def test_model_summary(self):
for learner in learners:
pipeline = Pipeline(
[OneHotVectorizer() << categorical_columns, learner])
train_stream = FileDataStream(train_file, schema=file_schema)
pipeline.fit(train_stream, label_column)
pipeline.summary()
def test_pipeline_summary_is_refreshed_after_refitting(self):
predictor = OrdinaryLeastSquaresRegressor()
pipeline = Pipeline([predictor])
pipeline.fit([0,1,2,3], [1,2,3,4])
summary1 = pipeline.summary()
pipeline.fit([0,1,2.5,3], [2,5,8,11])
summary2 = pipeline.summary()
self.assertFalse(summary1.equals(summary2))
def test_input_types(self):
df = DataFrame(data=dict(Label=[1, 2, 3, 4, 5],
f=[1.1, 2.2, 3.3, np.nan, 5.5],
f1=[2.2, np.nan, 4.4, 5.5, 6.6]))
h = Handler(replace_with='Mean')
ft = FastLinearRegressor(shuffle=False, number_of_threads=1)
p = Pipeline([h, ft])
p.fit(df[['f', 'f1']].values, df['Label'])
res = p.predict(df[['f', 'f1']].values)
print(res)
print(p.summary())
assert_allclose(res['Score'].values,
[4.965541, 0.519701, 4.992831, 3.877400, 5.020121],
rtol=1e-4)
def test_model_summary_not_supported_specific(self):
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path,
sep=',',
names={
0: 'row_num',
5: 'case'
})
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
FactorizationMachineBinaryClassifier(
feature=['induced', 'edu', 'parity'], label='case')
])
pipeline.fit(data)
try:
pipeline.summary()
except TypeError as e:
self.assertEqual(
e.args[0],
"One or more predictors in this pipeline do not support the .summary() function."
)
else:
assert False
import pandas as pd
from nimbusml import Pipeline, FileDataStream
from nimbusml.linear_model import FastLinearRegressor
from nimbusml.preprocessing.normalization import MeanVarianceScaler
X = np.array([[1, 2.0], [2, 4], [3, 0.7]])
Y = np.array([2, 3, 1.5])
df = pd.DataFrame(dict(y=Y, x1=X[:, 0], x2=X[:, 1]))
pipe = Pipeline([
MeanVarianceScaler(),
FastLinearRegressor()
])
# fit with pandas dataframe
pipe.fit(X, Y)
# Fit with FileDataStream
df.to_csv('data.csv', index=False)
ds = FileDataStream.read_csv('data.csv', sep=',')
pipe = Pipeline([
MeanVarianceScaler(),
FastLinearRegressor()
])
pipe.fit(ds, 'y')
print(pipe.summary())
# Bias Weights.x1 Weights.x2
# 0 1.032946 0.111758 1.210791