Introduction Cases of a novel coronavirus were rst reported in Wuhan, Hubei province, China, in December 2019

No answer yet for this question. Ask a Tutor

Question:

Introduction Cases of a novel coronavirus were rst reported in Wuhan, Hubei province, China, in December 2019 and have since spread across the world. Epidemio- logical studies have indicated human-to-human transmission in China and else- where. Epidemiological data is needed during emerging epidemics to best mon- itor and anticipate spread of infection. Data Sets The dataset has been made available publicly as of 20th January, 2020 con- taining dierent information about the patients: clinic, demographic and geo- graphic.

Here is the table with the name variables :

you can also find in this link:

https://drive.google.com/file/d/1FxzBRB_CBcT-f32W9Pz9DyhYjYJCrdUM/view

Note: To load a .csv le in Python, you can use the csv read() function
from Pandas library.
The epidemiological situation regarding the COVID-19 outbreak is continu-
ously evolving. Each of the rows represents a single individual case and ID. A
description of the fields in the database is shown in this paper: Epidemiological
data from the COVID-19 outbreak, real-time case information.
Goal
The goal of this project is to process this dataset using artificial intelligence
methods in order to help the community to better understand the spread of the
COVID-19 infection.
The project contains the following 4 parts:

Goal
The goal of this project is to process this dataset using articial intelligence
methods in order to help the community to better understand the spread of the
COVID-19 infection.

3. Machine Learning
In this part, we use a machine learning method in order to predict the outcome:
patients outcome as either 'died' or 'discharged' from hospital. You can use the
K-Nearest Neighbours (K-NN) or Bayes Classification.
1. The obtained results should be validated using some external indexes as
prediction error (Confusion matrix and Accuracy) or others as Recall, F-
Measure, etc. The obtained results should be analyzed in the report and
provide a solution to ameliorate the results.

2. Use the Regression to predict the age of persons based on other variables.
You have the choice on these explanatory variables? How you choose these
variables? Compute the quality of the prediction using MSE error (Mean
Squared Error).

Apply a clustering method (K-means) on the dataset to segment the persons into difrerent clusters. Use the Silhouette index to find out the best number of clusters. Plot the results using scatter to visually analyze the clustering structure.