def test_online_batch_consistent():
# Batch
batch = (
preprocessing.StandardScaler() |
multiclass.OneVsRestClassifier(
linear_model.LogisticRegression()
)
)
dataset = datasets.ImageSegments()
batch_metric = metrics.MacroF1()
for i, x in enumerate(pd.read_csv(dataset.path, chunksize=1)):
y = x.pop('category')
y_pred = batch.predict_many(x)
batch.fit_many(x, y)
for yt, yp in zip(y, y_pred):
if yp is not None:
batch_metric.update(yt, yp)
if i == 30:
break
# Online
online = (
preprocessing.StandardScaler() |
multiclass.OneVsRestClassifier(
linear_model.LogisticRegression()
)
)
online_metric = metrics.MacroF1()
X = pd.read_csv(dataset.path)
Y = X.pop('category')
for i, (x, y) in enumerate(stream.iter_pandas(X, Y)):
y_pred = online.predict_one(x)
online.fit_one(x, y)
if y_pred is not None:
online_metric.update(y, y_pred)
if i == 30:
break
assert online_metric.get() == batch_metric.get()
def build_oracle(self) -> compose.Pipeline:
model = compose.Pipeline(
('scale', preprocessing.StandardScaler()),
('learn',
multiclass.OneVsRestClassifier(
binary_classifier=linear_model.LogisticRegression())))
return model
else:
inst = obj()
yield inst
@pytest.mark.parametrize('estimator, check', [
pytest.param(
copy.deepcopy(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(),
preprocessing.PolynomialExtender(),
feature_selection.VarianceThreshold(),
feature_selection.SelectKBest(similarity=stats.PearsonCorrelation())
] for check in utils.estimator_checks.yield_checks(estimator)
])
def test_check_estimator(estimator, check):
check(estimator)
elif issubclass(obj, multiclass.OneVsRestClassifier):
inst = obj(binary_classifier=linear_model.LogisticRegression())
else:
inst = obj()
yield inst
@pytest.mark.parametrize('estimator', [
pytest.param(copy.deepcopy(estimator), id=str(estimator))
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(),
preprocessing.PolynomialExtender(),
feature_selection.VarianceThreshold(),
feature_selection.SelectKBest(similarity=stats.PearsonCorrelation())
]
])
def test_check_estimator(estimator):
utils.estimator_checks.check_estimator(estimator)
optimizer = optim.Adam(lr, beta_1, beta_2, eps)
elif (opt == "FTRLProximal"):
optimizer = optim.FTRLProximal(alpha, beta, l1, l2)
elif (opt == "Momentum"):
optimizer = optim.Momentum(lr, rho)
elif (opt == "RMSProp"):
optimizer = optim.RMSProp(lr, rho, eps)
elif (opt == "VanillaSGD"):
optimizer = optim.VanillaSGD(lr)
elif (opt == "NesterovMomentum"):
optimizer = optim.NesterovMomentum(lr, rho)
else:
optimizer = None
log_reg = linear_model.LogisticRegression(optimizer, l2=l2)
OVRClassifier = multiclass.OneVsRestClassifier(log_reg)
output = {}
while True:
#wait request
data = input()
Xi = json.loads(data)
y = float(Xi.pop(target))
output["Predict"] = OVRClassifier.predict_one(Xi)
output["Truth"] = y
model = OVRClassifier.fit_one(Xi, y)
