def test_factorizationmachinebinaryclassifier(self):
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'])
lr = FactorizationMachineBinaryClassifier().fit(X_train, y_train)
scores = lr.predict(X_test)
accuracy = np.mean(y_test == [i for i in scores])
assert_greater(accuracy, 0.98, "accuracy should be %s" % 0.98)
pr = lr.predict_proba(X_test)
assert pr.shape == (62, 2)
def test_model_summary_not_supported_specific(self):
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path,
sep=',',
names={
0: 'row_num',
5: 'case'
})
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
FactorizationMachineBinaryClassifier(
feature=['induced', 'edu', 'parity'], label='case')
])
pipeline.fit(data)
try:
pipeline.summary()
except TypeError as e:
self.assertEqual(
e.args[0],
"One or more predictors in this pipeline do not support the .summary() function."
)
else:
assert False
def test_pass_decision_function_binary_with_pipeline(self):
assert_almost_equal(decfun_sum(
Pipeline([FactorizationMachineBinaryClassifier()])),
-32.618393,
decimal=5,
err_msg=invalid_decision_function_output)
NOBINARY_CHECKS = [
'check_estimator_sparse_data', 'check_dtype_object',
'check_fit_score_takes_y', 'check_fit2d_predict1d', 'check_fit1d_1feature',
'check_dont_overwrite_parameters', 'check_supervised_y_2d',
'check_estimators_fit_returns_self', 'check_estimators_overwrite_params',
'check_estimators_dtypes', 'check_classifiers_classes',
'check_classifiers_train'
]
INSTANCES = {
'EnsembleClassifier':
EnsembleClassifier(num_models=3),
'EnsembleRegressor':
EnsembleRegressor(num_models=3),
'FactorizationMachineBinaryClassifier':
FactorizationMachineBinaryClassifier(shuffle=False),
'KMeansPlusPlus':
KMeansPlusPlus(n_clusters=2),
'LightGbmBinaryClassifier':
LightGbmBinaryClassifier(minimum_example_count_per_group=1,
minimum_example_count_per_leaf=1),
'LightGbmClassifier':
LightGbmClassifier(minimum_example_count_per_group=1,
minimum_example_count_per_leaf=1),
'LightGbmRegressor':
LightGbmRegressor(minimum_example_count_per_group=1,
minimum_example_count_per_leaf=1),
'LightGbmRanker':
LightGbmRanker(minimum_example_count_per_group=1,
minimum_example_count_per_leaf=1),
'NGramFeaturizer':
LogisticRegressionBinaryClassifier(),
LogisticRegressionClassifier(),
OnlineGradientDescentRegressor(),
SgdBinaryClassifier(),
# 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()),
]
numeric_dtype=numpy.float32,
names={
0: 'row_num',
5: 'case'
})
print(data.head())
# age case education induced parity pooled.stratum row_num ...
# 0 26.0 1.0 0-5yrs 1.0 6.0 3.0 1.0 ...
# 1 42.0 1.0 0-5yrs 1.0 1.0 1.0 2.0 ...
# 2 39.0 1.0 0-5yrs 2.0 6.0 4.0 3.0 ...
# 3 34.0 1.0 0-5yrs 2.0 4.0 2.0 4.0 ...
# 4 35.0 1.0 6-11yrs 1.0 3.0 32.0 5.0 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
FactorizationMachineBinaryClassifier(feature=['induced', 'edu', 'parity'],
label='case')
])
# train, predict, and evaluate
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Probability Score
# 0 0.0 0.370519 -0.529990
# 1 0.0 0.420984 -0.318737
# 2 0.0 0.364432 -0.556180
# 3 0.0 0.380421 -0.487761
# 4 0.0 0.365351 -0.552214
# print evaluation metrics
print(metrics)
def test_pass_decision_function_binary(self):
assert_almost_equal(decfun_sum(FactorizationMachineBinaryClassifier()),
-30.2316,
decimal=4,
err_msg=invalid_decision_function_output)
# FactorizationMachineBinaryClassifier
import numpy as np
from nimbusml.datasets import get_dataset
from nimbusml.decomposition import FactorizationMachineBinaryClassifier
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.drop('case', axis=1), df['case'])
fforest = FactorizationMachineBinaryClassifier().fit(X_train, y_train)
scores = fforest.predict(X_test)
# evaluate the model
print('Accuracy:', np.mean(y_test == [i for i in scores]))