def test_syntax12_mixed2(self):
X = pandas.DataFrame(dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
weight=[10., 1., 1., 1., 1.],
y=[1.1, 2.2, 1.24, 3.4, 3.4]))
exp = Pipeline(
[
OneHotVectorizer(
columns=[
'workclass', 'education']),
Concat(
columns={
'Feature': ['workclass', 'education']}),
FastTreesRegressor(
num_trees=5, feature='Feature', weight='weight') << {
Role.Label: 'y'}])
exp.fit(X, verbose=0)
assert exp.nodes[-1].feature_column_ == 'Feature'
assert exp.nodes[-1].label_column_ == 'y'
assert exp.nodes[-1].weight_column_ == 'weight'
# y is required here as well as weight.
# It is replaced by fakes values.
# The test does not fail but the weight is not taken into account.
X['y'] = -5
X['weight'] = -5
prediction = exp.predict(X)
assert isinstance(prediction, pandas.DataFrame)
assert list(prediction.columns) == ['Score']
assert prediction.shape == (5, 1)
def test_syntax6_regular_expression(self):
df = pandas.DataFrame(
dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
y=[1, 0, 1, 0, 0]))
X = df.drop('y', axis=1)
y = df['y']
exp = Pipeline([
OneHotVectorizer() << {
'f1': 'education'
},
OneHotHashVectorizer() << {
'f2': 'education'
},
OneHotVectorizer(max_num_terms=2) << {
'f3': 'workclass'
},
Concat() << {
'Features': ['f%d' % i for i in range(1, 4)]
},
Drop() << '~Features',
FastLinearBinaryClassifier(max_iterations=1)
])
exp.fit(X, y)
prediction = exp.predict(X)
assert isinstance(prediction, pandas.DataFrame)
assert sorted(list(
prediction.columns)) == ['PredictedLabel', 'Probability', 'Score']
assert prediction.shape == (5, 3)
def test_syntax5_regular_expression(self):
# REVIEW: not implemented yet
# The best would be to handle regular expression inside nimbusml.
# It could be handled in entrypoint.py just before calling nimbusml.
# It can be handled inside Pipeline if it is aware of
# the input schema.
df = pandas.DataFrame(
dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
y=[1, 0, 1, 0, 0]))
X = df.drop('y', axis=1)
y = df['y']
exp = Pipeline([
OneHotVectorizer() << {
'f1': 'education'
},
OneHotHashVectorizer() << {
'f2': 'education'
},
OneHotVectorizer(max_num_terms=2) << {
'f3': 'workclass'
},
Concat() << {
'Features': 'f[0-9]+'
},
FastLinearBinaryClassifier(max_iterations=1) << 'Features'
])
exp.fit(X, y)
prediction = exp.predict(X)
assert isinstance(prediction, pandas.DataFrame)
assert sorted(list(
prediction.columns)) == ['PredictedLabel', 'Probability', 'Score']
assert prediction.shape == (5, 3)
def test_syntax4_dict(self):
df = pandas.DataFrame(
dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
y=[1, 0, 1, 0, 0]))
X = df.drop('y', axis=1)
y = df['y']
exp = Pipeline([
OneHotVectorizer() << {
'edu1': 'education'
},
OneHotHashVectorizer() << {
'edu2': 'education'
},
OneHotVectorizer(max_num_terms=2) << {
'wki': 'workclass'
},
Concat() << {
'Inputs': ['edu1', 'edu2', 'wki']
},
FastLinearBinaryClassifier(max_iterations=1) << 'Inputs'
])
exp.fit(X, y)
prediction = exp.predict(X)
assert isinstance(prediction, pandas.DataFrame)
assert sorted(list(
prediction.columns)) == ['PredictedLabel', 'Probability', 'Score']
assert prediction.shape == (5, 3)
def test_syntax6_change_role(self):
# REVIEW: the pipeline drops all columns but one -->
# nimbusml still thinks the Features are eduction, workclass
# and does not automatically detects that the only remaining
# columns should play that role
# (maybe because the label column is here too even though
# the only remaining column without a role is Features).
df = pandas.DataFrame(dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
y=[1, 0, 1, 0, 0]))
X = df.drop('y', axis=1)
y = df['y']
exp = Pipeline([
OneHotVectorizer() << {'f1': 'education'},
OneHotHashVectorizer() << {'f2': 'education'},
OneHotVectorizer(max_num_terms=2) << {'f3': 'workclass'},
Concat() << {'Features': ['f%d' % i for i in range(1, 4)]},
Drop() << ['education', 'workclass', 'f1', 'f2', 'f3'],
FastLinearBinaryClassifier(maximum_number_of_iterations=1) << ['Features']
])
exp.fit(X, y, verbose=0)
prediction = exp.predict(X)
assert isinstance(prediction, pandas.DataFrame)
assert sorted(list(prediction.columns)) == [
'PredictedLabel', 'Probability', 'Score']
assert prediction.shape == (5, 3)
def test_syntax_concat_slots(self):
X = pandas.DataFrame(dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
weight=[10., 1., 1., 1., 1.],
y=[1.1, 2.2, 1.24, 3.4, 3.4]))
exp = Pipeline([
OneHotVectorizer() << ['workclass', 'education'],
Concat() << {'newcol': ['workclass', 'education']},
])
exp.fit(X, verbose=0)
exp.predict(X)
def test_syntax12_fail(self):
# This tests check that a learner raises an exception
# if a role is not allowed by the entrypoint.
X = pandas.DataFrame(dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
weight=[10., 1., 1., 1., 1.],
y=[1.1, 2.2, 1.24, 3.4, 3.4]))
try:
Pipeline([
OneHotVectorizer(columns=['workclass', 'education']),
Concat(columns={'Feature': ['workclass', 'education']}),
FastLinearBinaryClassifier(feature='Feature',
group_id='weight') << {
Role.Label: 'y'}
])
Pipeline.fit(X)
assert False
except (RuntimeError, NameError) as e:
exp = "Parameter 'group_id' is not allowed " \
"for class 'FastLinearBinaryClassifier'"
if exp not in str(e):
raise e
def test_syntax12_group(self):
# This tests check that a learner raises an exception
# if a role is not allowed by the entrypoint.
X = pandas.DataFrame(
dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
gr=[0, 0, 1, 1, 1],
y=[1.1, 2.2, 1.24, 3.4, 3.4]))
exp = Pipeline([
OneHotVectorizer(columns=['workclass', 'education']),
Concat(columns={'Feature': ['workclass', 'education']}),
ToKey() << 'gr',
FastTreesRegressor(
number_of_trees=5, feature='Feature', group_id='gr') << {
Role.Label: 'y'
}
])
exp.fit(X, verbose=0)
assert not hasattr(exp.nodes[-1], 'feature_')
assert not hasattr(exp.nodes[-1], 'group_id_')
assert exp.nodes[-1].feature_column_name_ == 'Feature'
assert exp.nodes[-1].label_column_name_ == 'y'
# assert not hasattr(exp.nodes[-1], 'row_group_column_name_')
assert not hasattr(exp.nodes[-1], 'group_id_column')
assert not hasattr(exp.nodes[-1], 'groupid_column_')
assert not hasattr(exp.nodes[-1], 'groupid_column')
if not hasattr(exp.nodes[-1], 'row_group_column_name_'):
raise AssertionError("Attribute not found: {0}".format(", ".join(
sorted(dir(exp.nodes[-1])))))
assert exp.nodes[-1].row_group_column_name_ == 'gr'
# y is required here as well as weight.
# It is replaced by fakes values.
# The test does not fail but the weight is not taken into account.
X['y'] = -5
X['weight'] = -5
prediction = exp.predict(X)
assert isinstance(prediction, pandas.DataFrame)
assert list(prediction.columns) == ['Score']
assert prediction.shape == (5, 1)