In this repository i explain how you can implement a text classifier on custom dataset using PyTorch This jupyter notebook is inspired from: https://pytorch.org/tutorials/beginner/text_sentiment_ngrams_tutorial.html
The dataset is from the Tweet Sentiment Extraction challenge from Kaggle(https://www.kaggle.com/c/tweet-sentiment-extraction/overview)
We would implement text classification using a simple embedding bag of words using PyTorch on tweet data to classify tweets as "positive","negative" or "neutral"
Pre-requisites:
PyTorch (https://pytorch.org/)
TorchText (https://anaconda.org/pytorch/torchtext)
Python 3.6 and above (https://www.anaconda.com/products/individual)