NLP-wine-recommendation

Pedagogical introduction to NLP.

Approach

In this notebook we apply the following concepts and methods:

• Data preprocessing:
  • Removal of duplicates.
  • Binning of target variable.
  • Pandas profiling.
• Natural Language Processing (NLP):
  • Bag of words.
  • TF-IDF.
  • Word embeddings.
  • (Bi-directional) RNNs, including Attention mechanism.
• Model stacking.
• Bayesian hyperparameter optimization.

Note

If you have problems viewing the .ipynb notebook, go to: https://nbviewer.jupyter.org/github/peitsche/NLP-wine-recommendation/blob/master/NLP_wine-reviews.ipynb