll.toposort(self.s_idxs_vals)
# -- Protocol for serialization.
# self.cmd indicates to e.g. MongoWorker how this domain
# should be [un]serialized.
# XXX This mechanism deserves review as support for ipython
# workers improves.
self.cmd = ('domain_attachment', 'FMinIter_Domain')
def test_vectorize_config0():
config = config0()
assert 'p3' == config.named_args[2][0]
p1 = config.named_args[2][1].pos_args[1]
assert p1.name == 'uniform'
assert p1.pos_args[0]._obj == 2
assert p1.pos_args[1]._obj == 3
N = as_apply(5)
expr = config
expr_idxs = scope.range(N)
vh = VectorizeHelper(expr, expr_idxs)
vh.build_idxs()
vh.build_vals()
vconfig = vh.vals_memo[expr]
full_output = as_apply([vconfig, vh.idxs_by_id(), vh.vals_by_id()])
if 0:
print '=' * 80
print 'VECTORIZED'
print full_output
print '\n' * 1
fo2 = replace_repeat_stochastic(full_output)
if 0:
print '=' * 80
print 'VECTORIZED STOCHASTIC'
print fo2
print '\n' * 1
new_vc = recursive_set_rng_kwarg(
fo2,
as_apply(np.random.RandomState(1))
)
if 0:
print '=' * 80
print 'VECTORIZED STOCHASTIC WITH RNGS'
print new_vc
foo, idxs, vals = rec_eval(new_vc)
print foo
#print idxs
#print vals
assert len(foo) == 5
assert foo[0] == {
'p0': 0.39676747423066994,
'p2': 0.39676747423066994,
'p3': 2.1281244479293568,
'p4': 1,
'p5': (3, 4, 0.39676747423066994) }
assert foo[1] != foo[2]
if 0:
print idxs[vh.node_id[p1]]
print vals[vh.node_id[p1]]
# - p1 is only used sometimes
assert len(idxs[vh.node_id[p1]]) < 5
for ii in range(5):
if ii in idxs[vh.node_id[p1]]:
assert foo[ii]['p3'] == vals[vh.node_id[p1]][list(idxs[vh.node_id[p1]]).index(ii)]
else:
assert foo[ii]['p3'] == -2, foo[ii]['p3']
def __init__(
self,
fn,
expr,
workdir=None,
pass_expr_memo_ctrl=None,
name=None,
loss_target=None,
):
"""
Paramaters
----------
fn : callable
This stores the `fn` argument to `fmin`. (See `hyperopt.fmin.fmin`)
expr : hyperopt.pyll.Apply
This is the `space` argument to `fmin`. (See `hyperopt.fmin.fmin`)
workdir : string (or None)
If non-None, the current working directory will be `workdir`while
`expr` and `fn` are evaluated. (XXX Currently only respected by
jobs run via MongoWorker)
pass_expr_memo_ctrl : bool
If True, `fn` will be called like this:
`fn(self.expr, memo, ctrl)`,
where `memo` is a dictionary mapping `Apply` nodes to their
computed values, and `ctrl` is a `Ctrl` instance for communicating
with a Trials database. This lower-level calling convention is
useful if you want to call e.g. `hyperopt.pyll.rec_eval` yourself
in some customized way.
name : string (or None)
Label, used for pretty-printing.
loss_target : float (or None)
The actual or estimated minimum of `fn`.
Some optimization algorithms may behave differently if their first
objective is to find an input that achieves a certain value,
rather than the more open-ended objective of pure minimization.
XXX: Move this from Domain to be an fmin arg.
"""
self.fn = fn
if pass_expr_memo_ctrl is None:
self.pass_expr_memo_ctrl = getattr(fn, 'fmin_pass_expr_memo_ctrl',
False)
else:
self.pass_expr_memo_ctrl = pass_expr_memo_ctrl
self.expr = pyll.as_apply(expr)
self.params = {}
for node in pyll.dfs(self.expr):
if node.name == 'hyperopt_param':
label = node.arg['label'].obj
if label in self.params:
raise DuplicateLabel(label)
self.params[label] = node.arg['obj']
self.loss_target = loss_target
self.name = name
self.workdir = workdir
self.s_new_ids = pyll.Literal('new_ids') # -- list at eval-time
before = pyll.dfs(self.expr)
# -- raises exception if expr contains cycles
pyll.toposort(self.expr)
vh = self.vh = VectorizeHelper(self.expr, self.s_new_ids)
# -- raises exception if v_expr contains cycles
pyll.toposort(vh.v_expr)
idxs_by_label = vh.idxs_by_label()
vals_by_label = vh.vals_by_label()
after = pyll.dfs(self.expr)
# -- try to detect if VectorizeHelper screwed up anything inplace
assert before == after
assert set(idxs_by_label.keys()) == set(vals_by_label.keys())
assert set(idxs_by_label.keys()) == set(self.params.keys())
self.s_rng = pyll.Literal('rng-placeholder')
# -- N.B. operates inplace:
self.s_idxs_vals = recursive_set_rng_kwarg(
pyll.scope.pos_args(idxs_by_label, vals_by_label), self.s_rng)
# -- raises an exception if no topological ordering exists
pyll.toposort(self.s_idxs_vals)
# -- Protocol for serialization.
# self.cmd indicates to e.g. MongoWorker how this domain
# should be [un]serialized.
# XXX This mechanism deserves review as support for ipython
# workers improves.
self.cmd = ('domain_attachment', 'FMinIter_Domain')
def test_vectorize_config0():
p0 = hp_uniform('p0', 0, 1)
p1 = hp_loguniform('p1', 2, 3)
p2 = hp_choice('p2', [-1, p0])
p3 = hp_choice('p3', [-2, p1])
p4 = 1
p5 = [3, 4, p0]
p6 = hp_choice('p6', [-3, p1])
d = locals()
d['p1'] = None # -- don't sample p1 all the time, only if p3 says so
config = as_apply(d)
N = as_apply('N:TBA')
expr = config
expr_idxs = scope.range(N)
vh = VectorizeHelper(expr, expr_idxs, build=True)
vconfig = vh.v_expr
full_output = as_apply([vconfig, vh.idxs_by_label(), vh.vals_by_label()])
if 1:
print '=' * 80
print 'VECTORIZED'
print full_output
print '\n' * 1
fo2 = replace_repeat_stochastic(full_output)
if 0:
print '=' * 80
print 'VECTORIZED STOCHASTIC'
print fo2
print '\n' * 1
new_vc = recursive_set_rng_kwarg(
fo2,
as_apply(np.random.RandomState(1))
)
if 0:
print '=' * 80
print 'VECTORIZED STOCHASTIC WITH RNGS'
print new_vc
Nval = 10
foo, idxs, vals = rec_eval(new_vc, memo={N: Nval})
print 'foo[0]', foo[0]
print 'foo[1]', foo[1]
assert len(foo) == Nval
if 0: # XXX refresh these values to lock down sampler
assert foo[0] == {
'p0': 0.39676747423066994,
'p1': None,
'p2': 0.39676747423066994,
'p3': 2.1281244479293568,
'p4': 1,
'p5': (3, 4, 0.39676747423066994) }
assert foo[1] != foo[2]
print idxs
print vals['p3']
print vals['p6']
print idxs['p1']
print vals['p1']
assert len(vals['p3']) == Nval
assert len(vals['p6']) == Nval
assert len(idxs['p1']) < Nval
p1d = dict(zip(idxs['p1'], vals['p1']))
for ii, (p3v, p6v) in enumerate(zip(vals['p3'], vals['p6'])):
if p3v == p6v == 0:
assert ii not in idxs['p1']
if p3v:
assert foo[ii]['p3'] == p1d[ii]
if p6v:
print 'p6', foo[ii]['p6'], p1d[ii]
assert foo[ii]['p6'] == p1d[ii]