Follow along and learn to code an NLP classification problem in TensorFlow Guided Python Project. In this guided project we will use the text review left by customers on Amazon's site and predict which star rating was left based on how they described their experience with the product.
In this TensorFlow NLP project, our teacher will guide you through a more thorough NLP preprocessing as we eliminate stop words using NLTK library, the natural language tool kit, and then remove punctuation using the string library in Python. Adding to the preprocessing steps here we also will be stemming our vocabulary to help reduce the number of total different words in our text hopefully making it easy for our model to predict.
In this level 5 guided project, we build a more advanced Sequential model in TensorFlow. This includes using an Embedding layer followed by a 1 Dimension Convolutional layer. In between these layers, we will include a Spatial Dropout layers which works well on NLP deep learning problems.
We will then follow these layers with the Bi-Directional layer that holds an LSTM layer while returning sequences. This is followed by a traditional dropout layer and another Bi-Directional layer with an LSTM inside however the second time it will not be returning sequences.
On the tail end, we finish with Dense fully connected layers and then our output layers with softmax activation needed for our classification problem.
Lastly, we will build a Python function that will take in any text and predict the final rating. You even be able to write your own review and see how positive or negative our deep learning model thinks is implied by what you wrote.
Follow Data Science Teacher Brandyn
dataGroups:
