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 yield_datasets(model):
from creme import base
from creme import datasets
from creme import stream
from sklearn import datasets as sk_datasets
model = guess_model(model)
if isinstance(model, (base.BinaryClassifier, base.MultiClassifier)):
yield datasets.Phishing()
if isinstance(model, base.MultiClassifier):
yield datasets.ImageSegments().take(500)
if isinstance(model, base.Regressor):
yield datasets.TrumpApproval()
if isinstance(model, base.MultiOutputRegressor):
yield stream.iter_sklearn_dataset(sk_datasets.load_linnerud())
if isinstance(model, base.MultiOutputClassifier):
yield datasets.Music()
def yield_datasets(model):
from creme import base
from creme import compose
from creme import datasets
from creme import preprocessing
from creme import stream
from sklearn import datasets as sk_datasets
model = guess_model(model)
# Classification
if isinstance(model, (base.BinaryClassifier, base.MultiClassifier)):
yield datasets.Phishing()
# Multi-class classification
if isinstance(model, base.MultiClassifier):
yield datasets.ImageSegments().take(500)
# Regression
if isinstance(model, base.Regressor):
yield datasets.TrumpApproval()
# Multi-output regression
if isinstance(model, base.MultiOutputRegressor):
# 1
yield stream.iter_sklearn_dataset(sk_datasets.load_linnerud())
# 2
class SolarFlare:
"""One-hot encoded version of `datasets.SolarFlare`."""
def __iter__(self):
oh = (compose.SelectType(str) |
preprocessing.OneHotEncoder()) + compose.SelectType(int)
for x, y in datasets.SolarFlare():
yield oh.transform_one(x), y
yield SolarFlare()
# Multi-output classification
if isinstance(model, base.MultiOutputClassifier):
yield datasets.Music()
def yield_datasets(model):
from creme import base
from creme import datasets
from creme import stream
from sklearn import datasets as sk_datasets
model = guess_model(model)
if isinstance(model, (base.BinaryClassifier, base.MultiClassifier)):
yield datasets.Phishing()
if isinstance(model, base.MultiClassifier):
yield datasets.ImageSegments().take(500)
if isinstance(model, base.Regressor):
yield datasets.TrumpApproval()
if isinstance(model, base.MultiOutputRegressor):
yield stream.iter_sklearn_dataset(sk_datasets.load_linnerud())
if isinstance(model, base.MultiOutputClassifier):
yeast = stream.iter_sklearn_dataset(sk_datasets.fetch_openml('yeast', version=4))
yield itertools.islice(yeast, 100)
def yield_datasets(model):
from creme import compose
from creme import datasets
from creme import preprocessing
from creme import stream
from creme import utils
from sklearn import datasets as sk_datasets
# Classification
if utils.inspect.isclassifier(model):
yield datasets.Phishing()
# Multi-class classification
if model._multiclass:
yield datasets.ImageSegments().take(500)
# Regression
if utils.inspect.isregressor(model):
yield datasets.TrumpApproval()
# Multi-output regression
if utils.inspect.ismoregressor(model):
# 1
yield stream.iter_sklearn_dataset(sk_datasets.load_linnerud())
# 2
class SolarFlare:
"""One-hot encoded version of `datasets.SolarFlare`."""
def __iter__(self):
oh = (compose.SelectType(str) | preprocessing.OneHotEncoder()) + compose.SelectType(int)
for x, y in datasets.SolarFlare():
yield oh.transform_one(x), y
yield SolarFlare()
# Multi-output classification
if utils.inspect.ismoclassifier(model):
yield datasets.Music()