diff --git a/summit/multiview_platform/multiview/exec_multiview.py b/summit/multiview_platform/multiview/exec_multiview.py
index 254b11b3a676e0a82e3c7ef6abb6a4dc0a181753..d2fbf8efb6d3e3f813823bb3126613688ec1e451 100644
--- a/summit/multiview_platform/multiview/exec_multiview.py
+++ b/summit/multiview_platform/multiview/exec_multiview.py
@@ -5,6 +5,7 @@ import time
import h5py
import numpy as np
+from matplotlib.style.core import available
from .multiview_utils import MultiviewResult, MultiviewResultAnalyzer
from .. import multiview_classifiers
@@ -256,7 +257,7 @@ def exec_multiview(directory, dataset_var, name, classification_indices,
logging.info("Info:\t Extraction duration " + str(extraction_time) + "s")
logging.info("Start:\t Getting train/test split")
- learning_indices, validation_indices = classification_indices
+ available_indices, validation_indices = classification_indices
logging.info("Done:\t Getting train/test split")
logging.info("Start:\t Getting classifiers modules")
@@ -275,11 +276,11 @@ def exec_multiview(directory, dataset_var, name, classification_indices,
**classifier_config)
estimator = get_mc_estim(estimator, random_state,
multiview=True,
- y=dataset_var.get_labels()[learning_indices])
+ y=dataset_var.get_labels()[available_indices])
hps = hps_method_class(estimator, scoring=metrics, cv=k_folds,
random_state=random_state, framework="multiview",
n_jobs=nb_cores,
- learning_indices=learning_indices,
+ available_indices=available_indices,
view_indices=views_indices, **hps_kwargs)
hps.fit(dataset_var, dataset_var.get_labels(), )
classifier_config = hps.get_best_params()
@@ -294,7 +295,7 @@ def exec_multiview(directory, dataset_var, name, classification_indices,
logging.info("Start:\t Fitting classifier")
fit_beg = time.monotonic()
classifier.fit(dataset_var, dataset_var.get_labels(),
- train_indices=learning_indices,
+ train_indices=available_indices,
view_indices=views_indices)
print("pou")
fit_duration = time.monotonic() - fit_beg
@@ -302,7 +303,7 @@ def exec_multiview(directory, dataset_var, name, classification_indices,
logging.info("Start:\t Predicting")
train_pred = classifier.predict(dataset_var,
- sample_indices=learning_indices,
+ sample_indices=available_indices,
view_indices=views_indices)
pred_beg = time.monotonic()
test_pred = classifier.predict(dataset_var,
@@ -310,7 +311,7 @@ def exec_multiview(directory, dataset_var, name, classification_indices,
view_indices=views_indices)
pred_duration = time.monotonic() - pred_beg
full_pred = np.zeros(dataset_var.get_labels().shape, dtype=int) - 100
- full_pred[learning_indices] = train_pred
+ full_pred[available_indices] = train_pred
full_pred[validation_indices] = test_pred
logging.info("Done:\t Pertidcting")
diff --git a/summit/multiview_platform/utils/dataset.py b/summit/multiview_platform/utils/dataset.py
index c474f8ad6c942cae74c4dd1eeae813ac641e7cc8..beaf5829d86231854630d0f935968b7e450e343a 100644
--- a/summit/multiview_platform/utils/dataset.py
+++ b/summit/multiview_platform/utils/dataset.py
@@ -215,11 +215,11 @@ class RAMDataset(Dataset):
def get_label_names(self, sample_indices=None, decode=True):
selected_labels = self.get_labels(sample_indices)
if decode:
- return [label_name.encode("utf-8")
+ return [label_name.encode('utf-8')
for label, label_name in enumerate(self.labels_names)
if label in selected_labels]
else:
- return [label_name.encode("utf-8")
+ return [label_name
for label, label_name in enumerate(self.labels_names)
if label in selected_labels]
@@ -484,7 +484,7 @@ class HDF5Dataset(Dataset):
"name"]] = view_index
return view_dict
- def get_label_names(self, decode=True, sample_indices=None):
+ def get_label_names(self, decode=False, sample_indices=None):
"""
Used to get the list of the label names for the given set of samples
@@ -502,8 +502,10 @@ class HDF5Dataset(Dataset):
seleted labels' names
"""
selected_labels = self.get_labels(sample_indices)
+ print("selected labels ", selected_labels)
+ print("self.dataset ", self.dataset["Labels"].attrs["names"])
if decode:
- return [label_name
+ return [label_name.decode("utf-8")
for label, label_name in
enumerate(self.dataset["Labels"].attrs["names"])
if label in selected_labels]
diff --git a/summit/multiview_platform/utils/hyper_parameter_search.py b/summit/multiview_platform/utils/hyper_parameter_search.py
index c5cf33f1e12fd9f9250c2dc52b828d61024ff561..49ed36bcc2da21e77cc61126504e5e034859b26d 100644
--- a/summit/multiview_platform/utils/hyper_parameter_search.py
+++ b/summit/multiview_platform/utils/hyper_parameter_search.py
@@ -55,6 +55,7 @@ class HPSearch:
return metric
def fit_multiview(self, X, y, groups=None, **fit_params):
+ print(self.available_indices)
n_splits = self.cv.get_n_splits(self.available_indices,
y[self.available_indices])
folds = list(
@@ -153,7 +154,7 @@ class HPSearch:
class Random(RandomizedSearchCV, HPSearch):
def __init__(self, estimator, param_distributions=None, n_iter=10,
- refit=False, n_jobs=1, scoring=None, cv=None, learning_indices=None,
+ refit=False, n_jobs=1, scoring=None, cv=None, available_indices=None,
random_state=None, view_indices=None,
framework="monoview",
equivalent_draws=True, track_tracebacks=True):
@@ -166,7 +167,7 @@ class Random(RandomizedSearchCV, HPSearch):
refit=refit, n_jobs=n_jobs, scoring=scoring,
cv=cv, random_state=random_state)
self.framework = framework
- self.available_indices = learning_indices
+ self.available_indices = available_indices
self.view_indices = view_indices
self.equivalent_draws = equivalent_draws
self.track_tracebacks = track_tracebacks
@@ -211,14 +212,14 @@ class Grid(GridSearchCV, HPSearch):
def __init__(self, estimator, param_grid={}, refit=False, n_jobs=1,
scoring=None, cv=None,
- learning_indices=None, view_indices=None, framework="monoview",
+ available_indices=None, view_indices=None, framework="monoview",
random_state=None, track_tracebacks=True):
scoring = HPSearch.get_scoring(self, scoring)
GridSearchCV.__init__(self, estimator, param_grid, scoring=scoring,
n_jobs=n_jobs, refit=refit,
cv=cv)
self.framework = framework
- self.available_indices = learning_indices
+ self.available_indices = available_indices
self.view_indices = view_indices
self.track_tracebacks = track_tracebacks
self.tracebacks = []
diff --git a/summit/multiview_platform/utils/multiclass.py b/summit/multiview_platform/utils/multiclass.py
index 98c6c1d6bfcf9e3c8fcbeec5eb72f093a873f73d..2d7189e242b1c9d98d8619acb415bb03220546f7 100644
--- a/summit/multiview_platform/utils/multiclass.py
+++ b/summit/multiview_platform/utils/multiclass.py
@@ -217,7 +217,7 @@ def _multiview_fit_ovo_binary(estimator, X, y, i, j, train_indices,
view_indices):
cond = np.logical_or(y == i, y == j)
# y = y[cond]
- y_binary = np.empty(y.shape, np.int)
+ y_binary = np.empty(y.shape, np.int_)
y_binary[y == i] = 0
y_binary[y == j] = 1
indcond = np.arange(X.get_nb_samples())[cond]
@@ -230,6 +230,12 @@ def _multiview_fit_ovo_binary(estimator, X, y, i, j, train_indices,
class MultiviewOVOWrapper(MultiviewWrapper, OneVsOneClassifier):
+ def get_tags(self):
+ """Get tags of estimateur see sklearn > 1.6.0 _pairwise attribut removed """
+ if hasattr(self.estimator, "get_tags"):
+ return self.estimator.get_tags()
+ return {"pairwise": False}
+
def fit(self, X, y, train_indices=None, view_indices=None):
"""Fit underlying estimators.
@@ -265,7 +271,7 @@ class MultiviewOVOWrapper(MultiviewWrapper, OneVsOneClassifier):
self.estimators_ = estimators_indices[0]
self.pairwise_indices_ = (
- estimators_indices[1] if self._pairwise else None)
+ estimators_indices[1] if self.get_tags()["pairwise"] else None)
return self
diff --git a/summit/tests/test_multi_view/test_multiview_utils.py b/summit/tests/test_multi_view/test_multiview_utils.py
index 99d725253c7a0341719913856259c00d65fba3a9..7ead1eb6bb4a174b75489f635e25a31b180a02c4 100644
--- a/summit/tests/test_multi_view/test_multiview_utils.py
+++ b/summit/tests/test_multi_view/test_multiview_utils.py
@@ -76,9 +76,11 @@ class TestFunctions(unittest.TestCase):
self.assertEqual(avail, ['adaboost',
'decision_tree',
'gradient_boosting',
+ 'imbalance_bagging',
'knn',
'lasso',
'random_forest',
+ 'random_scm',
'scm',
'sgd',
'svm_linear',
@@ -89,8 +91,10 @@ class TestFunctions(unittest.TestCase):
self.assertEqual(avail, ['adaboost',
'decision_tree',
'gradient_boosting',
+ 'imbalance_bagging',
'knn',
'random_forest',
+ 'random_scm',
'scm',
'svm_linear',
'svm_poly',
diff --git a/summit/tests/test_utils/test_GetMultiviewDB.py b/summit/tests/test_utils/test_GetMultiviewDB.py
index 13cab526f46e079f89c9ca540a2d3d10e2373058..ce4392f6662075bfdc6974f5f5cbaad13721305a 100644
--- a/summit/tests/test_utils/test_GetMultiviewDB.py
+++ b/summit/tests/test_utils/test_GetMultiviewDB.py
@@ -53,6 +53,8 @@ class Test_get_classic_db_hdf5(unittest.TestCase):
self.assertEqual(dataset.nb_view, 1)
self.assertEqual(labels_dictionary,
{0: "0", 1: "2", 2: "1"})
+ print(labels_dictionary)
+ print(dataset.get_labels())
self.assertEqual(dataset.get_nb_samples(), 5)
self.assertEqual(len(np.unique(dataset.get_labels())), 3)
diff --git a/summit/tests/test_utils/test_dataset.py b/summit/tests/test_utils/test_dataset.py
index 67750428c00bbe80f513c00fb35311c314900a3f..8536f90084493a8f8f7b7ec42d62f6010f1d2a61 100644
--- a/summit/tests/test_utils/test_dataset.py
+++ b/summit/tests/test_utils/test_dataset.py
@@ -162,7 +162,7 @@ class Test_Dataset(unittest.TestCase):
decoded_label_names = dataset_object.get_label_names()
restricted_label_names = dataset_object.get_label_names(
sample_indices=[3, 4])
- self.assertEqual(raw_label_names, [b'0', b'1', b'2'])
+ self.assertEqual(raw_label_names, ['0', '1', '2'])
self.assertEqual(decoded_label_names, ['0', '1', '2'])
self.assertEqual(restricted_label_names, ['2'])
@@ -319,7 +319,7 @@ class TestRAMDataset(unittest.TestCase):
self.assertEqual(shape, ['0'.encode('utf-8'),
'1'.encode('utf-8'),
'2'.encode('utf-8')])
- shape = dataset_object.get_label_names(decode=False)
+ shape = dataset_object.get_label_names(decode=True)
self.assertEqual(shape, ['0'.encode('utf-8'),
'1'.encode('utf-8'),
'2'.encode('utf-8')])
diff --git a/summit/tests/test_utils/test_hyper_parameter_search.py b/summit/tests/test_utils/test_hyper_parameter_search.py
index 8a5c9ec3d6fdca8bf6e50e5a408ae7ebf484a52e..65381b95bab105f09697abb73ec6975f8b948de7 100644
--- a/summit/tests/test_utils/test_hyper_parameter_search.py
+++ b/summit/tests/test_utils/test_hyper_parameter_search.py
@@ -66,7 +66,7 @@ class Test_Random(unittest.TestCase):
cls.scoring = make_scorer(accuracy_score, )
cls.cv = StratifiedKFold(n_splits=n_splits, )
cls.random_state = np.random.RandomState(42)
- # cls.learning_indices = np.array([0, 1, 2, 3, 4, ])
+ cls.available_indices = np.array([0, 1, 2, 3, 4, ])
cls.view_indices = None
cls.framework = "monoview"
cls.equivalent_draws = False
@@ -78,7 +78,8 @@ class Test_Random(unittest.TestCase):
self.estimator, self.param_distributions, n_iter=self.n_iter,
refit=self.refit, n_jobs=self.n_jobs, scoring=self.scoring, cv=self.cv,
random_state=self.random_state,
- view_indices=self.view_indices,
+ available_indices=self.available_indices,
+ view_indices=self.view_indices,
framework=self.framework,
equivalent_draws=self.equivalent_draws
)
@@ -89,6 +90,7 @@ class Test_Random(unittest.TestCase):
refit=self.refit, n_jobs=self.n_jobs, scoring=self.scoring,
cv=self.cv,
random_state=self.random_state,
+ available_indices=self.available_indices,
view_indices=self.view_indices,
framework=self.framework,
equivalent_draws=self.equivalent_draws
@@ -105,6 +107,7 @@ class Test_Random(unittest.TestCase):
refit=self.refit, n_jobs=self.n_jobs, scoring=self.scoring,
cv=self.cv,
random_state=self.random_state,
+ available_indices=self.available_indices,
view_indices=self.view_indices,
framework="multiview",
equivalent_draws=self.equivalent_draws
@@ -120,6 +123,7 @@ class Test_Random(unittest.TestCase):
cv=self.cv,
random_state=self.random_state,
view_indices=self.view_indices,
+ available_indices=self.available_indices,
framework="multiview",
equivalent_draws=True
)
@@ -134,6 +138,7 @@ class Test_Random(unittest.TestCase):
refit=self.refit, n_jobs=self.n_jobs, scoring=self.scoring,
cv=self.cv,
random_state=self.random_state,
+ available_indices=self.available_indices,
view_indices=self.view_indices,
framework="multiview",
equivalent_draws=False
@@ -200,7 +205,7 @@ class Test_Grid(unittest.TestCase):
# "splitter": "best"}
# cls.k_folds = StratifiedKFold(n_splits=3, random_state=cls.random_state,
# shuffle=True)
-# cls.learning_indices = np.array([1,2,3,4, 5,6,7,8,9])
+# cls.available_indices= np.array([1,2,3,4, 5,6,7,8,9])
# cls.dataset = HDF5Dataset(hdf5_file=cls.dataset_file)
#
# @classmethod