# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
print(data.head())
# age case education induced parity ... row_num spontaneous ...
# 0 26 1 0-5yrs 1 6 ... 1 2 ...
# 1 42 1 0-5yrs 1 1 ... 2 0 ...
# 2 39 1 0-5yrs 2 6 ... 3 0 ...
# 3 34 1 0-5yrs 2 4 ... 4 0 ...
# 4 35 1 6-11yrs 1 3 ... 5 1 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
GamRegressor(feature=['induced', 'edu'], label='age')
])
# train, predict, and evaluate
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# Score
# 0 35.390697
# 1 35.390697
# 2 34.603725
# 3 34.603725
# 4 32.455437
# print evaluation metrics
learners = [
AveragedPerceptronBinaryClassifier(),
FastLinearBinaryClassifier(),
FastLinearClassifier(),
FastLinearRegressor(),
LogisticRegressionBinaryClassifier(),
LogisticRegressionClassifier(),
OnlineGradientDescentRegressor(),
SgdBinaryClassifier(),
# Error on linux
# Unable to load shared library 'SymSgdNative' or one of its dependencies
#SymSgdBinaryClassifier(),
OrdinaryLeastSquaresRegressor(),
PoissonRegressionRegressor(),
OneVsRestClassifier(FastLinearBinaryClassifier()),
GamRegressor(),
GamBinaryClassifier(),
PcaAnomalyDetector(),
FactorizationMachineBinaryClassifier(),
KMeansPlusPlus(n_clusters=2),
NaiveBayesClassifier(),
FastForestBinaryClassifier(number_of_trees=2),
FastForestRegressor(number_of_trees=2),
FastTreesBinaryClassifier(number_of_trees=2),
FastTreesRegressor(number_of_trees=2),
FastTreesTweedieRegressor(number_of_trees=2),
LightGbmRegressor(number_of_iterations=2),
LightGbmClassifier(),
LightGbmBinaryClassifier(number_of_iterations=2)
]
PoissonRegressionRegressor()
]
learners_not_supported = [
NaiveBayesClassifier(),
# fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
KMeansPlusPlus(),
# fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
# fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
FactorizationMachineBinaryClassifier(),
PcaAnomalyDetector(),
# fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
# PcaTransformer(), # REVIEW: crashes
GamBinaryClassifier(),
# fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
GamRegressor(
), # fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
LightGbmClassifier(),
# fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
# LightGbmRanker(), # REVIEW: crashes
# fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
OneVsRestClassifier(FastLinearBinaryClassifier()),
]
class TestModelSummary(unittest.TestCase):
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)
###############################################################################
# GamRegressor
import numpy as np
from nimbusml.datasets import get_dataset
from nimbusml.ensemble import GamRegressor
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 = GamRegressor().fit(X_train, y_train)
scores = ftree.predict(X_test)
# evaluate the model
print('R-squared fit:', r2_score(y_test, scores))