def scale_svd_rf_pipe_new_import():
from h2o.estimators.svd import H2OSingularValueDecompositionEstimator
print("Importing USArrests.csv data...")
arrests = h2o.upload_file(pyunit_utils.locate("smalldata/pca_test/USArrests.csv"))
print("Compare with SVD")
# build transformation pipeline using sklearn's Pipeline and H2O estimators without H2OSingularValueDecompositionEstimator.init_for_pipeline()
# it should fail
# Note: if you use SVD algo in a different combination of pipeline tasks, it could not fail, for example
# if you comment line with H2ORandomForestEstimator task, the fit method doesn't fail because the pipeline doesn't
# use _fit_transform_one method thus does not use HH2OSingularValueDecompositionEstimator.transform method
try:
pipe = Pipeline([
("standardize", H2OScaler()),
("svd", H2OSingularValueDecompositionEstimator(nv=3)),
("rf", H2ORandomForestEstimator(seed=42,ntrees=50))
])
pipe.fit(arrests[1:], arrests[0])
assert False, "Pipeline should fail without using H2OSingularValueDecompositionEstimator.init_for_pipeline()"
except TypeError:
pass
# build transformation pipeline using sklearn's Pipeline and H2O estimators with H2OSingularValueDecompositionEstimator.init_for_pipeline()
pipe = Pipeline([
("standardize", H2OScaler()),
("svd", H2OSingularValueDecompositionEstimator(nv=3).init_for_pipeline()),
("rf", H2ORandomForestEstimator(seed=42,ntrees=50))
])
pipe.fit(arrests[1:], arrests[0])
print(pipe)
def scale_svd_rf_pipe():
from h2o.transforms.decomposition import H2OSVD
print("Importing USArrests.csv data...")
arrests = h2o.upload_file(
pyunit_utils.locate("smalldata/pca_test/USArrests.csv"))
# build transformation pipeline using sklearn's Pipeline and H2OSVD
pipe = Pipeline([("standardize", H2OScaler()), ("svd", H2OSVD()),
("rf", H2ORandomForestEstimator())])
params = {
"standardize__center": [True, False],
"standardize__scale": [True, False],
"svd__nv": [2, 3],
"rf__ntrees": randint(50, 60),
"rf__max_depth": randint(4, 8),
"rf__min_rows": randint(5, 10),
"svd__transform": ["none", "standardize"],
}
custom_cv = H2OKFold(arrests, n_folds=5, seed=42)
random_search = RandomizedSearchCV(pipe,
params,
n_iter=5,
scoring=make_scorer(h2o_r2_score),
cv=custom_cv,
random_state=42,
n_jobs=1)
random_search.fit(arrests[1:], arrests[0])
print(random_search.best_estimator_)
def scale_pca_rf_pipe_new_import():
from h2o.estimators.pca import H2OPrincipalComponentAnalysisEstimator
iris = h2o.import_file(path=pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
# build transformation pipeline using sklearn's Pipeline and H2O transforms
pipe = Pipeline([
("standardize", H2OScaler()),
("pca", H2OPrincipalComponentAnalysisEstimator().init_for_pipeline()),
("rf", H2ORandomForestEstimator())
])
params = {"standardize__center": [True, False], # Parameters to test
"standardize__scale": [True, False],
"pca__k": randint(2, iris[1:].shape[1]),
"rf__ntrees": randint(50,60),
"rf__max_depth": randint(4,8),
"rf__min_rows": randint(5,10),
"pca__transform": ["none", "standardize"],
}
custom_cv = H2OKFold(iris, n_folds=5, seed=42)
random_search = RandomizedSearchCV(pipe,
params,
n_iter=5,
scoring=make_scorer(h2o_r2_score),
cv=custom_cv,
random_state=42,
n_jobs=1)
random_search.fit(iris[1:],iris[0])
print(random_search.best_estimator_)
def scale_pca_rf_pipe_new_import():
from h2o.transforms.preprocessing import H2OScaler
from h2o.estimators.pca import H2OPrincipalComponentAnalysisEstimator
from h2o.estimators.random_forest import H2ORandomForestEstimator
from sklearn.pipeline import Pipeline
iris = h2o.import_file(
path=pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
# build transformation pipeline using sklearn's Pipeline and H2O estimators without H2OPrincipalComponentAnalysisEstimator.init_for_pipeline()
# it should fail
# Note: if you use PCA algo in a different combination of pipeline tasks, it could not fail, for example
# if you comment line with H2ORandomForestEstimator task, the fit method doesn't fail because the pipeline doesn't
# use _fit_transform_one method thus does not use H2OPrincipalComponentAnalysisEstimator.transform method
try:
pipe = Pipeline([("standardize", H2OScaler()),
("pca", H2OPrincipalComponentAnalysisEstimator(k=2)),
("rf", H2ORandomForestEstimator(seed=42, ntrees=5))])
pipe.fit(iris[:4], iris[4])
assert False, "Pipeline should fail without using H2OPrincipalComponentAnalysisEstimator.init_for_pipeline()"
except TypeError:
pass
# build transformation pipeline using sklearn's Pipeline and H2O estimators with H2OPrincipalComponentAnalysisEstimator.init_for_pipeline()
pipe = Pipeline([
("standardize", H2OScaler()),
("pca",
H2OPrincipalComponentAnalysisEstimator(k=2).init_for_pipeline()),
("rf", H2ORandomForestEstimator(seed=42, ntrees=5))
])
pipe.fit(iris[:4], iris[4])
print(pipe)
# set H2OPCA transform property
pca = H2OPrincipalComponentAnalysisEstimator(k=2)
pca.transform = "standardize"
pipe = Pipeline([("standardize", H2OScaler()),
("pca", pca.init_for_pipeline()),
("rf", H2ORandomForestEstimator(seed=42, ntrees=5))])
pipe.fit(iris[:4], iris[4])
print(pipe)
def test_scaler():
iris = h2o.import_file(pyunit_utils.locate("smalldata/iris/iris.csv"))
scaler = H2OScaler()
scaler.fit(iris)
iris_transformed = scaler.transform(iris)
assert [[u'Iris-setosa', u'Iris-versicolor',
u'Iris-virginica']] == iris_transformed["C5"].levels()
assert max(iris_transformed[[
"C1", "C2", "C3", "C4"
]].mean().as_data_frame().transpose()[0].tolist()) < 1e-10
def scale_svd_rf_pipe():
from h2o.transforms.decomposition import H2OSVD
print("Importing USArrests.csv data...")
arrests = h2o.upload_file(pyunit_utils.locate("smalldata/pca_test/USArrests.csv"))
# build transformation pipeline using sklearn's Pipeline and H2O transforms
pipe = Pipeline([
("standardize", H2OScaler()),
("svd", H2OSVD(nv=3)),
("rf", H2ORandomForestEstimator(seed=42,ntrees=50))
])
pipe.fit(arrests[1:], arrests[0])
print(pipe)
def scale_pca_rf_pipe():
from h2o.transforms.preprocessing import H2OScaler
from h2o.transforms.decomposition import H2OPCA
from h2o.estimators.random_forest import H2ORandomForestEstimator
from sklearn.pipeline import Pipeline
iris = h2o.import_file(
path=pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
# build transformation pipeline using sklearn's Pipeline and H2O transforms
pipe = Pipeline([("standardize", H2OScaler()), ("pca", H2OPCA(k=2)),
("rf", H2ORandomForestEstimator(seed=42, ntrees=50))])
pipe.fit(iris[:4], iris[4])
def scale_pca_rf_pipe():
from h2o.transforms.preprocessing import H2OScaler
from h2o.transforms.decomposition import H2OPCA
# this should work below, but it's not yet: https://0xdata.atlassian.net/browse/PUBDEV-5236
#from h2o.estimators.pca import H2OPrincipalComponentAnalysisEstimator as H2OPCA
from h2o.estimators.random_forest import H2ORandomForestEstimator
from sklearn.pipeline import Pipeline
iris = h2o.import_file(
path=pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
# build transformation pipeline using sklearn's Pipeline and H2O transforms
pipe = Pipeline([("standardize", H2OScaler()), ("pca", H2OPCA(k=2)),
("rf", H2ORandomForestEstimator(seed=42, ntrees=50))])
pipe.fit(iris[:4], iris[4])
def scale_pca_rf_pipe():
from h2o.transforms.preprocessing import H2OScaler
from h2o.estimators.pca import H2OPrincipalComponentAnalysisEstimator
from h2o.estimators.random_forest import H2ORandomForestEstimator
from sklearn.pipeline import Pipeline
from sklearn.grid_search import RandomizedSearchCV
from h2o.cross_validation import H2OKFold
from h2o.model.regression import h2o_r2_score
from sklearn.metrics.scorer import make_scorer
from scipy.stats import randint
iris = h2o.import_file(
path=pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
# build transformation pipeline using sklearn's Pipeline and H2O transforms
pipe = Pipeline([("standardize", H2OScaler()),
("pca", H2OPrincipalComponentAnalysisEstimator()),
("rf", H2ORandomForestEstimator())])
params = {
"standardize__center": [True, False], # Parameters to test
"standardize__scale": [True, False],
"pca__k": randint(2, iris[1:].shape[1]),
"rf__ntrees": randint(50, 60),
"rf__max_depth": randint(4, 8),
"rf__min_rows": randint(5, 10),
}
custom_cv = H2OKFold(iris, n_folds=5, seed=42)
random_search = RandomizedSearchCV(pipe,
params,
n_iter=5,
scoring=make_scorer(h2o_r2_score),
cv=custom_cv,
random_state=42,
n_jobs=1)
random_search.fit(iris[1:], iris[0])
print(random_search.best_estimator_)
hyper_parameters = {"ntrees": ntrees_opt, "max_depth":max_depth_opt, "learn_rate":learn_rate_opt}
from h2o.grid.grid_search import H2OGridSearch
gs = H2OGridSearch(H2OGradientBoostingEstimator(distribution="multinomial"), hyper_params=hyper_parameters)
gs.train(x=range(0,iris_df.ncol-1), y=iris_df.ncol-1, training_frame=iris_df, nfold=10)
print gs.sort_by('logloss', increasing=True)
# Pipeline
from h2o.transforms.preprocessing import H2OScaler
from sklearn.pipeline import Pipeline
# Turn off h2o progress bars
h2o.__PROGRESS_BAR__=False
h2o.no_progress()
# build transformation pipeline using sklearn's Pipeline and H2O transforms
pipeline = Pipeline([("standardize", H2OScaler()),
("pca", H2OPCA(k=2)),
("gbm", H2OGradientBoostingEstimator(distribution="multinomial"))])
pipeline.fit(iris_df[:4],iris_df[4])
# Random CV using H2O and Scikit-learn
from sklearn.grid_search import RandomizedSearchCV
from h2o.cross_validation import H2OKFold
from h2o.model.regression import h2o_r2_score
from sklearn.metrics.scorer import make_scorer
params = {"standardize__center": [True, False], # Parameters to test
"standardize__scale": [True, False],
"pca__k": [2,3],
"gbm__ntrees": [10,20],
"gbm__max_depth": [1,2,3],
"gbm__learn_rate": [0.1,0.2]}
#gs = H2OGridSearch(H2OGradientBoostingEstimator(distribution="multinomial"), hyper_params=hyper_parameters)
#gs.train(x=range(0, iris_df.ncol-1), y=iris_df.ncol-1, training_frame=iris_df, nfold=10)
##
## Pipeline
##
from h2o.transforms.preprocessing import H2OScaler
from h2o.transforms.decomposition import H2OPCA
from sklearn.pipeline import Pipeline
h2o.no_progress()
pipeline = Pipeline([
("standardize", H2OScaler()), ("pca", H2OPCA(k=2)),
("gbm", H2OGradientBoostingEstimator(distribution="multinomial"))
])
print pipeline.fit(iris_df[:4], iris_df[4])
##
## Randomized Gird Search
##
from sklearn.grid_search import RandomizedSearchCV
from h2o.cross_validation import H2OKFold
from h2o.model.regression import h2o_r2_score
from sklearn.metrics.scorer import make_scorer
params = {
"standardize__center": [True, False],
