COVID-19 Predictor - Polynomial Regression

covidPredictor.py

# COVID-19 cases predictor (polynomial regression for non-linear prediction)
# Data Source: https://ourworldindata.org/coronavirus-source-data

# Data Example
# id,cases
# 1,1
# 2,4
# 3,6
# 4,8
# 5,10
# 6,12
# 7,14
# 8,16
# 9,18
# 10,20

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import PolynomialFeatures
from sklearn import linear_model

### Load Data ###
data = pd.read_csv('covid_cases.csv', sep = ',')
data = data[['id', 'cases']]
num_rows = len(data.index)
print(f'Number of Rows: {num_rows}')
print('-' * 30);print(' Head ');print('-' * 30)
print(data.head())

### Prepare Data ###
print('-' * 30);print(' Prepare Data ');print('-' * 30)
x = np.array(data['id']).reshape(-1, 1)
y = np.array(data['cases']).reshape(-1, 1)
plt.plot(y, '-m')
#plt.show()

polyFeature = PolynomialFeatures(degree=3) # change degree to improve results
x = polyFeature.fit_transform(x)
#print(x)

### Training Data ###
print('-' * 30);print(' Training Data ');print('-' * 30)
model = linear_model.LinearRegression()
model.fit(x, y)
accuracy = model.score(x, y)
print(f'Accuracy: {round(accuracy * 100, 3)} %')
y0 = model.predict(x)

### Prediction ###
days = 10
print('-' * 30);print(' Prediction ');print('-' * 30)
print(f'Prediction - Cases after {days} days: ', end='')
print(round(int(model.predict(polyFeature.fit_transform([[ num_rows + days ]]))), 2), 'cases')

x1 = np.array(list(range(1, num_rows + days))).reshape(-1, 1)
y1 = model.predict(polyFeature.fit_transform(x1))
plt.plot(y1, '--r')
plt.plot(y0, '--b')
plt.show()