Skip to content
This repository has been archived by the owner on May 30, 2023. It is now read-only.

Backend for twentyq written in Python 3 with Flask

License

Notifications You must be signed in to change notification settings

I-Dont-Care-Anymore/twentyq-api

Repository files navigation

Twenty-Q Api

Inspiration

Have ideas and inventions for a startup? Would you like to know more about the industry your idea will be competing in? We did too. Now, answer some questions for us and we can give you a rundown of your market and competition.

What it does

Answer some questions for TwentyQ about your big idea and we will use a decision tree to determine what industry your idea belongs in as you progress. When you complete the questions we will give you curated information on the state of the industry and the big players in it.

How we built it

We used a nlp library to process and connect shared infinitive verbs and data. A decision tree of those terms will Our database was created by scraping information from more than 12,000 companies representing the top ten of each industry as defined by the North American Industry Classification System. We then analyzed our data and utilized MicroStrategy's Data Analytics to visualize and draw conclusions on different sectors and industries. We used what we learned to improve the analyses TwentyQ provides as well as improve on the supply, demand, and driving forces of each sector.

Challenges we ran into

Our initial intents were to fully leverage MicroStrategy's Data Analytics features to visualize and provide complex analyses on the data we presented to the user. However, difficulty with authentication meant that we could not show these graphs for current users. Still, we were able to use the visualization to give recommendations and written trends for different sectors.

Accomplishments that we're proud of

We are proud to leverage natural language processing to connect more than 1,200 different industries and be able to present our users with the industry their product most fits.

What we learned

The four of us at TwentyQ learned to divide the labor to maximize our time in the 36 hours we were given. This hackathon taught us to be much more conscientious of how long each task will take as we create a schedule. Most of us were new to Python and were able to use this project to practice a new language!

What's next for TwentyQ

TwentyQ will be receiving changes to include more information, more graphs, venture capital, further reading, a smoother and more human-like questioning phase, and even tailored recommendations! We hope to implement a relational database, embedded visualization from MicroStrategy, more granular data, and a more accurate and understandable question base with improved natural language processing.

Usage

Linux

sudo apt-get install python3 python3-pip python3-virtualenv virtualenv
virtualenv .env --python=python3
source .env/bin/activate
pip3 install -r requirements.txt
python -m spacy download en_core_web_lg
python3 main.py

Windows

Run in an administrator powershell:

Set-ExecutionPolicy AllSigned

This one doesn't need to be admin

virtualenv .\env --python=python3
.\env/bin/activate
pip3 install -r requirements.txt
python -m spacy download en_core_web_lg
python3 main.py

And now, a message from our sponsors

spongebob

About

Backend for twentyq written in Python 3 with Flask

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published