def cross_val_score(estimator,
X,
y=None,
score_func=None,
cv=None,
n_jobs=-1,
verbose=0,
as_dvalues=False):
"""Evaluate a score by cross-validation.
Replacement of :func:`sklearn.cross_validation.cross_val_score`, used to
support computation of decision values.
"""
X, y = check_arrays(X, y, sparse_format='csr')
cv = check_cv(cv, X, y, classifier=is_classifier(estimator))
if score_func is None:
if not hasattr(estimator, 'score'):
raise TypeError(
"If no score_func is specified, the estimator passed "
"should have a 'score' method. The estimator %s "
"does not." % estimator)
# We clone the estimator to make sure that all the folds are
# independent, and that it is pickle-able.
scores = Parallel(n_jobs=n_jobs, verbose=verbose)(
delayed(_cross_val_score)(clone(estimator), X, y, score_func, train,
test, verbose, as_dvalues)
for train, test in cv)
return np.array(scores)
def Bootstrap_cv(estimator1, estimator2, X, y, score_func, cv=None, n_jobs=1,
verbose=0, ratio=.5):
X, y = cross_validation.check_arrays(X, y, sparse_format='csr')
cv = cross_validation.check_cv(cv, X, y,
classifier=
cross_validation.is_classifier(estimator1))
if score_func is None:
if not hasattr(estimator1, 'score') or \
not hasattr(estimator2, 'score'):
raise TypeError(
"If no score_func is specified, the estimator passed "
"should have a 'score' method. The estimator %s "
"does not." % estimator1)
# We clone the estimator to make sure that all the folds are
# independent, and that it is pickle-able.
scores = \
cross_validation.Parallel(
n_jobs=n_jobs, verbose=verbose)(
cross_validation.delayed(
dual_cross_val_score)
(cross_validation.clone(estimator1),
cross_validation.clone(estimator2),
X, y, score_func, train, test, verbose, ratio)
for train, test in cv)
return np.array(scores)
def _grid_search(self, train_X, train_y):
if callable(self.inner_cv):
inner_cv = self.inner_cv(train_X, train_y)
else:
inner_cv = check_cv(self.inner_cv, train_X, train_y, classifier=is_classifier(self.estimator))
master = MPIGridSearchCVMaster(self.param_grid, inner_cv, self.estimator, self.scorer_, self.fit_params)
return master.run(train_X, train_y)
def dynamic_cross_val_predict(estimator, fv, esa_feature_list, unigram_feature_list, dynamic_X, y=None, cv=None,
verbose=0, fit_params=None):
print "dynamic predict cross val mit %s" % esa_feature_list + unigram_feature_list
vec = DictVectorizer()
tfidf = TfidfTransformer()
X = vec.fit_transform(fv).toarray()
# X = tfidf.fit_transform(X).toarray()
X, y = cross_validation.indexable(X, y)
cv = cross_validation.check_cv(cv, X, y, classifier=cross_validation.is_classifier(estimator))
preds_blocks = []
cross_val_step = 0
for train, test in cv:
fv_copy = copy.deepcopy(fv)
#baue X in jedem Schritt neu
for i in range(0,len(fv)): #jedes i steht für einen featuredict
feature_dict = fv_copy[i]
dynamic_vec = dynamic_X[cross_val_step] #zeigt auf esa_vec
for feature in esa_feature_list:
feature_dict.update(dynamic_vec[find_index_for_dynamic_feature(feature)][i]) #das i-te feature-dict mit esa-feature updaten
for feature in unigram_feature_list:
feature_dict.update(dynamic_vec[find_index_for_dynamic_feature(feature)][i]) #das i-te feature-dict mit esa-feature updaten
X = vec.fit_transform(fv_copy).toarray()
# X = tfidf.fit_transform(X).toarray()
preds_blocks.append(cross_validation._fit_and_predict(cross_validation.clone(estimator), X, y,
train, test, verbose,
fit_params))
cross_val_step+=1
preds = [p for p, _ in preds_blocks]
locs = np.concatenate([loc for _, loc in preds_blocks])
if not cross_validation._check_is_partition(locs, cross_validation._num_samples(X)):
raise ValueError('cross_val_predict only works for partitions')
inv_locs = np.empty(len(locs), dtype=int)
inv_locs[locs] = np.arange(len(locs))
# Check for sparse predictions
if sp.issparse(preds[0]):
preds = sp.vstack(preds, format=preds[0].format)
else:
preds = np.concatenate(preds)
return preds[inv_locs]
def _grid_search_params_iter(self, train_X, train_y):
if callable(self.inner_cv):
inner_cv = self.inner_cv(train_X, train_y)
else:
inner_cv = _check_cv(self.inner_cv, train_X, train_y, classifier=is_classifier(self.estimator))
param_iter = ParameterGrid(self.param_grid)
LOG.info("Performing grid search over %d configurations" % len(param_iter))
for fold_id, (train_index, test_index) in enumerate(inner_cv):
for parameters in param_iter:
yield fold_id + 1, train_index, test_index, parameters
def fit(self, X, y):
X, y = check_X_y(X,
y,
force_all_finite=False,
multi_output=self.multi_output)
_check_param_grid(self.param_grid)
cv = _check_cv(self.cv, X, y, classifier=is_classifier(self.estimator))
self.scorer_ = check_scoring(self.estimator, scoring=self.scoring)
if comm_rank == 0:
self._fit_master(X, y, cv)
else:
self._fit_slave()
return self
def fit(self, X, y):
if master:
LOG.info("comm_size:" + str(comm_size))
X, y = check_X_y(X, y, force_all_finite=False, multi_output=self.multi_output, accept_sparse='csr')
_check_param_grid(self.param_grid)
cv = check_cv(self.cv, X, y, classifier=is_classifier(self.estimator))
if master:
LOG.info("cv length:" + str(len(cv)))
self.scorer_ = check_scoring(self.estimator, scoring=self.scoring)
if master:
self._fit_master(X, y, cv)
else:
self._fit_slave()
return self
def dynamic_cross_val_score(estimator, fv, esa_feature_list, unigram_feature_list, dynamic_X, y=None, scoring=None, cv=None,
verbose=0, fit_params=None):
print "dynamic cross val mit %s" % esa_feature_list + unigram_feature_list
vec = DictVectorizer()
tfidf = TfidfTransformer()
X = vec.fit_transform(fv).toarray()
# X= tfidf.fit_transform(X).toarray()
X, y = cross_validation.indexable(X, y)
cv = cross_validation.check_cv(cv, X, y, classifier=cross_validation.is_classifier(estimator))
scorer = cross_validation.check_scoring(estimator, scoring=scoring)
scores = []
cross_val_step = 0
for train, test in cv:
fv_copy = copy.deepcopy(fv)
#baue X in jedem Schritt neu
for i in range(0,len(fv)): #jedes i steht für einen featuredict
feature_dict = fv_copy[i]
dynamic_vec = dynamic_X[cross_val_step] #zeigt auf esa_vec
for feature in esa_feature_list:
feature_dict.update(dynamic_vec[find_index_for_dynamic_feature(feature)][i]) #das i-te feature-dict mit esa-feature updaten
for feature in unigram_feature_list:
feature_dict.update(dynamic_vec[find_index_for_dynamic_feature(feature)][i]) #das i-te feature-dict mit esa-feature updaten
X = vec.fit_transform(fv_copy).toarray()
# X = tfidf.fit_transform(X).toarray()
scores.append(cross_validation._fit_and_score(cross_validation.clone(estimator), X, y, scorer,
train, test, verbose, None, fit_params))
cross_val_step += 1
return np.array(scores)[:, 0]
def cross_val_score(estimator, X, y=None, score_func=None, cv=None, n_jobs=-1,
verbose=0, as_dvalues=False):
"""Evaluate a score by cross-validation.
Replacement of :func:`sklearn.cross_validation.cross_val_score`, used to
support computation of decision values.
"""
X, y = check_arrays(X, y, sparse_format='csr')
cv = check_cv(cv, X, y, classifier=is_classifier(estimator))
if score_func is None:
if not hasattr(estimator, 'score'):
raise TypeError(
"If no score_func is specified, the estimator passed "
"should have a 'score' method. The estimator %s "
"does not." % estimator)
# We clone the estimator to make sure that all the folds are
# independent, and that it is pickle-able.
scores = Parallel(n_jobs=n_jobs, verbose=verbose)(
delayed(_cross_val_score)(clone(estimator), X, y, score_func, train, test,
verbose, as_dvalues)
for train, test in cv)
return np.array(scores)
print "RF+Logit Accuracy: %0.2f (+/- %0.2f)" % (bs_scores.mean(), bs_scores.std() / 2)
bse_scores = Bootstrap_cv(extra_forest, logit, train_data[0::,1::], train_data[0::,0], score_func=precision_score, cv=10, ratio=.8)
print "EF+Logit Accuracy: %0.2f (+/- %0.2f)" % (bse_scores.mean(), bse_scores.std() / 2)
"""
print 'Predicting'
score = []
ratio = .2
estimators = 20
train_size = .7
#output = ratio*forest.predict(test_data) + (1-ratio)*logit.predict(test_data)
#output = extra_forest.predict(test_data)
#Get bootstrapped data
bs = cross_validation.Bootstrap(train_data.shape[0], n_bootstraps=estimators, train_size=train_size, random_state=0)
cv = cross_validation.check_cv(bs, train_data[0::,1::], train_data[0::,0], classifier=cross_validation.is_classifier(extra_forest))
for train, test in cv:
#Create training data
X = train_data[0::,1::]
y = train_data[0::,0]
#Create estimator
ef = cross_validation.clone(extra_forest)
lgi = cross_validation.clone(logit)
est = Pipeline([('ef', ef), ('logit', lgi)])
est.fit(X[train], y[train])
#print est.feature_importances_
score.append(est.score(X[test], y[test]))
#Format output
score = np.array(score)
def fit(self, X, y, fit_params=None, predict_params=None, X_test=None, y_test=None):
"""Do nested cross-validation.
If ``X_test`` and ``y_test`` are not provided, nested cross-validation using
``X`` and ``y`' is performed, i.e., data is first split into *K* folds, where
*K-1* folds are used for training and hyper-parameter selection and the
remaining fold for testing. The training portion is again split into *T* folds
to perform a grid-search over hyper-parameters. The parameters that achieved the
best average performance across the *T* inner cross-validation folds are selected.
Using these parameters, a model is trained on the entire training data and applied
to the *K*-th testing fold.
If ``X_test`` and ``y_test`` are provided, a regular cross-validation is performed on
``X`` and ``y`` to determine hyper-parameters as for the inner cross-validation above.
Using the best performing parameters, a model is trained on all of ``X`` and ``y`` and
applied to ``X_test`` and ``y_test`` for testing.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Feature matrix.
y : structured array, shape = [n_samples]
A structured array containing the binary event indicator
as first field, and time of event or time of censoring as
second field.
fit_params : dict
Additional arguments passed to the fit method.
predict_params : dict
Additional arguments passed to the predict method.
X_test : array-like, shape = [n_test_samples, n_features]
Hold-out data to perform testing on.
y_test : array-like or sequence, shape = [n_test_samples]
Target values of hold-out test data.
Returns
-------
self
"""
if y.dtype.names is None:
X, y = check_X_y(X, y)
else:
X, event, time = check_arrays_survival(X, y, force_all_finite=False)
y = numpy.fromiter(zip(event, time), dtype=[('event', numpy.bool), ('time', numpy.float64)])
if X_test is not None:
X_test, event_test, time_test = check_arrays_survival(X_test, y_test, force_all_finite=False)
y_test = numpy.fromiter(zip(event_test, time_test), dtype=[('event', numpy.bool), ('time', numpy.float64)])
cv = _check_cv(self.cv, X, y, classifier=is_classifier(self.estimator))
self.scorer_ = check_scoring(self.estimator, scoring=self.scoring)
self._dview, self._lview = self._init_cluster()
if X_test is None:
self._fit(X, y, cv, fit_params, predict_params)
else:
self._fit_holdout(X, y, fit_params, predict_params, X_test, y_test)
del self._dview
del self._lview
return self