def test_ensemble_supports_user_defined_transforms(self):
test2_df = test_df.copy(deep=True)
test2_df = test2_df.append(pd.DataFrame({'c1': [9, 11], 'c2': [1, 1]}))
r1 = OrdinaryLeastSquaresRegressor(**olsrArgs)
r1.fit(train_df)
result1 = r1.predict(test2_df)
r2 = OnlineGradientDescentRegressor(**ogdArgs)
r2.fit(train_df)
result2 = r2.predict(test2_df)
r3 = LightGbmRegressor(**lgbmArgs)
r3.fit(train_df)
result3 = r3.predict(test2_df)
r1 = OrdinaryLeastSquaresRegressor(**olsrArgs)
r2 = OnlineGradientDescentRegressor(**ogdArgs)
r3 = LightGbmRegressor(**lgbmArgs)
pipeline = Pipeline([
RangeFilter(min=0, max=10, columns='c1'),
VotingRegressor(estimators=[r1, r2, r3], combiner='Average')
])
pipeline.fit(train_df)
result4 = pipeline.predict(test2_df)
self.assertEqual(len(result4), 3)
average1 = (result1[0] + result2[0] + result3[0]) / 3
average2 = (result1[1] + result2[1] + result3[1]) / 3
average3 = (result1[2] + result2[2] + result3[2]) / 3
self.assertAlmostEqual(average1, result4.loc[0, 'Score'], places=5)
self.assertAlmostEqual(average2, result4.loc[1, 'Score'], places=5)
self.assertAlmostEqual(average3, result4.loc[2, 'Score'], places=5)
def test_lightgbmregressor(self):
np.random.seed(0)
df = get_dataset("airquality").as_df().fillna(0)
df = df[df.Ozone.notnull()]
X_train, X_test, y_train, y_test = train_test_split(
df.loc[:, df.columns != 'Ozone'], df['Ozone'])
# Train a model and score
ftree = LightGbmRegressor().fit(X_train, y_train)
scores = ftree.predict(X_test)
r2 = r2_score(y_test, scores)
assert_greater(r2, 0.32, "should be greater than %s" % 0.32)
assert_less(r2, 0.33, "sum should be less than %s" % 0.33)
def test_ensemble_with_average_and_median_combiner(self):
r1 = OrdinaryLeastSquaresRegressor(**olsrArgs)
r1.fit(train_df)
result1 = r1.predict(test_df)
r2 = OnlineGradientDescentRegressor(**ogdArgs)
r2.fit(train_df)
result2 = r2.predict(test_df)
r3 = LightGbmRegressor(**lgbmArgs)
r3.fit(train_df)
result3 = r3.predict(test_df)
r1 = OrdinaryLeastSquaresRegressor(**olsrArgs)
r2 = OnlineGradientDescentRegressor(**ogdArgs)
r3 = LightGbmRegressor(**lgbmArgs)
pipeline = Pipeline([VotingRegressor(estimators=[r1, r2, r3], combiner='Average')])
pipeline.fit(train_df)
result4 = pipeline.predict(test_df)
average1 = (result1[0] + result2[0] + result3[0]) / 3
average2 = (result1[1] + result2[1] + result3[1]) / 3
self.assertAlmostEqual(average1, result4.loc[0, 'Score'], places=5)
self.assertAlmostEqual(average2, result4.loc[1, 'Score'], places=5)
r1 = OrdinaryLeastSquaresRegressor(**olsrArgs)
r2 = OnlineGradientDescentRegressor(**ogdArgs)
r3 = LightGbmRegressor(**lgbmArgs)
pipeline = Pipeline([VotingRegressor(estimators=[r1, r2, r3], combiner='Median')])
pipeline.fit(train_df)
result4 = pipeline.predict(test_df)
median1 = sorted([result1.loc[0], result2.loc[0], result3.loc[0]])[1]
median2 = sorted([result1.loc[1], result2.loc[1], result3.loc[1]])[1]
self.assertEqual(median1, result4.loc[0, 'Score'])
self.assertEqual(median2, result4.loc[1, 'Score'])
}
if show_individual_predictions:
r1 = OrdinaryLeastSquaresRegressor(**olsrArgs)
r1.fit(train_df)
result = r1.predict(test_df)
print(result)
r2 = OnlineGradientDescentRegressor(**ogdArgs)
r2.fit(train_df)
result = r2.predict(test_df)
print(result)
r3 = LightGbmRegressor(**lgbmArgs)
r3.fit(train_df)
result = r3.predict(test_df)
print(result)
# Perform a prediction using an ensemble
# of all three of the above predictors.
r1 = OrdinaryLeastSquaresRegressor(**olsrArgs)
r2 = OnlineGradientDescentRegressor(**ogdArgs)
r3 = LightGbmRegressor(**lgbmArgs)
pipeline = Pipeline(
[VotingRegressor(estimators=[r1, r2, r3], combiner='Average')])
pipeline.fit(train_df)
result = pipeline.predict(test_df)
print(result)
###############################################################################
# LightGbmRegressor
import numpy as np
from nimbusml.datasets import get_dataset
from nimbusml.ensemble import LightGbmRegressor
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split
# use the built-in data set 'airquality' to create test and train data
# Unnamed: 0 Ozone Solar_R Wind Temp Month Day
# 0 1 41.0 190.0 7.4 67 5 1
# 1 2 36.0 118.0 8.0 72 5 2
np.random.seed(0)
df = get_dataset("airquality").as_df().fillna(0)
df = df[df.Ozone.notnull()]
X_train, X_test, y_train, y_test = train_test_split(
df.loc[:, df.columns != 'Ozone'], df['Ozone'])
# train a model and score
ftree = LightGbmRegressor().fit(X_train, y_train)
scores = ftree.predict(X_test)
# evaluate the model
print('R-squared fit:', r2_score(y_test, scores))
