def test_fasttreestweedieregressor(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 = FastTreesTweedieRegressor().fit(X_train, y_train)
scores = ftree.predict(X_test)
r2 = r2_score(y_test, scores)
assert_greater(r2, 0.479, "sum should be greater than %s" % 0.479)
assert_less(r2, 0.480, "sum should be less than %s" % 0.480)
'CharTokenizer': CharTokenizer(columns={'SentimentText_Transform': 'SentimentText'}),
'ColumnConcatenator': ColumnConcatenator(columns={'Features': [
'Sepal_Length',
'Sepal_Width',
'Petal_Length',
'Petal_Width',
'Setosa']}),
'ColumnSelector': ColumnSelector(columns=['Sepal_Width', 'Sepal_Length']),
'ColumnDuplicator': ColumnDuplicator(columns={'dup': 'Sepal_Width'}),
'CountSelector': CountSelector(count=5, columns=['Sepal_Width']),
'DateTimeSplitter': DateTimeSplitter(prefix='dt'),
'FastForestBinaryClassifier': FastForestBinaryClassifier(feature=['Sepal_Width', 'Sepal_Length'],
label='Setosa'),
'FastLinearBinaryClassifier': FastLinearBinaryClassifier(feature=['Sepal_Width', 'Sepal_Length'],
label='Setosa'),
'FastTreesTweedieRegressor': FastTreesTweedieRegressor(label='Ozone'),
'Filter': Filter(columns=[ 'Petal_Length', 'Petal_Width']),
'FromKey': Pipeline([
ToKey(columns=['Sepal_Length']),
FromKey(columns=['Sepal_Length'])
]),
# GlobalContrastRowScaler currently requires a vector input to work
'GlobalContrastRowScaler': Pipeline([
ColumnConcatenator() << {
'concated_columns': [
'Petal_Length',
'Sepal_Width',
'Sepal_Length']},
GlobalContrastRowScaler(columns={'normed_columns': 'concated_columns'})
]),
'Handler': Handler(replace_with='Mean', columns={'NewVals': 'Petal_Length'}),
train_file = get_dataset("uciadult_train").as_filepath()
categorical_columns = [
'workclass', 'education', 'marital-status', 'occupation', 'relationship',
'ethnicity', 'sex', 'native-country-region'
]
file_schema = 'sep=, col=label:R4:0 col=Features:R4:9-14 col=workclass:TX:1 ' \
'col=education:TX:2 col=marital-status:TX:3 ' \
'col=occupation:TX:4 col=relationship:TX:5 col=ethnicity:TX:6 ' \
'col=sex:TX:7 col=native-country-region:TX:8 header+'
label_column = 'label'
learners = [
FastForestBinaryClassifier(),
FastForestRegressor(),
FastTreesBinaryClassifier(),
FastTreesRegressor(),
FastTreesTweedieRegressor(),
LightGbmRegressor(),
LightGbmBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastLinearBinaryClassifier(),
FastLinearClassifier(),
FastLinearRegressor(),
LogisticRegressionBinaryClassifier(),
LogisticRegressionClassifier(),
OnlineGradientDescentRegressor(),
SgdBinaryClassifier(),
# SymSgdBinaryClassifier(),
OrdinaryLeastSquaresRegressor(),
PoissonRegressionRegressor()
]
# 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)
]
learners_not_supported = [
#PcaTransformer(), # REVIEW: crashes
]
class TestModelSummary(unittest.TestCase):
def test_model_summary(self):
for learner in learners:
pipeline = Pipeline(
###############################################################################
# FastTreesRegressor
import numpy as np
from nimbusml.datasets import get_dataset
from nimbusml.ensemble import FastTreesTweedieRegressor
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 = FastTreesTweedieRegressor().fit(X_train, y_train)
scores = ftree.predict(X_test)
# evaluate the model
print('R-squared fit:', r2_score(y_test, scores))
# 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'}),
FastTreesTweedieRegressor(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 35.152565
# 1 35.152565
# 2 34.089958
# 3 34.089958
# 4 32.486031
# print evaluation metrics
print(metrics)