Coronavirus prediction using Machine Learning | A COVID-19 project using Machine Learning

Question

With the help of technology, we can predict how many cases can increase in the coming days. We can create web applications with the help of which people can predict how much they have got the virus. You can see a good visualization of how many cases are in which area. And many more , thus how technology is helping to cure coronavirus(COVID-19).

---

Develop Projects Like This

Answer 1

Coronavirus

Coronaviruses are a group of related RNA viruses that cause diseases in mammals and birds. In humans, these viruses cause respiratory tract infections that can range from mild to lethal. Mild illnesses include some cases of the common cold (which is caused also by certain other viruses, predominantly rhinoviruses), while more lethal varieties can cause SARS, MERS, and COVID-19.This virus originated from Wuhan city of China.

Technology

1. With the help of technology, we can predict how many cases can increase in the coming days.

2. We can create web applications with the help of which people can predict how much they have got the virus.

3. You can see a good visualization of how many cases are in which area. And many more , thus how technology is helping to cure coronavirus.

Practical Implementation

Importing Libraries

#importing required libraries  import numpy as np import pandas as pd import matplotlib.pyplot as plt import matplotlib.colors as mcolors import random  import math import time from sklearn.model_selection import RandomizedSearchCV , train_test_split import datetime import operator  plt.style.use("seaborn") %matplotlib inline

Note

Here we just imported some libraries , pandas- for tabular data manipulation , Numpy to handle array type structure and calculative part in python and matplotlib to handle graphs and visualization part of data.

Reading Data-Set 

Note 

We have three different datasets here. For confirmed cases, for recovered cases and for total deaths. (The data consist worldwide situation).

You can download datasets from keggle (click here).This datasets is not latest data it is just for learning purpose.Here you will get a zip file by clicking on the download and you can extract required data form the zip file.

#Reading coronavirus confirmed cases across the world  confirmed_cases=pd.read_csv("time_series_covid_19_confirmed.csv") confirmed_cases.head()

Output

Note

1. It is just small sanpshot of output if you want to see fi 

#Reading coronavirus deaths reported across the world  deaths_reported=pd.read_csv("time_series_covid_19_deaths.csv") deaths_reported.head()

Output

Note 

#Reading coronavirus recovered cases across the world  recovered_cases=pd.read_csv("time_series_covid_19_recovered.csv") recovered_cases.head()

Output 

cols= confirmed_cases.keys() cols

Output

Note

confirmed= confirmed_cases.loc[:, cols[4]:cols[-1]] confirmed

 Note

recovered= recovered_cases.loc[:, cols[4]:cols[-1]] recovered

Note

deaths= deaths_reported.loc[:, cols[4]:cols[-1]] deaths

Note

dates= confirmed.keys() dates world_cases=[] total_deaths=[] mortality_rate=[] total_recovered=[] for i in dates:     confirmed_sum=confirmed[i].sum()     print(confirmed[i])     death_sum=deaths[i].sum()     recovered_sum=recovered[i].sum()     world_cases.append(confirmed_sum)     total_deaths.append(death_sum)     mortality_rate.append(death_sum/confirmed_sum)     total_recovered.append(recovered_sum)

Note

print(confirmed_sum) print(death_sum) print(recovered_sum) print(world_cases) #print(mortality_rate)

Note

---

Develop Projects Like This