ML Based Review Api designed to handle reviews given by User(customers) and Predict whether the Review is positive or negative
In addition to the pure API implementation from Scratch, a number of high-level classes to make the development of API easy and straightforward.
* Methodology/Principal
It consists of two important steps : Creating and Production
1. Creation
Train the Model Using Historical Dataset and test Accuracy the Model
How to train and test the Model
2. Production
Serialization & Deserialization
In the context of data storage, serialization is the process of translating data structures or object state into a format that can be stored.
This is done to reduce the size and complexity of dataset and which reduces the time of re-execution.
* Creating an API using Flask
There are three important parts in constructing our wrapper function, Apicall():
i)- Getting the request data enter by user (for which predictions are to be made)
ii)- Loading our pickled estimator
iii)- jsonify our predictions and send the response back
* Deployment
i)- Heroku Cloud Station
Heroku is a cloud platform based on a managed container system, with integrated data services and a powerful ecosystem, for deploying and running modern apps.
Deployment Involves following process:
i)- Create Application
ii)- Provid GitHub Connection
iii)- Select Python as Build Packages
iv)-Heruko Postreg:: DataBase
v)-Deploy Application
9Apps 4.9
