def col_names_check():
iris_wheader = h2o.import_file(pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
expected_names = ["sepal_len", "sepal_wid", "petal_len", "petal_wid", "class"]
assert iris_wheader.col_names == expected_names, \
"Expected {0} for column names but got {1}".format(expected_names, iris_wheader.col_names)
iris = h2o.import_file(pyunit_utils.locate("smalldata/iris/iris.csv"))
expected_names = ["C1", "C2", "C3", "C4", "C5"]
assert iris.col_names == expected_names, \
"Expected {0} for column names but got {1}".format(expected_names, iris.col_names)
df = H2OFrame.from_python(np.random.randn(100, 4).tolist(), column_names=list("ABCD"), column_types=["enum"] * 4)
df.head()
expected_names = list("ABCD")
assert df.col_names == expected_names, \
"Expected {} for column names but got {}".format(expected_names, df.col_names)
assert list(df.types.values()) == ["enum"] * 4, \
"Expected {} for column types but got {}".format(["enum"] * 4, df.types)
df = H2OFrame(np.random.randn(100, 4).tolist())
df.head()
expected_names = ["C1", "C2", "C3", "C4"]
assert df.col_names == expected_names, \
"Expected {} for column names but got {}".format(expected_names, df.col_names)
assert list(df.types.values()) == ["real"] * 4, \
"Expected {} for column types but got {}".format(["real"] * 4, df.types)
df = H2OFrame({'B': ['a', 'a', 'b', 'NA', 'NA']})
df.head()
assert df.col_names == ["B"], "Expected {} for column names but got {}".format(["B"], df.col_names)
df = H2OFrame.from_python({'B': ['a', 'a', 'b', 'NA', 'NA']}, column_names=["X"])
df.head()
assert df.col_names == ["X"], "Expected {} for column names but got {}".format(["X"], df.col_names)
def from_pandas(X):
"""A simple wrapper for H2OFrame.from_python. This takes
a pandas dataframe and returns an H2OFrame with all the
default args (generally enough) plus named columns.
Parameters
----------
X : pd.DataFrame
The dataframe to convert.
Returns
-------
H2OFrame
"""
pd, _ = validate_is_pd(X, None)
# older version of h2o are super funky with this
if parse_version(h2o.__version__) < parse_version('3.10.0.7'):
h = 1
else:
h = 0
# if h2o hasn't started, we'll let this fail through
return H2OFrame.from_python(X, header=h, column_names=X.columns.tolist())
def from_pandas(X):
"""A simple wrapper for H2OFrame.from_python. This takes
a pandas dataframe and returns an H2OFrame with all the
default args (generally enough) plus named columns.
Parameters
----------
X : pd.DataFrame
The dataframe to convert.
Returns
-------
H2OFrame
"""
pd, _ = validate_is_pd(X, None)
# older version of h2o are super funky with this
if parse_version(h2o.__version__) < parse_version('3.10.0.7'):
h = 1
else:
h = 0
# if h2o hasn't started, we'll let this fail through
return H2OFrame.from_python(X, header=h, column_names=X.columns.tolist())
def transform(self, column):
check_is_fitted(self, 'encoder_')
column = h2o_col_to_numpy(column)
# transform--
# I don't like that we have to re-upload... but we do... for now...
return H2OFrame.from_python(self.encoder_.transform(column).reshape(column.shape[0], 1))
def col_names_check():
iris_wheader = h2o.import_file(
pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
expected_names = [
"sepal_len", "sepal_wid", "petal_len", "petal_wid", "class"
]
assert iris_wheader.col_names == expected_names, \
"Expected {0} for column names but got {1}".format(expected_names, iris_wheader.col_names)
iris = h2o.import_file(pyunit_utils.locate("smalldata/iris/iris.csv"))
expected_names = ["C1", "C2", "C3", "C4", "C5"]
assert iris.col_names == expected_names, \
"Expected {0} for column names but got {1}".format(expected_names, iris.col_names)
df = H2OFrame.from_python(np.random.randn(100, 4).tolist(),
column_names=list("ABCD"),
column_types=["enum"] * 4)
df.head()
expected_names = list("ABCD")
assert df.col_names == expected_names, \
"Expected {} for column names but got {}".format(expected_names, df.col_names)
assert list(df.types.values()) == ["enum"] * 4, \
"Expected {} for column types but got {}".format(["enum"] * 4, df.types)
df = H2OFrame(np.random.randn(100, 4).tolist())
df.head()
expected_names = ["C1", "C2", "C3", "C4"]
assert df.col_names == expected_names, \
"Expected {} for column names but got {}".format(expected_names, df.col_names)
assert list(df.types.values()) == ["real"] * 4, \
"Expected {} for column types but got {}".format(["real"] * 4, df.types)
df = H2OFrame({'B': ['a', 'a', 'b', 'NA', 'NA']})
df.head()
assert df.col_names == [
"B"
], "Expected {} for column names but got {}".format(["B"], df.col_names)
df = H2OFrame.from_python({'B': ['a', 'a', 'b', 'NA', 'NA']},
column_names=["X"])
df.head()
assert df.col_names == [
"X"
], "Expected {} for column names but got {}".format(["X"], df.col_names)
