def test_pipeline_info(self):
df = pandas.DataFrame(
dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
yy=[1.1, 2.2, 1.24, 3.4, 3.4]))
exp = Pipeline([
MeanVarianceScaler() << {
'new_y': 'yy'
},
OneHotVectorizer() << ['workclass', 'education'],
Drop() << 'yy',
FastLinearRegressor() << {
'Feature': ['workclass', 'education'],
Role.Label: 'new_y'
}
])
infos = exp.get_fit_info(df)[0]
for inf in infos:
if 'operator' in inf:
del inf['operator']
exp = [{
'name': None,
'schema_after': ['education', 'workclass', 'yy'],
'type': 'start',
'outputs': ['education', 'workclass', 'yy']
}, {
'name': 'TypeConverter',
'inputs': ['yy'],
'outputs': ['new_y'],
'schema_after': ['education', 'workclass', 'yy', 'new_y'],
'type': 'transform'
}, {
'name': 'MeanVarianceScaler',
'inputs': ['new_y'],
'type': 'transform',
'outputs': ['new_y'],
'schema_after': ['education', 'workclass', 'yy', 'new_y']
}, {
'name': 'OneHotVectorizer',
'inputs': ['workclass', 'education'],
'type': 'transform',
'outputs': ['workclass', 'education'],
'schema_after': ['education', 'workclass', 'yy', 'new_y']
}, {
'name': 'ColumnDropper',
'type': 'transform',
'schema_after': ['education', 'workclass', 'new_y'],
'inputs': ['education', 'workclass', 'yy', 'new_y'],
'outputs': ['education', 'workclass', 'new_y']
}, {
'name': 'FastLinearRegressor',
'inputs': ['Feature:education,workclass', 'Label:new_y'],
'type': 'regressor',
'outputs': ['Score'],
'schema_after': ['Score']
}]
if infos != exp:
raise Exception(infos)
def test_syntax8_label(self):
df = pandas.DataFrame(dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
yy=[1.1, 2.2, 1.24, 3.4, 3.4]))
X = df.drop('yy', axis=1)
exp = Pipeline([
MeanVarianceScaler() << {'new_y': 'yy'},
OneHotVectorizer() << ['workclass', 'education'],
Drop() << 'yy',
FastLinearRegressor() << {'Feature': ['workclass', 'education'],
Role.Label: 'new_y'}
])
exp.fit(df, verbose=0)
assert exp.nodes[-1].feature_column_ == 'Features'
assert exp.nodes[-1].label_column_ == 'new_y'
# The pipeline requires it now as it is transformed all along.
X['yy'] = 0.0
prediction = exp.predict(X, verbose=0)
assert isinstance(prediction, pandas.DataFrame)
assert list(prediction.columns) == ['Score']
assert prediction.shape == (5, 1)
if prediction['Score'].min() < 0.4:
raise Exception(prediction)
if prediction['Score'].max() > 2.00:
raise Exception(prediction)
def test_syntax7_rename(self):
# Error message are usually not informative enough.
# Missing column --> no indication of other columns.
# Error is (one transform should handle it)
# 'The label column 'y' of the training data has a data type
# not suitable for binary classification: Vec<Key<U4, 0-1>, 2>.
# Type must be Bool, R4, R8 or Key with two classes.
df = pandas.DataFrame(
dict(
education=[
'A', 'B', 'A', 'B', 'A'], workclass=[
'X', 'X', 'Y', 'Y', 'Y'], y=[
'red', 'white', 'red', 'white', 'white']))
X = df.drop('y', axis=1)
y = df['y']
exp = Pipeline([
OneHotVectorizer() << 'y',
OneHotVectorizer() << ['workclass', 'education'],
TypeConverter(result_type='R4') << {'yi': 'y'},
Drop() << 'y',
FastLinearBinaryClassifier(max_iterations=1) << 'yi'
])
exp.fit(X, y, verbose=0)
prediction = exp.predict(X)
assert isinstance(prediction, pandas.DataFrame)
assert list(prediction.columns) == ['Score']
assert prediction.shape == (5, 1)
assert prediction.min() > 0.01
assert prediction.max() < 0.05
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_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_pipeline_exports(self):
import graphviz.backend
df = pandas.DataFrame(
dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
yy=[1.1, 2.2, 1.24, 3.4, 3.4]))
exp = Pipeline([
MeanVarianceScaler() << {
'new_y': 'yy'
},
OneHotVectorizer() << ['workclass', 'education'],
Drop() << 'yy',
FastLinearRegressor() << {
'Feature': ['workclass', 'education'],
Role.Label: 'new_y'
}
])
gr = img_export_pipeline(exp, df)
name = next(tempfile._get_candidate_names())
try:
gr.render(name)
assert os.path.exists(name)
except graphviz.backend.ExecutableNotFound:
warnings.warn('Graphviz is not installed.')
if os.path.exists(name):
os.remove(name)
def test_pipeline_info_strategy_previous_drop(self):
df = pandas.DataFrame(
dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
yy=[1.1, 2.2, 1.24, 3.4, 3.4]))
X = df.drop('yy', axis=1)
y = df['yy']
exp = Pipeline([
OneHotVectorizer() << ['workclass', 'education'],
Drop() << ['education'],
FastLinearRegressor()
])
infos = exp.get_fit_info(X, y)[0]
for inf in infos:
if 'operator' in inf:
del inf['operator']
exp = [{
'name': None,
'schema_after': ['education', 'workclass', 'yy'],
'type': 'start',
'outputs': ['education', 'workclass', 'yy']
}, {
'name': 'OneHotVectorizer',
'inputs': ['workclass', 'education'],
'type': 'transform',
'outputs': ['workclass', 'education'],
'schema_after': ['education', 'workclass', 'yy']
}, {
'name': 'ColumnDropper',
'type': 'transform',
'schema_after': ['workclass', 'yy'],
'inputs': ['education', 'workclass', 'yy'],
'outputs': ['workclass', 'yy']
}, {
'name': 'FastLinearRegressor',
'inputs': ['Feature:workclass', 'Label:yy'],
'type': 'regressor',
'outputs': ['Score'],
'schema_after': ['Score']
}]
assert infos == exp
def test_pipeline_exports(self):
df = pandas.DataFrame(
dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
yy=[1.1, 2.2, 1.24, 3.4, 3.4]))
exp = Pipeline([
MeanVarianceScaler() << {
'new_y': 'yy'
},
OneHotVectorizer() << ['workclass', 'education'],
Drop() << 'yy',
FastLinearRegressor() << {
'Feature': ['workclass', 'education'],
Role.Label: 'new_y'
}
])
for node in exp.nodes:
if hasattr(node, 'label_column'):
assert node.label_column == 'new_y'
assert exp.nodes[-1].label_column == 'new_y'
res = dot_export_pipeline(exp, df).strip("\n\r ")
exp = """
digraph{
orientation=portrait;
sch0[label="<f0> education|<f1> workclass|<f2> yy",
shape=record,fontsize=8];
node1[label="TypeConverter",shape=box,style="filled,
rounded",color=cyan,fontsize=12];
sch0:f2 -> node1;
sch1[label="<f0> new_y",shape=record,fontsize=8];
node1 -> sch1:f0;
node2[label="MeanVarianceScaler",shape=box,
style="filled,rounded",color=cyan,fontsize=12];
sch1:f0 -> node2;
sch2[label="<f0> new_y",shape=record,fontsize=8];
node2 -> sch2:f0;
node3[label="OneHotVectorizer",shape=box,
style="filled,rounded",color=cyan,fontsize=12];
sch0:f1 -> node3;
sch0:f0 -> node3;
sch3[label="<f0> workclass|<f1> education",
shape=record,fontsize=8];
node3 -> sch3:f0;
node3 -> sch3:f1;
node5[label="FastLinearRegressor",shape=box,
style="filled,rounded",color=yellow,fontsize=12];
sch3:f1 -> node5 [label="Feature",fontsize=8];
sch3:f0 -> node5 [label="Feature",fontsize=8];
sch2:f0 -> node5 [label="Label",fontsize=8];
sch5[label="<f0> Score",shape=record,fontsize=8];
node5 -> sch5:f0;
}
""".replace(" ", "").strip("\n\r ")
if res.replace("\n", "").replace(" ", "") != exp.replace(
"\n", "").replace(" ", ""):
raise Exception(res)