def test_PcaAnomalyDetector(self):
np.random.seed(0)
df = get_dataset("iris").as_df()
df.drop(['Species'], inplace=True, axis=1)
X_train, X_test, y_train, y_test = train_test_split(
df.loc[:, df.columns != 'Label'], df['Label'])
svm = PcaAnomalyDetector(rank=3)
svm.fit(X_train, y_train)
scores = svm.predict(X_test)
assert_almost_equal(scores.sum().sum(),
4.181632,
decimal=7,
err_msg="Sum should be %s" % 4.181632)
OneVsRestClassifier(AveragedPerceptronBinaryClassifier(),
use_probabilities=True,
feature=['age',
'education_str.0-5yrs',
'education_str.6-11yrs',
'education_str.12+ yrs'],
label='induced'),
'OneVsRestClassifier(LinearSvmBinaryClassifier)': \
OneVsRestClassifier(LinearSvmBinaryClassifier(),
use_probabilities=True,
feature=['age',
'education_str.0-5yrs',
'education_str.6-11yrs',
'education_str.12+ yrs'],
label='induced'),
'PcaAnomalyDetector': PcaAnomalyDetector(rank=3),
'PcaTransformer': PcaTransformer(rank=2),
'PixelExtractor': Pipeline([
Loader(columns={'ImgPath': 'Path'}),
PixelExtractor(columns={'ImgPixels': 'ImgPath'}),
]),
'PrefixColumnConcatenator': PrefixColumnConcatenator(columns={'Features': 'Sepal_'}),
'Resizer': Pipeline([
Loader(columns={'ImgPath': 'Path'}),
Resizer(image_width=227, image_height=227,
columns={'ImgResize': 'ImgPath'})
]),
'SkipFilter': SkipFilter(count=5),
'SsaSpikeDetector': SsaSpikeDetector(columns=['Sepal_Length'],
seasonal_window_size=2),
'SsaChangePointDetector': SsaChangePointDetector(columns=['Sepal_Length'],
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()),
]
class TestModelSummary(unittest.TestCase):
# 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'}),
PcaAnomalyDetector(rank=3, feature=['induced', 'edu'])
])
# train, predict, and evaluate
metrics, predictions = pipeline.fit(data).test(data,
'case',
output_scores=True)
# Score
# 0 0.026155
# 1 0.026155
# 2 0.018055
# 3 0.018055
# 4 0.004043
# print predictions
print(predictions.head())
from sklearn.model_selection import train_test_split
# use 'iris' data set to create test and train data
# Sepal_Length Sepal_Width Petal_Length Petal_Width Label Species Setosa
# 0 5.1 3.5 1.4 0.2 0 setosa 1.0
# 1 4.9 3.0 1.4 0.2 0 setosa 1.0
df = get_dataset("iris").as_df()
df.drop(['Label', 'Setosa', 'Species'], axis=1, inplace=True)
X_train, X_test = train_test_split(df)
# homogenous values for labels, y-column required by scikit
y_train = np.ones(len(X_train))
svm = PcaAnomalyDetector(rank=3)
svm.fit(X_train)
# add additional non-iris data to the test data set
not_iris = pandas.DataFrame(data=dict(Sepal_Length=[2.5, 2.6],
Sepal_Width=[.75, .9],
Petal_Length=[2.5, 2.5],
Petal_Width=[.8, .7]))
merged_test = pandas.concat([X_test, not_iris], sort=False)
scores = svm.predict(merged_test)
# look at the last few observations
print(scores.tail())