Scrapes Vaccines Data for Michigan and Plots It

scrapevaccine.py

from selenium import webdriver
import numpy as np
import matplotlib.pyplot as plt
import scipy.stats as stats
np.set_printoptions(suppress=True)

def moving_avg(x, n):
    cumsum = np.cumsum(np.insert(x, 0, 0)) 
    return (cumsum[n:] - cumsum[:-n]) / float(n)
	
def polyfit(x, y, degree):
    results = {}
    coeffs = np.polyfit(x, y, degree)
    p = np.poly1d(coeffs)
    #calculate r-squared
    yhat = p(x)
    ybar = np.sum(y)/len(y)
    ssreg = np.sum((yhat-ybar)**2)
    sstot = np.sum((y - ybar)**2)
    results['r_squared'] = ssreg / sstot

    return results

def rundata(titleappend, url):
	driver = webdriver.Chrome()
	driver.get(url)
	acd = driver.execute_script("return acd_data")
	bcd = driver.execute_script("return bcd_data")
	driver.close()
	acd_arr = np.array([])
	bcd_arr = np.array([])
	for value in acd:
		if value["cv"] is None:
			acd_arr = np.append(acd_arr,int(0))
		else:
			acd_arr = np.append(acd_arr,int(value["cv"]))
	for value in bcd:
		if value["cv"] is None:
			bcd_arr = np.append(bcd_arr,int(0))
		else:
			bcd_arr = np.append(bcd_arr,int(value["cv"]))
	combo_vac = acd_arr+bcd_arr

	vac_increase = np.array([])

	prevval = combo_vac[0]
	for value in combo_vac:
		vac_increase = np.append(vac_increase,value-prevval)
		prevval = value
		
	vac_ma = moving_avg(vac_increase, 7)

	fig, axs = plt.subplots(1,3, figsize=(19,5))
	fig.suptitle(titleappend + ' Covid Data')

	x = np.arange(0,combo_vac.size)
	y = combo_vac
	axs[0].set_title("Vaccinations Since December 12th")
	axs[0].plot(x, y, color = "red", linewidth = 3)
	axs[0].set(ylabel='Total Vaccinations', xlabel='Days Since the 12th')
	model = np.poly1d(np.polyfit(x,y,1))
	model2 = np.poly1d(np.polyfit(x,y,2))
	polyline = np.linspace(0,combo_vac.size,50)
	mod1 = str(round(model[1],2))+'x + '+str(round(model[0],2))
	mod2 = str(round(model2[2],2))+'x^2 + '+str(round(model2[1],2))+'x + '+str(round(model2[0],2))
	axs[0].plot(polyline, model(polyline), dashes=[6, 2], label='Linear\n'+'y = '+mod1+'\nr^2 = ' + str(round(polyfit(x,y,1)['r_squared'],3)), color="green")
	axs[0].plot(polyline, model2(polyline), dashes=[2, 2, 10, 2], label='Quadratic\n'+'y = '+mod2+'\nr^2 = ' + str(round(polyfit(x,y,2)['r_squared'],3)), color="blue")
	axs[0].legend()
	
	x = np.arange(0,30)
	y = combo_vac[-30:]
	axs[1].set_title("Vaccinations Last 30 Days")
	axs[1].plot(x, y, color = "red", linewidth = 3)
	axs[1].set(ylabel='Total Vaccinations', xlabel='Days')
	model = np.poly1d(np.polyfit(x,y,1))
	model2 = np.poly1d(np.polyfit(x,y,2))
	polyline = np.linspace(0,30,50)
	mod1 = str(round(model[1],2))+'x + '+str(round(model[0],2))
	mod2 = str(round(model2[2],2))+'x^2 + '+str(round(model2[1],2))+'x + '+str(round(model2[0],2))
	axs[1].plot(polyline, model(polyline), dashes=[6, 2], label='Linear\n'+'y = '+mod1+'\nr^2 = ' + str(round(polyfit(x,y,1)['r_squared'],3)), color="green")
	axs[1].plot(polyline, model2(polyline), dashes=[2, 2, 10, 2], label='Quadratic\n' +'y = '+mod2+'\nr^2 = ' + str(round(polyfit(x,y,2)['r_squared'],3)), color="blue")
	axs[1].legend()

	x = np.arange(0,vac_ma.size)
	y = vac_ma
	axs[2].set_title("Moving Average Vaccinations Per Day (7 day range)")
	axs[2].plot(x, y, color = "red", linewidth = 3)
	axs[2].set(ylabel='Average Vaccinations', xlabel='Time')
	model = np.poly1d(np.polyfit(x,y,1))
	polyline = np.linspace(0,vac_ma.size,50)
	mod1 = str(round(model[1],2))+'x + '+str(round(model[0],2))
	axs[2].plot(polyline, model(polyline), dashes=[6, 2], label='Linear\n'+'y = '+mod1+' \nr^2 = ' + str(round(polyfit(x,y,1)['r_squared'],3)), color="green")
	axs[2].legend()
	
	fig.canvas.set_window_title(titleappend + ' Covid Data')

	plt.show()
	
#rundata('Oakland County',"https://data.lansingstatejournal.com/covid-19-vaccine-tracker/michigan/oakland-county-mi/26125/")
#rundata('Macomb County',"https://data.lansingstatejournal.com/covid-19-vaccine-tracker/michigan/macomb-county-mi/26099/")
rundata('Michigan',"https://data.lansingstatejournal.com/covid-19-vaccine-tracker/michigan/26/")