Guss the Goldfish

• 

  Guss's personal Twitter.

Inspiration

We wanted to make a twitter bot that we would post semisensical tweets. We did this mostly as a learning experience. The three of us all had very little to no experience with GitHub which we used throughout the project to gain more. We also did not have experienced with utilizing an API to push changes to a website like Twitter which we have now done. Two of us had very little to no experience with Python and treated this as sort of a crash course in it. Ultimately we just wanted to teach ourselves some new things and have some fun.

What it does and how we built it

Guss the Goldfish takes in a text file of sentences and generates Tweets using this vocabulary and syntax, sometimes with hashtags if he wants to. We used an open source toolkit called markovify which contains functions we could manipulate to our purposes for the sentence generating. His vernacular is currently built upon various strings from random openly available findings on the Internet and the entire script of Finding Nemo. Guss then uses the tweepy package to post to his Twitter. Guss is fully functional for his current purposes.

Challenges we ran into and what we learned

Our biggest challenges were having little to no experience with almost every part of what we were doing (namely using GitHub, Python, and the Twitter API). It was a fun and fast way to get a crash course in all of these new things. One of our team members was also only able to attend on Saturday and we wanted to complete it together, so we completed this within the first day of the Hackathon.

Accomplishments that we're proud of

We're very proud to have a finished product within the one day that we had to work and having little to no experience with anything we were working with. It was very exciting to be able to learn so much in such a short amount of time and pull it all together as a team. We were also very excited with the skills that we developed with GitHub as we went from barely understanding what a branch was to very efficiently sharing our code across them.

What's next for Guss?

We would like to allow Guss to live on one of our Raspberry Pi's and post at random times, whenever he wants to. We would also like to create an even more intelligent chatbot using more advanced machine learning strategies.

Built With

• python