It is my first time to attend the kaggle competition, and it is also my first time to deal with multi-type data, including text and numbers. It took some time for me to figure out houw to transform it into one-hot data.
Thanks to the github code (I am sorry I forget the author), I learn a lot from his code.
Thanks.
However, I think my model is not very good, cause the accuracy of the testing data is only 63%. You guys can try other models like the randomforest or someting else.