[go: nahoru, domu]

Skip to content

A complete end-to-end machine learning portal that covers processes starting from model training to the model predicting results using FastAPI.

Notifications You must be signed in to change notification settings

shreyas-jk/ML-Portal-FastAPI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

65 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Machine Learning Portal

Goal

A complete end-to-end machine learning portal that covers processes starting from model training to model predicting results using FastAPI.

Application

Main Menu

  • Dataset: Set default dataset from the list that will be used for training and building the models.
  • Train: Start the training process
  • Prediction: Upload test dataset to get predictions.

Save sample test data (sample_test.csv) for testing the prediction module.

Logger Menu

  • Data Preprocessing: Logs generated during preprocessing process.
  • Training: Logs generated during training process.
  • Prediction: Logs generated during prediction process.

Workflow

  • Import/upload dataset
  • Preprocessing
    • Categorical features cleaning
    • Handling missing value (categorical)
    • Handling missing value (numeric)
    • Encoding cateogrical feature
    • Over sampling
    • Clustering
    • Train-Test split
    • Model selection
      • Hyper parameter tuning
    • Saving best model
    • Download prediction results

Process Design

Design

Live Project

https://machine-learning-portal.herokuapp.com

YouTube Demo

https://www.youtube.com/watch?v=p7jGqMkxRG4

About

A complete end-to-end machine learning portal that covers processes starting from model training to the model predicting results using FastAPI.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages