W207 Final Project
Alan Jian, Ayda Nayeb Nazar, Kelly Zabors, Jocelyn Thai, Silas Santini
Fine tuned model can be found here
Presentation slides here
Data Gathering via PushShift.io: Take a look through the pulling_data.ipynb for details on how we utilized PushShift to get data from r/TwoSentenceHorror.
Data Cleaning and EDA: Our data exploration and cleaning steps can be found in the eda.ipynb file.
Model Training: To find our model and the training loop that we applied, you can take a look in the Copy_of_W207_Barty_Party.ipynb file.
Raw pulled Data: The full set of data that we were able to pull can be found in nov_thru_present.csv.
Cleaned Data: You can find the cleaned version of the data that was used for training in the final_horror_stories.csv.
Miscellaneous: The rest of the data are from trial runs of the PushShift API on r/TwoSentenceHorror.