def __init__(self):
optimizer = optim.SGD(0.1)
self.model = compose.Pipeline(
preprocessing.StandardScaler(),
linear_model.LogisticRegression(optimizer))
self.metric = metrics.Accuracy()
self.count = 0
def test_clone_idempotent():
model = preprocessing.StandardScaler() | linear_model.LogisticRegression(
optimizer=optim.Adam(), l2=0.1)
trace = []
for x, y in datasets.Phishing():
trace.append(model.predict_proba_one(x))
model.learn_one(x, y)
clone = model.clone()
for i, (x, y) in enumerate(datasets.Phishing()):
assert clone.predict_proba_one(x) == trace[i]
clone.learn_one(x, y)
def test_learn_one_warm_up_mode():
pipeline = compose.Pipeline(
("scale", preprocessing.StandardScaler()),
("log_reg", linear_model.LogisticRegression()),
)
dataset = [(dict(a=x, b=x), bool(x % 2)) for x in range(100)]
for x, y in dataset:
counts_pre = dict(pipeline["scale"].counts)
with utils.warm_up_mode():
pipeline.learn_one(x, y)
counts_post = dict(pipeline["scale"].counts)
pipeline.learn_one(x, y)
counts_no_learn = dict(pipeline["scale"].counts)
assert counts_pre != counts_post
assert counts_post == counts_no_learn
def test_learn_many_warm_up_mode():
pipeline = compose.Pipeline(
("scale", preprocessing.StandardScaler()),
("log_reg", linear_model.LogisticRegression()),
)
dataset = [(dict(a=x, b=x), x) for x in range(100)]
for i in range(0, len(dataset), 5):
X = pd.DataFrame([x for x, _ in dataset][i:i + 5])
y = pd.Series([bool(y % 2) for _, y in dataset][i:i + 5])
counts_pre = dict(pipeline["scale"].counts)
with utils.warm_up_mode():
pipeline.learn_many(X, y)
counts_post = dict(pipeline["scale"].counts)
pipeline.learn_many(X, y)
counts_no_learn = dict(pipeline["scale"].counts)
assert counts_pre != counts_post
assert counts_post == counts_no_learn
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[:]
def _unit_test_params(cls):
return {"classifier": linear_model.LogisticRegression(), "code_size": 6}