def _model_build(self, x, y, tframe, vframe, kwargs):
kwargs['training_frame'] = tframe
if vframe is not None: kwargs["validation_frame"] = vframe
if isinstance(y, int): y = tframe.names[y]
if y is not None: kwargs['response_column'] = y
if not isinstance(x, (list,tuple)): x=[x]
if isinstance(x[0], int):
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 [h2o.h2o._quoted(col) for col in ignored_columns]
kwargs["interactions"] = None if ("interactions" not in kwargs or kwargs["interactions"] is None) else [h2o.h2o._quoted(col) for col in kwargs["interactions"]]
kwargs = dict([(k, H2OEstimator._keyify_if_H2OFrame(kwargs[k])) for k in kwargs]) # gruesome one-liner
algo = self._compute_algo()
model = H2OJob(H2OConnection.post_json("ModelBuilders/"+algo, **kwargs), job_type=(algo+" Model Build"))
if self._future:
self._job = model
return
model.poll()
if '_rest_version' in list(kwargs.keys()): model_json = H2OConnection.get_json("Models/"+model.dest_key, _rest_version=kwargs['_rest_version'])["models"][0]
else: model_json = H2OConnection.get_json("Models/"+model.dest_key)["models"][0]
self._resolve_model(model.dest_key,model_json)
def _model_build(self, x, y, tframe, vframe, kwargs):
kwargs['training_frame'] = tframe
if vframe is not None: kwargs["validation_frame"] = vframe
if isinstance(y, int): y = tframe.names[y]
if y is not None: kwargs['response_column'] = y
if not isinstance(x, (list,tuple)): x=[x]
if isinstance(x[0], int):
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 [h2o.h2o._quoted(col) for col in ignored_columns]
kwargs = dict([(k, H2OEstimator._keyify_if_H2OFrame(kwargs[k])) for k in kwargs])
algo = self._compute_algo()
model = H2OJob(H2OConnection.post_json("ModelBuilders/"+algo, **kwargs), job_type=(algo+" Model Build"))
if self._future:
self._job = model
return
model.poll()
if '_rest_version' in list(kwargs.keys()): model_json = H2OConnection.get_json("Models/"+model.dest_key, _rest_version=kwargs['_rest_version'])["models"][0]
else: model_json = H2OConnection.get_json("Models/"+model.dest_key)["models"][0]
self._resolve_model(model.dest_key,model_json)
def makeGLMModel(model, coefs, threshold=.5):
model_json = H2OConnection.post_json(
"MakeGLMModel",
model=model._model_json['model_id']['name'],
names=list(coefs.keys()),
beta=list(coefs.values()),
threshold=threshold)
m = H2OGeneralizedLinearEstimator()
m._resolve_model(model_json['model_id']['name'], model_json)
return m
def _model_build(self, x, y, tframe, vframe, kwargs):
kwargs['training_frame'] = tframe
if vframe is not None: kwargs["validation_frame"] = vframe
if isinstance(y, int): y = tframe.names[y]
if y is not None: kwargs['response_column'] = y
if not isinstance(x, (list,tuple)): x=[x]
if isinstance(x[0], int):
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 [h2o.h2o._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
kwargs["_rest_version"] = 99 #unique to grid search
if self.grid_id is not None: kwargs["grid_id"] = self.grid_id
grid = H2OJob(H2OConnection.post_json("Grid/"+algo, **kwargs), job_type=(algo+" Grid Build"))
if self._future:
self._job = grid
return
grid.poll()
if '_rest_version' in list(kwargs.keys()):
grid_json = H2OConnection.get_json("Grids/"+grid.dest_key, _rest_version=kwargs['_rest_version'])
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 = H2OConnection.get_json("Grids/"+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 = H2OConnection.get_json("Models/"+grid_json['model_ids'][0]['name'],
_rest_version=kwargs['_rest_version'])['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 makeGLMModel(model, coefs, threshold=.5):
"""
Create a custom GLM model using the given coefficients.
Needs to be passed source model trained on the dataset to extract the dataset information from.
@param model - source model, used for extracting dataset information
@param coefs - dictionary containing model coefficients
@param threshold - (optional, only for binomial) decision threshold used for classification
"""
model_json = H2OConnection.post_json("MakeGLMModel", model=model._model_json["model_id"]["name"],
names=list(coefs.keys()), beta=list(coefs.values()), threshold=threshold)
m = H2OGeneralizedLinearEstimator()
m._resolve_model(model_json["model_id"]["name"], model_json)
return m
def _model_build(self, x, y, tframe, vframe, kwargs):
kwargs['training_frame'] = tframe
if vframe is not None: kwargs["validation_frame"] = vframe
if isinstance(y, int): y = tframe.names[y]
if y is not None: kwargs['response_column'] = y
if not isinstance(x, (list, tuple)): x = [x]
if isinstance(x[0], int):
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 [
h2o.h2o._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
kwargs["_rest_version"] = 99 #unique to grid search
if self.grid_id is not None: kwargs["grid_id"] = self.grid_id
grid = H2OJob(H2OConnection.post_json("Grid/" + algo, **kwargs),
job_type=(algo + " Grid Build"))
if self._future:
self._job = grid
return
grid.poll()
if '_rest_version' in list(kwargs.keys()):
grid_json = H2OConnection.get_json(
"Grids/" + grid.dest_key,
_rest_version=kwargs['_rest_version'])
for error_message in grid_json["failure_details"]:
print(error_message)
else:
grid_json = H2OConnection.get_json("Grids/" + 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)
first_model_json = H2OConnection.get_json(
"Models/" + grid_json['model_ids'][0]['name'],
_rest_version=kwargs['_rest_version'])['models'][0]
self._resolve_grid(grid.dest_key, grid_json, first_model_json)
def makeGLMModel(model, coefs, threshold=.5):
"""
Create a custom GLM model using the given coefficients.
Needs to be passed source model trained on the dataset to extract the dataset information from.
@param model - source model, used for extracting dataset information
@param coefs - dictionary containing model coefficients
@param threshold - (optional, only for binomial) decision threshold used for classification
"""
model_json = H2OConnection.post_json(
"MakeGLMModel",
model=model._model_json["model_id"]["name"],
names=list(coefs.keys()),
beta=list(coefs.values()),
threshold=threshold)
m = H2OGeneralizedLinearEstimator()
m._resolve_model(model_json["model_id"]["name"], model_json)
return m
def _model_build(self, x, y, tframe, vframe, kwargs):
kwargs['training_frame'] = tframe
if vframe is not None: kwargs["validation_frame"] = vframe
if isinstance(y, int): y = tframe.names[y]
if y is not None: kwargs['response_column'] = y
if not isinstance(x, (list,tuple)): x=[x]
if isinstance(x[0], int):
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 [h2o.h2o._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
kwargs["_rest_version"] = 99 #unique to grid search
if self.grid_id is not None: kwargs["grid_id"] = self.grid_id
grid = H2OJob(H2OConnection.post_json("Grid/"+algo, **kwargs), job_type=(algo+" Grid Build"))
if self._future:
self._job = grid
return
grid.poll()
if '_rest_version' in list(kwargs.keys()):
grid_json = H2OConnection.get_json("Grids/"+grid.dest_key, _rest_version=kwargs['_rest_version'])
for error_message in grid_json["failure_details"]:
print(error_message)
else: grid_json = H2OConnection.get_json("Grids/"+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)
first_model_json = H2OConnection.get_json("Models/"+grid_json['model_ids'][0]['name'], _rest_version=kwargs['_rest_version'])['models'][0]
self._resolve_grid(grid.dest_key, grid_json, first_model_json)
def _model_build(self, x, y, tframe, vframe, kwargs):
kwargs['training_frame'] = tframe
if vframe is not None: kwargs["validation_frame"] = vframe
if isinstance(y, int): y = tframe.names[y]
if y is not None: kwargs['response_column'] = y
if not isinstance(x, (list, tuple)): x = [x]
if isinstance(x[0], int):
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 [
h2o.h2o._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
kwargs["_rest_version"] = 99 #unique to grid search
if self.grid_id is not None: kwargs["grid_id"] = self.grid_id
grid = H2OJob(H2OConnection.post_json("Grid/" + algo, **kwargs),
job_type=(algo + " Grid Build"))
if self._future:
self._job = grid
return
grid.poll()
if '_rest_version' in list(kwargs.keys()):
grid_json = H2OConnection.get_json(
"Grids/" + grid.dest_key,
_rest_version=kwargs['_rest_version'])
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]))
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 = H2OConnection.get_json("Grids/" + 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 = H2OConnection.get_json(
"Models/" + grid_json['model_ids'][0]['name'],
_rest_version=kwargs['_rest_version'])['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 makeGLMModel(model, coefs, threshold=.5):
model_json = H2OConnection.post_json("MakeGLMModel",model=model._model_json['model_id']['name'], names=list(coefs.keys()), beta = list(coefs.values()), threshold = threshold)
m = H2OGeneralizedLinearEstimator()
m._resolve_model(model_json['model_id']['name'], model_json)
return m