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 test_one_many_consistent():
"""Checks that using fit_one or fit_many produces the same result."""
X = pd.read_csv(datasets.TrumpApproval().path)
Y = X.pop('five_thirty_eight')
one = lm.LinearRegression()
for x, y in stream.iter_pandas(X, Y):
one.fit_one(x, y)
many = lm.LinearRegression()
for xb, yb in zip(np.array_split(X, len(X)), np.array_split(Y, len(Y))):
many.fit_many(xb, yb)
for i in X:
assert math.isclose(one.weights[i], many.weights[i])
def test_standard_scaler_one_many_consistent():
"""Checks that using fit_one or fit_many produces the same result."""
X = pd.read_csv(datasets.TrumpApproval().path)
one = preprocessing.StandardScaler()
for x, _ in stream.iter_pandas(X):
one.fit_one(x)
many = preprocessing.StandardScaler()
for xb in np.array_split(X, 10):
many.fit_many(xb)
for i in X:
assert math.isclose(one.counts[i], many.counts[i])
assert math.isclose(one.means[i], many.means[i])
assert math.isclose(one.vars[i], many.vars[i])