def iter_sklearn_dataset(dataset: "sklearn.utils.Bunch",
**kwargs) -> base.typing.Stream:
"""Iterates rows from one of the datasets provided by scikit-learn.
This allows you to use any dataset from [scikit-learn's `datasets` module](https://scikit-learn.org/stable/modules/classes.html#module-sklearn.datasets). For instance, you can use the `fetch_openml` function to get access to all of the
datasets from the OpenML website.
Parameters
----------
dataset
A scikit-learn dataset.
kwargs
Extra keyword arguments are passed to the underlying call to `stream.iter_array`.
Examples
--------
>>> import pprint
>>> from sklearn import datasets
>>> from river import stream
>>> dataset = datasets.load_boston()
>>> for xi, yi in stream.iter_sklearn_dataset(dataset):
... pprint.pprint(xi)
... print(yi)
... break
{'AGE': 65.2,
'B': 396.9,
'CHAS': 0.0,
'CRIM': 0.00632,
'DIS': 4.09,
'INDUS': 2.31,
'LSTAT': 4.98,
'NOX': 0.538,
'PTRATIO': 15.3,
'RAD': 1.0,
'RM': 6.575,
'TAX': 296.0,
'ZN': 18.0}
24.0
"""
kwargs["X"] = dataset.data
kwargs["y"] = dataset.target
try:
kwargs["feature_names"] = dataset.feature_names
except AttributeError:
pass
if isinstance(kwargs["X"], pd.DataFrame):
yield from stream.iter_pandas(**kwargs)
else:
yield from stream.iter_array(**kwargs)
def iter_sklearn_dataset(dataset: "sklearn.utils.Bunch",
**kwargs) -> base.typing.Stream:
"""Iterates rows from one of the datasets provided by scikit-learn.
This allows you to use any dataset from [scikit-learn's `datasets` module](https://scikit-learn.org/stable/modules/classes.html#module-sklearn.datasets). For instance, you can use the `fetch_openml` function to get access to all of the
datasets from the OpenML website.
Parameters
----------
dataset
A scikit-learn dataset.
kwargs
Extra keyword arguments are passed to the underlying call to `stream.iter_array`.
Examples
--------
>>> import pprint
>>> from sklearn import datasets
>>> from river import stream
>>> dataset = datasets.load_diabetes()
>>> for xi, yi in stream.iter_sklearn_dataset(dataset):
... pprint.pprint(xi)
... print(yi)
... break
{'age': 0.0380759064334241,
'bmi': 0.0616962065186885,
'bp': 0.0218723549949558,
's1': -0.0442234984244464,
's2': -0.0348207628376986,
's3': -0.0434008456520269,
's4': -0.00259226199818282,
's5': 0.0199084208763183,
's6': -0.0176461251598052,
'sex': 0.0506801187398187}
151.0
"""
kwargs["X"] = dataset.data
kwargs["y"] = dataset.target
try:
kwargs["feature_names"] = dataset.feature_names
except AttributeError:
pass
if isinstance(kwargs["X"], pd.DataFrame):
yield from stream.iter_pandas(**kwargs)
else:
yield from stream.iter_array(**kwargs)
def test_one_many_consistent():
"""Checks that using learn_one or learn_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.learn_one(x, y)
many = lm.LinearRegression()
for xb, yb in zip(np.array_split(X, len(X)), np.array_split(Y, len(Y))):
many.learn_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 learn_one or learn_many produces the same result."""
X = pd.read_csv(datasets.TrumpApproval().path)
one = preprocessing.StandardScaler()
for x, _ in stream.iter_pandas(X):
one.learn_one(x)
many = preprocessing.StandardScaler()
for xb in np.array_split(X, 10):
many.learn_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])
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.learn_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.learn_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()