Vacation: Week 4

E-mailed Dr. Ng early in the week, requesting to set up a short meeting to discuss about the project and to seek his advice. Received an automated out-of-office reply as he was on vacation till 2nd Jan.

Downloaded and installed Weka. Read through parts of the manual and also some online tutorials. Managed to connect to MySQL database from Weka, so that the poem lines can be accessed and subsequently classified. In order to do this, an ODBC driver had to be downloaded and installed. Weka takes input data in ARFF formats primarily, even though it can also accept other data formats such as CSV and also data stored in databases. I have since familiarised myself with the ARFF file format to create input text data for text classification. I have also tried getting the SMO Classifer to operate on a training set of data so that it may commence its learning. However, at this point, I am unable to get it to operate on a test set of data. Have sought Hooman's help on this. Once this is resolved, I can try to perform the same operations through the CLI, following which I will try to incorporate it into the VC++ code.