def main():
bi.init("Python", "../../../h2o-py/h2o/estimators", clear_dir=False)
modules = [("deeplearning", "H2OAutoEncoderEstimator", "Unsupervised"),
("estimator_base", "H2OEstimator", "Miscellaneous"),
("grid_search", "H2OGridSearch", "Miscellaneous"),
("automl", "H2OAutoML", "Miscellaneous")]
builders = filter(
lambda b: b[0] != 'coxph',
bi.model_builders().items()) # CoxPH is not supported in Python yet
for name, mb in builders:
module = name
if name == "drf": module = "random_forest"
if name == "naivebayes": module = "naive_bayes"
bi.vprint("Generating model: " + name)
bi.write_to_file("%s.py" % module, gen_module(mb, name))
category = "Supervised" if mb["supervised"] else "Unsupervised"
if name in {"svd", "word2vec"}:
category = "Miscellaneous"
modules.append((module, algo_to_classname(name), category))
bi.write_to_file("__init__.py", gen_init(modules))
bi.write_to_file("../../docs/modeling.rst", gen_models_docs(modules))
type_adapter1.vprint_translation_map()
def main():
bi.init("Python", "../../../h2o-py/h2o/estimators", clear_dir=False)
modules = [("h2o.estimators.deeplearning", "deeplearning",
"H2OAutoEncoderEstimator", "Unsupervised"),
("h2o.estimators.estimator_base", "estimator_base",
"H2OEstimator", "Miscellaneous"),
("h2o.grid", "grid", "H2OGridSearch", "Miscellaneous"),
("h2o.automl", "automl", "H2OAutoML", "Miscellaneous")]
builders = bi.model_builders().items()
algo_to_module = dict(drf="random_forest",
naivebayes="naive_bayes",
isolationforest="isolation_forest",
extendedisolationforest="extended_isolation_forest")
algo_to_category = dict(svd="Miscellaneous", word2vec="Miscellaneous")
for name, mb in builders:
module = name
if name in algo_to_module:
module = algo_to_module[name]
bi.vprint("Generating model: " + name)
bi.write_to_file("%s.py" % module, gen_module(mb, name))
category = algo_to_category[name] if name in algo_to_category \
else "Supervised" if mb["supervised"] \
else "Unsupervised"
full_module = '.'.join(["h2o.estimators", module])
modules.append(
(full_module, module, algo_to_classname(name), category))
bi.write_to_file("__init__.py", gen_init(modules))
bi.write_to_file("../../docs/modeling.rst", gen_models_docs(modules))
type_adapter1.vprint_translation_map()
def main():
bi.init("R", "../../../h2o-r/h2o-package/R", clear_dir=False)
for name, mb in bi.model_builders().items():
module = name
if name == "drf": module = "random_forest"
if name == "naivebayes": module = "naive_bayes"
bi.vprint("Generating model: " + name)
if name == "deepwater" or name == "deeplearning":
print("Generating model:" + module)
bi.write_to_file("%s.R" % module, gen_module(mb, name))
def main():
bi.init("Python", "python")
for name, mb in bi.model_builders().items():
module = name
if name == "drf": module = "random_forest"
if name == "naivebayes": module = "naive_bayes"
bi.vprint("Generating model: " + name)
bi.write_to_file("%s.py" % module, gen_module(mb, name))
type_adapter.vprint_translation_map()
def main():
bi.init("R", "../../../h2o-r/h2o-package/R", clear_dir=False)
for name, mb in bi.model_builders().items():
module = name
file_name = name
if name == "drf":
module = "randomForest"
file_name = "randomforest"
if name == "naivebayes": module = "naiveBayes"
if name == "stackedensemble": module = "stackedEnsemble"
if name == "pca": module = "prcomp"
bi.vprint("Generating model: " + name)
bi.write_to_file("%s.R" % file_name, gen_module(mb, name, module))
def main():
bi.init("Python", "../../../h2o-py/h2o/estimators", clear_dir=False)
modules = [("deeplearning", "H2OAutoEncoderEstimator")] # deeplearning module contains 2 classes in it...
for name, mb in bi.model_builders().items():
module = name
if name == "drf": module = "random_forest"
if name == "naivebayes": module = "naive_bayes"
bi.vprint("Generating model: " + name)
bi.write_to_file("%s.py" % module, gen_module(mb, name))
modules.append((module, algo_to_classname(name)))
bi.write_to_file("__init__.py", gen_init(modules))
type_adapter.vprint_translation_map()
def main():
bi.init("Python", "../../../h2o-py/h2o/estimators", clear_dir=False)
modules = [("deeplearning", "H2OAutoEncoderEstimator")] # deeplearning module contains 2 classes in it...
for name, mb in bi.model_builders().items():
module = name
if name == "drf": module = "random_forest"
if name == "naivebayes": module = "naive_bayes"
bi.vprint("Generating model: " + name)
bi.write_to_file("%s.py" % module, gen_module(mb, name))
modules.append((module, algo_to_classname(name)))
bi.write_to_file("__init__.py", gen_init(modules))
type_adapter.vprint_translation_map()
def main():
bi.init("R", "../../../h2o-r/h2o-package/R", clear_dir=False)
for name, mb in bi.model_builders().items():
if name in ["aggregator"]:
continue
module = name
file_name = name
if name == "drf":
module = "randomForest"
file_name = "randomforest"
if name == "naivebayes": module = "naiveBayes"
if name == "stackedensemble": module = "stackedEnsemble"
if name == "pca": module = "prcomp"
bi.vprint("Generating model: " + name)
bi.write_to_file("%s.R" % file_name, gen_module(mb, name, module))
def main():
bi.init("Python", "../../../h2o-py/h2o/estimators", clear_dir=False)
modules = [("deeplearning", "H2OAutoEncoderEstimator", "Unsupervised"),
("estimator_base", "H2OEstimator", "Miscellaneous"),
("grid_search", "H2OGridSearch", "Miscellaneous"),
("automl", "H2OAutoML", "Miscellaneous")]
builders = filter(lambda b: b[0] != 'coxph', bi.model_builders().items()) # CoxPH is not supported in Python yet
for name, mb in builders:
module = name
if name == "drf": module = "random_forest"
if name == "naivebayes": module = "naive_bayes"
bi.vprint("Generating model: " + name)
bi.write_to_file("%s.py" % module, gen_module(mb, name))
category = "Supervised" if mb["supervised"] else "Unsupervised"
if name in {"svd", "word2vec"}:
category = "Miscellaneous"
modules.append((module, algo_to_classname(name), category))
bi.write_to_file("__init__.py", gen_init(modules))
bi.write_to_file("../../docs/modeling.rst", gen_models_docs(modules))
type_adapter1.vprint_translation_map()
