def test_countvectorizer_custom_vocabulary_pipeline(): what_we_like = ["pizza", "beer"] pipe = Pipeline([ ('count', CountVectorizer(vocabulary=what_we_like)), ('tfidf', TfidfTransformer())]) X = pipe.fit_transform(ALL_FOOD_DOCS) assert (set(pipe.named_steps['count'].vocabulary_) == set(what_we_like)) assert X.shape[1] == len(what_we_like)
def test_pipeline_fit_transform(): # Test whether pipeline works with a transformer missing fit_transform X = iris.data y = iris.target transf = Transf() pipeline = Pipeline([('mock', transf)]) # test fit_transform: X_trans = pipeline.fit_transform(X, y) X_trans2 = transf.fit(X, y).transform(X) assert_array_almost_equal(X_trans, X_trans2)
def test_pipeline_transform(): # Test whether pipeline works with a transformer at the end. # Also test pipeline.transform and pipeline.inverse_transform 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)
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]]))