def test_make_column_transformer_remainder_transformer():
scaler = StandardScaler()
norm = Normalizer()
remainder = StandardScaler()
ct = make_column_transformer((scaler, 'first'), (norm, ['second']),
remainder=remainder)
assert ct.remainder == remainder
def test_column_transformer_cloning():
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
ct = ColumnTransformer([('trans', StandardScaler(), [0])])
ct.fit(X_array)
assert not hasattr(ct.transformers[0][1], 'mean_')
assert hasattr(ct.transformers_[0][1], 'mean_')
ct = ColumnTransformer([('trans', StandardScaler(), [0])])
ct.fit_transform(X_array)
assert not hasattr(ct.transformers[0][1], 'mean_')
assert hasattr(ct.transformers_[0][1], 'mean_')
def test_column_transformer_named_estimators():
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
ct = ColumnTransformer([('trans1', StandardScaler(), [0]),
('trans2', StandardScaler(with_std=False), [1])])
assert not hasattr(ct, 'transformers_')
ct.fit(X_array)
assert hasattr(ct, 'transformers_')
assert isinstance(ct.named_transformers_['trans1'], StandardScaler)
assert isinstance(ct.named_transformers_.trans1, StandardScaler)
assert isinstance(ct.named_transformers_['trans2'], StandardScaler)
assert isinstance(ct.named_transformers_.trans2, StandardScaler)
assert not ct.named_transformers_.trans2.with_std
# check it are fitted transformers
assert ct.named_transformers_.trans1.mean_ == 1.
def generate_dataset(n_train, n_test, n_features, noise=0.1, verbose=False):
"""Generate a regression dataset with the given parameters."""
if verbose:
print("generating dataset...")
X, y, coef = make_regression(n_samples=n_train + n_test,
n_features=n_features,
noise=noise,
coef=True)
random_seed = 13
X_train, X_test, y_train, y_test = train_test_split(
X, y, train_size=n_train, test_size=n_test, random_state=random_seed)
X_train, y_train = shuffle(X_train, y_train, random_state=random_seed)
X_scaler = StandardScaler()
X_train = X_scaler.fit_transform(X_train)
X_test = X_scaler.transform(X_test)
y_scaler = StandardScaler()
y_train = y_scaler.fit_transform(y_train[:, None])[:, 0]
y_test = y_scaler.transform(y_test[:, None])[:, 0]
gc.collect()
if verbose:
print("ok")
return X_train, y_train, X_test, y_test
def test_transform_target_regressor_2d_transformer(X, y):
# Check consistency with transformer accepting only 2D array and a 1D/2D y
# array.
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
if y.ndim == 1: # create a 2D array and squeeze results
y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze()
else:
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(
y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
if y.ndim == 1: # create a 2D array and squeeze results
lr.fit(X, transformer2.fit_transform(y.reshape(-1, 1)).squeeze())
else:
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_pipeline_methods_preprocessing_svm():
# Test the various methods of the pipeline (preprocessing + svm).
iris = load_iris()
X = iris.data
y = iris.target
n_samples = X.shape[0]
n_classes = len(np.unique(y))
scaler = StandardScaler()
pca = PCA(n_components=2, svd_solver='randomized', whiten=True)
clf = SVC(probability=True, random_state=0, decision_function_shape='ovr')
for preprocessing in [scaler, pca]:
pipe = Pipeline([('preprocess', preprocessing), ('svc', clf)])
pipe.fit(X, y)
# check shapes of various prediction functions
predict = pipe.predict(X)
assert predict.shape == (n_samples,)
proba = pipe.predict_proba(X)
assert proba.shape == (n_samples, n_classes)
log_proba = pipe.predict_log_proba(X)
assert log_proba.shape == (n_samples, n_classes)
decision_function = pipe.decision_function(X)
assert decision_function.shape == (n_samples, n_classes)
pipe.score(X, y)
def test_permutation_importance_mixed_types_pandas():
pd = pytest.importorskip("pandas")
rng = np.random.RandomState(42)
n_repeats = 5
# Last column is correlated with y
X = pd.DataFrame({
'col1': [1.0, 2.0, 3.0, np.nan],
'col2': ['a', 'b', 'a', 'b']
})
y = np.array([0, 1, 0, 1])
num_preprocess = make_pipeline(SimpleImputer(), StandardScaler())
preprocess = ColumnTransformer([('num', num_preprocess, ['col1']),
('cat', OneHotEncoder(), ['col2'])])
clf = make_pipeline(preprocess, LogisticRegression(solver='lbfgs'))
clf.fit(X, y)
result = permutation_importance(clf,
X,
y,
n_repeats=n_repeats,
random_state=rng)
assert result.importances.shape == (X.shape[1], n_repeats)
# the correlated feature with y is the last column and should
# have the highest importance
assert np.all(result.importances_mean[-1] > result.importances_mean[:-1])
def test_make_column_transformer():
scaler = StandardScaler()
norm = Normalizer()
ct = make_column_transformer((scaler, 'first'), (norm, ['second']))
names, transformers, columns = zip(*ct.transformers)
assert names == ("standardscaler", "normalizer")
assert transformers == (scaler, norm)
assert columns == ('first', ['second'])
def test_fit_predict_on_pipeline_without_fit_predict():
# tests that a pipeline does not have fit_predict method when final
# step of pipeline does not have fit_predict defined
scaler = StandardScaler()
pca = PCA(svd_solver='full')
pipe = Pipeline([('scaler', scaler), ('pca', pca)])
assert_raises_regex(AttributeError,
"'PCA' object has no attribute 'fit_predict'",
getattr, pipe, 'fit_predict')
def test_column_transformer_get_set_params():
ct = ColumnTransformer([('trans1', StandardScaler(), [0]),
('trans2', StandardScaler(), [1])])
exp = {
'n_jobs': None,
'remainder': 'drop',
'sparse_threshold': 0.3,
'trans1': ct.transformers[0][1],
'trans1__copy': True,
'trans1__with_mean': True,
'trans1__with_std': True,
'trans2': ct.transformers[1][1],
'trans2__copy': True,
'trans2__with_mean': True,
'trans2__with_std': True,
'transformers': ct.transformers,
'transformer_weights': None,
'verbose': False
}
assert ct.get_params() == exp
ct.set_params(trans1__with_mean=False)
assert not ct.get_params()['trans1__with_mean']
ct.set_params(trans1='passthrough')
exp = {
'n_jobs': None,
'remainder': 'drop',
'sparse_threshold': 0.3,
'trans1': 'passthrough',
'trans2': ct.transformers[1][1],
'trans2__copy': True,
'trans2__with_mean': True,
'trans2__with_std': True,
'transformers': ct.transformers,
'transformer_weights': None,
'verbose': False
}
assert ct.get_params() == exp
def test_kde_pipeline_gridsearch():
# test that kde plays nice in pipelines and grid-searches
X, _ = make_blobs(cluster_std=.1,
random_state=1,
centers=[[0, 1], [1, 0], [0, 0]])
pipe1 = make_pipeline(StandardScaler(with_mean=False, with_std=False),
KernelDensity(kernel="gaussian"))
params = dict(kerneldensity__bandwidth=[0.001, 0.01, 0.1, 1, 10])
search = GridSearchCV(pipe1, param_grid=params)
search.fit(X)
assert search.best_params_['kerneldensity__bandwidth'] == .1
def test_column_transformer_error_msg_1D():
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
col_trans = ColumnTransformer([('trans', StandardScaler(), 0)])
assert_raise_message(ValueError, "1D data passed to a transformer",
col_trans.fit, X_array)
assert_raise_message(ValueError, "1D data passed to a transformer",
col_trans.fit_transform, X_array)
col_trans = ColumnTransformer([('trans', TransRaise(), 0)])
for func in [col_trans.fit, col_trans.fit_transform]:
assert_raise_message(ValueError, "specific message", func, X_array)
def test_column_transformer_no_estimators():
X_array = np.array([[0, 1, 2], [2, 4, 6], [8, 6, 4]]).astype('float').T
ct = ColumnTransformer([], remainder=StandardScaler())
params = ct.get_params()
assert params['remainder__with_mean']
X_trans = ct.fit_transform(X_array)
assert X_trans.shape == X_array.shape
assert len(ct.transformers_) == 1
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][2] == [0, 1, 2]
def test_partial_dependence_pipeline():
# check that the partial dependence support pipeline
iris = load_iris()
scaler = StandardScaler()
clf = DummyClassifier(random_state=42)
pipe = make_pipeline(scaler, clf)
clf.fit(scaler.fit_transform(iris.data), iris.target)
pipe.fit(iris.data, iris.target)
features = 0
pdp_pipe, values_pipe = partial_dependence(pipe,
iris.data,
features=[features])
pdp_clf, values_clf = partial_dependence(clf,
scaler.transform(iris.data),
features=[features])
assert_allclose(pdp_pipe, pdp_clf)
assert_allclose(
values_pipe[0],
values_clf[0] * scaler.scale_[features] + scaler.mean_[features])
def test_transform_target_regressor_error():
X, y = friedman
# provide a transformer and functions at the same time
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=StandardScaler(),
func=np.exp, inverse_func=np.log)
with pytest.raises(ValueError,
match="'transformer' and functions"
" 'func'/'inverse_func' cannot both be set."):
regr.fit(X, y)
# fit with sample_weight with a regressor which does not support it
sample_weight = np.ones((y.shape[0],))
regr = TransformedTargetRegressor(regressor=Lasso(),
transformer=StandardScaler())
with pytest.raises(TypeError, match=r"fit\(\) got an unexpected "
"keyword argument 'sample_weight'"):
regr.fit(X, y, sample_weight=sample_weight)
# func is given but inverse_func is not
regr = TransformedTargetRegressor(func=np.exp)
with pytest.raises(ValueError, match="When 'func' is provided, "
"'inverse_func' must also be provided"):
regr.fit(X, y)
def test_lasso_cv_with_some_model_selection():
from mrex.pipeline import make_pipeline
from mrex.preprocessing import StandardScaler
from mrex.model_selection import StratifiedKFold
from mrex import datasets
from mrex.linear_model import LassoCV
diabetes = datasets.load_diabetes()
X = diabetes.data
y = diabetes.target
pipe = make_pipeline(StandardScaler(), LassoCV(cv=StratifiedKFold()))
pipe.fit(X, y)
def test_column_transformer_list():
X_list = [[1, float('nan'), 'a'], [0, 0, 'b']]
expected_result = np.array([
[1, float('nan'), 1, 0],
[-1, 0, 0, 1],
])
ct = ColumnTransformer([
('numerical', StandardScaler(), [0, 1]),
('categorical', OneHotEncoder(), [2]),
])
assert_array_equal(ct.fit_transform(X_list), expected_result)
assert_array_equal(ct.fit(X_list).transform(X_list), expected_result)
def test_fit_predict_on_pipeline():
# test that the fit_predict method is implemented on a pipeline
# test that the fit_predict on pipeline yields same results as applying
# transform and clustering steps separately
iris = load_iris()
scaler = StandardScaler()
km = KMeans(random_state=0)
# As pipeline doesn't clone estimators on construction,
# it must have its own estimators
scaler_for_pipeline = StandardScaler()
km_for_pipeline = KMeans(random_state=0)
# first compute the transform and clustering step separately
scaled = scaler.fit_transform(iris.data)
separate_pred = km.fit_predict(scaled)
# use a pipeline to do the transform and clustering in one step
pipe = Pipeline([
('scaler', scaler_for_pipeline),
('Kmeans', km_for_pipeline)
])
pipeline_pred = pipe.fit_predict(iris.data)
assert_array_almost_equal(pipeline_pred, separate_pred)
def test_make_column_transformer_kwargs():
scaler = StandardScaler()
norm = Normalizer()
ct = make_column_transformer((scaler, 'first'), (norm, ['second']),
n_jobs=3,
remainder='drop',
sparse_threshold=0.5)
assert ct.transformers == make_column_transformer(
(scaler, 'first'), (norm, ['second'])).transformers
assert ct.n_jobs == 3
assert ct.remainder == 'drop'
assert ct.sparse_threshold == 0.5
# invalid keyword parameters should raise an error message
assert_raise_message(TypeError,
'Unknown keyword arguments: "transformer_weights"',
make_column_transformer, (scaler, 'first'),
(norm, ['second']),
transformer_weights={
'pca': 10,
'Transf': 1
})
def test_pls_scaling():
# sanity check for scale=True
n_samples = 1000
n_targets = 5
n_features = 10
rng = check_random_state(0)
Q = rng.randn(n_targets, n_features)
Y = rng.randn(n_samples, n_targets)
X = np.dot(Y, Q) + 2 * rng.randn(n_samples, n_features) + 1
X *= 1000
X_scaled = StandardScaler().fit_transform(X)
pls = pls_.PLSRegression(n_components=5, scale=True)
pls.fit(X, Y)
score = pls.score(X, Y)
pls.fit(X_scaled, Y)
score_scaled = pls.score(X_scaled, Y)
assert_approx_equal(score, score_scaled)
def test_transform_target_regressor_2d_transformer_multioutput():
# Check consistency with transformer accepting only 2D array and a 2D y
# array.
X = friedman[0]
y = np.vstack((friedman[1], friedman[1] ** 2 + 1)).T
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(
y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
from mrex.utils.testing import assert_array_equal
from mrex.utils.testing import assert_allclose
iris = load_iris()
def _get_valid_samples_by_column(X, col):
"""Get non NaN samples in column of X"""
return X[:, [col]][~np.isnan(X[:, col])]
@pytest.mark.parametrize(
"est, func, support_sparse, strictly_positive",
[(MaxAbsScaler(), maxabs_scale, True, False),
(MinMaxScaler(), minmax_scale, False, False),
(StandardScaler(), scale, False, False),
(StandardScaler(with_mean=False), scale, True, False),
(PowerTransformer('yeo-johnson'), power_transform, False, False),
(PowerTransformer('box-cox'), power_transform, False, True),
(QuantileTransformer(n_quantiles=10), quantile_transform, True, False),
(RobustScaler(), robust_scale, False, False),
(RobustScaler(with_centering=False), robust_scale, True, False)])
def test_missing_value_handling(est, func, support_sparse, strictly_positive):
# check that the preprocessing method let pass nan
rng = np.random.RandomState(42)
X = iris.data.copy()
n_missing = 50
X[rng.randint(X.shape[0], size=n_missing),
rng.randint(X.shape[1], size=n_missing)] = np.nan
if strictly_positive:
X += np.nanmin(X) + 0.1
# slicing by using a two-dim dataset
X = X[:, [0, 2]]
X_train, X_test, y_train, y_test = \
train_test_split(X, y, stratify=y, test_size=0.7, random_state=42)
h = .01 # step size in the mesh
# Create color maps
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF'])
cmap_bold = ListedColormap(['#FF0000', '#00FF00', '#0000FF'])
names = ['KNN', 'NCA, KNN']
classifiers = [
Pipeline([('scaler', StandardScaler()),
('knn', KNeighborsClassifier(n_neighbors=n_neighbors))]),
Pipeline([('scaler', StandardScaler()),
('nca', NeighborhoodComponentsAnalysis()),
('knn', KNeighborsClassifier(n_neighbors=n_neighbors))])
]
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
for name, clf in zip(names, classifiers):
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
# Dataset for decision function visualization: we only keep the first two # features in X and sub-sample the dataset to keep only 2 classes and # make it a binary classification problem. X_2d = X[:, :2] X_2d = X_2d[y > 0] y_2d = y[y > 0] y_2d -= 1 # It is usually a good idea to scale the data for SVM training. # We are cheating a bit in this example in scaling all of the data, # instead of fitting the transformation on the training set and # just applying it on the test set. scaler = StandardScaler() X = scaler.fit_transform(X) X_2d = scaler.fit_transform(X_2d) # ############################################################################# # Train classifiers # # For an initial search, a logarithmic grid with basis # 10 is often helpful. Using a basis of 2, a finer # tuning can be achieved but at a much higher cost. C_range = np.logspace(-2, 10, 13) gamma_range = np.logspace(-9, 3, 13) param_grid = dict(gamma=gamma_range, C=C_range) cv = StratifiedShuffleSplit(n_splits=5, test_size=0.2, random_state=42) grid = GridSearchCV(SVC(), param_grid=param_grid, cv=cv)
n_neighbors = 3
random_state = 0
# Load Digits dataset
X, y = datasets.load_digits(return_X_y=True)
# Split into train/test
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.5, stratify=y,
random_state=random_state)
dim = len(X[0])
n_classes = len(np.unique(y))
# Reduce dimension to 2 with PCA
pca = make_pipeline(StandardScaler(),
PCA(n_components=2, random_state=random_state))
# Reduce dimension to 2 with LinearDiscriminantAnalysis
lda = make_pipeline(StandardScaler(),
LinearDiscriminantAnalysis(n_components=2))
# Reduce dimension to 2 with NeighborhoodComponentAnalysis
nca = make_pipeline(StandardScaler(),
NeighborhoodComponentsAnalysis(n_components=2,
random_state=random_state))
# Use a nearest neighbor classifier to evaluate the methods
knn = KNeighborsClassifier(n_neighbors=n_neighbors)
# Make a list of the methods to be compared
t0 = time.time()
train_samples = 5000
# Load data from https://www.openml.org/d/554
X, y = fetch_openml('mnist_784', version=1, return_X_y=True)
random_state = check_random_state(0)
permutation = random_state.permutation(X.shape[0])
X = X[permutation]
y = y[permutation]
X = X.reshape((X.shape[0], -1))
X_train, X_test, y_train, y_test = train_test_split(
X, y, train_size=train_samples, test_size=10000)
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
# Turn up tolerance for faster convergence
clf = LogisticRegression(
C=50. / train_samples, penalty='l1', solver='saga', tol=0.1
)
clf.fit(X_train, y_train)
sparsity = np.mean(clf.coef_ == 0) * 100
score = clf.score(X_test, y_test)
# print('Best C % .4f' % clf.C_)
print("Sparsity with L1 penalty: %.2f%%" % sparsity)
print("Test score with L1 penalty: %.4f" % score)
coef = clf.coef_.copy()
(varied, {'eps': .18, 'n_neighbors': 2,
'min_samples': 5, 'xi': 0.035, 'min_cluster_size': .2}),
(aniso, {'eps': .15, 'n_neighbors': 2,
'min_samples': 20, 'xi': 0.1, 'min_cluster_size': .2}),
(blobs, {}),
(no_structure, {})]
for i_dataset, (dataset, algo_params) in enumerate(datasets):
# update parameters with dataset-specific values
params = default_base.copy()
params.update(algo_params)
X, y = dataset
# normalize dataset for easier parameter selection
X = StandardScaler().fit_transform(X)
# estimate bandwidth for mean shift
bandwidth = cluster.estimate_bandwidth(X, quantile=params['quantile'])
# connectivity matrix for structured Ward
connectivity = kneighbors_graph(
X, n_neighbors=params['n_neighbors'], include_self=False)
# make connectivity symmetric
connectivity = 0.5 * (connectivity + connectivity.T)
# ============
# Create cluster objects
# ============
ms = cluster.MeanShift(bandwidth=bandwidth, bin_seeding=True)
two_means = cluster.MiniBatchKMeans(n_clusters=params['n_clusters'])
features, target = load_wine(return_X_y=True)
# Make a train/test split using 30% test size
X_train, X_test, y_train, y_test = train_test_split(features,
target,
test_size=0.30,
random_state=RANDOM_STATE)
# Fit to data and predict using pipelined GNB and PCA.
unscaled_clf = make_pipeline(PCA(n_components=2), GaussianNB())
unscaled_clf.fit(X_train, y_train)
pred_test = unscaled_clf.predict(X_test)
# Fit to data and predict using pipelined scaling, GNB and PCA.
std_clf = make_pipeline(StandardScaler(), PCA(n_components=2), GaussianNB())
std_clf.fit(X_train, y_train)
pred_test_std = std_clf.predict(X_test)
# Show prediction accuracies in scaled and unscaled data.
print('\nPrediction accuracy for the normal test dataset with PCA')
print('{:.2%}\n'.format(metrics.accuracy_score(y_test, pred_test)))
print('\nPrediction accuracy for the standardized test dataset with PCA')
print('{:.2%}\n'.format(metrics.accuracy_score(y_test, pred_test_std)))
# Extract PCA from pipeline
pca = unscaled_clf.named_steps['pca']
pca_std = std_clf.named_steps['pca']
# Show first principal components
X_digits, y_digits = load_digits(n_class=3, return_X_y=True)
X_digits_multi = MinMaxScaler().fit_transform(X_digits[:200])
y_digits_multi = y_digits[:200]
X_digits, y_digits = load_digits(n_class=2, return_X_y=True)
X_digits_binary = MinMaxScaler().fit_transform(X_digits[:200])
y_digits_binary = y_digits[:200]
classification_datasets = [(X_digits_multi, y_digits_multi),
(X_digits_binary, y_digits_binary)]
boston = load_boston()
Xboston = StandardScaler().fit_transform(boston.data)[:200]
yboston = boston.target[:200]
regression_datasets = [(Xboston, yboston)]
iris = load_iris()
X_iris = iris.data
y_iris = iris.target
def test_alpha():
# Test that larger alpha yields weights closer to zero
X = X_digits_binary[:100]
y = y_digits_binary[:100]
# y = titanic.frame['survived']
# We will train our classifier with the following features:
# Numeric Features:
# - age: float.
# - fare: float.
# Categorical Features:
# - embarked: categories encoded as strings {'C', 'S', 'Q'}.
# - sex: categories encoded as strings {'female', 'male'}.
# - pclass: ordinal integers {1, 2, 3}.
# We create the preprocessing pipelines for both numeric and categorical data.
numeric_features = ['age', 'fare']
numeric_transformer = Pipeline(
steps=[('imputer',
SimpleImputer(strategy='median')), ('scaler', StandardScaler())])
categorical_features = ['embarked', 'sex', 'pclass']
categorical_transformer = Pipeline(
steps=[('imputer', SimpleImputer(strategy='constant', fill_value='missing')
), ('onehot', OneHotEncoder(handle_unknown='ignore'))])
preprocessor = ColumnTransformer(transformers=[(
'num', numeric_transformer,
numeric_features), ('cat', categorical_transformer, categorical_features)])
# Append classifier to preprocessing pipeline.
# Now we have a full prediction pipeline.
clf = Pipeline(steps=[('preprocessor',
preprocessor), ('classifier', LogisticRegression())])