def test_syntax12_mixed2(self):
X = pandas.DataFrame(dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
weight=[10., 1., 1., 1., 1.],
y=[1.1, 2.2, 1.24, 3.4, 3.4]))
exp = Pipeline(
[
OneHotVectorizer(
columns=[
'workclass', 'education']),
Concat(
columns={
'Feature': ['workclass', 'education']}),
FastTreesRegressor(
num_trees=5, feature='Feature', weight='weight') << {
Role.Label: 'y'}])
exp.fit(X, verbose=0)
assert exp.nodes[-1].feature_column_ == 'Feature'
assert exp.nodes[-1].label_column_ == 'y'
assert exp.nodes[-1].weight_column_ == 'weight'
# y is required here as well as weight.
# It is replaced by fakes values.
# The test does not fail but the weight is not taken into account.
X['y'] = -5
X['weight'] = -5
prediction = exp.predict(X)
assert isinstance(prediction, pandas.DataFrame)
assert list(prediction.columns) == ['Score']
assert prediction.shape == (5, 1)
def test_metrics_evaluate_regressor(self):
np.random.seed(0)
df = get_dataset("iris").as_df()
df.drop(['Species'], inplace=True, axis=1)
df.Label = [1 if x == 1 else 0 for x in df.Label]
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'Label'], df['Label'])
lr = FastTreesRegressor()
e = Pipeline([lr])
e.fit(X_train, y_train.to_frame(), verbose=0)
metrics, _ = e.test(X_test, y_test)
# TODO: debug flucations, and increase decimal precision on checks
assert_almost_equal(metrics['L1(avg)'][0],
0.107,
decimal=1,
err_msg="L1 loss should be %s" % 0.107)
assert_almost_equal(metrics['L2(avg)'][0],
0.0453,
decimal=1,
err_msg="L2(avg) should be %s" % 0.0453)
assert_almost_equal(metrics['Loss-fn(avg)'][0],
0.0453,
decimal=1,
err_msg="Loss-fn(avg)loss should be %s" % 0.0453)
def test_label_column_defaults_to_label_when_label_column_in_input_data(
self):
train_data = {
'c1': [2, 3, 4, 5],
'c2': [3, 4, 5, 6],
'c3': [4, 5, 6, 7],
'Label': [0, 1, 2, 1]
}
train_df = pd.DataFrame(train_data)
predictor = FastTreesRegressor()
pipeline = Pipeline([predictor])
result = json.loads(pipeline.fit(train_df, dry_run=True))
self.verify_regressor_nodes(result, "Label", ["c1", "c2", "c3"],
"Trainers.FastTreeRegressor")
def test_score_regressor(self):
np.random.seed(0)
df = get_dataset("iris").as_df()
df.drop(['Species'], inplace=True, axis=1)
df.Label = [1 if x == 1 else 0 for x in df.Label]
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'Label'], df['Label'])
lr = FastTreesRegressor(train_threads=1)
e = Pipeline([lr])
e.fit(X_train, y_train.to_frame())
metrics = e.score(X_test, y_test)
print(metrics)
assert_almost_equal(metrics,
0.814061733686017,
decimal=5,
err_msg="L1 loss should be %s" % 0.814061733686017)
def test_syntax12_group(self):
# This tests check that a learner raises an exception
# if a role is not allowed by the entrypoint.
X = pandas.DataFrame(
dict(education=['A', 'B', 'A', 'B', 'A'],
workclass=['X', 'X', 'Y', 'Y', 'Y'],
gr=[0, 0, 1, 1, 1],
y=[1.1, 2.2, 1.24, 3.4, 3.4]))
exp = Pipeline([
OneHotVectorizer(columns=['workclass', 'education']),
Concat(columns={'Feature': ['workclass', 'education']}),
ToKey() << 'gr',
FastTreesRegressor(
number_of_trees=5, feature='Feature', group_id='gr') << {
Role.Label: 'y'
}
])
exp.fit(X, verbose=0)
assert not hasattr(exp.nodes[-1], 'feature_')
assert not hasattr(exp.nodes[-1], 'group_id_')
assert exp.nodes[-1].feature_column_name_ == 'Feature'
assert exp.nodes[-1].label_column_name_ == 'y'
# assert not hasattr(exp.nodes[-1], 'row_group_column_name_')
assert not hasattr(exp.nodes[-1], 'group_id_column')
assert not hasattr(exp.nodes[-1], 'groupid_column_')
assert not hasattr(exp.nodes[-1], 'groupid_column')
if not hasattr(exp.nodes[-1], 'row_group_column_name_'):
raise AssertionError("Attribute not found: {0}".format(", ".join(
sorted(dir(exp.nodes[-1])))))
assert exp.nodes[-1].row_group_column_name_ == 'gr'
# y is required here as well as weight.
# It is replaced by fakes values.
# The test does not fail but the weight is not taken into account.
X['y'] = -5
X['weight'] = -5
prediction = exp.predict(X)
assert isinstance(prediction, pandas.DataFrame)
assert list(prediction.columns) == ['Score']
assert prediction.shape == (5, 1)
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()
]
# 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)
]
learners_not_supported = [
#PcaTransformer(), # REVIEW: crashes
]
class TestModelSummary(unittest.TestCase):
def test_model_summary(self):
for learner in learners:
###############################################################################
# FastTreesRegressor
import numpy as np
from nimbusml.datasets import get_dataset
from nimbusml.ensemble import FastTreesRegressor
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 = FastTreesRegressor().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'}),
FastTreesRegressor(feature=['induced', 'edu'], label='age')
])
# train, predict, and evaluate
# TODO: Replace with CV
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# Score
# 0 35.171112
# 1 35.171112
# 2 34.118595
# 3 34.118595
# 4 32.484325
# print evaluation metrics