Text_Classification | Text Classification in deep learning techniques | Machine Learning library

I am trying to understand the TensorFlow text classification example at https://www.tensorflow.org/tutorials/keras/text_classification. They define the model as follows:

I'm working on a classification model based on the example, everything is working great, now I want to deploy this model as a REST service so that my applications can easily consume it.

I'm new to tensorflow2/keras. I was following this tutorial on tensorflow website. Instead of downloading the text data to directory, I use tensorflow_datasets to load imdb dataset directly to tensors/numpy arrays. Below is my code.

I am trying to interact with my machine learning model where I can get the input value to the flask route method from HTML but not able to pass on the response with a string value to the ajax query.

THe click of the button hits the ajax function and does goto the flask route function, but it doesn't even hit the success or error part of the ajax function. Gives 405 Method not Allowed error. 127.0.0.1 - - [12/Oct/2020 13:15:17] "POST / HTTP/1.1" 405 -

I am new to Flask and not aware of data binding options. Any help would be appreciated.

HTML PART

I get some errors when I run the code in this tutorial. I want to predict on some test data. When I run the following it works:

I am new to tensorflow and now learning the tutorials of tensorflow.org. Here is the website of the tutorial I'm learning: https://www.tensorflow.org/tutorials/keras/text_classification

But it doesn't work when I run the code below:

I have 64 bit windows 10 OS I have installed python 3.6.8 I have installed torch and torchtext using pip. torch version is 1.2.0

I am trying to load AG_NEWS dataset using below code:

I'm completely new to statistical learning etc but have a particular interest in text classification. I was following a lab I found on the topic here: https://cfss.uchicago.edu/text_classification.html#fnref1. Unfortunately the lab ends before the trained model could be used on new data, so I tried to figure out how to complete it myself.

I have my model trained, Im using random forest. When I try to use predict() on new data it throws an error: Error in predict.randomForest(modelFit, newdata) : variables in the training data missing in newdata

Which in my mind doesn't make sense as the test data is literally a subset of the original data. I assume this error has something to do with how I built my model vs the data structure of the test data but I'm honestly not competent enough to figure out how to solve the error or where it is actually even stemming from (though I assume Im making some ridiculous error).

There are other posts with the same error but I think the source of their errors are different to mine, I've tried to find a fix for this all day!

Complete code I'm using below:

I'm running some tutorial code from text classification

I can run the scripts and it worked but when I tried to run it line by line trying to understand what each step is doing, I got a bit confused at this step: