def score(self, x, y):
"""
Returns the mean accuracy on the given test data and labels.
Parameters
----------
x : ds-array, shape=(n_samples, n_features)
Test samples.
y : ds-array, shape=(n_samples, 1)
True labels for x.
Returns
-------
score : float (as future object)
Mean accuracy of self.predict(x) wrt. y.
"""
assert (self._clf is not None or self._svs is not None), \
"Model has not been initialized. Call fit() first."
partial_scores = []
for x_row, y_row in _paired_partition(x, y):
partial = _score(x_row._blocks, y_row._blocks, self._clf)
partial_scores.append(partial)
return _merge_scores(*partial_scores)
def score(self, x, y, collect=False):
"""
Returns the mean accuracy on the given test data and labels.
Parameters
----------
x : ds-array, shape=(n_samples, n_features)
Test samples.
y : ds-array, shape=(n_samples, 1)
True labels for x.
collect : bool, optional (default=False)
When True, a synchronized result is returned.
Returns
-------
score : float (as future object)
Mean accuracy of self.predict(x) wrt. y.
"""
assert (self._clf is not None or self._svs is not None), \
"Model has not been initialized. Call fit() first."
partial_scores = []
for x_row, y_row in _paired_partition(x, y):
partial = _score(x_row._blocks, y_row._blocks, self._clf)
partial_scores.append(partial)
score = _merge_scores(*partial_scores)
return compss_wait_on(score) if collect else score
def score(self, x, y, collect=False):
"""Accuracy classification score.
Returns the mean accuracy of the predictions on the given test data.
Parameters
----------
x : ds-array, shape=(n_samples, n_features)
The training input samples.
y : ds-array, shape (n_samples, 1)
The true labels.
collect : bool, optional (default=False)
When True, a synchronized result is returned.
Returns
-------
score : float (as future object)
Fraction of correctly classified samples.
"""
assert self.trees is not None, "The random forest is not fitted."
partial_scores = []
if self.hard_vote:
for x_row, y_row in _paired_partition(x, y):
tree_predictions = []
for tree in self.trees:
tree_predictions.append(tree.predict(x_row))
subset_score = _hard_vote_score(y_row._blocks, self.classes,
*tree_predictions)
partial_scores.append(subset_score)
else:
for x_row, y_row in _paired_partition(x, y):
tree_predictions = []
for tree in self.trees:
tree_predictions.append(tree.predict_proba(x_row))
subset_score = _soft_vote_score(y_row._blocks, self.classes,
*tree_predictions)
partial_scores.append(subset_score)
score = _merge_classification_scores(*partial_scores)
return compss_wait_on(score) if collect else score
def score(self, x, y):
"""Accuracy classification score.
Returns the mean accuracy on the given test data.
Parameters
----------
x : ds-array, shape=(n_samples, n_features)
The training input samples.
y : ds-array, shape (n_samples, 1)
The true labels.
Returns
-------
score : float (as future object)
Fraction of correctly classified samples.
"""
assert self.trees is not None, 'The random forest is not fitted.'
partial_scores = []
if self.hard_vote:
for x_row, y_row in _paired_partition(x, y):
tree_predictions = []
for tree in self.trees:
tree_predictions.append(tree.predict(x_row))
subset_score = _hard_vote_score(y_row._blocks, self.classes,
*tree_predictions)
partial_scores.append(subset_score)
else:
for x_row, y_row in _paired_partition(x, y):
tree_predictions = []
for tree in self.trees:
tree_predictions.append(tree.predict_proba(x_row))
subset_score = _soft_vote_score(y_row._blocks, self.classes,
*tree_predictions)
partial_scores.append(subset_score)
return _merge_scores(*partial_scores)
def _w_step(self, x, y):
w_blocks = []
for xy_hblock, u_hblock in zip(_paired_partition(x, y),
self._u._iterator()):
x_hblock, y_hblock = xy_hblock
w_hblock = [object() for _ in range(x._n_blocks[1])]
x_blocks = x_hblock._blocks
y_blocks = y_hblock._blocks
u_blocks = u_hblock._blocks
_update_w(x_blocks, y_blocks, self._z, u_blocks, self.rho,
self.loss_fn, w_hblock)
w_blocks.append(w_hblock)
r_shape = self._u._reg_shape
self._w = Array(w_blocks, r_shape, r_shape, self._u.shape, x._sparse)
def _do_iteration(self, x, y, ids_list):
q = []
pars = self._clf_params
arity = self._arity
# first level
for partition, id_bk in zip(_paired_partition(x, y), ids_list):
x_data = partition[0]._blocks
y_data = partition[1]._blocks
ids = [id_bk]
if self._svs is not None:
x_data.append(self._svs)
y_data.append([self._sv_labels])
ids.append([self._sv_ids])
_tmp = _train(x_data, y_data, ids, self._random_state, **pars)
sv, sv_labels, sv_ids, self._clf = _tmp
q.append((sv, sv_labels, sv_ids))
# reduction
while len(q) > arity:
data = q[:arity]
del q[:arity]
x_data = [tup[0] for tup in data]
y_data = [[tup[1]] for tup in data]
ids = [[tup[2]] for tup in data]
_tmp = _train(x_data, y_data, ids, self._random_state, **pars)
sv, sv_labels, sv_ids, self._clf = _tmp
q.append((sv, sv_labels, sv_ids))
# delete partial results
for partial in data:
compss_delete_object(partial)
# last layer
x_data = [tup[0] for tup in q]
y_data = [[tup[1]] for tup in q]
ids = [[tup[2]] for tup in q]
_tmp = _train(x_data, y_data, ids, self._random_state, **pars)
self._svs, self._sv_labels, self._sv_ids, self._clf = _tmp
self.iterations += 1
def score(self, x, y, collect=False):
"""R2 regression score.
Returns the coefficient of determination $R^2$ of the prediction.
The coefficient $R^2$ is defined as $(1-u/v)$, where $u$
is the residual sum of squares `((y_true - y_pred) ** 2).sum()` and
$v$ is the total sum of squares
`((y_true - y_true.mean()) ** 2).sum()`.
The best possible score is 1.0 and it can be negative
if the model is arbitrarily worse.
A constant model that always predicts the expected value of y,
disregarding the input features, would get a $R^2$ score of 0.0.
Parameters
----------
x : ds-array, shape=(n_samples, n_features)
The training input samples.
y : ds-array, shape (n_samples, 1)
The true values.
collect : bool, optional (default=False)
When True, a synchronized result is returned.
Returns
-------
score : float (as future object)
Coefficient of determination $R^2$.
"""
assert self.trees is not None, "The random forest is not fitted."
partial_scores = []
for x_row, y_row in _paired_partition(x, y):
tree_predictions = []
for tree in self.trees:
tree_predictions.append(tree.predict(x_row))
subset_score = _regression_score(y_row._blocks, *tree_predictions)
partial_scores.append(subset_score)
score = _merge_regression_scores(*partial_scores)
return compss_wait_on(score) if collect else score