% FROM: http://pipelines.local:9001/p/data_tree_biology
% SCION: stability


A system that can maintain internal stability is called homeostatic. The systemic tendency can occur in any kind of system, but is taken from physiological system of higher animals, and their ability to coordinated response of its parts to any situation or stimulus that would tend to disturb its normal condition or function. Homeostasis is about balance. If a tree has too much water inside, it releases it by transpiration; in this way water is maintained at a constant state, water enters through the roots and released as water vapor through the leaves in order to keep the balance. The internal force that keeps a biological tree balanced, are not the same in data tree structures but that might be a source of inspiration. Red-black trees are an example of internal balance in tree graphs; which consist in an evolution of binary search trees that aim to keep the tree balanced without affecting the complexity of the primitive operations. This is done by coloring each node in the tree with either red or black and preserving a set of properties that guarantee that the deepest path in the tree is not longer than twice the shortest one. To ensure that its color scheme and properties don’t get thrown off, red-black trees employ a key operation known as rotation. Rotation is a binary operation, between a parent node and one of its children, that swaps nodes and modifys their pointers while preserving the inorder traversal of the tree (so that elements are still sorted).
% [_data_tree_biology_](http://pipelines.local:9001/p/data_tree_biology)

One of the questions that arises in a decision tree algorithm is the optimal size of the final tree. A tree that is too large risks overfitting the training data and poorly generalizing to new samples. A small tree might not capture important structural information about the sample space. A common strategy is to grow the tree until each node contains a small number of instances then use pruning to remove nodes that do not provide additional information. 
Decision tree pruning is an accepted technique for post-processing trees that reduces the size of decision trees by removing sections of the tree that provide little power to classify instances. Pruning removes nodes from an inferred decision tree. It has been demonstrated to improve the predictive accuracy of inferred decision trees in a wide variety of domains. Pruning reduces the number of partitions imposed on an instance space by a decision tree.
The metaphor for this method is taken from horticultural practice, where it involves the selective removal of parts of a plan to shape a tree, control or direct its growth, improve health, reduce risk from falling branches, prepare nursery specimens for transplanting, and both harvest and increase the yield or quality of flowers and fruits. The practice entails targeted removal of diseased, damaged, dead, non-productive, structurally unsound, or otherwise unwanted tissue. Pruning young trees, known as developmental tree pruning, is performed for structural enhancement. This tree care procedure helps ensure that young trees have a desirable branch architecture and structural integrity.
% [_data_tree_biology_](http://pipelines.local:9001/p/data_tree_biology)

In contrast to pruning, a number of recent studies have suggested that predictive accuracy may also be improved by more complex partitioning of an instance space than that formed by standard decision tree induction, using the grafting technique. Once the tree is constructed, then the new branches that can be added to the tree, which are grafted to improve the decision making process. Pruning and Grafting are complementary methods to improve the decision tree in supporting the decision. Pruning allows cutting parts of decision trees to give more clarity and grafting adds nodes to the decision trees to increase the predictive accuracy. To achieve grafting new branches can be added in the place of a single leaf or graft within leaves. However, the potential new branches have to be selected carefully to avoid increasing the error and failure cases.
Grafting in biological trees is also a useful technique. The method consist in asexual plant propagation that join plant parts so they will grow as one only structure. Some varieties of plants do not come true from seeds. The seed from a Haralson apple will produce an apple tree, but it will not produce a Haralson apple tree. Fruit trees cannot be reproduced "true" to the original cultivar from seed, they can only be reproduced by grafting. This process uses a root system better adapted to soil or climate than that produced naturally by an ungrafted plant
Although grafting can be successful if the two parts of the plants are compatible (scion on top and rootstock on the bottom), there are many reasons why a graft can result in failure:
	* Scion and rootstock not compatible (not fitting pipes) 
	* Not meeting properly of the vascular system of each plant (leakage) 
	* Scion is upside-down (contrary flow direction)
	* Grafting is performed at the wrong season (influence of weather and time)
	* Scion and rootstock are unhealthy
	* Scion is dried or injured by cold 
	* The union is displaced by storm, birds, or other means (leakage) 
% [_data_tree_biology_](http://pipelines.local:9001/p/data_tree_biology)