Concrete Compressive Strength Predictor. Machine learning web application, built using Django and PyCaret.
Estimating the compressive strength of a concrete mixture is such a complicated process, after doing a number of examinations and producing many samples. Here comes the job of the CCS-P, a machine learning program which can do this process by just passing to it the quantities of the mixture components.
PyCaret is an open source, low-code machine learning library in Python to train and deploy machine learning pipelines and models in production.
Django has its own naming system for all functions and components (e.g., HTTP responses are called “views”). It also has an admin panel, which is deemed easier to work with than in Lavarel or Yii, and other technical features, including:
- Simple syntax;
- Its own web server;
- MVC (Model-View-Controller) core architecture;
- “Batteries included” (comes with all the essentials needed to solve solving common cases);
- An ORM (Object Relational Mapper);
- HTTP libraries;
- Middleware support; and
- A Python unit test framework.
the Django framework can take on numerous tasks. Django can be used for creating:
-
Client relationship management (CRM) systems;
-
Content management systems (CMS) for internal and commercial use;
-
Communication platforms;
-
Booking engines;
-
Document administration platforms;
-
Among other things, Django is great for:
-
Algorithm-based generators
-
Emailing solutions
-
Verification systems
-
Filtering systems with dynamically changing rules and advanced parameters
-
Data analysis solutions and complicated calculations
-
Machine learning
-
There are thousands of websites across the globe with Django at their core.
