ConfirmedCase.py

xdata = np.array(list(abs(fmodel.day_count)))
ydata = np.array(list(abs(fmodel.Confirmed)))
cof,cov = curve_fit(sigmoid, xdata, ydata, method='trf',bounds=([0.,0., 0.],[indiapopulation,1, 100.]))
#‘trf’ : Trust Region Reflective algorithm, particularly suitable for large sparse problems with bounds. Generally robust method.

x = np.linspace(-1, fmodel.day_count.max()+40, 40)
y = sigmoid(x,cof[0],cof[1],cof[2])


fig = go.Figure()
fig.add_trace(go.Scatter(x=x, y=y,
                    mode="lines+text",
                    name='Confirmed Cases Approx',
                    marker_color='Orange',
                        ))
    
fig.add_trace(go.Scatter(x=xdata, y=ydata,
                    mode="markers",
                    name='Confirm Cases',
                    marker_color='Red',
                    marker_line_width=2, marker_size=10
                        ))
fig
fig.update_layout(
title='Daily Confirmed Cases in India is approx '+ str(int(cof[0])) +', Confirm case curve started flatten from day ' + str(int(cof[2])) +" and will flatten by day "+str(round(int(cof[2])*2.5)),
        template='gridon',
 font=dict(
        family="Courier New, monospace",
        size=7,
        color="blue"
    ))
fig.show()

#Total Confirmed Case
print(round(fmodel.Confirmed.sum()+((fmodel.day_count.max()+40-fmodel.day_count.max())*y[21:40].mean())))