def test_log_extreme_values_transformer():
st_helper = SklearnTestHelper()
levt = LogExtremeValuesTransformer(threshold_std=2.0)
x_extreme_vals = np.array(
[
[0.0, 0.0, 0.0],
[-1.0, 1.0, 1.0],
[-2.0, 2.0, 2.0],
[-3.0, 3.0, 3.0],
[-4.0, 4.0, 4.0],
[-5.0, 5.0, 5.0],
[-6.0, 6.0, 6.0],
[-7.0, 7.0, 7.0],
[-8.0, 8.0, 8.0],
[-9.0, 9.0, 9.0],
[-10.0, 10.0, 10.0],
[-1e5, 1e6, 11.0],
],
dtype=np.float32,
)
x_log_extreme_vals = np.column_stack([
log_transform(x_extreme_vals.copy()[:, 0]),
log_transform(x_extreme_vals.copy()[:, 1]),
x_extreme_vals[:, 2],
])
sklearn_out = levt.fit_transform(x_log_extreme_vals)
dshape = (relay.Any(), len(x_log_extreme_vals[0]))
_test_model_impl(st_helper, levt, dshape, x_log_extreme_vals)
def build_feature_transform():
""" Returns the model definition representing feature processing."""
# These features can be parsed as numeric.
numeric = HEADER.as_feature_indices([
'Account Length', 'VMail Message', 'Day Mins', 'Day Calls', 'Eve Mins',
'Eve Calls', 'Night Mins', 'Night Calls', 'Intl Mins', 'Intl Calls',
'CustServ Calls', 'State_AK', 'State_AL', 'State_AR', 'State_AZ',
'State_CA', 'State_CO', 'State_CT', 'State_DC', 'State_DE', 'State_FL',
'State_GA', 'State_HI', 'State_IA', 'State_ID', 'State_IL', 'State_IN',
'State_KS', 'State_KY', 'State_LA', 'State_MA', 'State_MD', 'State_ME',
'State_MI', 'State_MN', 'State_MO', 'State_MS', 'State_MT', 'State_NC',
'State_ND', 'State_NE', 'State_NH', 'State_NJ', 'State_NM', 'State_NV',
'State_NY', 'State_OH', 'State_OK', 'State_OR', 'State_PA', 'State_RI',
'State_SC', 'State_SD', 'State_TN', 'State_TX', 'State_UT', 'State_VA',
'State_VT', 'State_WA', 'State_WI', 'State_WV', 'State_WY',
'Area Code_408', 'Area Code_415', 'Area Code_510', "Int'l Plan_no",
"Int'l Plan_yes", 'VMail Plan_no', 'VMail Plan_yes'
])
numeric_processors = Pipeline(steps=[(
'featureunion',
FeatureUnion([('robust_imputer',
RobustImputer(strategy='constant', fill_values=nan)
), ('robust_missing_indicator',
RobustMissingIndicator())])
), ('logextremevaluestransformer', LogExtremeValuesTransformer())])
column_transformer = ColumnTransformer(transformers=[('numeric_processing',
numeric_processors,
numeric)])
return Pipeline(steps=[(
'column_transformer',
column_transformer), ('robustpca', RobustPCA(
n_components=338)), ('robuststandardscaler',
RobustStandardScaler())])
def test_log_extreme_value_transformer(X, X_expected):
transformer = LogExtremeValuesTransformer(threshold_std=2.0)
X_observed = transformer.fit_transform(X)
assert_array_almost_equal(X_observed, X_expected)
def test_log_extreme_value_transformer_state():
t = LogExtremeValuesTransformer(threshold_std=2.0)
X_observed = t.fit_transform(X_extreme_vals)
assert_array_almost_equal(t.nonnegative_cols_, [1, 2])
assert_array_almost_equal(X_observed, X_log_extreme_vals)
from sagemaker_sklearn_extension.impute import RobustMissingIndicator
from sagemaker_sklearn_extension.preprocessing import LogExtremeValuesTransformer
from sagemaker_sklearn_extension.preprocessing import NALabelEncoder
from sagemaker_sklearn_extension.preprocessing import QuadraticFeatures
from sagemaker_sklearn_extension.preprocessing import QuantileExtremeValuesTransformer
from sagemaker_sklearn_extension.preprocessing import RemoveConstantColumnsTransformer
from sagemaker_sklearn_extension.preprocessing import RobustLabelEncoder
from sagemaker_sklearn_extension.preprocessing import RobustStandardScaler
from sagemaker_sklearn_extension.preprocessing import ThresholdOneHotEncoder
@pytest.mark.parametrize(
"Estimator",
[
DateTimeVectorizer(),
LogExtremeValuesTransformer(),
MultiColumnTfidfVectorizer(),
NALabelEncoder(),
QuadraticFeatures(),
QuantileExtremeValuesTransformer(),
RobustImputer(),
RemoveConstantColumnsTransformer(),
RobustLabelEncoder(),
RobustMissingIndicator(),
RobustStandardScaler(),
ThresholdOneHotEncoder(),
],
)
def test_all_estimators(Estimator):
return check_estimator(Estimator)