def test_robust_imputer_categorical_custom_function():
robust_imputer = RobustImputer(
dtype=np.dtype("O"), strategy="constant", fill_values="not hot dog", mask_function=lambda x: x == "hot dog"
)
robust_imputer.fit(X_impute_categorical)
X_observed = robust_imputer.transform(X_impute_categorical)
assert_array_equal(X_observed, X_imputed_categorical)
def test_robust_imputer():
st_helper = SklearnTestHelper()
data = np.array(
[[4, 5, np.nan, 7], [0, np.nan, 2, 3], [8, 9, 10, 11], [np.inf, 13, 14, 15]],
dtype=np.float32,
)
ri = RobustImputer(dtype=None, strategy="constant", fill_values=np.nan, mask_function=None)
ri.fit(data)
dshape = (relay.Any(), len(data[0]))
_test_model_impl(st_helper, ri, dshape, data)
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=[('robustimputer', RobustImputer())])
column_transformer = ColumnTransformer(transformers=[('numeric_processing',
numeric_processors,
numeric)])
return Pipeline(steps=[(
'column_transformer',
column_transformer), ('robustpca', RobustPCA(
n_components=117)), ('robuststandardscaler',
RobustStandardScaler())])
def test_pipeline():
st_helper = SklearnTestHelper()
pipe = Pipeline([("imputer", RobustImputer()), ("scaler", RobustStandardScaler())])
data = np.array([[0.0, 1.0, 3], [2.0, 2.0, 5]], dtype=np.float32)
pipe.fit(data)
dshape = (relay.Any(), len(data[0]))
_test_model_impl(st_helper, pipe, dshape, data)
def fit(self, y):
"""Fit the encoder on y.
Parameters
----------
y : {array-like}, shape (n_samples,)
Input column, where `n_samples` is the number of samples.
Returns
-------
self : NALabelEncoder
"""
self.model_ = RobustImputer(strategy="constant", fill_values=np.nan, mask_function=self.mask_function)
y = y.reshape(-1, 1)
self.model_.fit(X=y)
return self
def build_feature_transform():
""" Returns the model definition representing feature processing."""
# These features can be parsed as numeric.
numeric = HEADER.as_feature_indices([
'age', 'duration', 'campaign', 'pdays', 'previous', 'emp.var.rate',
'cons.price.idx', 'cons.conf.idx', 'euribor3m', 'nr.employed'
])
# These features contain a relatively small number of unique items.
categorical = HEADER.as_feature_indices([
'job', 'marital', 'education', 'default', 'housing', 'loan', 'contact',
'month', 'day_of_week', 'poutcome'
])
numeric_processors = Pipeline(steps=[('robustimputer', RobustImputer())])
categorical_processors = Pipeline(steps=[('thresholdonehotencoder',
ThresholdOneHotEncoder(
threshold=11))])
column_transformer = ColumnTransformer(
transformers=[('numeric_processing', numeric_processors, numeric),
('categorical_processing', categorical_processors,
categorical)])
return Pipeline(steps=[(
'column_transformer',
column_transformer), ('robustpca', RobustPCA(
n_components=98)), ('robuststandardscaler',
RobustStandardScaler())])
def build_feature_transform():
""" Returns the model definition representing feature processing."""
# These features can be parsed as numeric.
numeric = HEADER.as_feature_indices([
'Unnamed: 0', 'V1', 'V2', 'V3', 'V4', 'V5', 'V6', 'V7', 'V8', 'V9',
'V10', 'V11', 'V12', 'V13', 'V14', 'V15', 'V16', 'V17', 'V18', 'V19',
'V20', 'V21', 'V22', 'V23', 'V24', 'V25', 'V26', 'V27', 'V28', 'amt'
])
# These features contain a relatively small number of unique items.
categorical = HEADER.as_feature_indices(['amt'])
numeric_processors = Pipeline(
steps=[('robustimputer',
RobustImputer(strategy='constant', fill_values=nan))])
categorical_processors = Pipeline(steps=[('thresholdonehotencoder',
ThresholdOneHotEncoder(
threshold=635))])
column_transformer = ColumnTransformer(
transformers=[('numeric_processing', numeric_processors, numeric),
('categorical_processing', categorical_processors,
categorical)])
return Pipeline(steps=[(
'column_transformer',
column_transformer), ('robuststandardscaler', RobustStandardScaler())])
def test_automl():
st_helper = SklearnTestHelper()
data = np.array(
[[4, 5, np.nan, 7], [0, np.nan, 2, 3], [8, 9, 10, 11],
[np.nan, 13, 14, 15]],
dtype=np.float32,
)
pipeline = Pipeline(
steps=[("robustimputer",
RobustImputer(fill_values=np.nan, strategy="constant"))])
ct = ColumnTransformer(transformers=[("numeric_processing", pipeline,
[0, 1, 2, 3])])
ct.fit(data)
pipeline = Pipeline(steps=[("column_transformer", ct)])
header = Header(column_names=["x1", "x2", "x3", "class"],
target_column_name="class")
na = NALabelEncoder()
na.fit(data)
automl_transformer = AutoMLTransformer(header, pipeline, na)
dshape = (relay.Any(), relay.Any())
_test_model_impl(st_helper, automl_transformer, dshape, data, auto_ml=True)
def build_feature_transform():
""" Returns the model definition representing feature processing."""
# These features can be parsed as numeric.
numeric = HEADER.as_feature_indices(
[
'Unnamed: 0', 'V1', 'V2', 'V3', 'V4', 'V5', 'V6', 'V7', 'V8', 'V9',
'V10', 'V11', 'V12', 'V13', 'V14', 'V15', 'V16', 'V17', 'V18',
'V19', 'V20', 'V21', 'V22', 'V23', 'V24', 'V25', 'V26', 'V27',
'V28', 'amt'
]
)
numeric_processors = Pipeline(
steps=[
(
'robustimputer',
RobustImputer(strategy='constant', fill_values=nan)
)
]
)
column_transformer = ColumnTransformer(
transformers=[('numeric_processing', numeric_processors, numeric)]
)
return Pipeline(
steps=[
('column_transformer', column_transformer
), ('robuststandardscaler', RobustStandardScaler())
]
)
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'
])
# These features contain a relatively small number of unique items.
categorical = HEADER.as_feature_indices([
'Account Length', 'VMail Message', 'Day Calls', 'Eve Calls',
'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=[('robustimputer',
RobustImputer(strategy='constant', fill_values=nan))])
categorical_processors = Pipeline(steps=[('thresholdonehotencoder',
ThresholdOneHotEncoder(
threshold=6))])
column_transformer = ColumnTransformer(
transformers=[('numeric_processing', numeric_processors, numeric),
('categorical_processing', categorical_processors,
categorical)])
return Pipeline(steps=[(
'column_transformer',
column_transformer), ('robuststandardscaler', RobustStandardScaler())])
def build_feature_transform():
""" Returns the model definition representing feature processing."""
# These features can be parsed as numeric.
numeric = HEADER.as_feature_indices([
'Unnamed: 0', 'V1', 'V2', 'V3', 'V4', 'V5', 'V6', 'V7', 'V8', 'V9',
'V10', 'V11', 'V12', 'V13', 'V14', 'V15', 'V16', 'V17', 'V18', 'V19',
'V20', 'V21', 'V22', 'V23', 'V24', 'V25', 'V26', 'V27', 'V28', 'amt'
])
# These features contain a relatively small number of unique items.
categorical = HEADER.as_feature_indices(['amt'])
numeric_processors = Pipeline(steps=[(
'featureunion',
FeatureUnion([('robust_imputer', RobustImputer()
), ('robust_missing_indicator',
RobustMissingIndicator())])
), ('quantileextremevaluestransformer',
QuantileExtremeValuesTransformer())])
categorical_processors = Pipeline(steps=[('thresholdonehotencoder',
ThresholdOneHotEncoder(
threshold=31))])
column_transformer = ColumnTransformer(
transformers=[('numeric_processing', numeric_processors, numeric),
('categorical_processing', categorical_processors,
categorical)])
return Pipeline(steps=[(
'column_transformer',
column_transformer), ('robustpca', RobustPCA(
n_components=147)), ('robuststandardscaler',
RobustStandardScaler())])
def test_automl_transformer_regression():
"""Tests that rows in a regression dataset where the target column is not a finite numeric are imputed"""
data = read_csv_data(source="test/data/csv/regression_na_labels.csv")
X = data[:, :3]
y = data[:, 3]
header = Header(column_names=["x1", "x2", "x3", "class"],
target_column_name="class")
automl_transformer = AutoMLTransformer(
header=header,
feature_transformer=RobustImputer(strategy="constant", fill_values=0),
target_transformer=NALabelEncoder(),
)
model = automl_transformer.fit(X, y)
X_transformed = model.transform(X)
assert X_transformed.shape == X.shape
Xy = np.concatenate((X, y.reshape(-1, 1)), axis=1)
Xy_transformed = model.transform(Xy)
assert Xy_transformed.shape == (3, 4)
assert np.array_equal(
Xy_transformed,
np.array([[1.1, 1.0, 2.0, 3.0], [2.2, 4.0, 0.0, 5.0],
[3.3, 12.0, 13.0, 14.0]]))
def test_robust_imputer_fill_values_dim_error():
with pytest.raises(ValueError, match=fill_values_error_msg):
robust_imputer = RobustImputer(strategy="constant", fill_values=np.zeros(5))
robust_imputer.fit(X_impute)
def build_feature_transform():
""" Returns the model definition representing feature processing."""
# These features can be parsed as numeric.
numeric = HEADER.as_feature_indices(
[
'tBodyAcc.mean.X', 'tBodyAcc.mean.Y', 'tBodyAcc.mean.Z',
'tBodyAcc.std.X', 'tBodyAcc.std.Y', 'tBodyAcc.std.Z',
'tBodyAcc.mad.X', 'tBodyAcc.mad.Y', 'tBodyAcc.mad.Z',
'tBodyAcc.max.X', 'tBodyAcc.max.Y', 'tBodyAcc.max.Z',
'tBodyAcc.min.X', 'tBodyAcc.min.Y', 'tBodyAcc.min.Z',
'tBodyAcc.sma', 'tBodyAcc.energy.X', 'tBodyAcc.energy.Y',
'tBodyAcc.energy.Z', 'tBodyAcc.iqr.X', 'tBodyAcc.iqr.Y',
'tBodyAcc.iqr.Z', 'tBodyAcc.entropy.X', 'tBodyAcc.entropy.Y',
'tBodyAcc.entropy.Z', 'tBodyAcc.arCoeff.X.1',
'tBodyAcc.arCoeff.X.2', 'tBodyAcc.arCoeff.X.3',
'tBodyAcc.arCoeff.X.4', 'tBodyAcc.arCoeff.Y.1',
'tBodyAcc.arCoeff.Y.2', 'tBodyAcc.arCoeff.Y.3',
'tBodyAcc.arCoeff.Y.4', 'tBodyAcc.arCoeff.Z.1',
'tBodyAcc.arCoeff.Z.2', 'tBodyAcc.arCoeff.Z.3',
'tBodyAcc.arCoeff.Z.4', 'tBodyAcc.correlation.X.Y',
'tBodyAcc.correlation.X.Z', 'tBodyAcc.correlation.Y.Z',
'tGravityAcc.mean.X', 'tGravityAcc.mean.Y', 'tGravityAcc.mean.Z',
'tGravityAcc.std.X', 'tGravityAcc.std.Y', 'tGravityAcc.std.Z',
'tGravityAcc.mad.X', 'tGravityAcc.mad.Y', 'tGravityAcc.mad.Z',
'tGravityAcc.max.X', 'tGravityAcc.max.Y', 'tGravityAcc.max.Z',
'tGravityAcc.min.X', 'tGravityAcc.min.Y', 'tGravityAcc.min.Z',
'tGravityAcc.sma', 'tGravityAcc.energy.X', 'tGravityAcc.energy.Y',
'tGravityAcc.energy.Z', 'tGravityAcc.iqr.X', 'tGravityAcc.iqr.Y',
'tGravityAcc.iqr.Z', 'tGravityAcc.entropy.X',
'tGravityAcc.entropy.Y', 'tGravityAcc.entropy.Z',
'tGravityAcc.arCoeff.X.1', 'tGravityAcc.arCoeff.X.2',
'tGravityAcc.arCoeff.X.3', 'tGravityAcc.arCoeff.X.4',
'tGravityAcc.arCoeff.Y.1', 'tGravityAcc.arCoeff.Y.2',
'tGravityAcc.arCoeff.Y.3', 'tGravityAcc.arCoeff.Y.4',
'tGravityAcc.arCoeff.Z.1', 'tGravityAcc.arCoeff.Z.2',
'tGravityAcc.arCoeff.Z.3', 'tGravityAcc.arCoeff.Z.4',
'tGravityAcc.correlation.X.Y', 'tGravityAcc.correlation.X.Z',
'tGravityAcc.correlation.Y.Z', 'tBodyAccJerk.mean.X',
'tBodyAccJerk.mean.Y', 'tBodyAccJerk.mean.Z', 'tBodyAccJerk.std.X',
'tBodyAccJerk.std.Y', 'tBodyAccJerk.std.Z', 'tBodyAccJerk.mad.X',
'tBodyAccJerk.mad.Y', 'tBodyAccJerk.mad.Z', 'tBodyAccJerk.max.X',
'tBodyAccJerk.max.Y', 'tBodyAccJerk.max.Z', 'tBodyAccJerk.min.X',
'tBodyAccJerk.min.Y', 'tBodyAccJerk.min.Z', 'tBodyAccJerk.sma',
'tBodyAccJerk.energy.X', 'tBodyAccJerk.energy.Y',
'tBodyAccJerk.energy.Z', 'tBodyAccJerk.iqr.X', 'tBodyAccJerk.iqr.Y',
'tBodyAccJerk.iqr.Z', 'tBodyAccJerk.entropy.X',
'tBodyAccJerk.entropy.Y', 'tBodyAccJerk.entropy.Z',
'tBodyAccJerk.arCoeff.X.1', 'tBodyAccJerk.arCoeff.X.2',
'tBodyAccJerk.arCoeff.X.3', 'tBodyAccJerk.arCoeff.X.4',
'tBodyAccJerk.arCoeff.Y.1', 'tBodyAccJerk.arCoeff.Y.2',
'tBodyAccJerk.arCoeff.Y.3', 'tBodyAccJerk.arCoeff.Y.4',
'tBodyAccJerk.arCoeff.Z.1', 'tBodyAccJerk.arCoeff.Z.2',
'tBodyAccJerk.arCoeff.Z.3', 'tBodyAccJerk.arCoeff.Z.4',
'tBodyAccJerk.correlation.X.Y', 'tBodyAccJerk.correlation.X.Z',
'tBodyAccJerk.correlation.Y.Z', 'tBodyGyro.mean.X',
'tBodyGyro.mean.Y', 'tBodyGyro.mean.Z', 'tBodyGyro.std.X',
'tBodyGyro.std.Y', 'tBodyGyro.std.Z', 'tBodyGyro.mad.X',
'tBodyGyro.mad.Y', 'tBodyGyro.mad.Z', 'tBodyGyro.max.X',
'tBodyGyro.max.Y', 'tBodyGyro.max.Z', 'tBodyGyro.min.X',
'tBodyGyro.min.Y', 'tBodyGyro.min.Z', 'tBodyGyro.sma',
'tBodyGyro.energy.X', 'tBodyGyro.energy.Y', 'tBodyGyro.energy.Z',
'tBodyGyro.iqr.X', 'tBodyGyro.iqr.Y', 'tBodyGyro.iqr.Z',
'tBodyGyro.entropy.X', 'tBodyGyro.entropy.Y', 'tBodyGyro.entropy.Z',
'tBodyGyro.arCoeff.X.1', 'tBodyGyro.arCoeff.X.2',
'tBodyGyro.arCoeff.X.3', 'tBodyGyro.arCoeff.X.4',
'tBodyGyro.arCoeff.Y.1', 'tBodyGyro.arCoeff.Y.2',
'tBodyGyro.arCoeff.Y.3', 'tBodyGyro.arCoeff.Y.4',
'tBodyGyro.arCoeff.Z.1', 'tBodyGyro.arCoeff.Z.2',
'tBodyGyro.arCoeff.Z.3', 'tBodyGyro.arCoeff.Z.4',
'tBodyGyro.correlation.X.Y', 'tBodyGyro.correlation.X.Z',
'tBodyGyro.correlation.Y.Z', 'tBodyGyroJerk.mean.X',
'tBodyGyroJerk.mean.Y', 'tBodyGyroJerk.mean.Z',
'tBodyGyroJerk.std.X', 'tBodyGyroJerk.std.Y', 'tBodyGyroJerk.std.Z',
'tBodyGyroJerk.mad.X', 'tBodyGyroJerk.mad.Y', 'tBodyGyroJerk.mad.Z',
'tBodyGyroJerk.max.X', 'tBodyGyroJerk.max.Y', 'tBodyGyroJerk.max.Z',
'tBodyGyroJerk.min.X', 'tBodyGyroJerk.min.Y', 'tBodyGyroJerk.min.Z',
'tBodyGyroJerk.sma', 'tBodyGyroJerk.energy.X',
'tBodyGyroJerk.energy.Y', 'tBodyGyroJerk.energy.Z',
'tBodyGyroJerk.iqr.X', 'tBodyGyroJerk.iqr.Y', 'tBodyGyroJerk.iqr.Z',
'tBodyGyroJerk.entropy.X', 'tBodyGyroJerk.entropy.Y',
'tBodyGyroJerk.entropy.Z', 'tBodyGyroJerk.arCoeff.X.1',
'tBodyGyroJerk.arCoeff.X.2', 'tBodyGyroJerk.arCoeff.X.3',
'tBodyGyroJerk.arCoeff.X.4', 'tBodyGyroJerk.arCoeff.Y.1',
'tBodyGyroJerk.arCoeff.Y.2', 'tBodyGyroJerk.arCoeff.Y.3',
'tBodyGyroJerk.arCoeff.Y.4', 'tBodyGyroJerk.arCoeff.Z.1',
'tBodyGyroJerk.arCoeff.Z.2', 'tBodyGyroJerk.arCoeff.Z.3',
'tBodyGyroJerk.arCoeff.Z.4', 'tBodyGyroJerk.correlation.X.Y',
'tBodyGyroJerk.correlation.X.Z', 'tBodyGyroJerk.correlation.Y.Z',
'tBodyAccMag.mean', 'tBodyAccMag.std', 'tBodyAccMag.mad',
'tBodyAccMag.max', 'tBodyAccMag.min', 'tBodyAccMag.sma',
'tBodyAccMag.energy', 'tBodyAccMag.iqr', 'tBodyAccMag.entropy',
'tBodyAccMag.arCoeff1', 'tBodyAccMag.arCoeff2',
'tBodyAccMag.arCoeff3', 'tBodyAccMag.arCoeff4',
'tGravityAccMag.mean', 'tGravityAccMag.std', 'tGravityAccMag.mad',
'tGravityAccMag.max', 'tGravityAccMag.min', 'tGravityAccMag.sma',
'tGravityAccMag.energy', 'tGravityAccMag.iqr',
'tGravityAccMag.entropy', 'tGravityAccMag.arCoeff1',
'tGravityAccMag.arCoeff2', 'tGravityAccMag.arCoeff3',
'tGravityAccMag.arCoeff4', 'tBodyAccJerkMag.mean',
'tBodyAccJerkMag.std', 'tBodyAccJerkMag.mad', 'tBodyAccJerkMag.max',
'tBodyAccJerkMag.min', 'tBodyAccJerkMag.sma',
'tBodyAccJerkMag.energy', 'tBodyAccJerkMag.iqr',
'tBodyAccJerkMag.entropy', 'tBodyAccJerkMag.arCoeff1',
'tBodyAccJerkMag.arCoeff2', 'tBodyAccJerkMag.arCoeff3',
'tBodyAccJerkMag.arCoeff4', 'tBodyGyroMag.mean', 'tBodyGyroMag.std',
'tBodyGyroMag.mad', 'tBodyGyroMag.max', 'tBodyGyroMag.min',
'tBodyGyroMag.sma', 'tBodyGyroMag.energy', 'tBodyGyroMag.iqr',
'tBodyGyroMag.entropy', 'tBodyGyroMag.arCoeff1',
'tBodyGyroMag.arCoeff2', 'tBodyGyroMag.arCoeff3',
'tBodyGyroMag.arCoeff4', 'tBodyGyroJerkMag.mean',
'tBodyGyroJerkMag.std', 'tBodyGyroJerkMag.mad',
'tBodyGyroJerkMag.max', 'tBodyGyroJerkMag.min',
'tBodyGyroJerkMag.sma', 'tBodyGyroJerkMag.energy',
'tBodyGyroJerkMag.iqr', 'tBodyGyroJerkMag.entropy',
'tBodyGyroJerkMag.arCoeff1', 'tBodyGyroJerkMag.arCoeff2',
'tBodyGyroJerkMag.arCoeff3', 'tBodyGyroJerkMag.arCoeff4',
'fBodyAcc.mean.X', 'fBodyAcc.mean.Y', 'fBodyAcc.mean.Z',
'fBodyAcc.std.X', 'fBodyAcc.std.Y', 'fBodyAcc.std.Z',
'fBodyAcc.mad.X', 'fBodyAcc.mad.Y', 'fBodyAcc.mad.Z',
'fBodyAcc.max.X', 'fBodyAcc.max.Y', 'fBodyAcc.max.Z',
'fBodyAcc.min.X', 'fBodyAcc.min.Y', 'fBodyAcc.min.Z',
'fBodyAcc.sma', 'fBodyAcc.energy.X', 'fBodyAcc.energy.Y',
'fBodyAcc.energy.Z', 'fBodyAcc.iqr.X', 'fBodyAcc.iqr.Y',
'fBodyAcc.iqr.Z', 'fBodyAcc.entropy.X', 'fBodyAcc.entropy.Y',
'fBodyAcc.entropy.Z', 'fBodyAcc.maxInds.X', 'fBodyAcc.maxInds.Y',
'fBodyAcc.maxInds.Z', 'fBodyAcc.meanFreq.X', 'fBodyAcc.meanFreq.Y',
'fBodyAcc.meanFreq.Z', 'fBodyAcc.skewness.X', 'fBodyAcc.kurtosis.X',
'fBodyAcc.skewness.Y', 'fBodyAcc.kurtosis.Y', 'fBodyAcc.skewness.Z',
'fBodyAcc.kurtosis.Z', 'fBodyAcc.bandsEnergy.1.8',
'fBodyAcc.bandsEnergy.9.16', 'fBodyAcc.bandsEnergy.17.24',
'fBodyAcc.bandsEnergy.25.32', 'fBodyAcc.bandsEnergy.33.40',
'fBodyAcc.bandsEnergy.41.48', 'fBodyAcc.bandsEnergy.49.56',
'fBodyAcc.bandsEnergy.57.64', 'fBodyAcc.bandsEnergy.1.16',
'fBodyAcc.bandsEnergy.17.32', 'fBodyAcc.bandsEnergy.33.48',
'fBodyAcc.bandsEnergy.49.64', 'fBodyAcc.bandsEnergy.1.24',
'fBodyAcc.bandsEnergy.25.48', 'fBodyAcc.bandsEnergy.1.8.1',
'fBodyAcc.bandsEnergy.9.16.1', 'fBodyAcc.bandsEnergy.17.24.1',
'fBodyAcc.bandsEnergy.25.32.1', 'fBodyAcc.bandsEnergy.33.40.1',
'fBodyAcc.bandsEnergy.41.48.1', 'fBodyAcc.bandsEnergy.49.56.1',
'fBodyAcc.bandsEnergy.57.64.1', 'fBodyAcc.bandsEnergy.1.16.1',
'fBodyAcc.bandsEnergy.17.32.1', 'fBodyAcc.bandsEnergy.33.48.1',
'fBodyAcc.bandsEnergy.49.64.1', 'fBodyAcc.bandsEnergy.1.24.1',
'fBodyAcc.bandsEnergy.25.48.1', 'fBodyAcc.bandsEnergy.1.8.2',
'fBodyAcc.bandsEnergy.9.16.2', 'fBodyAcc.bandsEnergy.17.24.2',
'fBodyAcc.bandsEnergy.25.32.2', 'fBodyAcc.bandsEnergy.33.40.2',
'fBodyAcc.bandsEnergy.41.48.2', 'fBodyAcc.bandsEnergy.49.56.2',
'fBodyAcc.bandsEnergy.57.64.2', 'fBodyAcc.bandsEnergy.1.16.2',
'fBodyAcc.bandsEnergy.17.32.2', 'fBodyAcc.bandsEnergy.33.48.2',
'fBodyAcc.bandsEnergy.49.64.2', 'fBodyAcc.bandsEnergy.1.24.2',
'fBodyAcc.bandsEnergy.25.48.2', 'fBodyAccJerk.mean.X',
'fBodyAccJerk.mean.Y', 'fBodyAccJerk.mean.Z', 'fBodyAccJerk.std.X',
'fBodyAccJerk.std.Y', 'fBodyAccJerk.std.Z', 'fBodyAccJerk.mad.X',
'fBodyAccJerk.mad.Y', 'fBodyAccJerk.mad.Z', 'fBodyAccJerk.max.X',
'fBodyAccJerk.max.Y', 'fBodyAccJerk.max.Z', 'fBodyAccJerk.min.X',
'fBodyAccJerk.min.Y', 'fBodyAccJerk.min.Z', 'fBodyAccJerk.sma',
'fBodyAccJerk.energy.X', 'fBodyAccJerk.energy.Y',
'fBodyAccJerk.energy.Z', 'fBodyAccJerk.iqr.X', 'fBodyAccJerk.iqr.Y',
'fBodyAccJerk.iqr.Z', 'fBodyAccJerk.entropy.X',
'fBodyAccJerk.entropy.Y', 'fBodyAccJerk.entropy.Z',
'fBodyAccJerk.maxInds.X', 'fBodyAccJerk.maxInds.Y',
'fBodyAccJerk.maxInds.Z', 'fBodyAccJerk.meanFreq.X',
'fBodyAccJerk.meanFreq.Y', 'fBodyAccJerk.meanFreq.Z',
'fBodyAccJerk.skewness.X', 'fBodyAccJerk.kurtosis.X',
'fBodyAccJerk.skewness.Y', 'fBodyAccJerk.kurtosis.Y',
'fBodyAccJerk.skewness.Z', 'fBodyAccJerk.kurtosis.Z',
'fBodyAccJerk.bandsEnergy.1.8', 'fBodyAccJerk.bandsEnergy.9.16',
'fBodyAccJerk.bandsEnergy.17.24', 'fBodyAccJerk.bandsEnergy.25.32',
'fBodyAccJerk.bandsEnergy.33.40', 'fBodyAccJerk.bandsEnergy.41.48',
'fBodyAccJerk.bandsEnergy.49.56', 'fBodyAccJerk.bandsEnergy.57.64',
'fBodyAccJerk.bandsEnergy.1.16', 'fBodyAccJerk.bandsEnergy.17.32',
'fBodyAccJerk.bandsEnergy.33.48', 'fBodyAccJerk.bandsEnergy.49.64',
'fBodyAccJerk.bandsEnergy.1.24', 'fBodyAccJerk.bandsEnergy.25.48',
'fBodyAccJerk.bandsEnergy.1.8.1', 'fBodyAccJerk.bandsEnergy.9.16.1',
'fBodyAccJerk.bandsEnergy.17.24.1',
'fBodyAccJerk.bandsEnergy.25.32.1',
'fBodyAccJerk.bandsEnergy.33.40.1',
'fBodyAccJerk.bandsEnergy.41.48.1',
'fBodyAccJerk.bandsEnergy.49.56.1',
'fBodyAccJerk.bandsEnergy.57.64.1',
'fBodyAccJerk.bandsEnergy.1.16.1',
'fBodyAccJerk.bandsEnergy.17.32.1',
'fBodyAccJerk.bandsEnergy.33.48.1',
'fBodyAccJerk.bandsEnergy.49.64.1',
'fBodyAccJerk.bandsEnergy.1.24.1',
'fBodyAccJerk.bandsEnergy.25.48.1',
'fBodyAccJerk.bandsEnergy.1.8.2', 'fBodyAccJerk.bandsEnergy.9.16.2',
'fBodyAccJerk.bandsEnergy.17.24.2',
'fBodyAccJerk.bandsEnergy.25.32.2',
'fBodyAccJerk.bandsEnergy.33.40.2',
'fBodyAccJerk.bandsEnergy.41.48.2',
'fBodyAccJerk.bandsEnergy.49.56.2',
'fBodyAccJerk.bandsEnergy.57.64.2',
'fBodyAccJerk.bandsEnergy.1.16.2',
'fBodyAccJerk.bandsEnergy.17.32.2',
'fBodyAccJerk.bandsEnergy.33.48.2',
'fBodyAccJerk.bandsEnergy.49.64.2',
'fBodyAccJerk.bandsEnergy.1.24.2',
'fBodyAccJerk.bandsEnergy.25.48.2', 'fBodyGyro.mean.X',
'fBodyGyro.mean.Y', 'fBodyGyro.mean.Z', 'fBodyGyro.std.X',
'fBodyGyro.std.Y', 'fBodyGyro.std.Z', 'fBodyGyro.mad.X',
'fBodyGyro.mad.Y', 'fBodyGyro.mad.Z', 'fBodyGyro.max.X',
'fBodyGyro.max.Y', 'fBodyGyro.max.Z', 'fBodyGyro.min.X',
'fBodyGyro.min.Y', 'fBodyGyro.min.Z', 'fBodyGyro.sma',
'fBodyGyro.energy.X', 'fBodyGyro.energy.Y', 'fBodyGyro.energy.Z',
'fBodyGyro.iqr.X', 'fBodyGyro.iqr.Y', 'fBodyGyro.iqr.Z',
'fBodyGyro.entropy.X', 'fBodyGyro.entropy.Y', 'fBodyGyro.entropy.Z',
'fBodyGyro.maxInds.X', 'fBodyGyro.maxInds.Y', 'fBodyGyro.maxInds.Z',
'fBodyGyro.meanFreq.X', 'fBodyGyro.meanFreq.Y',
'fBodyGyro.meanFreq.Z', 'fBodyGyro.skewness.X',
'fBodyGyro.kurtosis.X', 'fBodyGyro.skewness.Y',
'fBodyGyro.kurtosis.Y', 'fBodyGyro.skewness.Z',
'fBodyGyro.kurtosis.Z', 'fBodyGyro.bandsEnergy.1.8',
'fBodyGyro.bandsEnergy.9.16', 'fBodyGyro.bandsEnergy.17.24',
'fBodyGyro.bandsEnergy.25.32', 'fBodyGyro.bandsEnergy.33.40',
'fBodyGyro.bandsEnergy.41.48', 'fBodyGyro.bandsEnergy.49.56',
'fBodyGyro.bandsEnergy.57.64', 'fBodyGyro.bandsEnergy.1.16',
'fBodyGyro.bandsEnergy.17.32', 'fBodyGyro.bandsEnergy.33.48',
'fBodyGyro.bandsEnergy.49.64', 'fBodyGyro.bandsEnergy.1.24',
'fBodyGyro.bandsEnergy.25.48', 'fBodyGyro.bandsEnergy.1.8.1',
'fBodyGyro.bandsEnergy.9.16.1', 'fBodyGyro.bandsEnergy.17.24.1',
'fBodyGyro.bandsEnergy.25.32.1', 'fBodyGyro.bandsEnergy.33.40.1',
'fBodyGyro.bandsEnergy.41.48.1', 'fBodyGyro.bandsEnergy.49.56.1',
'fBodyGyro.bandsEnergy.57.64.1', 'fBodyGyro.bandsEnergy.1.16.1',
'fBodyGyro.bandsEnergy.17.32.1', 'fBodyGyro.bandsEnergy.33.48.1',
'fBodyGyro.bandsEnergy.49.64.1', 'fBodyGyro.bandsEnergy.1.24.1',
'fBodyGyro.bandsEnergy.25.48.1', 'fBodyGyro.bandsEnergy.1.8.2',
'fBodyGyro.bandsEnergy.9.16.2', 'fBodyGyro.bandsEnergy.17.24.2',
'fBodyGyro.bandsEnergy.25.32.2', 'fBodyGyro.bandsEnergy.33.40.2',
'fBodyGyro.bandsEnergy.41.48.2', 'fBodyGyro.bandsEnergy.49.56.2',
'fBodyGyro.bandsEnergy.57.64.2', 'fBodyGyro.bandsEnergy.1.16.2',
'fBodyGyro.bandsEnergy.17.32.2', 'fBodyGyro.bandsEnergy.33.48.2',
'fBodyGyro.bandsEnergy.49.64.2', 'fBodyGyro.bandsEnergy.1.24.2',
'fBodyGyro.bandsEnergy.25.48.2', 'fBodyAccMag.mean',
'fBodyAccMag.std', 'fBodyAccMag.mad', 'fBodyAccMag.max',
'fBodyAccMag.min', 'fBodyAccMag.sma', 'fBodyAccMag.energy',
'fBodyAccMag.iqr', 'fBodyAccMag.entropy', 'fBodyAccMag.maxInds',
'fBodyAccMag.meanFreq', 'fBodyAccMag.skewness',
'fBodyAccMag.kurtosis', 'fBodyBodyAccJerkMag.mean',
'fBodyBodyAccJerkMag.std', 'fBodyBodyAccJerkMag.mad',
'fBodyBodyAccJerkMag.max', 'fBodyBodyAccJerkMag.min',
'fBodyBodyAccJerkMag.sma', 'fBodyBodyAccJerkMag.energy',
'fBodyBodyAccJerkMag.iqr', 'fBodyBodyAccJerkMag.entropy',
'fBodyBodyAccJerkMag.maxInds', 'fBodyBodyAccJerkMag.meanFreq',
'fBodyBodyAccJerkMag.skewness', 'fBodyBodyAccJerkMag.kurtosis',
'fBodyBodyGyroMag.mean', 'fBodyBodyGyroMag.std',
'fBodyBodyGyroMag.mad', 'fBodyBodyGyroMag.max',
'fBodyBodyGyroMag.min', 'fBodyBodyGyroMag.sma',
'fBodyBodyGyroMag.energy', 'fBodyBodyGyroMag.iqr',
'fBodyBodyGyroMag.entropy', 'fBodyBodyGyroMag.maxInds',
'fBodyBodyGyroMag.meanFreq', 'fBodyBodyGyroMag.skewness',
'fBodyBodyGyroMag.kurtosis', 'fBodyBodyGyroJerkMag.mean',
'fBodyBodyGyroJerkMag.std', 'fBodyBodyGyroJerkMag.mad',
'fBodyBodyGyroJerkMag.max', 'fBodyBodyGyroJerkMag.min',
'fBodyBodyGyroJerkMag.sma', 'fBodyBodyGyroJerkMag.energy',
'fBodyBodyGyroJerkMag.iqr', 'fBodyBodyGyroJerkMag.entropy',
'fBodyBodyGyroJerkMag.maxInds', 'fBodyBodyGyroJerkMag.meanFreq',
'fBodyBodyGyroJerkMag.skewness', 'fBodyBodyGyroJerkMag.kurtosis',
'angle.tBodyAccMean.gravity', 'angle.tBodyAccJerkMean.gravityMean',
'angle.tBodyGyroMean.gravityMean',
'angle.tBodyGyroJerkMean.gravityMean', 'angle.X.gravityMean',
'angle.Y.gravityMean', 'angle.Z.gravityMean'
]
)
numeric_processors = Pipeline(
steps=[
(
'robustimputer',
RobustImputer(strategy='constant', fill_values=nan)
)
]
)
column_transformer = ColumnTransformer(
transformers=[('numeric_processing', numeric_processors, numeric)]
)
return Pipeline(
steps=[
('column_transformer', column_transformer
), ('robuststandardscaler', RobustStandardScaler())
]
)
def test_robust_imputer_transform_dim_error():
with pytest.raises(ValueError, match=transform_error_msg):
robust_imputer = RobustImputer()
robust_imputer.fit(X_impute)
robust_imputer.transform(np.zeros((3, 4)))
def build_feature_transform():
""" Returns the model definition representing feature processing."""
# These features can be parsed as numeric.
numeric = HEADER.as_feature_indices([
'tBodyAcc.mean.X', 'tBodyAcc.mean.Y', 'tBodyAcc.mean.Z',
'tBodyAcc.std.X', 'tBodyAcc.std.Y', 'tBodyAcc.std.Z', 'tBodyAcc.mad.X',
'tBodyAcc.mad.Y', 'tBodyAcc.mad.Z', 'tBodyAcc.max.X', 'tBodyAcc.max.Y',
'tBodyAcc.max.Z', 'tBodyAcc.min.X', 'tBodyAcc.min.Y', 'tBodyAcc.min.Z',
'tBodyAcc.sma', 'tBodyAcc.energy.X', 'tBodyAcc.energy.Y',
'tBodyAcc.energy.Z', 'tBodyAcc.iqr.X', 'tBodyAcc.iqr.Y',
'tBodyAcc.iqr.Z', 'tBodyAcc.entropy.X', 'tBodyAcc.entropy.Y',
'tBodyAcc.entropy.Z', 'tBodyAcc.arCoeff.X.1', 'tBodyAcc.arCoeff.X.2',
'tBodyAcc.arCoeff.X.3', 'tBodyAcc.arCoeff.X.4', 'tBodyAcc.arCoeff.Y.1',
'tBodyAcc.arCoeff.Y.2', 'tBodyAcc.arCoeff.Y.3', 'tBodyAcc.arCoeff.Y.4',
'tBodyAcc.arCoeff.Z.1', 'tBodyAcc.arCoeff.Z.2', 'tBodyAcc.arCoeff.Z.3',
'tBodyAcc.arCoeff.Z.4', 'tBodyAcc.correlation.X.Y',
'tBodyAcc.correlation.X.Z', 'tBodyAcc.correlation.Y.Z',
'tGravityAcc.mean.X', 'tGravityAcc.mean.Y', 'tGravityAcc.mean.Z',
'tGravityAcc.std.X', 'tGravityAcc.std.Y', 'tGravityAcc.std.Z',
'tGravityAcc.mad.X', 'tGravityAcc.mad.Y', 'tGravityAcc.mad.Z',
'tGravityAcc.max.X', 'tGravityAcc.max.Y', 'tGravityAcc.max.Z',
'tGravityAcc.min.X', 'tGravityAcc.min.Y', 'tGravityAcc.min.Z',
'tGravityAcc.sma', 'tGravityAcc.energy.X', 'tGravityAcc.energy.Y',
'tGravityAcc.energy.Z', 'tGravityAcc.iqr.X', 'tGravityAcc.iqr.Y',
'tGravityAcc.iqr.Z', 'tGravityAcc.entropy.X', 'tGravityAcc.entropy.Y',
'tGravityAcc.entropy.Z', 'tGravityAcc.arCoeff.X.1',
'tGravityAcc.arCoeff.X.2', 'tGravityAcc.arCoeff.X.3',
'tGravityAcc.arCoeff.X.4', 'tGravityAcc.arCoeff.Y.1',
'tGravityAcc.arCoeff.Y.2', 'tGravityAcc.arCoeff.Y.3',
'tGravityAcc.arCoeff.Y.4', 'tGravityAcc.arCoeff.Z.1',
'tGravityAcc.arCoeff.Z.2', 'tGravityAcc.arCoeff.Z.3',
'tGravityAcc.arCoeff.Z.4', 'tGravityAcc.correlation.X.Y',
'tGravityAcc.correlation.X.Z', 'tGravityAcc.correlation.Y.Z',
'tBodyAccJerk.mean.X', 'tBodyAccJerk.mean.Y', 'tBodyAccJerk.mean.Z',
'tBodyAccJerk.std.X', 'tBodyAccJerk.std.Y', 'tBodyAccJerk.std.Z',
'tBodyAccJerk.mad.X', 'tBodyAccJerk.mad.Y', 'tBodyAccJerk.mad.Z',
'tBodyAccJerk.max.X', 'tBodyAccJerk.max.Y', 'tBodyAccJerk.max.Z',
'tBodyAccJerk.min.X', 'tBodyAccJerk.min.Y', 'tBodyAccJerk.min.Z',
'tBodyAccJerk.sma', 'tBodyAccJerk.energy.X', 'tBodyAccJerk.energy.Y',
'tBodyAccJerk.energy.Z', 'tBodyAccJerk.iqr.X', 'tBodyAccJerk.iqr.Y',
'tBodyAccJerk.iqr.Z', 'tBodyAccJerk.entropy.X',
'tBodyAccJerk.entropy.Y', 'tBodyAccJerk.entropy.Z',
'tBodyAccJerk.arCoeff.X.1', 'tBodyAccJerk.arCoeff.X.2',
'tBodyAccJerk.arCoeff.X.3', 'tBodyAccJerk.arCoeff.X.4',
'tBodyAccJerk.arCoeff.Y.1', 'tBodyAccJerk.arCoeff.Y.2',
'tBodyAccJerk.arCoeff.Y.3', 'tBodyAccJerk.arCoeff.Y.4',
'tBodyAccJerk.arCoeff.Z.1', 'tBodyAccJerk.arCoeff.Z.2',
'tBodyAccJerk.arCoeff.Z.3', 'tBodyAccJerk.arCoeff.Z.4',
'tBodyAccJerk.correlation.X.Y', 'tBodyAccJerk.correlation.X.Z',
'tBodyAccJerk.correlation.Y.Z', 'tBodyGyro.mean.X', 'tBodyGyro.mean.Y',
'tBodyGyro.mean.Z', 'tBodyGyro.std.X', 'tBodyGyro.std.Y',
'tBodyGyro.std.Z', 'tBodyGyro.mad.X', 'tBodyGyro.mad.Y',
'tBodyGyro.mad.Z', 'tBodyGyro.max.X', 'tBodyGyro.max.Y',
'tBodyGyro.max.Z', 'tBodyGyro.min.X', 'tBodyGyro.min.Y',
'tBodyGyro.min.Z', 'tBodyGyro.sma', 'tBodyGyro.energy.X',
'tBodyGyro.energy.Y', 'tBodyGyro.energy.Z', 'tBodyGyro.iqr.X',
'tBodyGyro.iqr.Y', 'tBodyGyro.iqr.Z', 'tBodyGyro.entropy.X',
'tBodyGyro.entropy.Y', 'tBodyGyro.entropy.Z', 'tBodyGyro.arCoeff.X.1',
'tBodyGyro.arCoeff.X.2', 'tBodyGyro.arCoeff.X.3',
'tBodyGyro.arCoeff.X.4', 'tBodyGyro.arCoeff.Y.1',
'tBodyGyro.arCoeff.Y.2', 'tBodyGyro.arCoeff.Y.3',
'tBodyGyro.arCoeff.Y.4', 'tBodyGyro.arCoeff.Z.1',
'tBodyGyro.arCoeff.Z.2', 'tBodyGyro.arCoeff.Z.3',
'tBodyGyro.arCoeff.Z.4', 'tBodyGyro.correlation.X.Y',
'tBodyGyro.correlation.X.Z', 'tBodyGyro.correlation.Y.Z',
'tBodyGyroJerk.mean.X', 'tBodyGyroJerk.mean.Y', 'tBodyGyroJerk.mean.Z',
'tBodyGyroJerk.std.X', 'tBodyGyroJerk.std.Y', 'tBodyGyroJerk.std.Z',
'tBodyGyroJerk.mad.X', 'tBodyGyroJerk.mad.Y', 'tBodyGyroJerk.mad.Z',
'tBodyGyroJerk.max.X', 'tBodyGyroJerk.max.Y', 'tBodyGyroJerk.max.Z',
'tBodyGyroJerk.min.X', 'tBodyGyroJerk.min.Y', 'tBodyGyroJerk.min.Z',
'tBodyGyroJerk.sma', 'tBodyGyroJerk.energy.X',
'tBodyGyroJerk.energy.Y', 'tBodyGyroJerk.energy.Z',
'tBodyGyroJerk.iqr.X', 'tBodyGyroJerk.iqr.Y', 'tBodyGyroJerk.iqr.Z',
'tBodyGyroJerk.entropy.X', 'tBodyGyroJerk.entropy.Y',
'tBodyGyroJerk.entropy.Z', 'tBodyGyroJerk.arCoeff.X.1',
'tBodyGyroJerk.arCoeff.X.2', 'tBodyGyroJerk.arCoeff.X.3',
'tBodyGyroJerk.arCoeff.X.4', 'tBodyGyroJerk.arCoeff.Y.1',
'tBodyGyroJerk.arCoeff.Y.2', 'tBodyGyroJerk.arCoeff.Y.3',
'tBodyGyroJerk.arCoeff.Y.4', 'tBodyGyroJerk.arCoeff.Z.1',
'tBodyGyroJerk.arCoeff.Z.2', 'tBodyGyroJerk.arCoeff.Z.3',
'tBodyGyroJerk.arCoeff.Z.4', 'tBodyGyroJerk.correlation.X.Y',
'tBodyGyroJerk.correlation.X.Z', 'tBodyGyroJerk.correlation.Y.Z',
'tBodyAccMag.mean', 'tBodyAccMag.std', 'tBodyAccMag.mad',
'tBodyAccMag.max', 'tBodyAccMag.min', 'tBodyAccMag.sma',
'tBodyAccMag.energy', 'tBodyAccMag.iqr', 'tBodyAccMag.entropy',
'tBodyAccMag.arCoeff1', 'tBodyAccMag.arCoeff2', 'tBodyAccMag.arCoeff3',
'tBodyAccMag.arCoeff4', 'tGravityAccMag.mean', 'tGravityAccMag.std',
'tGravityAccMag.mad', 'tGravityAccMag.max', 'tGravityAccMag.min',
'tGravityAccMag.sma', 'tGravityAccMag.energy', 'tGravityAccMag.iqr',
'tGravityAccMag.entropy', 'tGravityAccMag.arCoeff1',
'tGravityAccMag.arCoeff2', 'tGravityAccMag.arCoeff3',
'tGravityAccMag.arCoeff4', 'tBodyAccJerkMag.mean',
'tBodyAccJerkMag.std', 'tBodyAccJerkMag.mad', 'tBodyAccJerkMag.max',
'tBodyAccJerkMag.min', 'tBodyAccJerkMag.sma', 'tBodyAccJerkMag.energy',
'tBodyAccJerkMag.iqr', 'tBodyAccJerkMag.entropy',
'tBodyAccJerkMag.arCoeff1', 'tBodyAccJerkMag.arCoeff2',
'tBodyAccJerkMag.arCoeff3', 'tBodyAccJerkMag.arCoeff4',
'tBodyGyroMag.mean', 'tBodyGyroMag.std', 'tBodyGyroMag.mad',
'tBodyGyroMag.max', 'tBodyGyroMag.min', 'tBodyGyroMag.sma',
'tBodyGyroMag.energy', 'tBodyGyroMag.iqr', 'tBodyGyroMag.entropy',
'tBodyGyroMag.arCoeff1', 'tBodyGyroMag.arCoeff2',
'tBodyGyroMag.arCoeff3', 'tBodyGyroMag.arCoeff4',
'tBodyGyroJerkMag.mean', 'tBodyGyroJerkMag.std',
'tBodyGyroJerkMag.mad', 'tBodyGyroJerkMag.max', 'tBodyGyroJerkMag.min',
'tBodyGyroJerkMag.sma', 'tBodyGyroJerkMag.energy',
'tBodyGyroJerkMag.iqr', 'tBodyGyroJerkMag.entropy',
'tBodyGyroJerkMag.arCoeff1', 'tBodyGyroJerkMag.arCoeff2',
'tBodyGyroJerkMag.arCoeff3', 'tBodyGyroJerkMag.arCoeff4',
'fBodyAcc.mean.X', 'fBodyAcc.mean.Y', 'fBodyAcc.mean.Z',
'fBodyAcc.std.X', 'fBodyAcc.std.Y', 'fBodyAcc.std.Z', 'fBodyAcc.mad.X',
'fBodyAcc.mad.Y', 'fBodyAcc.mad.Z', 'fBodyAcc.max.X', 'fBodyAcc.max.Y',
'fBodyAcc.max.Z', 'fBodyAcc.min.X', 'fBodyAcc.min.Y', 'fBodyAcc.min.Z',
'fBodyAcc.sma', 'fBodyAcc.energy.X', 'fBodyAcc.energy.Y',
'fBodyAcc.energy.Z', 'fBodyAcc.iqr.X', 'fBodyAcc.iqr.Y',
'fBodyAcc.iqr.Z', 'fBodyAcc.entropy.X', 'fBodyAcc.entropy.Y',
'fBodyAcc.entropy.Z', 'fBodyAcc.maxInds.X', 'fBodyAcc.maxInds.Y',
'fBodyAcc.maxInds.Z', 'fBodyAcc.meanFreq.X', 'fBodyAcc.meanFreq.Y',
'fBodyAcc.meanFreq.Z', 'fBodyAcc.skewness.X', 'fBodyAcc.kurtosis.X',
'fBodyAcc.skewness.Y', 'fBodyAcc.kurtosis.Y', 'fBodyAcc.skewness.Z',
'fBodyAcc.kurtosis.Z', 'fBodyAcc.bandsEnergy.1.8',
'fBodyAcc.bandsEnergy.9.16', 'fBodyAcc.bandsEnergy.17.24',
'fBodyAcc.bandsEnergy.25.32', 'fBodyAcc.bandsEnergy.33.40',
'fBodyAcc.bandsEnergy.41.48', 'fBodyAcc.bandsEnergy.49.56',
'fBodyAcc.bandsEnergy.57.64', 'fBodyAcc.bandsEnergy.1.16',
'fBodyAcc.bandsEnergy.17.32', 'fBodyAcc.bandsEnergy.33.48',
'fBodyAcc.bandsEnergy.49.64', 'fBodyAcc.bandsEnergy.1.24',
'fBodyAcc.bandsEnergy.25.48', 'fBodyAcc.bandsEnergy.1.8.1',
'fBodyAcc.bandsEnergy.9.16.1', 'fBodyAcc.bandsEnergy.17.24.1',
'fBodyAcc.bandsEnergy.25.32.1', 'fBodyAcc.bandsEnergy.33.40.1',
'fBodyAcc.bandsEnergy.41.48.1', 'fBodyAcc.bandsEnergy.49.56.1',
'fBodyAcc.bandsEnergy.57.64.1', 'fBodyAcc.bandsEnergy.1.16.1',
'fBodyAcc.bandsEnergy.17.32.1', 'fBodyAcc.bandsEnergy.33.48.1',
'fBodyAcc.bandsEnergy.49.64.1', 'fBodyAcc.bandsEnergy.1.24.1',
'fBodyAcc.bandsEnergy.25.48.1', 'fBodyAcc.bandsEnergy.1.8.2',
'fBodyAcc.bandsEnergy.9.16.2', 'fBodyAcc.bandsEnergy.17.24.2',
'fBodyAcc.bandsEnergy.25.32.2', 'fBodyAcc.bandsEnergy.33.40.2',
'fBodyAcc.bandsEnergy.41.48.2', 'fBodyAcc.bandsEnergy.49.56.2',
'fBodyAcc.bandsEnergy.57.64.2', 'fBodyAcc.bandsEnergy.1.16.2',
'fBodyAcc.bandsEnergy.17.32.2', 'fBodyAcc.bandsEnergy.33.48.2',
'fBodyAcc.bandsEnergy.49.64.2', 'fBodyAcc.bandsEnergy.1.24.2',
'fBodyAcc.bandsEnergy.25.48.2', 'fBodyAccJerk.mean.X',
'fBodyAccJerk.mean.Y', 'fBodyAccJerk.mean.Z', 'fBodyAccJerk.std.X',
'fBodyAccJerk.std.Y', 'fBodyAccJerk.std.Z', 'fBodyAccJerk.mad.X',
'fBodyAccJerk.mad.Y', 'fBodyAccJerk.mad.Z', 'fBodyAccJerk.max.X',
'fBodyAccJerk.max.Y', 'fBodyAccJerk.max.Z', 'fBodyAccJerk.min.X',
'fBodyAccJerk.min.Y', 'fBodyAccJerk.min.Z', 'fBodyAccJerk.sma',
'fBodyAccJerk.energy.X', 'fBodyAccJerk.energy.Y',
'fBodyAccJerk.energy.Z', 'fBodyAccJerk.iqr.X', 'fBodyAccJerk.iqr.Y',
'fBodyAccJerk.iqr.Z', 'fBodyAccJerk.entropy.X',
'fBodyAccJerk.entropy.Y', 'fBodyAccJerk.entropy.Z',
'fBodyAccJerk.maxInds.X', 'fBodyAccJerk.maxInds.Y',
'fBodyAccJerk.maxInds.Z', 'fBodyAccJerk.meanFreq.X',
'fBodyAccJerk.meanFreq.Y', 'fBodyAccJerk.meanFreq.Z',
'fBodyAccJerk.skewness.X', 'fBodyAccJerk.kurtosis.X',
'fBodyAccJerk.skewness.Y', 'fBodyAccJerk.kurtosis.Y',
'fBodyAccJerk.skewness.Z', 'fBodyAccJerk.kurtosis.Z',
'fBodyAccJerk.bandsEnergy.1.8', 'fBodyAccJerk.bandsEnergy.9.16',
'fBodyAccJerk.bandsEnergy.17.24', 'fBodyAccJerk.bandsEnergy.25.32',
'fBodyAccJerk.bandsEnergy.33.40', 'fBodyAccJerk.bandsEnergy.41.48',
'fBodyAccJerk.bandsEnergy.49.56', 'fBodyAccJerk.bandsEnergy.57.64',
'fBodyAccJerk.bandsEnergy.1.16', 'fBodyAccJerk.bandsEnergy.17.32',
'fBodyAccJerk.bandsEnergy.33.48', 'fBodyAccJerk.bandsEnergy.49.64',
'fBodyAccJerk.bandsEnergy.1.24', 'fBodyAccJerk.bandsEnergy.25.48',
'fBodyAccJerk.bandsEnergy.1.8.1', 'fBodyAccJerk.bandsEnergy.9.16.1',
'fBodyAccJerk.bandsEnergy.17.24.1', 'fBodyAccJerk.bandsEnergy.25.32.1',
'fBodyAccJerk.bandsEnergy.33.40.1', 'fBodyAccJerk.bandsEnergy.41.48.1',
'fBodyAccJerk.bandsEnergy.49.56.1', 'fBodyAccJerk.bandsEnergy.57.64.1',
'fBodyAccJerk.bandsEnergy.1.16.1', 'fBodyAccJerk.bandsEnergy.17.32.1',
'fBodyAccJerk.bandsEnergy.33.48.1', 'fBodyAccJerk.bandsEnergy.49.64.1',
'fBodyAccJerk.bandsEnergy.1.24.1', 'fBodyAccJerk.bandsEnergy.25.48.1',
'fBodyAccJerk.bandsEnergy.1.8.2', 'fBodyAccJerk.bandsEnergy.9.16.2',
'fBodyAccJerk.bandsEnergy.17.24.2', 'fBodyAccJerk.bandsEnergy.25.32.2',
'fBodyAccJerk.bandsEnergy.33.40.2', 'fBodyAccJerk.bandsEnergy.41.48.2',
'fBodyAccJerk.bandsEnergy.49.56.2', 'fBodyAccJerk.bandsEnergy.57.64.2',
'fBodyAccJerk.bandsEnergy.1.16.2', 'fBodyAccJerk.bandsEnergy.17.32.2',
'fBodyAccJerk.bandsEnergy.33.48.2', 'fBodyAccJerk.bandsEnergy.49.64.2',
'fBodyAccJerk.bandsEnergy.1.24.2', 'fBodyAccJerk.bandsEnergy.25.48.2',
'fBodyGyro.mean.X', 'fBodyGyro.mean.Y', 'fBodyGyro.mean.Z',
'fBodyGyro.std.X', 'fBodyGyro.std.Y', 'fBodyGyro.std.Z',
'fBodyGyro.mad.X', 'fBodyGyro.mad.Y', 'fBodyGyro.mad.Z',
'fBodyGyro.max.X', 'fBodyGyro.max.Y', 'fBodyGyro.max.Z',
'fBodyGyro.min.X', 'fBodyGyro.min.Y', 'fBodyGyro.min.Z',
'fBodyGyro.sma', 'fBodyGyro.energy.X', 'fBodyGyro.energy.Y',
'fBodyGyro.energy.Z', 'fBodyGyro.iqr.X', 'fBodyGyro.iqr.Y',
'fBodyGyro.iqr.Z', 'fBodyGyro.entropy.X', 'fBodyGyro.entropy.Y',
'fBodyGyro.entropy.Z', 'fBodyGyro.maxInds.X', 'fBodyGyro.maxInds.Y',
'fBodyGyro.maxInds.Z', 'fBodyGyro.meanFreq.X', 'fBodyGyro.meanFreq.Y',
'fBodyGyro.meanFreq.Z', 'fBodyGyro.skewness.X', 'fBodyGyro.kurtosis.X',
'fBodyGyro.skewness.Y', 'fBodyGyro.kurtosis.Y', 'fBodyGyro.skewness.Z',
'fBodyGyro.kurtosis.Z', 'fBodyGyro.bandsEnergy.1.8',
'fBodyGyro.bandsEnergy.9.16', 'fBodyGyro.bandsEnergy.17.24',
'fBodyGyro.bandsEnergy.25.32', 'fBodyGyro.bandsEnergy.33.40',
'fBodyGyro.bandsEnergy.41.48', 'fBodyGyro.bandsEnergy.49.56',
'fBodyGyro.bandsEnergy.57.64', 'fBodyGyro.bandsEnergy.1.16',
'fBodyGyro.bandsEnergy.17.32', 'fBodyGyro.bandsEnergy.33.48',
'fBodyGyro.bandsEnergy.49.64', 'fBodyGyro.bandsEnergy.1.24',
'fBodyGyro.bandsEnergy.25.48', 'fBodyGyro.bandsEnergy.1.8.1',
'fBodyGyro.bandsEnergy.9.16.1', 'fBodyGyro.bandsEnergy.17.24.1',
'fBodyGyro.bandsEnergy.25.32.1', 'fBodyGyro.bandsEnergy.33.40.1',
'fBodyGyro.bandsEnergy.41.48.1', 'fBodyGyro.bandsEnergy.49.56.1',
'fBodyGyro.bandsEnergy.57.64.1', 'fBodyGyro.bandsEnergy.1.16.1',
'fBodyGyro.bandsEnergy.17.32.1', 'fBodyGyro.bandsEnergy.33.48.1',
'fBodyGyro.bandsEnergy.49.64.1', 'fBodyGyro.bandsEnergy.1.24.1',
'fBodyGyro.bandsEnergy.25.48.1', 'fBodyGyro.bandsEnergy.1.8.2',
'fBodyGyro.bandsEnergy.9.16.2', 'fBodyGyro.bandsEnergy.17.24.2',
'fBodyGyro.bandsEnergy.25.32.2', 'fBodyGyro.bandsEnergy.33.40.2',
'fBodyGyro.bandsEnergy.41.48.2', 'fBodyGyro.bandsEnergy.49.56.2',
'fBodyGyro.bandsEnergy.57.64.2', 'fBodyGyro.bandsEnergy.1.16.2',
'fBodyGyro.bandsEnergy.17.32.2', 'fBodyGyro.bandsEnergy.33.48.2',
'fBodyGyro.bandsEnergy.49.64.2', 'fBodyGyro.bandsEnergy.1.24.2',
'fBodyGyro.bandsEnergy.25.48.2', 'fBodyAccMag.mean', 'fBodyAccMag.std',
'fBodyAccMag.mad', 'fBodyAccMag.max', 'fBodyAccMag.min',
'fBodyAccMag.sma', 'fBodyAccMag.energy', 'fBodyAccMag.iqr',
'fBodyAccMag.entropy', 'fBodyAccMag.maxInds', 'fBodyAccMag.meanFreq',
'fBodyAccMag.skewness', 'fBodyAccMag.kurtosis',
'fBodyBodyAccJerkMag.mean', 'fBodyBodyAccJerkMag.std',
'fBodyBodyAccJerkMag.mad', 'fBodyBodyAccJerkMag.max',
'fBodyBodyAccJerkMag.min', 'fBodyBodyAccJerkMag.sma',
'fBodyBodyAccJerkMag.energy', 'fBodyBodyAccJerkMag.iqr',
'fBodyBodyAccJerkMag.entropy', 'fBodyBodyAccJerkMag.maxInds',
'fBodyBodyAccJerkMag.meanFreq', 'fBodyBodyAccJerkMag.skewness',
'fBodyBodyAccJerkMag.kurtosis', 'fBodyBodyGyroMag.mean',
'fBodyBodyGyroMag.std', 'fBodyBodyGyroMag.mad', 'fBodyBodyGyroMag.max',
'fBodyBodyGyroMag.min', 'fBodyBodyGyroMag.sma',
'fBodyBodyGyroMag.energy', 'fBodyBodyGyroMag.iqr',
'fBodyBodyGyroMag.entropy', 'fBodyBodyGyroMag.maxInds',
'fBodyBodyGyroMag.meanFreq', 'fBodyBodyGyroMag.skewness',
'fBodyBodyGyroMag.kurtosis', 'fBodyBodyGyroJerkMag.mean',
'fBodyBodyGyroJerkMag.std', 'fBodyBodyGyroJerkMag.mad',
'fBodyBodyGyroJerkMag.max', 'fBodyBodyGyroJerkMag.min',
'fBodyBodyGyroJerkMag.sma', 'fBodyBodyGyroJerkMag.energy',
'fBodyBodyGyroJerkMag.iqr', 'fBodyBodyGyroJerkMag.entropy',
'fBodyBodyGyroJerkMag.maxInds', 'fBodyBodyGyroJerkMag.meanFreq',
'fBodyBodyGyroJerkMag.skewness', 'fBodyBodyGyroJerkMag.kurtosis',
'angle.tBodyAccMean.gravity', 'angle.tBodyAccJerkMean.gravityMean',
'angle.tBodyGyroMean.gravityMean',
'angle.tBodyGyroJerkMean.gravityMean', 'angle.X.gravityMean',
'angle.Y.gravityMean', 'angle.Z.gravityMean'
])
# These features contain a relatively small number of unique items.
categorical = HEADER.as_feature_indices([
'tBodyAcc.mean.X', 'tBodyAcc.energy.Y', 'tBodyAcc.energy.Z',
'tGravityAcc.std.X', 'tGravityAcc.std.Y', 'tGravityAcc.std.Z',
'tGravityAcc.mad.X', 'tGravityAcc.mad.Y', 'tGravityAcc.mad.Z',
'tGravityAcc.iqr.X', 'tGravityAcc.iqr.Y', 'tGravityAcc.iqr.Z',
'tGravityAcc.entropy.Y', 'tBodyAccJerk.energy.Z', 'tBodyGyro.energy.X',
'tBodyGyro.energy.Y', 'tBodyGyro.energy.Z', 'tBodyGyroJerk.energy.X',
'tBodyGyroJerk.energy.Y', 'tBodyGyroJerk.energy.Z', 'tBodyAccMag.min',
'tGravityAccMag.min', 'tBodyAccJerkMag.energy',
'tBodyGyroJerkMag.energy', 'fBodyAcc.min.Y', 'fBodyAcc.min.Z',
'fBodyAcc.maxInds.X', 'fBodyAcc.maxInds.Y', 'fBodyAcc.maxInds.Z',
'fBodyAcc.bandsEnergy.9.16', 'fBodyAcc.bandsEnergy.25.32',
'fBodyAcc.bandsEnergy.33.40', 'fBodyAcc.bandsEnergy.41.48',
'fBodyAcc.bandsEnergy.49.56', 'fBodyAcc.bandsEnergy.57.64',
'fBodyAcc.bandsEnergy.33.48', 'fBodyAcc.bandsEnergy.49.64',
'fBodyAcc.bandsEnergy.25.48', 'fBodyAcc.bandsEnergy.25.32.1',
'fBodyAcc.bandsEnergy.33.40.1', 'fBodyAcc.bandsEnergy.41.48.1',
'fBodyAcc.bandsEnergy.49.56.1', 'fBodyAcc.bandsEnergy.57.64.1',
'fBodyAcc.bandsEnergy.33.48.1', 'fBodyAcc.bandsEnergy.49.64.1',
'fBodyAcc.bandsEnergy.25.48.1', 'fBodyAcc.bandsEnergy.9.16.2',
'fBodyAcc.bandsEnergy.17.24.2', 'fBodyAcc.bandsEnergy.25.32.2',
'fBodyAcc.bandsEnergy.33.40.2', 'fBodyAcc.bandsEnergy.41.48.2',
'fBodyAcc.bandsEnergy.49.56.2', 'fBodyAcc.bandsEnergy.57.64.2',
'fBodyAcc.bandsEnergy.1.16.2', 'fBodyAcc.bandsEnergy.17.32.2',
'fBodyAcc.bandsEnergy.33.48.2', 'fBodyAcc.bandsEnergy.49.64.2',
'fBodyAcc.bandsEnergy.25.48.2', 'fBodyAccJerk.min.X',
'fBodyAccJerk.min.Z', 'fBodyAccJerk.energy.Z',
'fBodyAccJerk.maxInds.X', 'fBodyAccJerk.maxInds.Y',
'fBodyAccJerk.maxInds.Z', 'fBodyAccJerk.kurtosis.Y',
'fBodyAccJerk.kurtosis.Z', 'fBodyAccJerk.bandsEnergy.1.8',
'fBodyAccJerk.bandsEnergy.9.16', 'fBodyAccJerk.bandsEnergy.17.24',
'fBodyAccJerk.bandsEnergy.25.32', 'fBodyAccJerk.bandsEnergy.33.40',
'fBodyAccJerk.bandsEnergy.41.48', 'fBodyAccJerk.bandsEnergy.49.56',
'fBodyAccJerk.bandsEnergy.57.64', 'fBodyAccJerk.bandsEnergy.1.16',
'fBodyAccJerk.bandsEnergy.33.48', 'fBodyAccJerk.bandsEnergy.49.64',
'fBodyAccJerk.bandsEnergy.9.16.1', 'fBodyAccJerk.bandsEnergy.25.32.1',
'fBodyAccJerk.bandsEnergy.33.40.1', 'fBodyAccJerk.bandsEnergy.41.48.1',
'fBodyAccJerk.bandsEnergy.49.56.1', 'fBodyAccJerk.bandsEnergy.57.64.1',
'fBodyAccJerk.bandsEnergy.33.48.1', 'fBodyAccJerk.bandsEnergy.49.64.1',
'fBodyAccJerk.bandsEnergy.25.48.1', 'fBodyAccJerk.bandsEnergy.1.8.2',
'fBodyAccJerk.bandsEnergy.9.16.2', 'fBodyAccJerk.bandsEnergy.17.24.2',
'fBodyAccJerk.bandsEnergy.25.32.2', 'fBodyAccJerk.bandsEnergy.33.40.2',
'fBodyAccJerk.bandsEnergy.41.48.2', 'fBodyAccJerk.bandsEnergy.49.56.2',
'fBodyAccJerk.bandsEnergy.57.64.2', 'fBodyAccJerk.bandsEnergy.1.16.2',
'fBodyAccJerk.bandsEnergy.17.32.2', 'fBodyAccJerk.bandsEnergy.33.48.2',
'fBodyAccJerk.bandsEnergy.49.64.2', 'fBodyAccJerk.bandsEnergy.1.24.2',
'fBodyAccJerk.bandsEnergy.25.48.2', 'fBodyGyro.min.X',
'fBodyGyro.min.Y', 'fBodyGyro.min.Z', 'fBodyGyro.energy.X',
'fBodyGyro.energy.Y', 'fBodyGyro.energy.Z', 'fBodyGyro.maxInds.X',
'fBodyGyro.maxInds.Y', 'fBodyGyro.maxInds.Z',
'fBodyGyro.bandsEnergy.1.8', 'fBodyGyro.bandsEnergy.9.16',
'fBodyGyro.bandsEnergy.17.24', 'fBodyGyro.bandsEnergy.25.32',
'fBodyGyro.bandsEnergy.33.40', 'fBodyGyro.bandsEnergy.41.48',
'fBodyGyro.bandsEnergy.49.56', 'fBodyGyro.bandsEnergy.57.64',
'fBodyGyro.bandsEnergy.1.16', 'fBodyGyro.bandsEnergy.17.32',
'fBodyGyro.bandsEnergy.33.48', 'fBodyGyro.bandsEnergy.49.64',
'fBodyGyro.bandsEnergy.1.24', 'fBodyGyro.bandsEnergy.25.48',
'fBodyGyro.bandsEnergy.1.8.1', 'fBodyGyro.bandsEnergy.9.16.1',
'fBodyGyro.bandsEnergy.17.24.1', 'fBodyGyro.bandsEnergy.25.32.1',
'fBodyGyro.bandsEnergy.33.40.1', 'fBodyGyro.bandsEnergy.41.48.1',
'fBodyGyro.bandsEnergy.49.56.1', 'fBodyGyro.bandsEnergy.57.64.1',
'fBodyGyro.bandsEnergy.1.16.1', 'fBodyGyro.bandsEnergy.17.32.1',
'fBodyGyro.bandsEnergy.33.48.1', 'fBodyGyro.bandsEnergy.49.64.1',
'fBodyGyro.bandsEnergy.1.24.1', 'fBodyGyro.bandsEnergy.25.48.1',
'fBodyGyro.bandsEnergy.1.8.2', 'fBodyGyro.bandsEnergy.9.16.2',
'fBodyGyro.bandsEnergy.17.24.2', 'fBodyGyro.bandsEnergy.25.32.2',
'fBodyGyro.bandsEnergy.33.40.2', 'fBodyGyro.bandsEnergy.41.48.2',
'fBodyGyro.bandsEnergy.49.56.2', 'fBodyGyro.bandsEnergy.57.64.2',
'fBodyGyro.bandsEnergy.1.16.2', 'fBodyGyro.bandsEnergy.17.32.2',
'fBodyGyro.bandsEnergy.33.48.2', 'fBodyGyro.bandsEnergy.49.64.2',
'fBodyGyro.bandsEnergy.1.24.2', 'fBodyGyro.bandsEnergy.25.48.2',
'fBodyAccMag.min', 'fBodyAccMag.maxInds',
'fBodyBodyAccJerkMag.maxInds', 'fBodyBodyGyroMag.min',
'fBodyBodyGyroMag.energy', 'fBodyBodyGyroMag.maxInds',
'fBodyBodyGyroJerkMag.min', 'fBodyBodyGyroJerkMag.energy',
'fBodyBodyGyroJerkMag.maxInds'
])
numeric_processors = Pipeline(steps=[('robustimputer', RobustImputer())])
categorical_processors = Pipeline(steps=[('thresholdonehotencoder',
ThresholdOneHotEncoder(
threshold=7))])
column_transformer = ColumnTransformer(
transformers=[('numeric_processing', numeric_processors, numeric),
('categorical_processing', categorical_processors,
categorical)])
return Pipeline(steps=[(
'column_transformer',
column_transformer), ('robustpca', RobustPCA(
n_components=171)), ('robuststandardscaler',
RobustStandardScaler())])
def test_robust_imputer(X, X_expected, strategy, fill_values):
robust_imputer = RobustImputer(strategy=strategy, fill_values=fill_values)
robust_imputer.fit(X)
X_observed = robust_imputer.transform(X)
assert_array_equal(X_observed, X_expected)
class NALabelEncoder(BaseEstimator, TransformerMixin):
"""Encoder for transforming labels to NA values.
Uses `RobustImputer` on 1D inputs of labels
- Uses `is_finite_numeric` mask for encoding by default
- Only uses the `RobustImputer` strategy `constant` and fills using `np.nan`
- Default behavior encodes non-float and non-finite values as nan values in
the target column of a given regression dataset
Parameters
----------
mask_function : callable -> np.array, dtype('bool') (default=None)
A vectorized python function, accepts np.array, returns np.array
with dtype('bool')
For each value, if mask_function(val) == False, that value will
be imputed. mask_function is used to create a boolean mask that determines
which values in the input to impute.
Use np.vectorize to vectorize singular python functions.
"""
def __init__(self, mask_function=None):
self.mask_function = mask_function
def fit(self, y):
"""Fit the encoder on y.
Parameters
----------
y : {array-like}, shape (n_samples,)
Input column, where `n_samples` is the number of samples.
Returns
-------
self : NALabelEncoder
"""
self.model_ = RobustImputer(strategy="constant",
fill_values=np.nan,
mask_function=self.mask_function)
y = y.reshape(-1, 1)
self.model_.fit(X=y)
return self
def transform(self, y):
"""Encode all non-float and non-finite values in y as NA values.
Parameters
----------
y : {array-like}, shape (n_samples)
The input column to encode.
Returns
-------
yt : {ndarray}, shape (n_samples,)
The encoded input column.
"""
check_is_fitted(self, "model_")
y = y.reshape(-1, 1)
return self.model_.transform(y).flatten()
def inverse_transform(self, y):
"""Returns input column"""
return y
def _more_tags(self):
return {"X_types": ["1dlabels"]}
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)