def interaction_check():
# Connect to a pre-existing cluster
iris = h2o.import_file(path=pyunit_utils.locate("smalldata/iris/iris.csv"))
# add a couple of factor columns to iris
iris = iris.cbind(iris[4] == "Iris-setosa")
iris[5] = iris[5].asfactor()
iris.set_name(5, "C6")
iris = iris.cbind(iris[4] == "Iris-virginica")
iris[6] = iris[6].asfactor()
iris.set_name(6, name="C7")
# create a frame of the two-way interactions
two_way_interactions = h2o.interaction(iris,
factors=[4, 5, 6],
pairwise=True,
max_factors=10000,
min_occurrence=1)
assert two_way_interactions.nrow == 150 and two_way_interactions.ncol == 3, \
"Expected 150 rows and 3 columns, but got {0} rows and {1} " \
"columns".format(two_way_interactions.nrow, two_way_interactions.ncol)
levels1 = two_way_interactions[0].levels()
levels2 = two_way_interactions[1].levels()
levels3 = two_way_interactions[2].levels()
assert levels1 == ["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"],
levels1)
assert levels2 == ["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"],
levels2)
assert levels3 == [
"0_0", "1_0", "0_1"
], "Expected the following levels {0}, but got {1}".format(
["0_0", "1_0", "0_1"], levels3)
# do the same thing, but set 'factors' arg to list of column names
two_way_interactions = h2o.interaction(iris,
factors=["C5", "C6", "C7"],
pairwise=True,
max_factors=10000,
min_occurrence=1)
assert two_way_interactions.nrow == 150 and two_way_interactions.ncol == 3, \
"Expected 150 rows and 3 columns, but got {0} rows and {1} " \
"columns".format(two_way_interactions.nrow, two_way_interactions.ncol)
levels1 = two_way_interactions[0].levels()
levels2 = two_way_interactions[1].levels()
levels3 = two_way_interactions[2].levels()
assert levels1 == ["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"],
levels1)
assert levels2 == ["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"],
levels2)
assert levels3 == [
"0_0", "1_0", "0_1"
], "Expected the following levels {0}, but got {1}".format(
["0_0", "1_0", "0_1"], levels3)
def interaction_check():
# Connect to a pre-existing cluster
iris = h2o.import_file(path=h2o.locate("smalldata/iris/iris.csv"))
# add a couple of factor columns to iris
iris = iris.cbind(iris[4] == "Iris-setosa")
iris[5] = iris[5].asfactor()
iris.setName(5,"C6")
iris = iris.cbind(iris[4] == "Iris-virginica")
iris[6] = iris[6].asfactor()
iris.setName(6, name="C7")
# create a frame of the two-way interactions
two_way_interactions = h2o.interaction(iris, factors=[4,5,6], pairwise=True, max_factors=10000, min_occurrence=1)
assert two_way_interactions.nrow == 150 and two_way_interactions.ncol == 3, \
"Expected 150 rows and 3 columns, but got {0} rows and {1} " \
"columns".format(two_way_interactions.nrow, two_way_interactions.ncol)
levels1 = two_way_interactions[0].levels()
levels2 = two_way_interactions[1].levels()
levels3 = two_way_interactions[2].levels()
assert levels1 == ["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"],
levels1)
assert levels2 == ["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"],
levels2)
assert levels3 == ["0_0", "1_0", "0_1"], "Expected the following levels {0}, but got {1}".format(["0_0", "1_0", "0_1"],
levels3)
# do the same thing, but set 'factors' arg to list of column names
two_way_interactions = h2o.interaction(iris, factors=["C5","C6","C7"], pairwise=True, max_factors=10000, min_occurrence=1)
assert two_way_interactions.nrow == 150 and two_way_interactions.ncol == 3, \
"Expected 150 rows and 3 columns, but got {0} rows and {1} " \
"columns".format(two_way_interactions.nrow, two_way_interactions.ncol)
levels1 = two_way_interactions[0].levels()
levels2 = two_way_interactions[1].levels()
levels3 = two_way_interactions[2].levels()
assert levels1 == ["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"],
levels1)
assert levels2 == ["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"],
levels2)
assert levels3 == ["0_0", "1_0", "0_1"], "Expected the following levels {0}, but got {1}".format(["0_0", "1_0", "0_1"],
levels3)
def interaction(self, 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.
:param factors: factors Factor columns (either indices or column names).
:param pairwise: Whether to create pairwise interactions between factors (otherwise create one higher-order interaction). Only applicable if there are 3 or more factors.
:param max_factors: Max. number of factor levels in pair-wise interaction terms (if enforced, one extra catch-all factor will be made)
:param min_occurrence: Min. occurrence threshold for factor levels in pair-wise interaction terms
:param destination_frame: A string indicating the destination key. If empty, this will be auto-generated by H2O.
:return: H2OFrame
"""
return h2o.interaction(data=self, factors=factors, pairwise=pairwise, max_factors=max_factors,
min_occurrence=min_occurrence, destination_frame=destination_frame)
def h2ointeraction():
"""
Python API test: h2o.interaction(data, factors, pairwise, max_factors, min_occurrence, destination_frame=None)
Copied from pyunit_interaction.py
"""
try:
iris = h2o.import_file(
path=pyunit_utils.locate("smalldata/iris/iris.csv"))
# add a couple of factor columns to iris
iris = iris.cbind(iris[4] == "Iris-setosa")
iris[5] = iris[5].asfactor()
iris.set_name(5, "C6")
iris = iris.cbind(iris[4] == "Iris-virginica")
iris[6] = iris[6].asfactor()
iris.set_name(6, name="C7")
# create a frame of the two-way interactions
two_way_interactions = h2o.interaction(iris,
factors=[4, 5, 6],
pairwise=True,
max_factors=10000,
min_occurrence=1)
assert_is_type(two_way_interactions, H2OFrame)
assert two_way_interactions.nrow == 150 and two_way_interactions.ncol == 3, \
"Expected 150 rows and 3 columns, but got {0} rows and {1} " \
"columns".format(two_way_interactions.nrow, two_way_interactions.ncol)
levels1 = two_way_interactions.levels()[0]
levels2 = two_way_interactions.levels()[1]
levels3 = two_way_interactions.levels()[2]
assert levels1 == ["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"],
levels1)
assert levels2 == ["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"],
levels2)
assert levels3 == [
"0_0", "1_0", "0_1"
], "Expected the following levels {0}, but got {1}".format(
["0_0", "1_0", "0_1"], levels3)
except:
assert False, "h2o.interaction() command not is working."
def h2ointeraction():
"""
Python API test: h2o.interaction(data, factors, pairwise, max_factors, min_occurrence, destination_frame=None)
Copied from pyunit_interaction.py
"""
iris = h2o.import_file(path=pyunit_utils.locate("smalldata/iris/iris.csv"))
# add a couple of factor columns to iris
iris = iris.cbind(iris[4] == "Iris-setosa")
iris[5] = iris[5].asfactor()
iris.set_name(5,"C6")
iris = iris.cbind(iris[4] == "Iris-virginica")
iris[6] = iris[6].asfactor()
iris.set_name(6, name="C7")
# create a frame of the two-way interactions
two_way_interactions = h2o.interaction(iris, factors=[4,5,6], pairwise=True, max_factors=10000,
min_occurrence=1)
assert_is_type(two_way_interactions, H2OFrame)
assert two_way_interactions.nrow == 150 and two_way_interactions.ncol == 3, \
"Expected 150 rows and 3 columns, but got {0} rows and {1} " \
"columns".format(two_way_interactions.nrow, two_way_interactions.ncol)
levels1 = two_way_interactions.levels()[0]
levels2 = two_way_interactions.levels()[1]
levels3 = two_way_interactions.levels()[2]
assert levels1 == ["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_1", "Iris-versicolor_0", "Iris-virginica_0"],
levels1)
assert levels2 == ["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"], \
"Expected the following levels {0}, but got {1}".format(["Iris-setosa_0", "Iris-versicolor_0", "Iris-virginica_1"],
levels2)
assert levels3 == ["0_0", "1_0", "0_1"], "Expected the following levels {0}, but got {1}".format(["0_0", "1_0", "0_1"],
levels3)