modAL-python · talolard · talolard · talolard · Apr 3, 2020 · talolard
diff --git a/modAL/datamanager.py b/modAL/datamanager.py
+        """
+        This is where the magic happens.
+        We take self.unlabeled_mask.nonzero()[0] which gives us an array of the indices that appear in the unlabeled
+        data. So if the original label was at position 0 we look up the "real index" in the unlabeled_indices array to
+        get it's true index
+        :param labels:
+        :return:
+        """
diff --git a/modAL/datamanager.py b/modAL/datamanager.py
+    def _update_masks(self, labels: Union[LabelList, Label]):
+        for label in labels:
+            self.labeled_mask[label[0]] = True
diff --git a/modAL/datamanager.py b/modAL/datamanager.py
+            self._labels[label[0]] = label[1]
+
+    @property
+    def unlabeld(self):
diff --git a/modAL/datamanager.py b/modAL/datamanager.py
+            raise Exception(
+                "Malformed input. Please add either a tuple (ix,label) or a list [(ix,label),..]"
+            )
diff --git a/modAL/datamanager.py b/modAL/datamanager.py
+        correctLabels: LabelList = []
+        unlabeled_indices = self.unlabeled_mask.nonzero()[0]
+
+        for label in labels:
+            newIndex = unlabeled_indices[label[0]]
+            newLabel: Label = (newIndex, label[1])
+            correctLabels.append(newLabel)
diff --git a/modAL/datamanager.py b/modAL/datamanager.py
+        for label in labels:
+            self.labeled_mask[label[0]] = True
+
+    def _offset_new_labes(self, labels: LabelList):
diff --git a/modAL/datamanager.py b/modAL/datamanager.py
+    @property
+    def labels(self):
+        '''
+
+        Returns the labels indexed with respect to LD
+
+        '''
+        return self._labels[self.labeled_mask]
diff --git a/modAL/datamanager.py b/modAL/datamanager.py
+        elif isinstance(labels, list):
+            pass
+        else:
+            raise Exception(
+                "Malformed input. Please add either a tuple (ix,label) or a list [(ix,label),..]"
+            )
diff --git a/modAL/datamanager.py b/modAL/datamanager.py
+
+        :param features: An array of the features that will be used for AL.
+        :param labels: Any prexesiting labels. Each label is a tuple(idx,label)
+        :param source: A list of the original data
diff --git a/examples/data_manager_and_text_classification.py b/examples/data_manager_and_text_classification.py
+        for index in range(1):
+            # query the learner as usual, in this case we are using a batch learning strategy
+            # so indices_to_label is an array
+            indices_to_label, query_instance = learner.query(manager.unlabeld)
+            labels = []  # Hold a list of the new labels
+            for ix in indices_to_label:
+                """
+                Here is the tricky part that the manager solves. The indicies are indexed with respect to unlabeled data
+                but we want to work with them with respect to the original data. The manager makes this almost transparent
+                """
+                # Map the index that is with respect to unlabeled data back to an index with respect to the whole dataset
+                original_ix = manager.get_original_index_from_unlabeled_index(ix)
+                # print(manager.sources[original_ix]) #Show the original data so we can decide what to label
+                # Now we can lookup the label in the original set of labels without any bookkeeping
+                y = original_labels_train[original_ix]
+                # We create a Label instance, a tuple of index and label
+                # The index should be with respect to the unlabeled data, the add_labels function will automatically
+                # calculate the offsets
+                label = (ix, y)
+                # append the labels to a list
+                labels.append(label)
+            # Insert them all at once.
+            manager.add_labels(labels)
+            # Note that if you need to add labels with indicies that repsect the original dataset you can do
+            # manager.add_labels(labels,offset_to_unlabeled=False)