Balancing String based Binary Search Tree (For Spellchecking)

Question

Update: I can't get "Balancing" to work, because I cannot get "doAVLBalance" to recognize the member functions "isBalanced()", "isRightHeavy()", "isLeftHeavy". And I don't know why! I tried Sash's example(3rd answer) exactly but I get "deceleration is incompatible" and I couldn't fix that...so I tried doing it my way...and it tells me those member functions don't exist, when they clearly do.

"Error: class "IntBinaryTree:TreeNode" has no member "isRightHeavy". I'm stuck after trying for the last 4 hours :(. Updated code below, help would be much appreciated!!

I'm creating a String based Binary Search Tree and need to make it a "Balanced" tree. How do I do this?* Help please!! Thanks in advance!

BinarySearchTree.cpp:

    bool IntBinaryTree::leftRotation(TreeNode *root)
    {
        //TreeNode *nodePtr = root;  // Can use nodePtr instead of root, better?
        // root, nodePtr, this->?

        if(NULL == root)
        {return NULL;}

        TreeNode *rightOfTheRoot = root->right;
        root->right = rightOfTheRoot->left;
        rightOfTheRoot->left = root;

        return rightOfTheRoot;
    }

    bool IntBinaryTree::rightRotation(TreeNode *root)
    {
        if(NULL == root)
        {return NULL;}
        TreeNode *leftOfTheRoot = root->left;
        root->left = leftOfTheRoot->right;
        leftOfTheRoot->right = root;

        return leftOfTheRoot;
    }

    bool IntBinaryTree::doAVLBalance(TreeNode *root)
    {


        if(NULL==root)
            {return NULL;}
        else if(root->isBalanced()) // Don't have "isBalanced"
            {return root;}

        root->left = doAVLBalance(root->left);
        root->right = doAVLBalance(root->right);

        getDepth(root); //Don't have this function yet

        if(root->isRightHeavy()) // Don't have "isRightHeavey"
        {
            if(root->right->isLeftheavey())
            {
                root->right = rightRotation(root->right);
            }
            root = leftRotation(root);
        }
        else if(root->isLeftheavey()) // Don't have "isLeftHeavey"
        {
            if(root->left->isRightHeavey())
            {
                root->left = leftRotation(root->left);
            }
            root = rightRotation(root);
        }
        return root;
    }

    void IntBinaryTree::insert(TreeNode *&nodePtr, TreeNode *&newNode)
    {
        if(nodePtr == NULL)
            nodePtr = newNode;                  //Insert node
        else if(newNode->value < nodePtr->value)
            insert(nodePtr->left, newNode);     //Search left branch
        else
            insert(nodePtr->right, newNode);    //search right branch
    }

//
// Displays the number of nodes in the Tree


int IntBinaryTree::numberNodes(TreeNode *root)
{
    TreeNode *nodePtr = root;

    if(root == NULL)
        return 0;

    int count = 1; // our actual node
    if(nodePtr->left !=NULL)
    { count += numberNodes(nodePtr->left);
    }
    if(nodePtr->right != NULL)
    {
        count += numberNodes(nodePtr->right);
    }
    return count;
} 

    // Insert member function

    void IntBinaryTree::insertNode(string num)
    {
        TreeNode *newNode; // Poitner to a new node.

        // Create a new node and store num in it.
        newNode = new TreeNode;
        newNode->value = num;
        newNode->left = newNode->right = NULL;

        //Insert the node.
        insert(root, newNode);
    }

    // More member functions, etc.

BinarySearchTree.h:

class IntBinaryTree
{
private:
    struct TreeNode
    {
        string value; // Value in the node
        TreeNode *left; // Pointer to left child node
        TreeNode *right; // Pointer to right child node
    };

    //Private Members Functions
    // Removed for shortness
    void displayInOrder(TreeNode *) const;


public:
    TreeNode *root;
    //Constructor
    IntBinaryTree()
        { root = NULL; }
    //Destructor
    ~IntBinaryTree()
        { destroySubTree(root); }

    // Binary tree Operations
    void insertNode(string);
    // Removed for shortness

    int numberNodes(TreeNode *root);
    //int balancedTree(string, int, int); // TreeBalanced

    bool leftRotation(TreeNode *root);
    bool rightRotation(TreeNode *root);
    bool doAVLBalance(TreeNode *root); // void doAVLBalance();
    bool isAVLBalanced();

    int calculateAndGetAVLBalanceFactor(TreeNode *root);

    int getAVLBalanceFactor()
    {
        TreeNode *nodePtr = root; // Okay to do this? instead of just
        // left->mDepth
        // right->mDepth

        int leftTreeDepth = (left !=NULL) ? nodePtr->left->Depth : -1;
        int rightTreeDepth = (right != NULL) ? nodePtr->right->Depth : -1;
        return(leftTreeDepth - rightTreeDepth);
    }

    bool isRightheavey() { return (getAVLBalanceFactor() <= -2); }

    bool isLeftheavey() { return (getAVLBalanceFactor() >= 2); }


    bool isBalanced()
    {
        int balanceFactor = getAVLBalanceFactor();
        return (balanceFactor >= -1 && balanceFactor <= 1);
    }


    int getDepth(TreeNode *root); // getDepth

    void displayInOrder() const
        { displayInOrder(root); }
    // Removed for shortness
};

Answer 1

There are many ways to do this, but I'd suggest that you actually not do this as all. If you want to store a BST of strings, there are much better options:

1. Use a prewritten binary search tree class. The C++ std::set class offers the same time guarantees as a balanced binary search tree and is often implemented as such. It's substantially easier to use than rolling you own BST.

2. Use a trie instead. The trie data structure is simpler and more efficient than a BST of strings, requires no balancing at all, and is faster than a BST.

If you really must write your own balanced BST, you have many options. Most BST implementations that use balancing are extremely complex and are not for the faint of heart. I'd suggest implementing either a treap or a splay tree, which are two balanced BST structures that are rather simple to implement. They're both more complex than the code you have above and I can't in this short space provide an implementation, but a Wikipedia search for these structures should give you plenty of advice on how to proceed.

Hope this helps!

Answer 2

Unfortunately, we programmers are literal beasts.

make it a "Balanced" tree.

"Balanced" is context dependent. The introductory data structures classes typically refer to a tree being "balanced" when the difference between the node of greatest depth and the node of least depth is minimized. However, as mentioned by Sir Templatetypedef, a splay tree is considered a balancing tree. This is because it can balance trees rather well in cases that few nodes accessed together at one time frequently. This is because it takes less node traversals to get at the data in a splay tree than a conventional binary tree in these cases. On the other hand, its worst-case performance on an access-by-access basis can be as bad as a linked list.

Speaking of linked lists...

Because otherwise without the "Balancing" it's the same as a linked-list I read and defeats the purpose.

It can be as bad, but for randomized inserts it isn't. If you insert already-sorted data, most binary search tree implementations will store data like an bloated and ordered linked list. However, that's only because you're building one side of the tree continually. (Imagine inserting 1, 2, 3, 4, 5, 6, 7, etc... into a binary tree. Try it on paper and see what happens.)

If you have to balance in a theoretical worst-case-must-guaranteed sense, I recommend looking up red-black trees. (Google it, second link is pretty good.)

If you have to balance it in a reasonable way for this particular scenario, I'd go with integer indices and a decent hash function -- that way the balancing will happen probabilistically without any extra code. That is to say, make your comparison function look like hash(strA) < hash(strB) instead of what you've got now. (For a quick but effective hash for this case, look up FNV hashing. First hit on Google. Go down until you see useful code.) You can worry about the details of implementation efficiency if you want to. (For example, you don't have to perform both hashes every single time you compare since one of the strings never changes.)

If you can get away with it, I strongly recommend the latter if you're in a crunch for time and want something fast. Otherwise, red-black trees are worthwhile since they're extremely useful in practice when you need to roll your own height-balanced binary trees.

Finally, addressing your code above, see the comments in the code below:

int IntBinaryTree::numberNodes(TreeNode *root)
{
    if(root = NULL) // You're using '=' where you want '==' -- common mistake.
                    // Consider getting used to putting the value first -- that is,
                    // "NULL == root". That way if you make that mistake again, the
                    // compiler will error in many cases.
        return 0;
    /*
    if(TreeNode.left=null && TreeNode.right==null)  // Meant to use '==' again.
    { return 1; }

    return numberNodes(node.left) + numberNodes(node.right);
    */

    int count = 1; // our actual node
    if (left != NULL)
    {
        // You likely meant 'root.left' on the next line, not 'TreeNode.left'.
        count += numberNodes(TreeNode.left);
        // That's probably the line that's giving you the error.
    }
    if (right != NULL)
    {
        count += numberNodes(root.right);
    }
    return count;
}

Answer 3

Programmers use AVL Tree concepts to balance binary trees. It is quite simple. More information can be found online. Quick wiki link

Below is the sample code which does tree balance using AVL algorithm.

Node *BinarySearchTree::leftRotation(Node *root)
{
    if(NULL == root)
    {
        return NULL;
    }
    Node *rightOfTheRoot = root->mRight;
    root->mRight = rightOfTheRoot->mLeft;
    rightOfTheRoot->mLeft = root;

    return rightOfTheRoot;
}

Node *BinarySearchTree::rightRotation(Node *root)
{
    if(NULL == root)
    {
        return NULL;
    }
    Node *leftOfTheRoot = root->mLeft;
    root->mLeft = leftOfTheRoot->mRight;
    leftOfTheRoot->mRight = root;

    return leftOfTheRoot;
}

Node *BinarySearchTree::doAVLBalance(Node *root)
{
    if(NULL == root)
    {
        return NULL;
    }
    else if(root->isBalanced())
    {
        return root;
    }

    root->mLeft  = doAVLBalance(root->mLeft);
    root->mRight = doAVLBalance(root->mRight);

    getDepth(root);

    if(root->isRightHeavy())
    {
        if(root->mRight->isLeftHeavy())
        {
            root->mRight = rightRotation(root->mRight);
        }
        root = leftRotation(root);
    }
    else if(root->isLeftHeavy())
    {
        if(root->mLeft->isRightHeavy())
        {
            root->mLeft = leftRotation(root->mLeft);
        }
        root = rightRotation(root);
    }

    return root;
}

Class Definition

class BinarySearchTree
{
public:
    // .. lots of methods 
    Node *getRoot();
    int getDepth(Node *root);

    bool isAVLBalanced();
    int calculateAndGetAVLBalanceFactor(Node *root);
    void doAVLBalance();

private:
     Node *mRoot;
};

class Node
{
public:
    int  mData;
    Node *mLeft;
    Node *mRight;
    bool mHasVisited;
    int mDepth;
public:

    Node(int data)
    : mData(data),
      mLeft(NULL),
      mRight(NULL),
      mHasVisited(false),
      mDepth(0)
    {
    }

    int getData()              { return mData; }

    void setData(int data)     { mData = data;  }

    void setRight(Node *right) { mRight = right;}

    void setLeft(Node *left)   { mLeft = left; }

    Node * getRight()          { return mRight; }

    Node * getLeft()           { return mLeft; }

    bool hasLeft()             { return (mLeft != NULL);  }

    bool hasRight()            { return (mRight != NULL); }

    bool isVisited()           { return (mHasVisited == true); }

    int getAVLBalanceFactor()
    {
        int leftTreeDepth = (mLeft != NULL) ? mLeft->mDepth : -1;
        int rightTreeDepth = (mRight != NULL) ? mRight->mDepth : -1;
        return(leftTreeDepth - rightTreeDepth);
    }

    bool isRightHeavy() { return (getAVLBalanceFactor() <= -2); }

    bool isLeftHeavy()  { return (getAVLBalanceFactor() >= 2);  }

    bool isBalanced()
    {
        int balanceFactor = getAVLBalanceFactor();
        return (balanceFactor >= -1 && balanceFactor <= 1);
    }
};