Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

GH-15915: Craft MS Examples #16001

Merged
merged 6 commits into from
Feb 1, 2024
Merged

GH-15915: Craft MS Examples #16001

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
63024e7
ms-examples-docs
shaunyogeshwaran Jan 3, 2024
9f1e7f5
ht/built gradle, trimmed examples, added coef/coef_norm/mode
hannah-tillman Jan 12, 2024
195bc71
ht/spacing update
hannah-tillman Jan 18, 2024
353f1c3
ht/requested updates
hannah-tillman Jan 22, 2024
df77e31
ht/removed nparallelism & mpn update
hannah-tillman Jan 25, 2024
6a76d36
ht/fix
hannah-tillman Jan 31, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
173 changes: 173 additions & 0 deletions h2o-bindings/bin/custom/python/gen_modelselection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,23 @@ def coef_norm(self, predictor_size=None):

:param predictor_size: predictor subset size, will only return model coefficients of that subset size.
:return: list of Python Dicts of coefficients for all models built with different predictor numbers

:examples:

>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr")
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff_norm = maxrModel.coef_norm()
>>> print(coeff_norm)
"""
model_ids = self._model_json["output"]["best_model_ids"]
if not(self.actual_params["build_glm_model"]) and self.actual_params["mode"]=="maxrsweep":
Expand Down Expand Up @@ -95,6 +112,23 @@ def coef(self, predictor_size=None):

:param predictor_size: predictor subset size, will only return model coefficients of that subset size.
:return: list of Python Dicts of coefficients for all models built with different predictor numbers

:examples:

>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr")
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff = maxrModel.coef()
>>> print(coeff)
"""
if not self.actual_params["build_glm_model"] and self.actual_params["mode"]=="maxrsweep":
coef_names = self._model_json["output"]["coefficient_names"]
Expand Down Expand Up @@ -148,6 +182,7 @@ def coef(self, predictor_size=None):
def result(self):
"""
Get result frame that contains information about the model building process like for modelselection and anovaglm.

:return: the H2OFrame that contains information about the model building process like for modelselection and anovaglm.
"""
return H2OFrame._expr(expr=ExprNode("result", ASTId(self.key)))._frame(fill_cache=True)
Expand Down Expand Up @@ -225,3 +260,141 @@ def get_best_model_predictors(self):
mode=maxr, the model returned is no longer guaranteed to have the best R2 value.
"""
)

examples = dict(
build_glm_model="""
>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr",
... build_glm_model=False)
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff = maxrModel.coef()
>>> print(coeff)
""",
influence="""
>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr",
... influence="dfbetas")
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff = maxrModel.coef()
>>> print(coeff)
""",
multinode_mode="""
>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr",
... multinode_mode=False)
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff = maxrModel.coef()
>>> print(coeff)
""",
nparallelism="""
>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr",
... nparallelism=0)
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff = maxrModel.coef()
>>> print(coeff)
""",
p_values_threshold="""
>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr",
... p_values_threshold=0.0)
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff = maxrModel.coef()
>>> print(coeff)
""",
custom_metric_func="""
>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr",
... early_stopping=False)
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff = maxrModel.coef()
>>> print(coeff)
""",
obj_reg="""
>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr",
... obj_reg=-1.0)
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff = maxrModel.coef()
>>> print(coeff)
""",
mode="""
>>> import h2o
>>> from h2o.estimators import H2OModelSelectionEstimator
>>> h2o.init()
>>> prostate = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv")
>>> predictors = ["AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
>>> response = "GLEASON"
>>> maxrModel = H2OModelSelectionEstimator(max_predictor_number=7,
... seed=12345,
... mode="maxr")
>>> maxrModel.train(x=predictors, y=response, training_frame=prostate)
>>> results = maxrModel.result()
>>> print(results)
>>> coeff = maxrModel.coef()
>>> print(coeff)
"""
)
Loading