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_predict_with_predict_params():
# tests that Pipeline passes predict_params to the final estimator
# when predict is invoked
pipe = Pipeline([('transf', Transf()), ('clf', DummyEstimatorParams())])
pipe.fit(None, None)
pipe.predict(X=None, got_attribute=True)
assert pipe.named_steps['clf'].got_attribute
def test_pipeline_sample_weight_supported():
# Pipeline should pass sample_weight
X = np.array([[1, 2]])
pipe = Pipeline([('transf', Transf()), ('clf', FitParamT())])
pipe.fit(X, y=None)
assert pipe.score(X) == 3
assert pipe.score(X, y=None) == 3
assert pipe.score(X, y=None, sample_weight=None) == 3
assert pipe.score(X, sample_weight=np.array([2, 3])) == 8
def test_pipeline_init_tuple():
# Pipeline accepts steps as tuple
X = np.array([[1, 2]])
pipe = Pipeline((('transf', Transf()), ('clf', FitParamT())))
pipe.fit(X, y=None)
pipe.score(X)
pipe.set_params(transf='passthrough')
pipe.fit(X, y=None)
pipe.score(X)
def test_pipeline_with_cache_attribute():
X = np.array([[1, 2]])
pipe = Pipeline([('transf', Transf()), ('clf', Mult())],
memory=DummyMemory())
pipe.fit(X, y=None)
dummy = WrongDummyMemory()
pipe = Pipeline([('transf', Transf()), ('clf', Mult())],
memory=dummy)
assert_raises_regex(ValueError, "'memory' should be None, a string or"
" have the same interface as joblib.Memory."
" Got memory='{}' instead.".format(dummy), pipe.fit, X)
def test_pipeline_sample_weight_unsupported():
# When sample_weight is None it shouldn't be passed
X = np.array([[1, 2]])
pipe = Pipeline([('transf', Transf()), ('clf', Mult())])
pipe.fit(X, y=None)
assert pipe.score(X) == 3
assert pipe.score(X, sample_weight=None) == 3
assert_raise_message(
TypeError,
"score() got an unexpected keyword argument 'sample_weight'",
pipe.score, X, sample_weight=np.array([2, 3])
)
def test_pipeline_methods_anova():
# Test the various methods of the pipeline (anova).
iris = load_iris()
X = iris.data
y = iris.target
# Test with Anova + LogisticRegression
clf = LogisticRegression()
filter1 = SelectKBest(f_classif, k=2)
pipe = Pipeline([('anova', filter1), ('logistic', clf)])
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.predict_log_proba(X)
pipe.score(X, y)
def test_pipeline_methods_pca_svm():
# Test the various methods of the pipeline (pca + svm).
iris = load_iris()
X = iris.data
y = iris.target
# Test with PCA + SVC
clf = SVC(probability=True, random_state=0)
pca = PCA(svd_solver='full', n_components='mle', whiten=True)
pipe = Pipeline([('pca', pca), ('svc', clf)])
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.predict_log_proba(X)
pipe.score(X, y)
def test_pipeline_score_samples_pca_lof():
iris = load_iris()
X = iris.data
# Test that the score_samples method is implemented on a pipeline.
# Test that the score_samples method on pipeline yields same results as
# applying transform and score_samples steps separately.
pca = PCA(svd_solver='full', n_components='mle', whiten=True)
lof = LocalOutlierFactor(novelty=True)
pipe = Pipeline([('pca', pca), ('lof', lof)])
pipe.fit(X)
# Check the shapes
assert pipe.score_samples(X).shape == (X.shape[0],)
# Check the values
lof.fit(pca.fit_transform(X))
assert_allclose(pipe.score_samples(X), lof.score_samples(pca.transform(X)))
def test_pipeline_fit_params():
# Test that the pipeline can take fit parameters
pipe = Pipeline([('transf', Transf()), ('clf', FitParamT())])
pipe.fit(X=None, y=None, clf__should_succeed=True)
# classifier should return True
assert pipe.predict(None)
# and transformer params should not be changed
assert pipe.named_steps['transf'].a is None
assert pipe.named_steps['transf'].b is None
# invalid parameters should raise an error message
assert_raise_message(
TypeError,
"fit() got an unexpected keyword argument 'bad'",
pipe.fit, None, None, clf__bad=True
)
def test_pipeline_correctly_adjusts_steps(passthrough):
X = np.array([[1]])
y = np.array([1])
mult2 = Mult(mult=2)
mult3 = Mult(mult=3)
mult5 = Mult(mult=5)
pipeline = Pipeline([
('m2', mult2),
('bad', passthrough),
('m3', mult3),
('m5', mult5)
])
pipeline.fit(X, y)
expected_names = ['m2', 'bad', 'm3', 'm5']
actual_names = [name for name, _ in pipeline.steps]
assert expected_names == actual_names
def test_pipeline_transform():
# Test whether pipeline works with a transformer at the end.
# Also test pipeline.transform and pipeline.inverse_transform
iris = load_iris()
X = iris.data
pca = PCA(n_components=2, svd_solver='full')
pipeline = Pipeline([('pca', pca)])
# test transform and fit_transform:
X_trans = pipeline.fit(X).transform(X)
X_trans2 = pipeline.fit_transform(X)
X_trans3 = pca.fit_transform(X)
assert_array_almost_equal(X_trans, X_trans2)
assert_array_almost_equal(X_trans, X_trans3)
X_back = pipeline.inverse_transform(X_trans)
X_back2 = pca.inverse_transform(X_trans)
assert_array_almost_equal(X_back, X_back2)
# TASK: Build a vectorizer that splits strings into sequence of 1 to 3
# characters instead of word tokens
vectorizer = TfidfVectorizer(ngram_range=(1, 3),
analyzer='char',
use_idf=False)
# TASK: Build a vectorizer / classifier pipeline using the previous analyzer
# the pipeline instance should stored in a variable named clf
clf = Pipeline([
('vec', vectorizer),
('clf', Perceptron()),
])
# TASK: Fit the pipeline on the training set
clf.fit(docs_train, y_train)
# TASK: Predict the outcome on the testing set in a variable named y_predicted
y_predicted = clf.predict(docs_test)
# Print the classification report
print(
metrics.classification_report(y_test,
y_predicted,
target_names=dataset.target_names))
# Plot the confusion matrix
cm = metrics.confusion_matrix(y_test, y_predicted)
print(cm)
#import matlotlib.pyplot as plt
degrees = [1, 4, 15]
X = np.sort(np.random.rand(n_samples))
y = true_fun(X) + np.random.randn(n_samples) * 0.1
plt.figure(figsize=(14, 5))
for i in range(len(degrees)):
ax = plt.subplot(1, len(degrees), i + 1)
plt.setp(ax, xticks=(), yticks=())
polynomial_features = PolynomialFeatures(degree=degrees[i],
include_bias=False)
linear_regression = LinearRegression()
pipeline = Pipeline([("polynomial_features", polynomial_features),
("linear_regression", linear_regression)])
pipeline.fit(X[:, np.newaxis], y)
# Evaluate the models using crossvalidation
scores = cross_val_score(pipeline, X[:, np.newaxis], y,
scoring="neg_mean_squared_error", cv=10)
X_test = np.linspace(0, 1, 100)
plt.plot(X_test, pipeline.predict(X_test[:, np.newaxis]), label="Model")
plt.plot(X_test, true_fun(X_test), label="True function")
plt.scatter(X, y, edgecolor='b', s=20, label="Samples")
plt.xlabel("x")
plt.ylabel("y")
plt.xlim((0, 1))
plt.ylim((-2, 2))
plt.legend(loc="best")
plt.title("Degree {}\nMSE = {:.2e}(+/- {:.2e})".format(
# #############################################################################
# Compute the coefs of a Bayesian Ridge with GridSearch
cv = KFold(2) # cross-validation generator for model selection
ridge = BayesianRidge()
cachedir = tempfile.mkdtemp()
mem = Memory(location=cachedir, verbose=1)
# Ward agglomeration followed by BayesianRidge
connectivity = grid_to_graph(n_x=size, n_y=size)
ward = FeatureAgglomeration(n_clusters=10,
connectivity=connectivity,
memory=mem)
clf = Pipeline([('ward', ward), ('ridge', ridge)])
# Select the optimal number of parcels with grid search
clf = GridSearchCV(clf, {'ward__n_clusters': [10, 20, 30]}, n_jobs=1, cv=cv)
clf.fit(X, y) # set the best parameters
coef_ = clf.best_estimator_.steps[-1][1].coef_
coef_ = clf.best_estimator_.steps[0][1].inverse_transform(coef_)
coef_agglomeration_ = coef_.reshape(size, size)
# Anova univariate feature selection followed by BayesianRidge
f_regression = mem.cache(feature_selection.f_regression) # caching function
anova = feature_selection.SelectPercentile(f_regression)
clf = Pipeline([('anova', anova), ('ridge', ridge)])
# Select the optimal percentage of features with grid search
clf = GridSearchCV(clf, {'anova__percentile': [5, 10, 20]}, cv=cv)
clf.fit(X, y) # set the best parameters
coef_ = clf.best_estimator_.steps[-1][1].coef_
coef_ = clf.best_estimator_.steps[0][1].inverse_transform(coef_.reshape(1, -1))
coef_selection_ = coef_.reshape(size, size)
stratify=y,
random_state=42)
categorical_pipe = Pipeline([
('imputer', SimpleImputer(strategy='constant', fill_value='missing')),
('onehot', OneHotEncoder(handle_unknown='ignore'))
])
numerical_pipe = Pipeline([('imputer', SimpleImputer(strategy='mean'))])
preprocessing = ColumnTransformer([('cat', categorical_pipe,
categorical_columns),
('num', numerical_pipe, numerical_columns)])
rf = Pipeline([('preprocess', preprocessing),
('classifier', RandomForestClassifier(random_state=42))])
rf.fit(X_train, y_train)
##############################################################################
# Accuracy of the Model
# ---------------------
# Prior to inspecting the feature importances, it is important to check that
# the model predictive performance is high enough. Indeed there would be little
# interest of inspecting the important features of a non-predictive model.
#
# Here one can observe that the train accuracy is very high (the forest model
# has enough capacity to completely memorize the training set) but it can still
# generalize well enough to the test set thanks to the built-in bagging of
# random forests.
#
# It might be possible to trade some accuracy on the training set for a
# slightly better accuracy on the test set by limiting the capacity of the
]),
1),
],
# weight components in ColumnTransformer
transformer_weights={
'subject': 0.8,
'body_bow': 0.5,
'body_stats': 1.0,
})),
# Use a SVC classifier on the combined features
('svc', LinearSVC(dual=False)),
],
verbose=True)
# limit the list of categories to make running this example faster.
categories = ['alt.atheism', 'talk.religion.misc']
X_train, y_train = fetch_20newsgroups(random_state=1,
subset='train',
categories=categories,
return_X_y=True)
X_test, y_test = fetch_20newsgroups(random_state=1,
subset='test',
categories=categories,
return_X_y=True)
pipeline.fit(X_train, y_train)
y_pred = pipeline.predict(X_test)
print(classification_report(y_pred, y_test))
def test_pipeline_memory():
iris = load_iris()
X = iris.data
y = iris.target
cachedir = mkdtemp()
try:
if LooseVersion(joblib.__version__) < LooseVersion('0.12'):
# Deal with change of API in joblib
memory = joblib.Memory(cachedir=cachedir, verbose=10)
else:
memory = joblib.Memory(location=cachedir, verbose=10)
# Test with Transformer + SVC
clf = SVC(probability=True, random_state=0)
transf = DummyTransf()
pipe = Pipeline([('transf', clone(transf)), ('svc', clf)])
cached_pipe = Pipeline([('transf', transf), ('svc', clf)],
memory=memory)
# Memoize the transformer at the first fit
cached_pipe.fit(X, y)
pipe.fit(X, y)
# Get the time stamp of the transformer in the cached pipeline
ts = cached_pipe.named_steps['transf'].timestamp_
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert not hasattr(transf, 'means_')
# Check that we are reading the cache while fitting
# a second time
cached_pipe.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert ts == cached_pipe.named_steps['transf'].timestamp_
# Create a new pipeline with cloned estimators
# Check that even changing the name step does not affect the cache hit
clf_2 = SVC(probability=True, random_state=0)
transf_2 = DummyTransf()
cached_pipe_2 = Pipeline([('transf_2', transf_2), ('svc', clf_2)],
memory=memory)
cached_pipe_2.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe_2.predict(X))
assert_array_equal(pipe.predict_proba(X),
cached_pipe_2.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe_2.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe_2.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe_2.named_steps['transf_2'].means_)
assert ts == cached_pipe_2.named_steps['transf_2'].timestamp_
finally:
shutil.rmtree(cachedir)
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())])
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
clf.fit(X_train, y_train)
print("model score: %.3f" % clf.score(X_test, y_test))
###############################################################################
# Using the prediction pipeline in a grid search
###############################################################################
# Grid search can also be performed on the different preprocessing steps
# defined in the ``ColumnTransformer`` object, together with the classifier's
# hyperparameters as part of the ``Pipeline``.
# We will search for both the imputer strategy of the numeric preprocessing
# and the regularization parameter of the logistic regression using
# :class:`mrex.model_selection.GridSearchCV`.
param_grid = {
'preprocessor__num__imputer__strategy': ['mean', 'median'],
'classifier__C': [0.1, 1.0, 10, 100],
def test_set_pipeline_step_passthrough(passthrough):
X = np.array([[1]])
y = np.array([1])
mult2 = Mult(mult=2)
mult3 = Mult(mult=3)
mult5 = Mult(mult=5)
def make():
return Pipeline([('m2', mult2), ('m3', mult3), ('last', mult5)])
pipeline = make()
exp = 2 * 3 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
pipeline.set_params(m3=passthrough)
exp = 2 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
assert (pipeline.get_params(deep=True) ==
{'steps': pipeline.steps,
'm2': mult2,
'm3': passthrough,
'last': mult5,
'memory': None,
'm2__mult': 2,
'last__mult': 5,
'verbose': False
})
pipeline.set_params(m2=passthrough)
exp = 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
# for other methods, ensure no AttributeErrors on None:
other_methods = ['predict_proba', 'predict_log_proba',
'decision_function', 'transform', 'score']
for method in other_methods:
getattr(pipeline, method)(X)
pipeline.set_params(m2=mult2)
exp = 2 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
pipeline = make()
pipeline.set_params(last=passthrough)
# mult2 and mult3 are active
exp = 6
assert_array_equal([[exp]], pipeline.fit(X, y).transform(X))
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
assert_raise_message(AttributeError,
"'str' object has no attribute 'predict'",
getattr, pipeline, 'predict')
# Check 'passthrough' step at construction time
exp = 2 * 5
pipeline = Pipeline(
[('m2', mult2), ('m3', passthrough), ('last', mult5)])
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
# #############################################################################
# Training
# Hyper-parameters. These were set by cross-validation,
# using a GridSearchCV. Here we are not performing cross-validation to
# save time.
rbm.learning_rate = 0.06
rbm.n_iter = 10
# More components tend to give better prediction performance, but larger
# fitting time
rbm.n_components = 100
logistic.C = 6000
# Training RBM-Logistic Pipeline
rbm_features_classifier.fit(X_train, Y_train)
# Training the Logistic regression classifier directly on the pixel
raw_pixel_classifier = clone(logistic)
raw_pixel_classifier.C = 100.
raw_pixel_classifier.fit(X_train, Y_train)
# #############################################################################
# Evaluation
Y_pred = rbm_features_classifier.predict(X_test)
print("Logistic regression using RBM features:\n%s\n" %
(metrics.classification_report(Y_test, Y_pred)))
Y_pred = raw_pixel_classifier.predict(X_test)
print("Logistic regression using raw pixel features:\n%s\n" %