/e_summit

Primary LanguageJupyter Notebook

PyAnalyzer

Open In Colab Binder

This project aims to predict the psychological traits of a person on the basis of his/her social media posts. It predicts the following traits:

  • EXT - Extraversion
  • OPN - Openness
  • NEU - Neuorticism
  • CON - Conscientiousness
  • AGR - Agreeableness

Here's How it Works:

Run on Google Colab (no installation required)

Link to colab notebook This notebook demostrates how our script works.

Local Setup

  1. Clone the repository
git clone https://github.com/Mainakdeb/e_summit.git
  1. Navigate to specific Directory
cd e_summit
  1. Install the requirements from requirements.txt file
pip install -r requirements.txt
  1. In case you don't want to train the algorithm, download pretrained models from Google drive link

Run Via Command Line:

Add desired names in names.txt along with some keywords(some names and keywords already exist in the given file).

Run the command down below

python3 predict_type.py --testcase 7 --inputfile "names.txt"

See the output using:

cat predictions.txt

Props!

  1. Python
  2. Socialreaper
  3. SkLearn
  4. MatplotLib
  5. Pandas
  6. GSearch Library

Demos

1. Providing input through names.txt

Screenshot from 2021-02-08 15-23-23

2. Output of Personality predictions

Screenshot from 2021-02-08 15-25-51

3. Visualized Report (in the colab notebook)

Screenshot from 2021-02-08 15-29-07

Tasks Completed

Done Set Of Tasks
✔️ Main file and/or other header files if used
✔️ The trained model
✔️ A Readme with instructions on how to run the code
✔️ A brief one page description of the methods used with proper citations
✔️ Outcome Report