Logistic_model = compose.Pipeline(
('features',
compose.TransformerUnion(
('pipe1',
compose.Pipeline(('drop_non_features',
compose.Discard('body', 'date', 'subject', 'text',
'title', 'title_clean')),
('scale', preprocessing.StandardScaler()))),
('pipe2',
compose.Pipeline(
('drop_non_featuress',
compose.Discard('body', 'body_len', 'body_num', 'date',
'punct%', 'subject', 'text', 'title',
'title_len', 'title_num')),
('tfidf', feature_extraction.TFIDF(on='title_clean')))))),
('modeling', linear_model.LogisticRegression()))
#metric = metrics.Accuracy()
#evaluate.progressive_val_score(dataset_tuple_a, model, metric)
#model.predict_proba_one(z)
#model.predict_one(z)
#print(Logistic_model.draw())
metric = metrics.ROCAUC()
train1 = train[:]
submodule = f"river.{submodule}"
for _, obj in inspect.getmembers(importlib.import_module(submodule),
is_estimator):
if issubclass(obj, ignored):
continue
params = obj._unit_test_params()
yield obj(**params)
@pytest.mark.parametrize(
"estimator, check",
[
pytest.param(estimator, check, id=f"{estimator}:{check.__name__}")
for estimator in list(get_all_estimators()) + [
feature_extraction.TFIDF(),
linear_model.LogisticRegression(),
preprocessing.StandardScaler() | linear_model.LinearRegression(),
preprocessing.StandardScaler() | linear_model.PAClassifier(),
(preprocessing.StandardScaler()
| multiclass.OneVsRestClassifier(
linear_model.LogisticRegression())),
(preprocessing.StandardScaler()
| multiclass.OneVsRestClassifier(linear_model.PAClassifier())),
naive_bayes.GaussianNB(),
preprocessing.StandardScaler(),
cluster.KMeans(n_clusters=5, seed=42),
preprocessing.MinMaxScaler(),
preprocessing.MinMaxScaler() + preprocessing.StandardScaler(),
feature_extraction.PolynomialExtender(),
(feature_extraction.PolynomialExtender()
train = train_tuple[:]
test = test_tuple[:]
#Passive Aggressive Classifier
PA_model = compose.Pipeline(
('features',
compose.TransformerUnion(
('pipe1',
compose.Pipeline(('select_numeric_features',
compose.Select('length', 'punct%', 'similarity')),
('scale', preprocessing.MinMaxScaler()))),
('pipe2',
compose.Pipeline(
('select_text_features', compose.Select('content')),
('tfidf', feature_extraction.TFIDF(on='content')))))),
('modeling', linear_model.PAClassifier()))
metric = metrics.ROCAUC()
train1 = train[:]
PA_score1 = []
y_pred_l1 = []
y_l1 = []
for x, y in train1:
x = text_processing(x)
y_pred = PA_model.predict_one(x)
y_pred_l1.append(y_pred)
y_l1.append(y)
PA_model.learn_one(x, y)
metric.update(y, y_pred)
PA_score1.append(float(str(metric).split(':')[1]))