def get_hyperparams(self, id, display=True):
"""
Get the hyperparameters of a model explored by grid search.
Parameters
----------
id: str
The model id of the model with hyperparameters of interest.
display: boolean
Flag to indicate whether to display the hyperparameter names.
Returns
-------
A list of the hyperparameters for the specified model.
"""
idx = id if is_int(id) else self.model_ids.index(id)
model = self[idx]
# if cross-validation is turned on, parameters in one of the fold model actuall contains the max_runtime_secs
# parameter and not the main model that is returned.
if model._is_xvalidated:
model = h2o.get_model(model._xval_keys[0])
res = [
model.params[h]['actual'][0] if isinstance(
model.params[h]['actual'], list) else model.params[h]['actual']
for h in self.hyper_params
]
if display:
print('Hyperparameters: [' +
', '.join(list(self.hyper_params.keys())) + ']')
return res
def get_hyperparams_dict(self, id, display=True):
"""
Derived and returned the model parameters used to train the particular grid search model.
Parameters
----------
id: str
The model id of the model with hyperparameters of interest.
display: boolean
Flag to indicate whether to display the hyperparameter names.
Returns
-------
A dict of model pararmeters derived from the hyper-parameters used to train this particular model.
"""
idx = id if is_int(id) else self.model_ids.index(id)
model = self[idx]
model_params = dict()
# if cross-validation is turned on, parameters in one of the fold model actual contains the max_runtime_secs
# parameter and not the main model that is returned.
if model._is_xvalidated:
model = h2o.get_model(model._xval_keys[0])
for param_name in self.hyper_names:
model_params[param_name] = model.params[param_name]['actual'][0] if \
isinstance(model.params[param_name]['actual'], list) else model.params[param_name]['actual']
if display:
print('Hyperparameters: [' +
', '.join(list(self.hyper_params.keys())) + ']')
return model_params
def interaction(data,
factors,
pairwise,
max_factors,
min_occurrence,
destination_frame=None):
"""
Categorical Interaction Feature Creation in H2O.
Creates a frame in H2O with n-th order interaction features between categorical columns, as specified by
the user.
Parameters
----------
data : H2OFrame
the H2OFrame that holds the target categorical columns.
factors : list
factors Factor columns (either indices or column names).
pairwise : bool
Whether to create pairwise interactions between factors (otherwise create one
higher-order interaction). Only applicable if there are 3 or more factors.
max_factors : int
Max. number of factor levels in pair-wise interaction terms (if enforced, one extra
catch-all factor will be made)
min_occurrence : int
Min. occurrence threshold for factor levels in pair-wise interaction terms
destination_frame : str
A string indicating the destination key. If empty, this will be auto-generated by H2O.
Returns
-------
H2OFrame
"""
factors = [data.names[n] if is_int(n) else n for n in factors]
parms = {
"dest":
py_tmp_key(append=h2oconn.session_id)
if destination_frame is None else destination_frame,
"source_frame":
data.frame_id,
"factor_columns": [quoted(f) for f in factors],
"pairwise":
pairwise,
"max_factors":
max_factors,
"min_occurrence":
min_occurrence,
}
H2OJob(api("POST /3/Interaction", data=parms), "Interactions").poll()
return get_frame(parms["dest"])
def _get_type_name(types):
"""
Return the name of the provided type.
>>> _get_type_name([int]) == "integer"
>>> _get_type_name([str]) == "string"
>>> _get_type_name([tuple]) == "tuple"
>>> _get_type_name([Exception]) == "Exception"
>>> _get_type_name((int, float, bool)) == "integer|float|bool"
>>> _get_type_name((H2OFrame, None)) == "?H2OFrame"
"""
from h2o.utils.typechecks import is_str, is_int, U, I, numeric
maybe_type = False
res = []
for tt in types:
if tt is None:
maybe_type = True
elif tt is str:
res.append("string")
elif tt is int:
res.append("integer")
elif tt is numeric:
res.append("numeric")
elif is_str(tt):
res.append('"%s"' % repr(tt)[1:-1])
elif is_int(tt):
res.append(str(tt))
elif isinstance(tt, U):
res.append(H2OTypeError._get_type_name(tt))
elif isinstance(tt, I):
res.append("&".join(
H2OTypeError._get_type_name([tttt]) for tttt in tt))
elif isinstance(tt, type):
res.append(tt.__name__)
elif isinstance(tt, list):
res.append("list(%s)" % H2OTypeError._get_type_name(tt))
elif isinstance(tt, set):
res.append("set(%s)" % H2OTypeError._get_type_name(tt))
elif isinstance(tt, tuple):
res.append("(%s)" % ", ".join(
H2OTypeError._get_type_name([item]) for item in tt))
elif isinstance(tt, dict):
res.append("dict(%s)" %
", ".join("%s: %s" %
(H2OTypeError._get_type_name([tk]),
H2OTypeError._get_type_name([tv]))
for tk, tv in tt.items()))
else:
raise RuntimeError("Unexpected `tt`: %r" % tt)
if maybe_type:
if not res: return "None"
res[0] = "?" + res[0]
return "|".join(res)
def _get_type_name(types):
"""
Return the name of the provided type.
>>> _get_type_name([int]) == "integer"
>>> _get_type_name([str]) == "string"
>>> _get_type_name([tuple]) == "tuple"
>>> _get_type_name([Exception]) == "Exception"
>>> _get_type_name((int, float, bool)) == "integer|float|bool"
>>> _get_type_name((H2OFrame, None)) == "?H2OFrame"
"""
from h2o.utils.typechecks import is_str, is_int, U, I, numeric
maybe_type = False
res = []
for tt in types:
if tt is None:
maybe_type = True
elif tt is str:
res.append("string")
elif tt is int:
res.append("integer")
elif tt is numeric:
res.append("numeric")
elif is_str(tt):
res.append('"%s"' % repr(tt)[1:-1])
elif is_int(tt):
res.append(str(tt))
elif isinstance(tt, U):
res.append(H2OTypeError._get_type_name(tt))
elif isinstance(tt, I):
res.append("&".join(H2OTypeError._get_type_name([tttt]) for tttt in tt))
elif isinstance(tt, type):
res.append(tt.__name__)
elif isinstance(tt, list):
res.append("list(%s)" % H2OTypeError._get_type_name(tt))
elif isinstance(tt, set):
res.append("set(%s)" % H2OTypeError._get_type_name(tt))
elif isinstance(tt, tuple):
res.append("(%s)" % ", ".join(H2OTypeError._get_type_name([item]) for item in tt))
elif isinstance(tt, dict):
res.append("dict(%s)" % ", ".join(
"%s: %s" % (H2OTypeError._get_type_name([tk]), H2OTypeError._get_type_name([tv]))
for tk, tv in tt.items()
))
else:
raise RuntimeError("Unexpected `tt`: %r" % tt)
if maybe_type:
if not res: return "None"
res[0] = "?" + res[0]
return "|".join(res)
def _model_build(self, x, y, tframe, vframe, kwargs):
kwargs['training_frame'] = tframe
if vframe is not None: kwargs["validation_frame"] = vframe
if is_int(y): y = tframe.names[y]
if y is not None: kwargs['response_column'] = y
if not isinstance(x, (list, tuple)): x = [x]
if is_int(x[0]):
x = [tframe.names[i] for i in x]
offset = kwargs["offset_column"]
folds = kwargs["fold_column"]
weights = kwargs["weights_column"]
ignored_columns = list(
set(tframe.names) - set(x + [y, offset, folds, weights]))
kwargs["ignored_columns"] = None if ignored_columns == [] else [
quoted(col) for col in ignored_columns
]
kwargs["interactions"] = None if (
"interactions" not in kwargs or kwargs["interactions"] is None
) else [quoted(col) for col in kwargs["interactions"]]
kwargs = dict([(k, H2OEstimator._keyify_if_H2OFrame(kwargs[k]))
for k in kwargs]) # gruesome one-liner
rest_ver = kwargs.pop(
"_rest_version") if "_rest_version" in kwargs else 3
algo = self._compute_algo()
model = H2OJob(h2o.api("POST /%d/ModelBuilders/%s" % (rest_ver, algo),
data=kwargs),
job_type=(algo + " Model Build"))
if self._future:
self._job = model
return
model.poll()
model_json = h2o.api("GET /%d/Models/%s" %
(rest_ver, model.dest_key))["models"][0]
self._resolve_model(model.dest_key, model_json)
def _add_agg(self, op, col, na):
if op == "nrow": col = 0
if col is None:
for i in range(self._fr.ncol):
if i not in self._by: self._add_agg(op, i, na)
return self
elif is_str(col):
cidx = self._fr.names.index(col)
elif is_int(col):
cidx = col
elif is_listlike(col):
for i in col:
self._add_agg(op, i, na)
return self
else:
raise ValueError("col must be a column name or index.")
name = "{}_{}".format(op, self._fr.names[cidx])
self._aggs[name] = [op, cidx, na]
return self
def interaction(data, factors, pairwise, max_factors, min_occurrence, destination_frame=None):
"""
Categorical Interaction Feature Creation in H2O.
Creates a frame in H2O with n-th order interaction features between categorical columns, as specified by
the user.
Parameters
----------
data : H2OFrame
the H2OFrame that holds the target categorical columns.
factors : list
factors Factor columns (either indices or column names).
pairwise : bool
Whether to create pairwise interactions between factors (otherwise create one
higher-order interaction). Only applicable if there are 3 or more factors.
max_factors : int
Max. number of factor levels in pair-wise interaction terms (if enforced, one extra
catch-all factor will be made)
min_occurrence : int
Min. occurrence threshold for factor levels in pair-wise interaction terms
destination_frame : str
A string indicating the destination key. If empty, this will be auto-generated by H2O.
Returns
-------
H2OFrame
"""
factors = [data.names[n] if is_int(n) else n for n in factors]
parms = {"dest": py_tmp_key(append=h2oconn.session_id) if destination_frame is None else destination_frame,
"source_frame": data.frame_id,
"factor_columns": [quoted(f) for f in factors],
"pairwise": pairwise,
"max_factors": max_factors,
"min_occurrence": min_occurrence,
}
H2OJob(api("POST /3/Interaction", data=parms), "Interactions").poll()
return get_frame(parms["dest"])
def start(jar_path=None, nthreads=-1, enable_assertions=True, max_mem_size=None, min_mem_size=None,
ice_root=None, port="54321+", verbose=True):
"""
Start new H2O server on the local machine.
:param jar_path: Path to the h2o.jar executable. If not given, then we will search for h2o.jar in the
locations returned by `._jar_paths()`.
:param nthreads: Number of threads in the thread pool. This should be related to the number of CPUs used.
-1 means use all CPUs on the host. A positive integer specifies the number of CPUs directly.
:param enable_assertions: If True, pass `-ea` option to the JVM.
:param max_mem_size: Maximum heap size (jvm option Xmx), in bytes.
:param min_mem_size: Minimum heap size (jvm option Xms), in bytes.
:param ice_root: A directory where H2O stores its temporary files. Default location is determined by
tempfile.mkdtemp().
:param port: Port where to start the new server. This could be either an integer, or a string of the form
"DDDDD+", indicating that the server should start looking for an open port starting from DDDDD and up.
:param verbose: If True, then connection info will be printed to the stdout.
:returns: a new H2OLocalServer instance
"""
assert jar_path is None or is_str(jar_path), "`jar_path` should be string, got %s" % type(jar_path)
assert jar_path is None or jar_path.endswith("h2o.jar"), \
"`jar_path` should be a path to an h2o.jar executable, got %s" % jar_path
assert is_int(nthreads), "`nthreads` should be integer, got %s" % type(nthreads)
assert nthreads == -1 or 1 <= nthreads <= 4096, "`nthreads` is out of bounds: %d" % nthreads
assert isinstance(enable_assertions, bool), \
"`enable_assertions` should be bool, got %s" % type(enable_assertions)
assert max_mem_size is None or is_int(max_mem_size), \
"`max_mem_size` should be integer, got %s" % type(max_mem_size)
assert max_mem_size is None or max_mem_size >= 1 << 25, "`max_mem_size` too small: %d" % max_mem_size
assert min_mem_size is None or is_int(min_mem_size), \
"`min_mem_size` should be integer, got %s" % type(min_mem_size)
assert min_mem_size is None or max_mem_size is None or min_mem_size <= max_mem_size, \
"`min_mem_size`=%d is larger than the `max_mem_size`=%d" % (min_mem_size, max_mem_size)
if ice_root:
assert is_str(ice_root), "`ice_root` should be string, got %r" % type(ice_root)
assert os.path.isdir(ice_root), "`ice_root` is not a valid directory: %s" % ice_root
if port is None: port = "54321+"
baseport = None
if is_str(port):
if port.isdigit():
port = int(port)
else:
assert port[-1] == "+" and port[:-1].isdigit(), \
"`port` should be of the form 'DDDD+', where D is a digit. Got: %s" % port
baseport = int(port[:-1])
port = 0
assert is_int(port), "`port` should be integer (or string). Got: %s" % type(port)
hs = H2OLocalServer()
hs._verbose = bool(verbose)
hs._jar_path = hs._find_jar(jar_path)
hs._ice_root = ice_root
if not ice_root:
hs._ice_root = tempfile.mkdtemp()
hs._tempdir = hs._ice_root
if verbose: print("Attempting to start a local H2O server...")
hs._launch_server(port=port, baseport=baseport, nthreads=int(nthreads), ea=enable_assertions,
mmax=max_mem_size, mmin=min_mem_size)
if verbose: print("Server is running at %s://%s:%d" % (hs.scheme, hs.ip, hs.port))
atexit.register(lambda: hs.shutdown())
return hs
def _model_build(self, x, y, tframe, vframe, kwargs):
kwargs['training_frame'] = tframe
if vframe is not None: kwargs["validation_frame"] = vframe
if is_int(y): y = tframe.names[y]
if y is not None: kwargs['response_column'] = y
if not is_listlike(x): x = [x]
if is_int(x[0]):
x = [tframe.names[i] for i in x]
offset = kwargs["offset_column"]
folds = kwargs["fold_column"]
weights = kwargs["weights_column"]
ignored_columns = list(
set(tframe.names) - set(x + [y, offset, folds, weights]))
kwargs["ignored_columns"] = None if not ignored_columns else [
quoted(col) for col in ignored_columns
]
kwargs = dict([(k, kwargs[k].frame_id if isinstance(
kwargs[k], H2OFrame) else kwargs[k]) for k in kwargs
if kwargs[k] is not None]) # gruesome one-liner
algo = self.model._compute_algo() # unique to grid search
if self.grid_id is not None: kwargs["grid_id"] = self.grid_id
rest_ver = kwargs.pop(
"_rest_version") if "_rest_version" in kwargs else None
grid = H2OJob(h2o.api("POST /99/Grid/%s" % algo, data=kwargs),
job_type=(algo + " Grid Build"))
if self._future:
self._job = grid
return
grid.poll()
if rest_ver is not None:
grid_json = h2o.api("GET /99/Grids/%s" % (grid.dest_key))
error_index = 0
if len(grid_json["failure_details"]) > 0:
print("Errors/Warnings building gridsearch model\n")
for error_message in grid_json["failure_details"]:
if isinstance(grid_json["failed_params"][error_index],
dict):
for h_name in grid_json['hyper_names']:
print("Hyper-parameter: {0}, {1}".format(
h_name, grid_json['failed_params'][error_index]
[h_name]))
if len(grid_json["failure_stack_traces"]) > error_index:
print("failure_details: {0}\nfailure_stack_traces: "
"{1}\n".format(
error_message,
grid_json['failure_stack_traces']
[error_index]))
error_index += 1
else:
grid_json = h2o.api("GET /99/Grids/%s" % grid.dest_key)
self.models = [
h2o.get_model(key['name']) for key in grid_json['model_ids']
]
# get first model returned in list of models from grid search to get model class (binomial, multinomial, etc)
# sometimes no model is returned due to bad parameter values provided by the user.
if len(grid_json['model_ids']) > 0:
first_model_json = h2o.api(
"GET /%d/Models/%s" %
(rest_ver
or 3, grid_json['model_ids'][0]['name']))['models'][0]
self._resolve_grid(grid.dest_key, grid_json, first_model_json)
else:
raise ValueError(
"Gridsearch returns no model due to bad parameter values or other reasons...."
)
def start(jar_path=None,
nthreads=-1,
enable_assertions=True,
max_mem_size=None,
min_mem_size=None,
ice_root=None,
port="54321+",
verbose=True):
"""
Start new H2O server on the local machine.
:param jar_path: Path to the h2o.jar executable. If not given, then we will search for h2o.jar in the
locations returned by `._jar_paths()`.
:param nthreads: Number of threads in the thread pool. This should be related to the number of CPUs used.
-1 means use all CPUs on the host. A positive integer specifies the number of CPUs directly.
:param enable_assertions: If True, pass `-ea` option to the JVM.
:param max_mem_size: Maximum heap size (jvm option Xmx), in bytes.
:param min_mem_size: Minimum heap size (jvm option Xms), in bytes.
:param ice_root: A directory where H2O stores its temporary files. Default location is determined by
tempfile.mkdtemp().
:param port: Port where to start the new server. This could be either an integer, or a string of the form
"DDDDD+", indicating that the server should start looking for an open port starting from DDDDD and up.
:param verbose: If True, then connection info will be printed to the stdout.
:returns: a new H2OLocalServer instance
"""
assert jar_path is None or is_str(
jar_path), "`jar_path` should be string, got %s" % type(jar_path)
assert jar_path is None or jar_path.endswith("h2o.jar"), \
"`jar_path` should be a path to an h2o.jar executable, got %s" % jar_path
assert is_int(
nthreads), "`nthreads` should be integer, got %s" % type(nthreads)
assert nthreads == -1 or 1 <= nthreads <= 4096, "`nthreads` is out of bounds: %d" % nthreads
assert isinstance(enable_assertions, bool), \
"`enable_assertions` should be bool, got %s" % type(enable_assertions)
assert max_mem_size is None or is_int(max_mem_size), \
"`max_mem_size` should be integer, got %s" % type(max_mem_size)
assert max_mem_size is None or max_mem_size >= 1 << 25, "`max_mem_size` too small: %d" % max_mem_size
assert min_mem_size is None or is_int(min_mem_size), \
"`min_mem_size` should be integer, got %s" % type(min_mem_size)
assert min_mem_size is None or max_mem_size is None or min_mem_size <= max_mem_size, \
"`min_mem_size`=%d is larger than the `max_mem_size`=%d" % (min_mem_size, max_mem_size)
if ice_root:
assert is_str(
ice_root
), "`ice_root` should be string, got %r" % type(ice_root)
assert os.path.isdir(
ice_root), "`ice_root` is not a valid directory: %s" % ice_root
if port is None: port = "54321+"
baseport = None
if is_str(port):
if port.isdigit():
port = int(port)
else:
assert port[-1] == "+" and port[:-1].isdigit(), \
"`port` should be of the form 'DDDD+', where D is a digit. Got: %s" % port
baseport = int(port[:-1])
port = 0
assert is_int(
port), "`port` should be integer (or string). Got: %s" % type(port)
hs = H2OLocalServer()
hs._verbose = bool(verbose)
hs._jar_path = hs._find_jar(jar_path)
hs._ice_root = ice_root
if not ice_root:
hs._ice_root = tempfile.mkdtemp()
hs._tempdir = hs._ice_root
if verbose: print("Attempting to start a local H2O server...")
hs._launch_server(port=port,
baseport=baseport,
nthreads=int(nthreads),
ea=enable_assertions,
mmax=max_mem_size,
mmin=min_mem_size)
if verbose:
print(" Server is running at %s://%s:%d" %
(hs.scheme, hs.ip, hs.port))
atexit.register(lambda: hs.shutdown())
return hs