This library is for us to explore natural language processing (NLP) techniques. We will be implementing some of the NLP models to the Hacker News Dataset.
In order keep the project active, we will be meeting on a weekly basis in order discuss and determine tasks for past and future assignments.
| Date | Meeting # | Description |
|---|---|---|
| 2018.12.04 | Meeting 1 | Project structure and definition is discussed. |
Meetings will be updated regularly.
## To Do List
- Defining project introduction
- Defining objectives, KPIs and goals
- General exploration of NLP based on courses, tutorials, etc.
- Achieving consensus for objectives
- Achieving consensus for EDA
- Achieving consensus for data cleaning
- Achieving consensus for feature selection
- Achieving consensus for data modeling
- Achieving consensus for model evaluation
- Achieving consensus for performance metrics
The following versions will be decided for the given accomplishments, respectively.
- 0.0.1 Completing Project Structure & Definition
- 0.1.0 First Draft of Documentation
- 0.2.0 Expoloratory Data Analysis
- 1.0.0 Text summarization
- 2.0.0 Text Classification
Project based on the cookiecutter data science project template. #cookiecutterdatascience
Project branching based on the A Successful Git Branching Model. By Vincent Driessen.