def test_limit_features(self): X, X_rdd = self.make_text_rdd() params = [{ 'min_df': .5 }, { 'min_df': 2, 'max_df': .9 }, { 'min_df': 1, 'max_df': .6 }, { 'min_df': 2, 'max_features': 3 }] for paramset in params: local = CountVectorizer(**paramset) dist = SparkCountVectorizer(**paramset) result_local = local.fit_transform(X).toarray() result_dist = dist.fit_transform(X_rdd).toarray() assert_equal(local.vocabulary_, dist.vocabulary_) assert_array_equal(result_local, result_dist) result_dist = dist.transform(X_rdd).toarray() assert_array_equal(result_local, result_dist)
def test_same_result(self): X, Z = self.make_text_rdd(2) loc_char = CountVectorizer(analyzer="char_wb", ngram_range=(3, 3)) dist_char = SparkCountVectorizer(analyzer="char_wb", ngram_range=(3, 3)) loc_word = CountVectorizer(analyzer="word") dist_word = SparkCountVectorizer(analyzer="word") loc_union = FeatureUnion([ ("chars", loc_char), ("words", loc_word) ]) dist_union = SparkFeatureUnion([ ("chars", dist_char), ("words", dist_word) ]) # test same feature names loc_union.fit(X) dist_union.fit(Z) assert_equal( loc_union.get_feature_names(), dist_union.get_feature_names() ) # test same results X_transformed = loc_union.transform(X) Z_transformed = sp.vstack(dist_union.transform(Z).collect()) assert_array_equal(X_transformed.toarray(), Z_transformed.toarray()) # test same results with fit_transform X_transformed = loc_union.fit_transform(X) Z_transformed = sp.vstack(dist_union.fit_transform(Z).collect()) assert_array_equal(X_transformed.toarray(), Z_transformed.toarray()) # test same results in parallel loc_union_par = FeatureUnion([ ("chars", loc_char), ("words", loc_word) ], n_jobs=2) dist_union_par = SparkFeatureUnion([ ("chars", dist_char), ("words", dist_word) ], n_jobs=2) loc_union_par.fit(X) dist_union_par.fit(Z) X_transformed = loc_union_par.transform(X) Z_transformed = sp.vstack(dist_union_par.transform(Z).collect()) assert_array_equal(X_transformed.toarray(), Z_transformed.toarray())
def test_pipeline_init(self): # Test the various init parameters of the pipeline. assert_raises(TypeError, SparkPipeline) # Check that we can't instantiate pipelines with objects without fit # method pipe = assert_raises(TypeError, SparkPipeline, [('svc', IncorrectT)]) # Smoke test with only an estimator clf = T() pipe = SparkPipeline([('svc', clf)]) assert_equal(pipe.get_params(deep=True), dict(svc__a=None, svc__b=None, svc=clf, **pipe.get_params(deep=False) )) # Check that params are set pipe.set_params(svc__a=0.1) assert_equal(clf.a, 0.1) assert_equal(clf.b, None) # Smoke test the repr: repr(pipe) # Test with two objects vect = SparkCountVectorizer() filter = SparkVarianceThreshold() pipe = SparkPipeline([('vect', vect), ('filter', filter)]) # Check that we can't use the same stage name twice assert_raises(ValueError, SparkPipeline, [('vect', vect), ('vect', vect)]) # Check that params are set pipe.set_params(vect__min_df=0.1) assert_equal(vect.min_df, 0.1) # Smoke test the repr: repr(pipe) # Check that params are not set when naming them wrong assert_raises(ValueError, pipe.set_params, filter__min_df=0.1) # Test clone pipe2 = clone(pipe) assert_false(pipe.named_steps['vect'] is pipe2.named_steps['vect']) # Check that apart from estimators, the parameters are the same params = pipe.get_params(deep=True) params2 = pipe2.get_params(deep=True) for x in pipe.get_params(deep=False): params.pop(x) for x in pipe2.get_params(deep=False): params2.pop(x) # Remove estimators that where copied params.pop('vect') params.pop('filter') params2.pop('vect') params2.pop('filter') assert_equal(params, params2)
def test_same_output(self): X, X_rdd = self.make_text_rdd() local = CountVectorizer() dist = SparkCountVectorizer() result_local = local.fit_transform(X).toarray() result_dist = dist.fit_transform(X_rdd).toarray() assert_equal(local.vocabulary_, dist.vocabulary_) assert_array_equal(result_local, result_dist)
def test_same_result_weight(self): X, Z = self.make_text_rdd(2) loc_char = CountVectorizer(analyzer="char_wb", ngram_range=(3, 3)) dist_char = SparkCountVectorizer(analyzer="char_wb", ngram_range=(3, 3)) loc_word = CountVectorizer(analyzer="word") dist_word = SparkCountVectorizer(analyzer="word") loc_union = FeatureUnion([("chars", loc_char), ("words", loc_word)], transformer_weights={"words": 10}) dist_union = SparkFeatureUnion([("chars", dist_char), ("words", dist_word)], transformer_weights={"words": 10}) loc_union.fit(X) dist_union.fit(Z) X_transformed = loc_union.transform(X) Z_transformed = sp.vstack(dist_union.transform(Z).collect()) assert_array_equal(X_transformed.toarray(), Z_transformed.toarray())
def test_same_result_withdictrdd(self): X, X_rdd = self.make_text_rdd(2) Y_rdd = ArrayRDD(self.sc.parallelize([None] * len(X), 4), bsize=2) Z = DictRDD([X_rdd, Y_rdd], columns=("X", "y"), bsize=2) loc_char = CountVectorizer(analyzer="char_wb", ngram_range=(3, 3)) dist_char = SparkCountVectorizer(analyzer="char_wb", ngram_range=(3, 3)) loc_word = CountVectorizer(analyzer="word") loc_word_2 = CountVectorizer(analyzer="word") dist_word = SparkCountVectorizer(analyzer="word") dist_word_2 = SparkCountVectorizer(analyzer="word") loc_union = FeatureUnion([("chars", loc_char), ("words", loc_word), ("words2", loc_word_2)]) dist_union = SparkFeatureUnion([("chars", dist_char), ("words", dist_word), ("words2", dist_word_2)]) # test same feature names loc_union.fit(X) dist_union.fit(Z) converted_union = dist_union.to_scikit() assert_equal( loc_union.get_feature_names(), dist_union.get_feature_names(), converted_union.get_feature_names(), ) # test same results Z_transformed = sp.vstack(dist_union.transform(Z)[:, 'X'].collect()) assert_array_equal( loc_union.transform(X).toarray(), Z_transformed.toarray()) assert_array_equal( loc_union.transform(X).toarray(), converted_union.transform(X).toarray()) # test same results with fit_transform X_transformed = loc_union.fit_transform(X) X_converted_transformed = converted_union.fit_transform(X) Z_transformed = sp.vstack( dist_union.fit_transform(Z)[:, 'X'].collect()) assert_array_equal(X_transformed.toarray(), Z_transformed.toarray()) assert_array_equal(X_transformed.toarray(), X_converted_transformed.toarray()) # test same results in parallel loc_union_par = FeatureUnion([("chars", loc_char), ("words", loc_word)], n_jobs=2) dist_union_par = SparkFeatureUnion([("chars", dist_char), ("words", dist_word)], n_jobs=2) loc_union_par.fit(X) dist_union_par.fit(Z) converted_union = dist_union_par.to_scikit() X_transformed = loc_union_par.transform(X) Z_transformed = sp.vstack( dist_union_par.transform(Z)[:, 'X'].collect()) assert_array_equal(X_transformed.toarray(), Z_transformed.toarray()) assert_array_equal(X_transformed.toarray(), converted_union.transform(X).toarray())