2. add gedlib module.
3. add ged module.
4. create Kernel class and StructrualSP class.
5. rearrange directory.

2. modify the treelet kernel, use tuples to store canonkeys instead of strings in case that some labels strings contain more than 1 character.

* rewrite the implementation of the marginalized kernel.
* implement four computing methods of the generalized random walk kernel.
* in the path kernel up to length h, use trie to save all paths, saving tremendous memories; use the Deep-first search to get paths from graphs.
* in model_selection_for_precomputed_kernel method, complete the part to do cross validation when Gram matrices are read from file.
* in get_dataset_attributes methods, correct three sub-methods about getting node degrees, add sub-methods to get fill factors of graphs.
* change default chunksize of pool.imap_unordered parallel method to 100.
* remove try... except blocks in case they hidden bugs.

2. model_selection_precomputed can now save all results as human readable text.
3. modify pygraph.utils.utils.floydTransformation and pygraph.utils.graphdataset.get_dataset_attributes.

MOD modify tree pattern kernel, remove tottering.
MOD save output in function model_selection_precpmputed.