The Organization of this folder is as follows:

• ml_project2.ipynb a notebook containing our code (data processing/feature engineering/model training)
• Word2Vec_CNN.ipynb a notebook containing a convolutional neural network
• a notebook run.ipynb containing the code used to sumbit our prediction on kaggle
• a scripty run.py containing the code used to sumbit our prediction on kaggle
• opinion-lexicon-folder containing a list of positive and negative words on emojis
• pca_results some of our results saved as csv files
• our pdf report
• a readme

To run all the codes we need following libraries: TensorFlow, Keras (open source neural network library capable of running on top of TensorFlow), Word2Vec, Gensim, Scikit-learn, Pandas, Numpy, Matplotlib, Random, Sqdm, Nltk, Spacy.