diff --git a/multimodal/boosting/boost.py b/multimodal/boosting/boost.py
index c689eea3ca6eb633cc102f2136e16e45cef4e942..94362ecc216ad608250ed8bba2d2f9e62d913ae4 100644
--- a/multimodal/boosting/boost.py
+++ b/multimodal/boosting/boost.py
@@ -59,13 +59,6 @@ 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_:
@@ -73,8 +66,15 @@ 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:
@@ -83,10 +83,6 @@ 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):
@@ -97,10 +93,10 @@ 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/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/tests/test_combo.py b/multimodal/tests/test_combo.py
index f0588935bcfd2e8f435058ebf5d7ab468a196a4e..f8d085dfa2138313b8060fc51eb81456dc87876f 100644
--- a/multimodal/tests/test_combo.py
+++ b/multimodal/tests/test_combo.py
@@ -374,6 +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]],
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 1a8f58c8b1e43e17f21e560c15260219dde3b3da..af9c5c69f222c26ad892c1cbf2e4bfb68104574b 100644
--- a/multimodal/tests/test_mumbo.py
+++ b/multimodal/tests/test_mumbo.py
@@ -909,6 +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 7b1cb4c3479d5d58486c7bba52204db1f33a9bb6..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
@@ -271,6 +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()