def test_GamBinaryClassifier(self):
np.random.seed(0)
df = get_dataset("infert").as_df()
df.columns = [i.replace(': ', '') for i in df.columns]
df = (OneHotVectorizer() << 'education_str').fit_transform(df)
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'case'], df['case'])
lr = GamBinaryClassifier().fit(X_train, y_train)
scores = lr.predict(X_test)
acc = np.mean(y_test == [i for i in scores])
assert_greater(acc, 0.70, "accuracy should %s" % 0.70)
def test_ovr_accuracy(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(number_of_threads=1),
FastForestBinaryClassifier(minimum_example_count_per_leaf=1,
number_of_threads=1),
GamBinaryClassifier(number_of_threads=1),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(minimum_example_count_per_leaf=1,
number_of_threads=1),
FastLinearBinaryClassifier(number_of_threads=1),
SgdBinaryClassifier(number_of_threads=1),
# SymSgdBinaryClassifier(number_of_threads=1),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf, use_probabilities=True)
metrics = accuracy(ovr)
accu = metrics['Accuracy(micro-avg)'][0]
# algos will have wide range of accuracy, so use low bar. Also
# checks Pipeline + Ova + clf
assert_greater(
accu, 0.65,
"{} accuracy is too low {}".format(clf.__class__, accu))
def test_failing_predict_proba_called_with_use_probabilites_false(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(),
FastForestBinaryClassifier(minimum_example_count_per_leaf=1),
GamBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(minimum_example_count_per_leaf=1),
LightGbmBinaryClassifier(),
FastLinearBinaryClassifier(),
SgdBinaryClassifier(),
# SymSgdBinaryClassifier(),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf, use_probabilities=False)
check_predict_proba_when_trained_with_use_probabilites_false(
self, ovr, clf)
def test_failing_decision_function_called_with_use_probabilites_true(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(),
FastForestBinaryClassifier(min_split=1),
GamBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(min_split=1),
LightGbmBinaryClassifier(),
FastLinearBinaryClassifier(),
SgdBinaryClassifier(),
# SymSgdBinaryClassifier(),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf, use_probabilities=True)
check_decision_function_when_trained_with_use_probabilites_true(
self, ovr, clf)
def test_decision_function_produces_distribution_not_sum_to_1(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(),
FastForestBinaryClassifier(minimum_example_count_per_leaf=1),
GamBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(minimum_example_count_per_leaf=1),
LightGbmBinaryClassifier(),
FastLinearBinaryClassifier(),
SgdBinaryClassifier(),
# SymSgdBinaryClassifier(),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf, use_probabilities=False)
scoremean = decfun_average(ovr)
assert_not_equal(
scoremean, 1.0,
'{} raw scores should not sum to 1.0 over 3 classes'.format(
clf.__class__))
def test_predict_proba_produces_distribution_sum_to_1(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(),
FastForestBinaryClassifier(minimum_example_count_per_leaf=1),
GamBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(minimum_example_count_per_leaf=1),
LightGbmBinaryClassifier(),
FastLinearBinaryClassifier(),
SgdBinaryClassifier(),
# TODO: why symsgd does not sum to 1.0
# SymSgdBinaryClassifier(),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf)
probmean = proba_average(ovr)
assert_equal(
probmean, 1.0,
'{} probabilites {} do not sum to 1.0 over 3 classes'.format(
clf.__class__, probmean))
# 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'}),
GamBinaryClassifier(feature=['age', 'edu'], label='case')
])
# train, predict, and evaluate
# TODO: Replace with CV
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Score
# 0 0 -0.050461
# 1 0 -0.049737
# 2 0 -0.049737
# 3 0 -0.050461
# 4 0 -0.050552
# print evaluation metrics
# GamBinaryClassifier
import numpy as np
from nimbusml.datasets import get_dataset
from nimbusml.ensemble import GamBinaryClassifier
from nimbusml.feature_extraction.categorical import OneHotVectorizer
from sklearn.model_selection import train_test_split
# use the built-in data set 'infert' to create test and train data
# Unnamed: 0 education age parity induced case spontaneous stratum \
# 0 1 0.0 26.0 6.0 1.0 1.0 2.0 1.0
# 1 2 0.0 42.0 1.0 1.0 1.0 0.0 2.0
# pooled.stratum education_str
# 0 3.0 0-5yrs
# 1 1.0 0-5yrs
np.random.seed(0)
df = get_dataset("infert").as_df()
# remove : and ' ' from column names, and encode categorical column
df.columns = [i.replace(': ', '') for i in df.columns]
df = (OneHotVectorizer() << 'education_str').fit_transform(df)
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'case'], df['case'])
ftree = GamBinaryClassifier().fit(X_train, y_train)
scores = ftree.predict(X_test)
# evaluate the model
print('Accuracy:', np.mean(y_test == [i for i in scores]))
# SymSgdBinaryClassifier(),
OrdinaryLeastSquaresRegressor(),
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(