Skip to content Skip to sidebar Skip to footer

Data Science: Diabetes Prediction- Model Building Deployment

Data Science: Diabetes Prediction- Model Building Deployment

End-to-End Machine Learning Project: Train and Deploy Models as Web Apps Using Flask and Heroku. Building a Diabetes Prediction app using Machine Learning. Data Science: Diabetes Prediction- Model Building Deployment

What you'll learn

  • Data Analysis and Understanding
  • Data Cleaning and Imputation
  • Data Preparation
  • Model Building for Diabetes Prediction
  • Hyperparameter Tuning
  • Classification Metrics
  • Model Evaluation
  • Running the model on a local Streamlit Server
  • Pushing your notebooks and project files to GitHub repository
  • Deploying the project on Heroku Cloud Platform

Requirements

  • Very Basic knowledge of Python and Anaconda
  • Familiarity with Github

Description

This course is about predicting whether or not the person has diabetes using Machine Learning Models. This is a hands on project where I will teach you the step by step process in creating and evaluating a machine learning model and finally deploying the same on Cloud platforms to let your customers interact with your model via an user interface.

This course will walk you through the initial data exploration and understanding, data analysis, data preparation, model building, evaluation and deployment techniques. We will explore multiple ML algorithms to create our model and finally zoom into one which performs the best on the given dataset.

At the end we will learn to create an User Interface to interact with our created model and finally deploy the same on Cloud.

I have splitted and segregated the entire course in Tasks below, for ease of understanding of what will be covered.

  • Task 1  :  Installing Packages.
  • Task 2  :  Importing Libraries.
  • Task 3  :  Loading the data from source.
  • Task 4  :  Pandas Profiling
  • Task 5  :  Understanding the data
  • Task 6  :  Data Cleaning and Imputation
  • Task 7  :  Train Test Split
  • Task 8  :  Scaling using StandardScaler
  • Task 9  :  About Confusion Matrix
  • Task 10 :  About Classification Report
  • Task 11 :  About AUC-ROC
  • Task 12 :  Checking for model performance across a wide range of models
  • Task 13 :  Creating Random Forest model with default parameters
  • Task 14 :  Model Evaluation – Classification Report,Confusion Matrix,AUC-ROC
  • Task 15 :  Hyperparameter Tuning using RandomizedSearchCV
  • Task 16 :  Building RandomForestClassifier model with the selected hyperparameters
  • Task 17 :  Final Model Evaluation – Classification Report,Confusion Matrix,AUC-ROC
  • Task 18 :  Final Inference
  • Task 19 :  Loading the saved model and scaler objects
  • Task 20 :  Testing the model on random data
  • Task 21 :  What is Streamlit and Installation steps.
  • Task 22 :  Creating an user interface to interact with our created model.
  • Task 23 :  Running your notebook on Streamlit Server in your local machine.
  • Task 24 :  Pushing your project to GitHub repository.
  • Task 25 :  Project Deployment on Heroku Platform for free.

Data Analysis, Model Building and Deployment is one of the most demanded skill of the 21st century. Take the course now, and have a much stronger grasp of data analysis, machine learning and deployment in just a few hours!

Enroll Now Udemy Course

Views > Building Machine Learning Web Apps with Python

Post a Comment for "Data Science: Diabetes Prediction- Model Building Deployment"

N7DWHALVYX3VQRL