diff --git a/multiview_platform/mono_multi_view_classifiers/exec_classif.py b/multiview_platform/mono_multi_view_classifiers/exec_classif.py
index cd066e7274fbda67eeffe406339c0decae445a55..a7d4eb653fa572477eb8b94c2d94b3e53ac44383 100644
--- a/multiview_platform/mono_multi_view_classifiers/exec_classif.py
+++ b/multiview_platform/mono_multi_view_classifiers/exec_classif.py
@@ -691,7 +691,7 @@ def execClassif(arguments):
kFolds = execution.genKFolds(statsIter, args["Classification"]["nb_folds"],
statsIterRandomStates)
- datasetFiles = dataset.initMultipleDatasets(args["Base"]["pathf"], args["Base"]["name"], nbCores)
+ datasetFiles = dataset.init_multiple_datasets(args["Base"]["pathf"], args["Base"]["name"], nbCores)
views, viewsIndices, allViews = execution.initViews(DATASET, args["Base"]["views"])
diff --git a/multiview_platform/mono_multi_view_classifiers/monoview/exec_classif_mono_view.py b/multiview_platform/mono_multi_view_classifiers/monoview/exec_classif_mono_view.py
index 5745e67a992696783362632e4c868be410cdcd2b..bf1f766bc359b739a5c55bd903f58ac3ede9862b 100644
--- a/multiview_platform/mono_multi_view_classifiers/monoview/exec_classif_mono_view.py
+++ b/multiview_platform/mono_multi_view_classifiers/monoview/exec_classif_mono_view.py
@@ -16,7 +16,7 @@ from . import monoview_utils
from .analyze_result import execute
# Import own modules
from .. import monoview_classifiers
-from ..utils.dataset import getValue, extractSubset
+from ..utils.dataset import get_value, extract_subset
from ..utils import hyper_parameter_search
# Author-Info
@@ -146,7 +146,7 @@ def initConstants(args, X, classificationIndices, labelsNames, name, directory):
else:
feat = X.attrs["name"]
CL_type = kwargs["classifier_name"]
- X = getValue(X)
+ X = get_value(X)
learningRate = float(len(classificationIndices[0])) / (
len(classificationIndices[0]) + len(classificationIndices[1]))
labelsString = "-".join(labelsNames)
@@ -166,10 +166,10 @@ def initConstants(args, X, classificationIndices, labelsNames, name, directory):
def initTrainTest(X, Y, classificationIndices):
trainIndices, testIndices, testIndicesMulticlass = classificationIndices
- X_train = extractSubset(X, trainIndices)
- X_test = extractSubset(X, testIndices)
+ X_train = extract_subset(X, trainIndices)
+ X_test = extract_subset(X, testIndices)
if np.array(testIndicesMulticlass).size != 0:
- X_test_multiclass = extractSubset(X, testIndicesMulticlass)
+ X_test_multiclass = extract_subset(X, testIndicesMulticlass)
else:
X_test_multiclass = []
y_train = Y[trainIndices]
@@ -319,7 +319,7 @@ def saveResults(stringAnalysis, outputFileName, full_labels_pred, y_train_pred,
# databaseType = None
#
# # Extract the data using MPI
-# X, Y = dataset.getMonoviewShared(path, name, viewName)
+# X, Y = dataset.get_monoview_shared(path, name, viewName)
#
# # Init log
# logFileName = time.strftime(
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview/exec_multiview.py b/multiview_platform/mono_multi_view_classifiers/multiview/exec_multiview.py
index 02ba90af927f6fa24b101e88dc067d261850db6e..bcc9f201f61d1f26ccaa90d66196955bded3bc36 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview/exec_multiview.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview/exec_multiview.py
@@ -11,7 +11,7 @@ from .multiview_utils import MultiviewResult
from . import analyze_results
from .. import multiview_classifiers
from ..utils import hyper_parameter_search
-from ..utils.dataset import getShape
+from ..utils.dataset import get_shape
# Author-Info
__author__ = "Baptiste Bauvin"
@@ -38,7 +38,7 @@ def initConstants(kwargs, classificationIndices, metrics, name, nbCores, KFolds,
for viewIndex, viewName in zip(viewsIndices, views):
logging.info("Info:\t Shape of " + str(viewName) + " :" + str(
- getShape(DATASET, viewIndex)))
+ get_shape(DATASET, viewIndex)))
return classifier_name, t_start, viewsIndices, classifier_config, views, learningRate
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/EarlyFusion.py b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/EarlyFusion.py
index 07a63a6f8e6380c6ff463a0359cd73a63625a34b..4bb84dc6daf14a9ee282f8f233018370b5d91c3d 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/EarlyFusion.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/EarlyFusion.py
@@ -2,7 +2,7 @@
# -*- encoding: utf-8
import numpy as np
-from ....utils.dataset import getV
+from ....utils.dataset import get_v
from .... import monoview_classifiers
class EarlyFusionClassifier(object):
@@ -38,5 +38,5 @@ class EarlyFusionClassifier(object):
weights = np.array([1 / nbView for i in range(nbView)])
if sum(weights) != 1:
weights = weights / sum(weights)
- self.monoviewData = np.concatenate([getV(DATASET, viewIndex, usedIndices)
+ self.monoviewData = np.concatenate([get_v(DATASET, viewIndex, usedIndices)
for index, viewIndex in enumerate(viewsIndices)], axis=1)
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusion.py b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusion.py
index 8beb6a299404e32d8b1791da34cad45961f87668..314b11bb3b85b0fb570450fc93923997c47c58e9 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusion.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusion.py
@@ -9,7 +9,7 @@ import math
from .... import monoview_classifiers
from .... import metrics
-from ....utils.dataset import getV
+from ....utils.dataset import get_v
# def canProbasClassifier(classifierConfig):
@@ -142,7 +142,7 @@ class LateFusionClassifier(object):
trainIndices = range(DATASET.get("Metadata").attrs["datasetLength"])
self.monoviewClassifiers = Parallel(n_jobs=self.nbCores)(
delayed(fitMonoviewClassifier)(self.monoviewClassifiers[index],
- getV(DATASET, viewIndex, trainIndices),
+ get_v(DATASET, viewIndex, trainIndices),
labels[trainIndices],
self.needProbas, self.randomState)
for index, viewIndex in enumerate(viewsIndices))
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/BayesianInference.py b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/BayesianInference.py
index 2f6d9b723fedf68094fe591b37b638fe81f729f5..61ec3838f238adeafa98a02471890e58eb1ccbd2 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/BayesianInference.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/BayesianInference.py
@@ -2,7 +2,7 @@ import numpy as np
from sklearn.metrics import accuracy_score
import pkgutil
-from .....utils.dataset import getV
+from .....utils.dataset import get_v
from ..... import monoview_classifiers
from ..LateFusion import LateFusionClassifier, getClassifiers, getConfig
@@ -78,7 +78,7 @@ class BayesianInference(LateFusionClassifier):
viewScores = []#np.zeros((nbView, len(usedIndices), DATASET.get("Metadata").attrs["nbClass"]))
for index, viewIndex in enumerate(viewsIndices):
viewScores.append(np.power(
- self.monoviewClassifiers[index].predict_proba(getV(DATASET, viewIndex, usedIndices)),
+ self.monoviewClassifiers[index].predict_proba(get_v(DATASET, viewIndex, usedIndices)),
self.weights[index]))
viewScores = np.array(viewScores)
predictedLabels = np.argmax(np.prod(viewScores, axis=0), axis=1)
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/MajorityVoting.py b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/MajorityVoting.py
index bef30f9cd687e389745a8b1f117718b84faeb2d4..bcdbfa8222d9f4aa79333dbf52132dff757da227 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/MajorityVoting.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/MajorityVoting.py
@@ -2,7 +2,7 @@ import numpy as np
# from sklearn.metrics import accuracy_score
# import pkgutil
-from .....utils.dataset import getV
+from .....utils.dataset import get_v
from ..LateFusion import LateFusionClassifier, getClassifiers, getConfig
from ..... import monoview_classifiers
@@ -78,7 +78,7 @@ class MajorityVoting(LateFusionClassifier):
monoViewDecisions = np.zeros((len(usedIndices), nbView), dtype=int)
for index, viewIndex in enumerate(viewsIndices):
monoViewDecisions[:, index] = self.monoviewClassifiers[index].predict(
- getV(DATASET, viewIndex, usedIndices))
+ get_v(DATASET, viewIndex, usedIndices))
for exampleIndex in range(datasetLength):
for viewIndex, featureClassification in enumerate(monoViewDecisions[exampleIndex, :]):
votes[exampleIndex, featureClassification] += self.weights[viewIndex]
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/SCMForLinear.py b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/SCMForLinear.py
index c5e7b9acab1504a506751722ebfbd13aa8637a9f..739ba0233224cd84057d66ec2b9442a72cbf69b2 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/SCMForLinear.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/SCMForLinear.py
@@ -9,7 +9,7 @@ import itertools
from ..LateFusion import LateFusionClassifier, getClassifiers, getConfig
from ..... import monoview_classifiers
-from .....utils.dataset import getV
+from .....utils.dataset import get_v
class DecisionStumpSCMNew(BaseEstimator, ClassifierMixin):
@@ -119,7 +119,7 @@ class SCMForLinear(LateFusionClassifier):
if trainIndices is None:
trainIndices = range(DATASET.get("Metadata").attrs["datasetLength"])
for index, viewIndex in enumerate(viewsIndices):
- self.monoviewClassifiers[index].fit(getV(DATASET, viewIndex, trainIndices),
+ self.monoviewClassifiers[index].fit(get_v(DATASET, viewIndex, trainIndices),
labels[trainIndices])
self.SCMForLinearFusionFit(DATASET, labels, usedIndices=trainIndices, viewsIndices=viewsIndices)
@@ -133,7 +133,7 @@ class SCMForLinear(LateFusionClassifier):
# accus = []
for index, viewIndex in enumerate(viewsIndices):
monoviewDecision = self.monoviewClassifiers[index].predict(
- getV(DATASET, viewIndex, usedIndices))
+ get_v(DATASET, viewIndex, usedIndices))
# accus.append(accuracy_score(DATASET.get("Labels").value[usedIndices], monoviewDecision))
monoviewDecisions[:, index] = monoviewDecision
features = self.generateInteractions(monoviewDecisions)
@@ -150,7 +150,7 @@ class SCMForLinear(LateFusionClassifier):
monoViewDecisions = np.zeros((len(usedIndices), nbView), dtype=int)
for index, viewIndex in enumerate(viewsIndices):
monoViewDecisions[:, index] = self.monoviewClassifiers[index].predict(
- getV(DATASET, viewIndex, usedIndices))
+ get_v(DATASET, viewIndex, usedIndices))
features = self.generateInteractions(monoViewDecisions)
features = np.array([np.array([feat for feat in feature]) for feature in features])
self.SCMClassifier.fit(features, labels[usedIndices].astype(int))
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/SVMForLinear.py b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/SVMForLinear.py
index 8b4c984039282d8aa49e91a6328663f0a48768e8..509256190aaa545ae1dbae70083c183ff24f4ec8 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/SVMForLinear.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/SVMForLinear.py
@@ -4,7 +4,7 @@ from sklearn.svm import SVC
import pkgutil
from ..LateFusion import LateFusionClassifier, getClassifiers, getConfig
-from .....utils.dataset import getV
+from .....utils.dataset import get_v
from ..... import monoview_classifiers
@@ -63,7 +63,7 @@ class SVMForLinear(LateFusionClassifier):
if trainIndices is None:
trainIndices = range(DATASET.get("Metadata").attrs["datasetLength"])
for index, viewIndex in enumerate(viewsIndices):
- self.monoviewClassifiers[index].fit(getV(DATASET, viewIndex, trainIndices),
+ self.monoviewClassifiers[index].fit(get_v(DATASET, viewIndex, trainIndices),
labels[trainIndices])
self.SVMForLinearFusionFit(DATASET, labels, usedIndices=trainIndices, viewsIndices=viewsIndices)
@@ -79,7 +79,7 @@ class SVMForLinear(LateFusionClassifier):
monoviewDecisions = np.zeros((len(usedIndices), nbView), dtype=int)
for index, viewIndex in enumerate(viewsIndices):
monoviewDecisions[:, index] = self.monoviewClassifiers[index].predict(
- getV(DATASET, viewIndex, usedIndices))
+ get_v(DATASET, viewIndex, usedIndices))
predictedLabels = self.SVMClassifier.predict(monoviewDecisions)
return predictedLabels
@@ -91,7 +91,7 @@ class SVMForLinear(LateFusionClassifier):
monoViewDecisions = np.zeros((len(usedIndices), nbView), dtype=int)
for index, viewIndex in enumerate(viewsIndices):
monoViewDecisions[:, index] = self.monoviewClassifiers[index].predict(
- getV(DATASET, viewIndex, usedIndices))
+ get_v(DATASET, viewIndex, usedIndices))
self.SVMClassifier.fit(monoViewDecisions, labels[usedIndices])
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/WeightedLinear.py b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/WeightedLinear.py
index d7d9f418bdaeccf190e9534e2ea407b71fdc1eef..baf9c56b9fab46b7702b0754da894a4e053e044f 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/WeightedLinear.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/Methods/LateFusionPackage/WeightedLinear.py
@@ -4,7 +4,7 @@ import pkgutil
from ..... import monoview_classifiers
from ..LateFusion import LateFusionClassifier, getClassifiers, getConfig
-from .....utils.dataset import getV
+from .....utils.dataset import get_v
def genParamsSets(classificationKWARGS, randomState, nIter=1):
@@ -76,7 +76,7 @@ class WeightedLinear(LateFusionClassifier):
viewScores = []#np.zeros((nbView, len(usedIndices), DATASET.get("Metadata").attrs["nbClass"]))
for index, viewIndex in enumerate(viewsIndices):
viewScores.append(np.array(self.monoviewClassifiers[index].predict_proba(
- getV(DATASET, viewIndex, usedIndices))) * self.weights[index])
+ get_v(DATASET, viewIndex, usedIndices))) * self.weights[index])
viewScores = np.array(viewScores)
predictedLabels = np.argmax(np.sum(viewScores, axis=0), axis=1)
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/fusion.py b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/fusion.py
index f3d586fb424079f418525963737065397f42c1e0..c26387fb1057cb648ad97a8be10d0e54da1a5082 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/fusion.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/fusion/fusion.py
@@ -11,7 +11,7 @@ except ValueError:
import pdb;pdb.set_trace()
from ... import monoview_classifiers
-from ...utils.dataset import getV
+from ...utils.dataset import get_v
# Author-Info
__author__ = "Baptiste Bauvin"
@@ -111,7 +111,7 @@ def makeMonoviewData_hdf5(DATASET, weights=None, usedIndices=None, viewsIndices=
weights = np.array([1 / NB_VIEW for i in range(NB_VIEW)])
if sum(weights) != 1:
weights = weights / sum(weights)
- monoviewData = np.concatenate([weights[index] * getV(DATASET, viewIndex, usedIndices)
+ monoviewData = np.concatenate([weights[index] * get_v(DATASET, viewIndex, usedIndices)
for index, viewIndex in enumerate(viewsIndices)], axis=1)
return monoviewData
@@ -140,7 +140,7 @@ def genParamsSets(classificationKWARGS, randomState, nIter=1):
# classifierModule = getattr(monoview_classifiers, classifierName)
# classifierMethod = getattr(classifierModule, "hyperParamSearch")
# if fusionTypeName == "LateFusion":
-# bestSettings.append(classifierMethod(getV(DATASET, viewsIndices[classifierIndex], learningIndices),
+# bestSettings.append(classifierMethod(get_v(DATASET, viewsIndices[classifierIndex], learningIndices),
# DATASET.get("Labels")[learningIndices], metric=metric,
# nIter=nIter))
# else:
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/weighted_linear_early_fusion.py b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/weighted_linear_early_fusion.py
index bb7fcbe09ccb9e93d3cf6c2dc147415e8a5ee88c..c21ee488974c8663fd863cacc1fe2572f03d59f3 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/weighted_linear_early_fusion.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview_classifiers/weighted_linear_early_fusion.py
@@ -1,7 +1,7 @@
import numpy as np
import pkgutil
-from ..utils.dataset import getV
+from ..utils.dataset import get_v
from ..multiview.multiview_utils import BaseMultiviewClassifier, get_train_views_indices
from .. import monoview_classifiers
@@ -64,7 +64,7 @@ class WeightedLinearEarlyFusion(BaseMultiviewClassifier):
def hdf5_to_monoview(self, dataset, exmaples):
"""Here, we concatenate the views for the asked examples """
monoview_data = np.concatenate(
- [getV(dataset, view_idx, exmaples)
+ [get_v(dataset, view_idx, exmaples)
for view_weight, (index, view_idx)
in zip(self.view_weights, enumerate(self.view_indices))]
, axis=1)
diff --git a/multiview_platform/mono_multi_view_classifiers/utils/dataset.py b/multiview_platform/mono_multi_view_classifiers/utils/dataset.py
index 6a19674c653148ab554121ba41f8f31c66cf9904..9f38fa1f86c278709a3bb75bc8dde544f39e31fa 100644
--- a/multiview_platform/mono_multi_view_classifiers/utils/dataset.py
+++ b/multiview_platform/mono_multi_view_classifiers/utils/dataset.py
@@ -10,86 +10,86 @@ from scipy import sparse
from . import get_multiview_db as DB
-def getV(DATASET, viewIndex, usedIndices=None):
+def get_view(dataset, view_index, used_indices=None):
"""Used to extract a view as a numpy array or a sparse mat from the HDF5 dataset"""
- if usedIndices is None:
- usedIndices = range(DATASET.get("Metadata").attrs["datasetLength"])
- if type(usedIndices) is int:
- return DATASET.get("View" + str(viewIndex))[usedIndices, :]
+ if used_indices is None:
+ used_indices = range(dataset.get("Metadata").attrs["datasetLength"])
+ if type(used_indices) is int:
+ return dataset.get("View" + str(view_index))[used_indices, :]
else:
- usedIndices = np.array(usedIndices)
- sortedIndices = np.argsort(usedIndices)
- usedIndices = usedIndices[sortedIndices]
+ used_indices = np.array(used_indices)
+ sorted_indices = np.argsort(used_indices)
+ used_indices = used_indices[sorted_indices]
- if not DATASET.get("View" + str(viewIndex)).attrs["sparse"]:
- return DATASET.get("View" + str(viewIndex))[usedIndices, :][
- np.argsort(sortedIndices), :]
+ if not dataset.get("View" + str(view_index)).attrs["sparse"]:
+ return dataset.get("View" + str(view_index))[used_indices, :][
+ np.argsort(sorted_indices), :]
else:
sparse_mat = sparse.csr_matrix(
- (DATASET.get("View" + str(viewIndex)).get("data").value,
- DATASET.get("View" + str(viewIndex)).get("indices").value,
- DATASET.get("View" + str(viewIndex)).get("indptr").value),
- shape=DATASET.get("View" + str(viewIndex)).attrs["shape"])[
- usedIndices, :][
- np.argsort(sortedIndices), :]
+ (dataset.get("View" + str(view_index)).get("data").value,
+ dataset.get("View" + str(view_index)).get("indices").value,
+ dataset.get("View" + str(view_index)).get("indptr").value),
+ shape=dataset.get("View" + str(view_index)).attrs["shape"])[
+ used_indices, :][
+ np.argsort(sorted_indices), :]
return sparse_mat
-def getShape(DATASET, viewIndex):
+def get_shape(dataset, view_index):
"""Used to get the dataset shape even if it's sparse"""
- if not DATASET.get("View" + str(viewIndex)).attrs["sparse"]:
- return DATASET.get("View" + str(viewIndex)).shape
+ if not dataset.get("View" + str(view_index)).attrs["sparse"]:
+ return dataset.get("View" + str(view_index)).shape
else:
- return DATASET.get("View" + str(viewIndex)).attrs["shape"]
+ return dataset.get("View" + str(view_index)).attrs["shape"]
-def getValue(DATASET):
+def get_value(dataset):
"""Used to get the value of a view in the HDF5 dataset even if it sparse"""
- if not DATASET.attrs["sparse"]:
- return DATASET.value
+ if not dataset.attrs["sparse"]:
+ return dataset.value
else:
- sparse_mat = sparse.csr_matrix((DATASET.get("data").value,
- DATASET.get("indices").value,
- DATASET.get("indptr").value),
- shape=DATASET.attrs["shape"])
+ sparse_mat = sparse.csr_matrix((dataset.get("data").value,
+ dataset.get("indices").value,
+ dataset.get("indptr").value),
+ shape=dataset.attrs["shape"])
return sparse_mat
-def extractSubset(matrix, usedIndices):
+def extract_subset(matrix, used_indices):
"""Used to extract a subset of a matrix even if it's sparse"""
if sparse.issparse(matrix):
- newIndptr = np.zeros(len(usedIndices) + 1, dtype=int)
+ new_indptr = np.zeros(len(used_indices) + 1, dtype=int)
oldindptr = matrix.indptr
- for exampleIndexIndex, exampleIndex in enumerate(usedIndices):
- newIndptr[exampleIndexIndex + 1] = newIndptr[exampleIndexIndex] + (
+ for exampleIndexIndex, exampleIndex in enumerate(used_indices):
+ new_indptr[exampleIndexIndex + 1] = new_indptr[exampleIndexIndex] + (
oldindptr[exampleIndex + 1] - oldindptr[exampleIndex])
- newData = np.ones(newIndptr[-1], dtype=bool)
- newIndices = np.zeros(newIndptr[-1], dtype=int)
- oldIndices = matrix.indices
- for exampleIndexIndex, exampleIndex in enumerate(usedIndices):
- newIndices[newIndptr[exampleIndexIndex]:newIndptr[
- exampleIndexIndex + 1]] = oldIndices[
+ new_data = np.ones(new_indptr[-1], dtype=bool)
+ new_indices = np.zeros(new_indptr[-1], dtype=int)
+ old_indices = matrix.indices
+ for exampleIndexIndex, exampleIndex in enumerate(used_indices):
+ new_indices[new_indptr[exampleIndexIndex]:new_indptr[
+ exampleIndexIndex + 1]] = old_indices[
oldindptr[exampleIndex]:
oldindptr[exampleIndex + 1]]
- return sparse.csr_matrix((newData, newIndices, newIndptr),
- shape=(len(usedIndices), matrix.shape[1]))
+ return sparse.csr_matrix((new_data, new_indices, new_indptr),
+ shape=(len(used_indices), matrix.shape[1]))
else:
- return matrix[usedIndices]
+ return matrix[used_indices]
-def initMultipleDatasets(pathF, name, nbCores):
+def init_multiple_datasets(path_f, name, nb_cores):
r"""Used to create copies of the dataset if multicore computation is used.
This is a temporary solution to fix the sharing memory issue with HDF5 datasets.
Parameters
----------
- pathF : string
+ path_f : string
Path to the original dataset directory
name : string
Name of the dataset
- nbCores : int
+ nb_cores : int
The number of threads that the benchmark can use
Returns
@@ -97,25 +97,25 @@ def initMultipleDatasets(pathF, name, nbCores):
datasetFiles : None
Dictionary resuming which mono- and multiview algorithms which will be used in the benchmark.
"""
- if nbCores > 1:
- if DB.datasetsAlreadyExist(pathF, name, nbCores):
+ if nb_cores > 1:
+ if DB.datasetsAlreadyExist(path_f, name, nb_cores):
logging.debug(
"Info:\t Enough copies of the dataset are already available")
pass
else:
logging.debug("Start:\t Creating " + str(
- nbCores) + " temporary datasets for multiprocessing")
+ nb_cores) + " temporary datasets for multiprocessing")
logging.warning(
" WARNING : /!\ This may use a lot of HDD storage space : " +
- str(os.path.getsize(pathF + name + ".hdf5") * nbCores / float(
+ str(os.path.getsize(path_f + name + ".hdf5") * nb_cores / float(
1024) / 1000 / 1000) + " Gbytes /!\ ")
confirmation = confirm()
if not confirmation:
sys.exit(0)
else:
- datasetFiles = DB.copyHDF5(pathF, name, nbCores)
+ dataset_files = DB.copyHDF5(path_f, name, nb_cores)
logging.debug("Start:\t Creating datasets for multiprocessing")
- return datasetFiles
+ return dataset_files
def confirm(resp=True, timeout=15):
@@ -141,10 +141,9 @@ def input_(timeout=15):
else:
return "y"
-
-def getMonoviewShared(path, name, viewName, labelsNames, classificationIndices):
+def get_monoview_shared(path, name, view_name, labels_names, classification_indices):
"""ATM is not used with shared memory, but soon :)"""
- HDF5_dataset_file = h5py.File(path + name + ".hdf5", "w")
- X = HDF5_dataset_file.get(viewName).value
- Y = HDF5_dataset_file.get("Labels").value
- return X, Y
+ hdf5_dataset_file = h5py.File(path + name + ".hdf5", "w")
+ X = hdf5_dataset_file.get(view_name).value
+ y = hdf5_dataset_file.get("Labels").value
+ return X, y