Data science on COVID-19 / CORONA virus spread data

Name: Data science on COVID-19 / CORONA virus spread data
Rating: 4.6 (142 reviews)

Analysis of CORONA / COVID-19 virus data with Python: data handling, machine learning, visualisation, spread simulations

Created byFrank Kienle

Last updated 5/2023

English

What you'll learn

Analytics project applied on COVID 19 data, understanding spread of the virus
Data Science best practices from industry with full project walkthrough from setting up a project to delivery
Python with analysis, machine learning, visualisation, Facebook Prophet, SIR epidemic simulations, Tableau Dashboards

Course content

14 sections • 67 lectures • 7h 39m total length

Introduction1:36
Personal Introduction
Learning Goals and Content Overview5:44
Used Python Resources2:55

Introduction to Data Science5:35
CRISP-DM6:24
Terminology Data Science6:22
Python Project Setup9:29
Adwise for this section:
Remember the goal of all exercises is to set up everything on your own environment
Python file and Html file show the output of this section
Try to replicate each step in your own environment
Check if the project structure is set up in the correct way
Many different python packages are used throughout this lecture, the requirements file is added to inspect (However, most of the packages should be installed in our own Anaconda environment)

Introduction Data Understanding0:59
Adwise for this section:
Remember, the goal of the lecture is to set up everything on your own environment to enable you to do more own analysis
Python file and Html file show the output of this section
Try to replicate each step in your own environment
Check if the project structure is set up in the correct way
For the API Access (Lecture 11) you have to organize your own API key
Data Gathering GITHUB - Johns Hopkins GITHUB6:02
Data Gathering Web Scraping Example10:10
Data Gathering API call7:14
Data Gathering REST API call5:56
Data Gathering Wrap Up3:39

Modeling Introduction1:07
Adwise for this section:
Remember, the goal of the lecture is to set up everything on your own environment to enable you to do more own analysis
Ensure that the packages scikit-learn and scipy are installed
Play with the parameters for regression and filtering to get a feeling for the data set
Try to extract another country which you are interested in and do the analysis
The regression is only an approximation, go with the closed doubling formula to see correct numbers for larger window sizes
Modeling start with helper functions8:27
Exponential Slopes3:46
Machine Learning Basics Introduction7:16
Scikit-Learn Linear Regression6:45
ML Model Hypothesis5:26
Logarithmic Feature Space2:42
Piecewise Linear Regression11:25
Filtering the COVID Input and Doubling Rate calculations7:59

Requirements

Python basics
Math basics

Description

The goal of this lecture is to transport the best practices of data science from the industry while developing a CORONA / COVID-19 analysis prototype

The student should learn the process of modeling (Python) and a methodology to approach a business problem based on daily updated COVID 19 data sets

The final result will be a dynamic dashboard - which can be updated by one click - of COVID-19 data with filtered and calculated data sets like the current Doubling Rate of confirmed cases

Techniques used are REST Services, Python Pandas, scikit-learn, Facebook Prophet, Plotly, Dash, and SIR virus spread simulations + bonus section Tableau for visual analytics

For this, we will follow an industry-standard CRISP process by focusing on the iterative nature of agile development

Business understanding (what is our goal)
Data Understanding (where do we get data and cleaning of data)
Data Preparation (data transformation and visualization)
Modeling (Statistics, Machine Learning, and SIR Simulations on COVID Data)
Deployment (how to deliver results, dynamic dashboards in python and Tableau)

Who this course is for:

Beginner data science
Practitioners with basic understanding of Python

Data science on COVID-19 / CORONA virus spread data

What you'll learn

Explore related topics

Course content

Introduction3 lectures • 10min

Business Understanding4 lectures • 28min

Data Understanding6 lectures • 34min

Data Preparation3 lectures • 18min

Explorative Data Analysis - Dynamic Dashboards4 lectures • 23min

Modeling9 lectures • 55min

Evaluation - Full Walkthrough5 lectures • 42min

Deployment2 lectures • 19min

Predictive Machine Learning Modeling10 lectures • 1hr 5min

Simulation of SIR compartmental model5 lectures • 28min

Requirements

Description

Who this course is for: