diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 96070201033c21397c009349deeedd08ab6a2e01..2b8e89e8f39c952aa07f380aa39b3f2c653a78a0 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -40,6 +40,7 @@ pages:
script:
- export LC_ALL=$(locale -a | grep en_US)
- export LANG=$(locale -a | grep en_US)
+ - python3 setup.py install
- python3 setup.py build_sphinx
- cp -r build/sphinx/html public
artifacts:
diff --git a/multimodal/boosting/boost.py b/multimodal/boosting/boost.py
index f6d7c685f0c4fe6172e69ed858f6c458d2814269..bab7c806721c891bec828f7c25ff7864a734d366 100644
--- a/multimodal/boosting/boost.py
+++ b/multimodal/boosting/boost.py
@@ -44,12 +44,12 @@ import scipy.sparse as sp
from abc import ABCMeta
from sklearn.utils import check_array, check_X_y, check_random_state
from sklearn.tree import DecisionTreeClassifier
-from sklearn.tree.tree import BaseDecisionTree
+from sklearn.tree import BaseDecisionTree
from sklearn.tree._tree import DTYPE
-from sklearn.ensemble.forest import BaseForest
from sklearn.base import clone
from sklearn.ensemble._base import _set_random_states
from sklearn.ensemble import BaseEnsemble
+from sklearn.ensemble._forest import BaseForest
from multimodal.datasets.data_sample import DataSample
from multimodal.datasets.data_sample import MultiModalData, MultiModalArray, MultiModalSparseArray
@@ -83,13 +83,6 @@ class UBoosting(metaclass=ABCMeta):
def _validate_X_predict(self, X):
"""Ensure that X is in the proper format."""
- if (self.base_estimator is None or
- isinstance(self.base_estimator,
- (BaseDecisionTree, BaseForest))):
- check_array(X, accept_sparse='csr', dtype=DTYPE)
-
- else:
- check_array(X, accept_sparse=['csr', 'csc'])
if X.ndim < 2:
X = X[np.newaxis, :]
if X.shape[1] != self.n_features_:
@@ -97,8 +90,15 @@ class UBoosting(metaclass=ABCMeta):
"match the input. Model n_features is %s and "
"input n_features is %s " % (self.n_features_, X.shape[1]))
else:
- mes = "Reshape your data"
+ mes = "Reshape your data as a 2D-array "
raise ValueError(mes)
+ if (self.base_estimator is None or
+ isinstance(self.base_estimator,
+ (BaseDecisionTree, BaseForest))):
+ check_array(X, accept_sparse='csr', dtype=DTYPE)
+
+ else:
+ check_array(X, accept_sparse=['csr', 'csc'])
if X.ndim > 1:
if X.shape[1] != self.n_features_:
if X.shape[0] == self.n_features_ and X.shape[1] > 1:
@@ -107,10 +107,6 @@ class UBoosting(metaclass=ABCMeta):
raise ValueError("Number of features of the model must "
"match the input. Model n_features is %s and "
"input n_features is %s " % (self.n_features_, X.shape[1]))
-
-
- #
- # raise ValueError(mes)
return X
def _global_X_transform(self, X, views_ind=None):
@@ -121,10 +117,10 @@ class UBoosting(metaclass=ABCMeta):
X_ = MultiModalSparseArray(X, views_ind)
else:
X_ = MultiModalArray(X, views_ind)
- if not isinstance(X_, MultiModalData):
- try:
- X_ = np.asarray(X)
- X_ = MultiModalArray(X_)
- except Exception as e:
- raise TypeError('Reshape your data')
+ # if not isinstance(X_, MultiModalData):
+ # try:
+ # X_ = np.asarray(X)
+ # X_ = MultiModalArray(X_)
+ # except Exception as e:
+ # raise TypeError('Reshape your data')
return X_
diff --git a/multimodal/boosting/combo.py b/multimodal/boosting/combo.py
index 5b67ba8215c3d44b59e69b8d2f03f7caddd6d1b4..c5be4a1bfbda7f9dc43a30123fc3f8535f738ea7 100644
--- a/multimodal/boosting/combo.py
+++ b/multimodal/boosting/combo.py
@@ -48,11 +48,11 @@ estimator for classification implemented in the ``MuComboClassifier`` class.
import numpy as np
from sklearn.base import ClassifierMixin
from sklearn.ensemble import BaseEnsemble
-from sklearn.ensemble.forest import BaseForest
+from sklearn.ensemble._forest import BaseForest
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree._tree import DTYPE
-from sklearn.tree.tree import BaseDecisionTree
+from sklearn.tree import BaseDecisionTree
from sklearn.utils import check_array, check_X_y, check_random_state
from sklearn.utils.multiclass import check_classification_targets
from sklearn.utils.validation import check_is_fitted, has_fit_parameter
@@ -127,13 +127,13 @@ class MuComboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
>>> views_ind = [0, 2, 4] # view 0: sepal data, view 1: petal data
>>> clf = MuComboClassifier(random_state=0)
>>> clf.fit(X, y, views_ind) # doctest: +NORMALIZE_WHITESPACE
- MuComboClassifier(base_estimator=None, n_estimators=50, random_state=0)
+ MuComboClassifier(random_state=0)
>>> print(clf.predict([[ 5., 3., 1., 1.]]))
[0]
>>> views_ind = [[0, 2], [1, 3]] # view 0: length data, view 1: width data
>>> clf = MuComboClassifier(random_state=0)
>>> clf.fit(X, y, views_ind) # doctest: +NORMALIZE_WHITESPACE
- MuComboClassifier(base_estimator=None, n_estimators=50, random_state=0)
+ MuComboClassifier(random_state=0)
>>> print(clf.predict([[ 5., 3., 1., 1.]]))
[0]
@@ -141,13 +141,8 @@ class MuComboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
>>> base_estimator = DecisionTreeClassifier(max_depth=2)
>>> clf = MuComboClassifier(base_estimator=base_estimator, random_state=1)
>>> clf.fit(X, y, views_ind) # doctest: +NORMALIZE_WHITESPACE
- MuComboClassifier(base_estimator=DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=2,
- max_features=None, max_leaf_nodes=None,
- min_impurity_decrease=0.0, min_impurity_split=None,
- min_samples_leaf=1, min_samples_split=2,
- min_weight_fraction_leaf=0.0, presort=False, random_state=None,
- splitter='best'),
- n_estimators=50, random_state=1)
+ MuComboClassifier(base_estimator=DecisionTreeClassifier(max_depth=2),
+ random_state=1)
>>> print(clf.predict([[ 5., 3., 1., 1.]]))
[0]
@@ -222,8 +217,9 @@ class MuComboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
dist = np.empty(cost.shape[:2], dtype=cost.dtype, order="C")
# NOTE: In Sokol's PhD thesis, the formula for dist is mistakenly given
# with a minus sign in section 2.2.2 page 31
- dist[:, :] = cost[:, np.arange(n_samples), y] \
- / np.sum(cost[:, np.arange(n_samples), y], axis=1)[:, np.newaxis]
+ sum_cost = np.sum(cost[:, np.arange(n_samples), y], axis=1)[:, np.newaxis]
+ sum_cost[sum_cost==0] = 1
+ dist[:, :] = cost[:, np.arange(n_samples), y] / sum_cost
return dist
def _indicatrice(self, predicted_classes, y_i):
@@ -444,6 +440,8 @@ class MuComboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
views_ind_, n_views = self.X_._validate_views_ind(self.X_.views_ind,
self.X_.shape[1])
check_X_y(self.X_, y)
+ if not isinstance(y, np.ndarray):
+ y = np.asarray(y)
check_classification_targets(y)
self._validate_estimator()
@@ -452,6 +450,7 @@ class MuComboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
self.n_classes_ = len(self.classes_)
self.n_views_ = n_views
self.n_features_ = self.X_.shape[1]
+ self.n_features_in_ = self.n_features_
if self.n_classes_ == 1:
# This case would lead to division by 0 when computing the cost
# matrix so it needs special handling (but it is an obvious case as
diff --git a/multimodal/boosting/mumbo.py b/multimodal/boosting/mumbo.py
index 690061b420691d17ceca22be85bcef2812d5c248..0ced162f9a3446d04d3b17cdc1d08d4e0c13d8dc 100644
--- a/multimodal/boosting/mumbo.py
+++ b/multimodal/boosting/mumbo.py
@@ -49,10 +49,10 @@ import numpy as np
from sklearn.base import ClassifierMixin, clone
from sklearn.ensemble import BaseEnsemble
from sklearn.ensemble._base import _set_random_states
-from sklearn.ensemble.forest import BaseForest
+from sklearn.ensemble._forest import BaseForest
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier
-from sklearn.tree.tree import BaseDecisionTree
+from sklearn.tree import BaseDecisionTree
from sklearn.tree._tree import DTYPE
from sklearn.utils import check_array, check_X_y, check_random_state
from sklearn.utils.multiclass import check_classification_targets
@@ -128,15 +128,13 @@ class MumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
>>> views_ind = [0, 2, 4] # view 0: sepal data, view 1: petal data
>>> clf = MumboClassifier(random_state=0)
>>> clf.fit(X, y, views_ind) # doctest: +NORMALIZE_WHITESPACE
- MumboClassifier(base_estimator=None, best_view_mode='edge',
- n_estimators=50, random_state=0)
+ MumboClassifier(random_state=0)
>>> print(clf.predict([[ 5., 3., 1., 1.]]))
[1]
>>> views_ind = [[0, 2], [1, 3]] # view 0: length data, view 1: width data
>>> clf = MumboClassifier(random_state=0)
>>> clf.fit(X, y, views_ind) # doctest: +NORMALIZE_WHITESPACE
- MumboClassifier(base_estimator=None, best_view_mode='edge',
- n_estimators=50, random_state=0)
+ MumboClassifier(random_state=0)
>>> print(clf.predict([[ 5., 3., 1., 1.]]))
[1]
@@ -144,13 +142,8 @@ class MumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
>>> base_estimator = DecisionTreeClassifier(max_depth=2)
>>> clf = MumboClassifier(base_estimator=base_estimator, random_state=0)
>>> clf.fit(X, y, views_ind) # doctest: +NORMALIZE_WHITESPACE
- MumboClassifier(base_estimator=DecisionTreeClassifier(class_weight=None,
- criterion='gini', max_depth=2, max_features=None,
- max_leaf_nodes=None, min_impurity_decrease=0.0,
- min_impurity_split=None, min_samples_leaf=1, min_samples_split=2,
- min_weight_fraction_leaf=0.0, presort=False, random_state=None,
- splitter='best'),
- best_view_mode='edge', n_estimators=50, random_state=0)
+ MumboClassifier(base_estimator=DecisionTreeClassifier(max_depth=2),
+ random_state=0)
>>> print(clf.predict([[ 5., 3., 1., 1.]]))
[1]
@@ -192,7 +185,6 @@ class MumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
"""Check the estimator and set the base_estimator_ attribute."""
super(MumboClassifier, self)._validate_estimator(
default=DecisionTreeClassifier(max_depth=1))
-
if type(self.base_estimator_) is list:
for estimator in self.base_estimator_:
if not has_fit_parameter(estimator, "sample_weight"):
@@ -411,12 +403,15 @@ class MumboClassifier(BaseEnsemble, ClassifierMixin, UBoosting):
views_ind_, n_views = self.X_._validate_views_ind(self.X_.views_ind,
self.X_.shape[1])
check_X_y(self.X_, y, accept_sparse=accept_sparse, dtype=dtype)
+ if not isinstance(y, np.ndarray):
+ y = np.asarray(y)
check_classification_targets(y)
self._validate_estimator()
self.classes_, y = np.unique(y, return_inverse=True)
self.n_classes_ = len(self.classes_)
self.n_features_ = self.X_.shape[1]
+ self.n_features_in_ = self.n_features_
if self.n_classes_ == 1:
# This case would lead to division by 0 when computing the cost
# matrix so it needs special handling (but it is an obvious case as
diff --git a/multimodal/datasets/data_sample.py b/multimodal/datasets/data_sample.py
index ac20e3fdd446c52303acf6c86ff2cc0c881dd453..a4b5f9c310c9cb0ce314e682074f17b5da62b3f1 100644
--- a/multimodal/datasets/data_sample.py
+++ b/multimodal/datasets/data_sample.py
@@ -365,14 +365,14 @@ class MultiModalArray(np.ndarray, MultiModalData):
views_ind.append(dat_values.shape[1] + views_ind[index])
index += 1
thekeys = data.keys()
- if new_data.ndim < 2 :
- raise ValueError('Reshape your data')
- if new_data.ndim > 1 and (new_data.shape == (1, 1) or new_data.shape == ()):
+ # if new_data.ndim < 2 :
+ # raise ValueError('Reshape your data')
+ if new_data.ndim > 1 and (new_data.shape == (1, 1) or new_data.shape == ()):
raise ValueError('Reshape your data')
elif isinstance(data, np.ndarray) and views_ind is None and data.ndim == 1:
try:
dat0 = np.array(data[0])
- except Exception:
+ except Exception: # pragma: no cover
raise TypeError("input format is not supported")
if dat0.ndim < 2:
@@ -388,13 +388,13 @@ class MultiModalArray(np.ndarray, MultiModalData):
elif (isinstance(data, np.ndarray) ) and data.ndim > 1:
try:
data = np.asarray(data)
- except:
+ except: # pragma: no cover
raise TypeError("input format is not supported")
if views_ind is not None:
try:
views_ind = np.asarray(views_ind)
- except :
+ except : # pragma: no cover
raise TypeError("n_views should be list or nparray")
elif views_ind is None:
if data.shape[1] > 1:
@@ -413,7 +413,7 @@ class MultiModalArray(np.ndarray, MultiModalData):
elif not isinstance(views_ind, np.ndarray):
try:
views_ind = np.asarray(views_ind)
- except Exception:
+ except Exception: # pragma: no cover
raise TypeError("format of views_ind is not list or nd array")
except Exception as e:
raise ValueError('Reshape your data')
@@ -421,8 +421,8 @@ class MultiModalArray(np.ndarray, MultiModalData):
raise ValueError('Reshape your data')
if new_data.ndim > 1 and (new_data.shape == (1, 1) or new_data.shape == ()):
raise ValueError('Reshape your data')
- if views_ind.ndim < 2 and new_data.ndim < 2 and views_ind[-1] > new_data.shape[1]:
- raise ValueError('Reshape your data')
+ # if views_ind.ndim < 2 and new_data.ndim < 2 and views_ind[-1] > new_data.shape[1]:
+ # raise ValueError('Reshape your data')
# views_ind_self = views_ind
# if new_data.shape[1] < 1:
@@ -437,7 +437,7 @@ class MultiModalArray(np.ndarray, MultiModalData):
# obj = ma.MaskedArray.__new(new_data) # new_data.view() a.MaskedArray(new_data, mask=new_data.mask).view(cls)
# bj = super(Metriclearn_array, cls).__new__(cls, new_data.data, new_data.mask)
- if hasattr(new_data, "mask"):
+ if hasattr(new_data, "mask"): # pragma: no cover
obj = ma.masked_array(new_data.data, new_data.mask).view(cls)
elif hasattr(new_data, "data") and \
hasattr(new_data, "shape") and len(new_data.shape) > 0:
@@ -462,7 +462,7 @@ class MultiModalArray(np.ndarray, MultiModalData):
for dat_values in data:
try:
dat_values = np.array(dat_values)
- except Exception:
+ except Exception: # pragma: no cover
raise TypeError("input format is not supported")
new_data = cls._populate_new_data(index, dat_values, new_data)
views_ind[index + 1] = dat_values.shape[1] + views_ind[index]
@@ -471,7 +471,8 @@ class MultiModalArray(np.ndarray, MultiModalData):
return new_data, shapes_int, views_ind
@staticmethod
- def _populate_new_data(index, dat_values, new_data):
+ def _populate_new_data(index, dat_values, new_data): # pragma: no cover
+ """Work in progress : including missing data"""
if index == 0:
if isinstance(dat_values, ma.MaskedArray) or \
isinstance(dat_values, np.ndarray) or sp.issparse(dat_values):
@@ -525,30 +526,32 @@ class MultiModalArray(np.ndarray, MultiModalData):
def set_view(self, view, data):
start = int(np.sum(np.asarray(self.shapes_int[0: view])))
stop = int(start + self.shapes_int[view])
- if stop-start == data.shape[0] and data.shape[1]== self.data.shape[1]:
+ if stop-start == data.shape[1] and data.shape[0] == self.data.shape[0]:
self[:, start:stop] = data
else:
raise ValueError(
- "shape of data does not match (%d, %d)" %stop-start %self.data.shape[1])
+ "shape of data does not match (%d, %d)" %(stop-start ,self.data.shape[0]))
- def get_raw(self, view, raw):
- start = np.sum(np.asarray(self.shapes_int[0: view]))
- stop = np.sum(np.asarray(self.shapes_int[0: view+1]))
- return self.data[start:stop, raw]
-
- def add_view(self, v, data):
- if len(self.shape) > 0:
- if data.shape[0] == self.data.shape[0]:
- indice = self.shapes_int[v]
- np.insert(self.data, data, indice+1, axis=0)
- self.shapes_int.append(data.shape[1])
- self.n_views +=1
- else:
- raise ValueError("New view can't initialazed")
- # self.shapes_int= [data.shape[1]]
- # self.data.reshape(data.shape[0],)
- # np.insert(self.data, data, 0)
- # self.n_views = 1
+ def get_row(self, view, row):
+ start = int(np.sum(np.asarray(self.shapes_int[0: view])))
+ stop = int(np.sum(np.asarray(self.shapes_int[0: view+1])))
+ return self[row, start:stop]
+
+ # def add_view(self, data):
+ # if len(self.shape) > 0:
+ # if data.shape[0] == self.data.shape[0]:
+ # print(self.data.shape, data.shape)
+ # new_data = np.hstack((self.data, data))
+ # self.shapes_int.append(data.shape[1])
+ # self.n_views +=1
+ # print(new_data.shape)
+ #
+ # else:
+ # raise ValueError("New view can't initialazed")
+ # # self.shapes_int= [data.shape[1]]
+ # # self.data.reshape(data.shape[0],)
+ # # np.insert(self.data, data, 0)
+ # # self.n_views = 1
def _todict(self):
dico = {}
diff --git a/multimodal/kernels/mkernel.py b/multimodal/kernels/mkernel.py
index 7334e7916866ea13c3b6d88d7321899d83103682..2b8d6d5f4ea94911f1122d0fb1e0c8ae963c8681 100644
--- a/multimodal/kernels/mkernel.py
+++ b/multimodal/kernels/mkernel.py
@@ -124,22 +124,22 @@ class MKernel(metaclass=ABCMeta):
X = X_
if isinstance(X, MultiModalArray):
X_ = X
- if not isinstance(X_, MultiModalArray):
- try:
- X_ = np.asarray(X)
- X_ = MultiModalArray(X_, views_ind)
- except Exception as e:
- pass
+ # if not isinstance(X_, MultiModalArray):
+ # try:
+ # X_ = np.asarray(X)
+ # X_ = MultiModalArray(X_, views_ind)
+ # except Exception as e:
+ # pass
# raise TypeError('Reshape your data')
if isinstance(X_, MultiModalArray):
for v in range(X.n_views):
if Y is not None: y = Y.get_view(v) # y = self._global_check_pairwise(X, Y, v)
kernel_dict[v] = self._get_kernel(X_.get_view(v), y)
- if not isinstance(X_, MultiModalArray):
- if sp.sparse.issparse(X):
- raise TypeError("Nonsensical Error: no sparse data are allowed as input")
- raise TypeError('Reshape your data')
+ # if not isinstance(X_, MultiModalArray):
+ # if sp.sparse.issparse(X):
+ # raise TypeError("Nonsensical Error: no sparse data are allowed as input")
+ # raise TypeError('Reshape your data')
K_ = MultiModalArray(kernel_dict)
return X_, K_
diff --git a/multimodal/kernels/mvml.py b/multimodal/kernels/mvml.py
index e261661636d5851369b896be336f0b9e3be975b7..8444ff3636f3cd0bc10b495f30cfabfe93da6646 100644
--- a/multimodal/kernels/mvml.py
+++ b/multimodal/kernels/mvml.py
@@ -152,8 +152,7 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin, RegressorMixin):
>>> clf.get_params()
{'eta': 1, 'kernel': 'linear', 'kernel_params': None, 'learn_A': 1, 'learn_w': 0, 'lmbda': 0.1, 'n_loops': 6, 'nystrom_param': 1.0, 'precision': 0.0001}
>>> clf.fit(X, y, views_ind) # doctest: +NORMALIZE_WHITESPACE
- MVML(eta=1, kernel='linear', kernel_params=None, learn_A=1, learn_w=0,
- lmbda=0.1, n_loops=6, nystrom_param=1.0, precision=0.0001)
+ MVML()
>>> print(clf.predict([[ 5., 3., 1., 1.]]))
0
@@ -230,9 +229,10 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin, RegressorMixin):
# if type_of_target(y) not in "binary":
# raise ValueError("target should be binary")
- check_classification_targets(y)
+
if type_of_target(y) in "binary":
+ check_classification_targets(y)
self.classes_, y = np.unique(y, return_inverse=True)
y[y==0] = -1.0
self.n_classes = len(self.classes_)
@@ -342,7 +342,7 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin, RegressorMixin):
else:
# A_inv = self._inverse_precond_LU(A + 1e-8 * np.eye(views * self.n_approx), pos="precond_A") # self._inverse_precond_jacobi(A + 1e-8 * np.eye(views * self.n_approx), pos="precond_A")
A_inv = self._inv_best_precond(A + 1e-8 * np.eye(views * self.n_approx), pos="precond_A")
- except spli.LinAlgError:
+ except spli.LinAlgError: # pragma: no cover
self.warning_message["LinAlgError"] = self.warning_message.get("LinAlgError", 0) + 1
try:
A_inv = spli.pinv(A + 1e-07 * np.eye(views * self.n_approx))
@@ -352,7 +352,7 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin, RegressorMixin):
except ValueError:
self.warning_message["ValueError"] = self.warning_message.get("ValueError", 0) + 1
return A_prev, g_prev
- except ValueError:
+ except ValueError: # pragma: no cover
self.warning_message["ValueError"] = self.warning_message.get("ValueError", 0) + 1
return A_prev, g_prev, w_prev
# print("A_inv ",np.sum(A_inv))
@@ -372,7 +372,7 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin, RegressorMixin):
else:
# g = np.dot(self._inverse_precond_LU(A_inv, pos="precond_A_1"), g)
g = np.dot(self._inv_best_precond(A_inv, pos="precond_A_1"), g)
- except spli.LinAlgError:
+ except spli.LinAlgError: # pragma: no cover
self.warning_message["LinAlgError"] = self.warning_message.get("LinAlgError", 0) + 1
g = spli.solve(A_inv, g)
@@ -428,7 +428,7 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin, RegressorMixin):
A_inv = spli.pinv(A)
return A_inv
- def _inverse_precond_jacobi(self, A, pos="precond_A"):
+ def _inverse_precond_jacobi(self, A, pos="precond_A"): # pragma: no cover
J_1 = np.diag(1.0/np.diag(A))
# J_1 = np.linalg.inv(J)
P = np.dot(J_1, A)
@@ -438,10 +438,9 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin, RegressorMixin):
self.warning_message[pos] = self.warning_message.get(pos, 0) + 1
else:
A_inv = self._inverse_precond_LU(A, pos=pos)
-
return A_inv
- def _inverse_precond_LU(self, A, pos="precond_A"):
+ def _inverse_precond_LU(self, A, pos="precond_A"): # pragma: no cover
P, L, U = spli.lu(A)
M = spli.inv(np.dot(L, U))
P = np.dot(M, A)
@@ -606,17 +605,17 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin, RegressorMixin):
try:
# minA_inv = np.min(np.absolute(A_prev)) , rcond=self.r_cond*minA_inv
A_prev_inv = spli.pinv(A_prev)
- except spli.LinAlgError:
+ except spli.LinAlgError: # pragma: no cover
try:
A_prev_inv = spli.pinv(A_prev + 1e-6 * np.eye(views * m))
except spli.LinAlgError:
return A_prev
except ValueError:
return A_prev
- except ValueError:
+ except ValueError: # pragma: no cover
return A_prev
- if np.any(np.isnan(A_prev_inv)):
+ if np.any(np.isnan(A_prev_inv)): # pragma: no cover
# just in case the inverse didn't return a proper solution (happened once or twice)
return A_prev
@@ -625,9 +624,9 @@ class MVML(MKernel, BaseEstimator, ClassifierMixin, RegressorMixin):
# if there is one small negative eigenvalue this gets rid of it
try:
val, vec = spli.eigh(A_tmp)
- except spli.LinAlgError:
+ except spli.LinAlgError: # pragma: no cover
return A_prev
- except ValueError:
+ except ValueError: # pragma: no cover
return A_prev
val[val < 0] = 0
diff --git a/multimodal/tests/test_combo.py b/multimodal/tests/test_combo.py
index 52c59f09a8998981f40f1e8c3fb30830b926c504..f8d085dfa2138313b8060fc51eb81456dc87876f 100644
--- a/multimodal/tests/test_combo.py
+++ b/multimodal/tests/test_combo.py
@@ -54,7 +54,7 @@ from scipy.sparse import csc_matrix, csr_matrix, coo_matrix, dok_matrix
from scipy.sparse import lil_matrix
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
-from sklearn.ensemble.forest import RandomForestClassifier
+from sklearn.ensemble import RandomForestClassifier
from sklearn.cluster import KMeans
from sklearn.linear_model import Lasso
from sklearn.tree import DecisionTreeClassifier
@@ -64,6 +64,12 @@ from multimodal.boosting.combo import MuComboClassifier
from multimodal.tests.data.get_dataset_path import get_dataset_path
from multimodal.datasets.data_sample import MultiModalArray
+class NoSampleWeightLasso(Lasso):
+
+ def fit(self, X, y, check_input=True):
+ return Lasso.fit(self, X, y, sample_weight=None, check_input=True)
+
+
class TestMuComboClassifier(unittest.TestCase):
@classmethod
@@ -368,6 +374,8 @@ class TestMuComboClassifier(unittest.TestCase):
[ 4.49110023, 1., -2. ],
[ 8., 2.49110023, 1. ]]])
np.testing.assert_almost_equal(label_score, expected_label_score,6)
+
+
#
# label_score = np.array(
# [[[-1, -2, 4], [-8, 1, 4], [2, 8, -4], [2, -1, 4]],
@@ -836,7 +844,7 @@ class TestMuComboClassifier(unittest.TestCase):
#
def test_classifier(self):
- return check_estimator(MuComboClassifier)
+ return check_estimator(MuComboClassifier())
#
#
# def test_iris():
@@ -957,7 +965,8 @@ class TestMuComboClassifier(unittest.TestCase):
# # Check that using a base estimator that doesn't support sample_weight
# # raises an error.
- clf = MuComboClassifier(Lasso())
+ clf = MuComboClassifier(NoSampleWeightLasso())
+
self.assertRaises(ValueError, clf.fit, self.iris.data, self.iris.target, self.iris.views_ind)
# assert_raises(ValueError, clf.fit, iris.data, iris.target, iris.views_ind)
#
diff --git a/multimodal/tests/test_data_sample.py b/multimodal/tests/test_data_sample.py
index 469ba500685e879a6c2816fe7455466bb5d87ca1..a25977e9c6b1bd9bc38521dd5e739da3ad7a04b1 100644
--- a/multimodal/tests/test_data_sample.py
+++ b/multimodal/tests/test_data_sample.py
@@ -47,6 +47,7 @@ from multimodal.tests.datasets.get_dataset_path import get_dataset_path
from multimodal.datasets.data_sample import MultiModalArray
import pickle
+
class UnitaryTest(unittest.TestCase):
@classmethod
@@ -85,6 +86,44 @@ class UnitaryTest(unittest.TestCase):
array_x = a.data
b = MultiModalArray(a)
np.testing.assert_equal(b.views_ind, np.array([0, 120, 240]))
+ view_1 = np.random.randint(1,10,10)
+ view_2 = np.random.randint(1,10,11)
+ data = {0 : view_1,
+ 1 : view_2,}
+ c = MultiModalArray(data)
+ np.testing.assert_array_equal(np.asarray(c[0,:]), np.concatenate((view_1, view_2)))
+ view_1 = np.random.randint(1, 10, 1)
+ data = {0: view_1, }
+ self.assertRaises(ValueError, MultiModalArray, data)
+ view_1 = np.array([0,])
+ data = view_1
+ d = MultiModalArray(data)
+ np.testing.assert_array_equal(d.views_ind, np.array([0,1]))
+ view_1 = [[0]]
+ data = view_1
+ self.assertRaises(ValueError, MultiModalArray, data)
+ view_1 = [[0,1,2 ],[0,1,2 ]]
+ data = view_1
+ d = MultiModalArray(data, [0,1])
+ np.testing.assert_array_equal(d.views_ind, np.array([0, 1]))
+ view_1 = [[0]]
+ data = view_1
+ self.assertRaises(ValueError, MultiModalArray, data)
+
+ def test_view_functions(self):
+ view_1 = np.random.randint(1, 10, (5, 10))
+ view_2 = np.random.randint(1, 10, (5, 10))
+ view_3 = np.random.randint(1, 10, (5, 10))
+ data = {0: view_1,
+ 1: view_2, }
+ c = MultiModalArray(data)
+ c.set_view(1, view_3)
+ np.testing.assert_array_equal(c.get_view(1), view_3)
+ view_3 = np.random.randint(1, 10, (12, 10))
+ c = MultiModalArray(data)
+ self.assertRaises(ValueError, c.set_view, 1, view_3)
+ np.testing.assert_array_equal(c.get_row(0, 2), view_1[2, :])
+
if __name__ == '__main__':
diff --git a/multimodal/tests/test_mumbo.py b/multimodal/tests/test_mumbo.py
index e0ec2cd1aa7a0df3952ad83b71769e3c2d8f8084..af9c5c69f222c26ad892c1cbf2e4bfb68104574b 100644
--- a/multimodal/tests/test_mumbo.py
+++ b/multimodal/tests/test_mumbo.py
@@ -57,6 +57,7 @@ from sklearn.tree import DecisionTreeClassifier
from sklearn import datasets
from multimodal.boosting.mumbo import MumboClassifier
+from multimodal.tests.test_combo import NoSampleWeightLasso
class TestMumboClassifier(unittest.TestCase):
@@ -730,7 +731,7 @@ class TestMumboClassifier(unittest.TestCase):
# e = MumboClassifier()
# e.fit(X_zero_features, y)
# print(e.predict(X_zero_features))
- return check_estimator(MumboClassifier)
+ return check_estimator(MumboClassifier())
def test_iris(self):
# Check consistency on dataset iris.
@@ -840,7 +841,7 @@ class TestMumboClassifier(unittest.TestCase):
# Check that using a base estimator that doesn't support sample_weight
# raises an error.
- clf = MumboClassifier(Lasso())
+ clf = MumboClassifier(NoSampleWeightLasso())
self.assertRaises(ValueError, clf.fit, self.iris.data, self.iris.target, self.iris.views_ind)
@@ -908,6 +909,18 @@ class TestMumboClassifier(unittest.TestCase):
else:
self.assertTrue(all([issubclass(type_, csr_matrix) for type_ in types]))
+ def test_validate_X_predict(self):
+ clf = MumboClassifier()
+ X = np.random.randint(1, 10, (2, 10))
+ y = [1, 0]
+ clf.fit(X, y)
+ X_pred = np.random.randint(1, 10, 10)
+ self.assertRaises(ValueError, clf._validate_X_predict, X_pred)
+ X_pred = np.random.randint(1,10,9)
+ self.assertRaises(ValueError, clf._validate_X_predict, X_pred)
+ X_pred = np.random.randint(1, 10, (2, 9))
+ self.assertRaises(ValueError, clf._validate_X_predict, X_pred)
+
if __name__ == '__main__':
unittest.main()
\ No newline at end of file
diff --git a/multimodal/tests/test_mvml.py b/multimodal/tests/test_mvml.py
index 9f33c3b5959835ed1e441d602e8ecc4202b02c6d..83c6ea3125032a0574398185fbe3b220da427453 100644
--- a/multimodal/tests/test_mvml.py
+++ b/multimodal/tests/test_mvml.py
@@ -43,6 +43,7 @@ import pickle
import unittest
import numpy as np
+import scipy as sp
from sklearn.exceptions import NotFittedError
from multimodal.datasets.data_sample import MultiModalArray
@@ -95,6 +96,22 @@ class MVMLTest(unittest.TestCase):
w_expected = np.array([[0.5],[0.5]])
np.testing.assert_almost_equal(mvml.w, w_expected, 8)
+ def testFitMVMLRegression(self):
+ #######################################################
+ # task with dict and not precomputed
+ #######################################################
+ y = self.y
+ y += np.random.uniform(0,1, size=y.shape)
+ mvml = MVML(lmbda=0.1, eta=1,
+ kernel=['rbf'], kernel_params=[{'gamma':50}],
+ nystrom_param=0.2)
+ views_ind = [120, 240]
+ mvml.fit(self.kernel_dict, y=y, views_ind=None)
+ self.assertEqual(mvml.A.shape, (48, 48))
+ self.assertEqual(mvml.g.shape,(48, 1))
+ w_expected = np.array([[0.5],[0.5]])
+ np.testing.assert_almost_equal(mvml.w, w_expected, 8)
+
def testFitMVMLPrecision(self):
#######################################################
# task with dict and not precomputed
@@ -255,6 +272,21 @@ class MVMLTest(unittest.TestCase):
pass
# return check_estimator(MVML)
+ def test_check_kernel(self):
+ clf = MVML()
+ clf.kernel = "an_unknown_kernel"
+ self.assertRaises(ValueError, clf._check_kernel)
+
+ def testFitMVMLSparesArray(self):
+ #######################################################
+ # task with nparray 2d
+ #######################################################
+ x_metricl = MultiModalArray(self.kernel_dict)
+ x_array = np.asarray(x_metricl)
+ x_array_sparse = sp.sparse.csr_matrix(x_array)
+ mvml3 = MVML(lmbda=0.1, eta=1, nystrom_param=1.0)
+ self.assertRaises(TypeError, mvml3.fit, x_array_sparse, self.y, [0, 120, 240])
+
if __name__ == "__main__":
# import sys;sys.argv = ['', 'Test.testName']
unittest.main()
diff --git a/setup.cfg b/setup.cfg
index 2b8e7f45560df1bf68c6b693c57d29a50f6e0434..f3b90c5a82a8077eedee2012c96b090952131fb2 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -14,3 +14,6 @@ branch = True
source = multimodal
include = */multimodal/*
omit = */tests/*
+
+[coverage:report]
+exclude_lines = pragma: no cover
\ No newline at end of file
diff --git a/setup.py b/setup.py
index fa4dd7e49a88f535d56e3a7241f63a2bf8a25512..0bb17e2c7a939f99098001af1fe6ce404bcdcf90 100644
--- a/setup.py
+++ b/setup.py
@@ -176,8 +176,8 @@ def setup_package():
keywords = ('machine learning, supervised learning, classification, '
'ensemble methods, boosting, kernel')
packages = find_packages(exclude=['*.tests'])
- install_requires = ['scikit-learn>=0.19', 'numpy', 'scipy', 'cvxopt' ]
- python_requires = '>=3.5'
+ install_requires = ['scikit-learn>=0.24', 'numpy', 'scipy', 'cvxopt' ]
+ python_requires = '>=3.6'
extras_require = {
'dev': ['pytest', 'pytest-cov'],
'doc': ['sphinx', 'numpydoc', 'sphinx_gallery', 'matplotlib']}