In this I compare three supervised learning algorithms on the Twitter US Airline Dataset from kaggle: https://www.kaggle.com/crowdflower/twitter-airline-sentiment
- Naive Bayes
- KNeighbors Nearest
- RandomForest
In the TSE.py file you can check all the models with respective accuracy of each model after run this file.
In the Supervised Learning file I train the best model from all the previous one and predict the result.
Its colab notebook you dont need to run, it already shown the output.
One model is Tfidf model to transform the text into vector and the other is RandomForest Model with best accuracy.