def predict(self, X):
"""Predicts the target of an entire dataset contained in memory.
Parameters:
X: array-like of shape (n_samples, n_features).
Returns:
array of shape (n_samples,): Predicted target values for each row of `X`.
"""
# Check the fit method has been called
utils.validation.check_is_fitted(self, attributes='instance_')
# Check the input
X = utils.check_array(X, **SKLEARN_INPUT_X_PARAMS)
if X.shape[1] != self.n_features_in_:
raise ValueError(f'Expected {self.n_features_in_} features, got {X.shape[1]}')
# Make a prediction for each observation
y_pred = [None] * len(X)
for i, (x, _) in enumerate(stream.iter_array(X)):
y_pred[i] = self.instance_.predict_one(x)
# Convert back to the expected labels if an encoder was necessary for BinaryClassifier
y_pred = np.asarray(y_pred)
if hasattr(self, 'label_encoder_'):
y_pred = self.label_encoder_.inverse_transform(y_pred.astype(int))
return y_pred
def predict_proba(self, X):
"""Predicts the target probability of an entire dataset contained in memory.
Parameters:
X (array-like of shape (n_samples, n_features))
Returns:
array of shape (n_samples,): Predicted target values for each row of `X`.
"""
# Check the fit method has been called
utils.validation.check_is_fitted(self, attributes='instance_')
# Check the input
X = utils.check_array(X, **SKLEARN_INPUT_X_PARAMS)
if X.shape[1] != self.n_features_in_:
raise ValueError(f'Expected {self.n_features_in_} features, got {X.shape[1]}')
# creme's predictions have to converted to follow the scikit-learn conventions
def reshape_probas(y_pred):
return [y_pred.get(c, 0) for c in self.classes_]
# Make a prediction for each observation
y_pred = np.empty(shape=(len(X), len(self.classes_)))
for i, (x, _) in enumerate(stream.iter_array(X)):
y_pred[i] = reshape_probas(self.instance_.predict_proba_one(x))
return y_pred
def predict(self, X):
"""Predicts the target of an entire dataset contained in memory.
Parameters:
X: array-like of shape (n_samples, n_features).
Returns:
array of shape (n_samples,): Predicted target values for each row of `X`.
"""
# Check the fit method has been called
utils.validation.check_is_fitted(self, attributes='instance_')
# Check the input
X = utils.check_array(X, **SKLEARN_INPUT_X_PARAMS)
if X.shape[1] != self.n_features_in_:
raise ValueError(f'Expected {self.n_features_in_} features, got {X.shape[1]}')
# Make a prediction for each observation
y_pred = np.empty(shape=len(X))
for i, (x, _) in enumerate(stream.iter_array(X)):
y_pred[i] = self.instance_.predict_one(x)
return y_pred
def iter_pandas(X: pd.DataFrame, y: typing.Union[pd.Series, pd.DataFrame] = None,
**kwargs) -> base.typing.Stream:
"""Iterates over the rows of a `pandas.DataFrame`.
Parameters:
X: A dataframe of features.
y: A series or a dataframe with one column per target.
Example:
>>> import pandas as pd
>>> from creme import stream
>>> X = pd.DataFrame({
... 'x1': [1, 2, 3, 4],
... 'x2': ['blue', 'yellow', 'yellow', 'blue'],
... 'y': [True, False, False, True]
... })
>>> y = X.pop('y')
>>> for xi, yi in stream.iter_pandas(X, y):
... print(xi, yi)
{'x1': 1, 'x2': 'blue'} True
{'x1': 2, 'x2': 'yellow'} False
{'x1': 3, 'x2': 'yellow'} False
{'x1': 4, 'x2': 'blue'} True
"""
kwargs['feature_names'] = X.columns
if isinstance(y, pd.DataFrame):
kwargs['target_names'] = y.columns
yield from stream.iter_array(X=X.to_numpy(), y=y if y is None else y.to_numpy(), **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.
Example:
>>> import pprint
>>> from sklearn import datasets
>>> from creme 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
yield from stream.iter_array(**kwargs)
def iter_sklearn_dataset(dataset: 'sklearn.utils.Bunch',
**kwargs) -> base.typing.Stream:
"""Yields rows from one of the datasets provided by scikit-learn.
Parameters:
dataset: A scikit-learn dataset.
Example:
>>> import pprint
>>> from sklearn import datasets
>>> from creme 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
yield from stream.iter_array(**kwargs)