My project is divided into two parts. The project is the data cleaing related part while the ML project2 is the latter steps.(modeling, training , parameter adjusting and evaluation) 
Since I used the wrong code (to print all the dataset in the notebook), \
this file is really difficult to be used.(Took up too resources on CPU)
Though I dropped the code now it is still hard to merge the two file. 
At the end of the data cleaning, I put all the data cleaned in a csv called output.csv to use later in the second part.