#!/usr/bin/python
# vim: set fileencoding=utf-8 :

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

import datetime
import re
import requests as req
import locale
import os.path
import shutil

locale.setlocale(locale.LC_ALL, 'de_DE.UTF-8')

site_folder = 'site/'
data_folder = 'data/'

einwohner_deutschland = 83190556
herd_immunity = 0.7

today = datetime.date.today()
print_today = today.isoformat()

filename_now = datetime.datetime.now().strftime("%Y%m%d%H%M%S")

# DIN A4 Plots
plt.rcParams["figure.figsize"] = [11.69, 8.27]


# Download

data_filename = '{}/{}_Impfquotenmonitoring.xlsx'.format(data_folder, filename_now)

r = req.get('https://www.rki.de/DE/Content/InfAZ/N/Neuartiges_Coronavirus/Daten/Impfquotenmonitoring.xlsx?__blob=publicationFile')

with open(data_filename, 'wb') as outfile:
	outfile.write(r.content)

#data_filename = 'data/20210118151908_Impfquotenmonitoring.xlsx'

rki_file = pd.read_excel(data_filename, sheet_name=None, engine='openpyxl')

raw_data = rki_file['Impfungen_proTag']

impfungen = raw_data[:-1].dropna(subset=['Datum'])#.fillna(0)

dates = impfungen['Datum']

start_of_reporting_date = dates.iloc[0].date()

def calculate_vaccination_data(data):
	cumulative = np.cumsum(data)

	total = int(np.sum(data))
	total_percentage = float(total) / einwohner_deutschland * 100

	mean_all_time = np.mean(data)
	mean_seven_days = np.mean(data[-7:])

	to_be_vaccinated = einwohner_deutschland - total

	last_date = dates.iloc[-1].date()
	start_of_vaccination_date = dates[data.first_valid_index()].date()
	days_since_start_of_vaccination = (last_date - start_of_vaccination_date).days
	days_since_start_of_reporting = (last_date - start_of_reporting_date).days

	def extrapolate(rate, to_be_vaccinated):
		days_extrapolated = int(np.ceil(to_be_vaccinated / rate))
		extrapolated_dates = np.array([dates[0] + datetime.timedelta(days=i) for i in range(days_extrapolated)])

		date_done = extrapolated_dates[-1]
		date_herd_immunity = extrapolated_dates[int(np.ceil(days_extrapolated * herd_immunity))]

		extrapolated_vaccinations = total + rate * range(-days_since_start_of_reporting, days_extrapolated - days_since_start_of_reporting)

		return {
			'rate': rate,
			'rate_int': int(np.round(rate)),
			'days_extrapolated': days_extrapolated,
			'dates': extrapolated_dates,
			'date_done': date_done,
			'date_done_str': date_done.strftime('%d. %B %Y'),
			'date_herd_immunity': date_herd_immunity,
			'date_herd_immunity_str': date_herd_immunity.strftime('%d. %B %Y'),
			'extrapolated_vaccinations': extrapolated_vaccinations
		}


	extrapolation_mean_all_time = extrapolate(mean_all_time, to_be_vaccinated)
	extrapolation_last_rate = extrapolate(data.iloc[-1], to_be_vaccinated)
	extrapolation_mean_seven_days = extrapolate(mean_seven_days, to_be_vaccinated)

	mean_vaccination_rates_daily  = np.round(cumulative / range(1, len(cumulative) + 1))

	return {
		'daily': data,
		'cumulative': cumulative,
		'total': total,
		'total_percentage': total_percentage,
		'to_be_vaccinated': to_be_vaccinated,
		'last_date': last_date,
		'last_date_str': last_date.strftime('%d. %B %Y'),
		'days_since_start': days_since_start_of_vaccination + 1, # Shift from zero to one-based-index
		'start_of_vaccination_date': start_of_vaccination_date,
		'start_of_vaccination_date_str': start_of_vaccination_date.strftime('%d. %B %Y'),
		'extrapolation_mean_all_time': extrapolation_mean_all_time,
		'extrapolation_last_rate': extrapolation_last_rate,
		'extrapolation_mean_seven_days': extrapolation_mean_seven_days,
		'mean_vaccination_rates_daily': mean_vaccination_rates_daily
	}


data_first_vaccination = calculate_vaccination_data(impfungen['Erstimpfung'])
data_second_vaccination = calculate_vaccination_data(impfungen['Zweitimpfung'])

# Stand aus Daten auslesen
#stand = dates.iloc[-1]
#print_stand = stand.isoformat()

# Stand aus offiziellen Angaben auslesen
stand = rki_file['Erläuterung'].iloc[1][0]

stand_regex = re.compile('^Datenstand: (\d\d.\d\d.\d\d\d\d, \d\d:\d\d) Uhr$')
m = stand_regex.match(stand)
stand_date = datetime.datetime.strptime(m.groups()[0], '%d.%m.%Y, %H:%M')
print_stand = stand_date.isoformat()

filename_stand = stand_date.strftime("%Y%m%d%H%M%S")


'''

# Infos der einzelnen Länder
details_sheet_name = (set(rki_file.keys()) - {'Erläuterung', 'Impfungen_proTag'}).pop()

details_sheet = rki_file[details_sheet_name]

regionalcodes = details_sheet['RS'].iloc[0:17]
land_names = details_sheet['Bundesland'].iloc[0:17]

total_vaccinations_by_land = details_sheet['Impfungen kumulativ'].iloc[0:17]
vaccination_per_mille_by_land = details_sheet['Impfungen pro 1.000 Einwohner'].iloc[0:17]

vaccination_reason_age_by_land = details_sheet['Indikation nach Alter*'].iloc[0:17]
vaccination_reason_job_by_land = details_sheet['Berufliche Indikation*'].iloc[0:17]
vaccination_reason_medical_by_land = details_sheet['Medizinische Indikation*'].iloc[0:17]
vaccination_reason_oldhome_by_land = details_sheet['Pflegeheim-bewohnerIn*'].iloc[0:17]

details_per_land = {}
details_per_land_formatted = {}

# Regionalcodes der Länder zu Abkürzung und Name (Plus gesamt)
laendernamen = [
	('SH', 'Schleswig-Holstein'),
	('HH', 'Hamburg'),
	('NI', 'Niedersachsen'),
	('HB', 'Bremen'),
	('NW', 'Nordrhein-Westfalen'),
	('HE', 'Hessen'),
	('RP', 'Rheinland-Pfalz'),
	('BW', 'Baden-Württemberg'),
	('BY', 'Bayern'),
	('SL', 'Saarland'),
	('BE', 'Berlin'),
	('BB', 'Brandenburg'),
	('MV', 'Mecklenburg-Vorpommern'),
	('SN', 'Sachsen'),
	('ST', 'Sachsen-Anhalt'),
	('TH', 'Thüringen'),
	('𝚺', 'Gesamt')
]

def row_to_details(i):
	regionalcode = regionalcodes[i] if i != 16 else 16

	print(laendernamen[regionalcode])

	shortname, name = laendernamen[regionalcode]

	return {
		'name': name,
		'shortname': shortname,
		'total_vaccinations': int(total_vaccinations_by_land[i]),
		'total_vaccinations_percentage': vaccination_per_mille_by_land[i] / 10,
		'vaccination_reason_age': int(vaccination_reason_age_by_land[i]),
		'vaccination_reason_age_percentage': np.round(vaccination_reason_age_by_land[i] / total_vaccinations_by_land[i] * 100),
		'vaccination_reason_job': int(vaccination_reason_job_by_land[i]),
		'vaccination_reason_job_percentage': np.round(vaccination_reason_job_by_land[i] / total_vaccinations_by_land[i] * 100),
		'vaccination_reason_medical': int(vaccination_reason_medical_by_land[i]),
		'vaccination_reason_medical_percentage': np.round(vaccination_reason_medical_by_land[i] / total_vaccinations_by_land[i] * 100),
		'vaccination_reason_oldhome': int(vaccination_reason_oldhome_by_land[i]),
		'vaccination_reason_oldhome_percentage': np.round(vaccination_reason_oldhome_by_land[i] / total_vaccinations_by_land[i] * 100),
	}

def row_to_details_formatted(i):
	regionalcode = regionalcodes[i] if i != 16 else 16

	print(laendernamen[regionalcode])

	shortname, name = laendernamen[regionalcode]

	return {
		'name': name,
		'shortname': shortname,
		'total_vaccinations': '{:n}'.format(int(total_vaccinations_by_land[i])).replace('.', ' '),
		'total_vaccinations_percentage': '{:.3n}'.format(np.round(vaccination_per_mille_by_land[i] / 10, 2)),
		'vaccination_reason_age': '{:n}'.format(int(vaccination_reason_age_by_land[i])).replace('.', ' '),
		'vaccination_reason_age_percentage': '{:n}'.format(np.round(vaccination_reason_age_by_land[i] / total_vaccinations_by_land[i] * 100)),
		'vaccination_reason_job': '{:n}'.format(int(vaccination_reason_job_by_land[i])).replace('.', ' '),
		'vaccination_reason_job_percentage': '{:n}'.format(np.round(vaccination_reason_job_by_land[i] / total_vaccinations_by_land[i] * 100)),
		'vaccination_reason_medical': '{:n}'.format(int(vaccination_reason_medical_by_land[i])).replace('.', ' '),
		'vaccination_reason_medical_percentage': '{:n}'.format(np.round(vaccination_reason_medical_by_land[i] / total_vaccinations_by_land[i] * 100)),
		'vaccination_reason_oldhome': '{:n}'.format(int(vaccination_reason_oldhome_by_land[i])).replace('.', ' '),
		'vaccination_reason_oldhome_percentage': '{:n}'.format(np.round(vaccination_reason_oldhome_by_land[i] / total_vaccinations_by_land[i] * 100))
	}


for i in range(len(land_names) - 1):

	details_per_land[land_names[i]] = row_to_details(i)
	details_per_land_formatted[land_names[i]] = row_to_details_formatted(i)

details_total = row_to_details(16)
details_total_formatted = row_to_details_formatted(16)

'''






archive_folder = site_folder + 'archive/' + filename_stand

if os.path.isdir(archive_folder):
	print('Archive folder {} already exists'.format(archive_folder))
else:
	os.mkdir(archive_folder)




def plot_extrapolation_portion(percentage):

	print_percentage = int(percentage * 100)
	archive_plot_filename = '{}/extrapolated_to_{}_percent'.format(archive_folder, print_percentage)
	latest_plot_filename = '{}/extrapolated_to_{}_percent'.format(site_folder, print_percentage)

	if os.path.isfile(archive_plot_filename + '.pdf'):
		print('Plot {} already exists'.format(archive_plot_filename))
		return

	fig, ax = plt.subplots(1)


	plt.title(
		'Tägliche Impfrate (Erst- und Zweitimpfung), kumulierte Impfungen und lineare Extrapolation bis {:n} % der Bevölkerung Deutschlands\n'
		'Datenquelle: RKI, Stand: {}. Erstellung: {}, Ersteller: Benedikt Bastin, Lizenz: CC BY-SA 4.0\n'
		'Erstimpfungen: {:n} ({:n} %), Durchschnittliche Impfrate: {:n} Impfungen/Tag (läuft seit {:n} Tagen)\n'
		'Zweitimpfungen: {:n} ({:n} %), Durchschnittliche Impfrate: {:n} Impfungen/Tag (läuft seit {:n} Tagen)'.format(
			print_percentage,
			print_stand, print_today,
			data_first_vaccination['total'], np.round(data_first_vaccination['total_percentage'], 2), data_first_vaccination['extrapolation_mean_all_time']['rate'], data_first_vaccination['days_since_start'],
			data_second_vaccination['total'], np.round(data_second_vaccination['total_percentage'], 2), data_second_vaccination['extrapolation_mean_all_time']['rate'], data_second_vaccination['days_since_start']
		)
	)

	ax2 = ax.twinx()

	ax.bar(dates, data_first_vaccination['daily'], label='Tägliche Erstimpfungen', color='blue')
	ax.bar(dates, data_second_vaccination['daily'], label='Tägliche Zweitimpfungen', color='lightblue')

	ax.plot(dates, data_first_vaccination['mean_vaccination_rates_daily'], color='violet', label='Durchschnittliche Erstimpfrate\nbis zu diesem Tag (inkl.)')
	ax.plot(dates, data_second_vaccination['mean_vaccination_rates_daily'], color='magenta', label='Durchschnittliche Zweitimpfrate\nbis zu diesem Tag (inkl.)')

	ax2.set_ylim([0, einwohner_deutschland * percentage])
	ax2.set_xlim(xmax=dates[0] + datetime.timedelta(days=percentage * data_first_vaccination['extrapolation_mean_all_time']['days_extrapolated']))
	ax2.grid(True)

	ax2.plot(dates, data_first_vaccination['cumulative'], color='red', label='Kumulierte Erstimpfungen')
	ax2.plot(dates, data_second_vaccination['cumulative'], color='indianred', label='Kumulierte Zweitimpfungen')

	ax2.plot(data_first_vaccination['extrapolation_mean_all_time']['dates'], data_first_vaccination['extrapolation_mean_all_time']['extrapolated_vaccinations'], color='orange', label='Extrap. kumulierte Erstimpfungen (Ø gesamt)\n{:n} Impfungen/Tag'.format(data_first_vaccination['extrapolation_mean_all_time']['rate_int']))
	ax2.plot(data_first_vaccination['extrapolation_mean_seven_days']['dates'], data_first_vaccination['extrapolation_mean_seven_days']['extrapolated_vaccinations'], color='goldenrod', label='Extrap. kumulierte Erstimpfungen (Ø 7 Tage)\n{:n} Impfungen/Tag'.format(data_first_vaccination['extrapolation_mean_seven_days']['rate_int']))
	ax2.plot()

	ax2.plot(data_second_vaccination['extrapolation_mean_all_time']['dates'], data_second_vaccination['extrapolation_mean_all_time']['extrapolated_vaccinations'], color='orange', label='Extrap. kumulierte Zweitimpfungen (Ø gesamt)\n{:n} Impfungen/Tag'.format(data_second_vaccination['extrapolation_mean_all_time']['rate_int']))
	ax2.plot(data_second_vaccination['extrapolation_mean_seven_days']['dates'], data_second_vaccination['extrapolation_mean_seven_days']['extrapolated_vaccinations'], color='goldenrod', label='Extrap. kumulierte Zweitimpfungen (Ø 7 Tage)\n{:n} Impfungen/Tag'.format(data_second_vaccination['extrapolation_mean_seven_days']['rate_int']))
	#ax2.plot()

	ax.legend(loc='upper left')
	ax.get_yaxis().get_major_formatter().set_scientific(False)

	ax.set_xlabel('Datum')
	ax.set_ylabel('Tägliche Impfungen')

	ax2.legend(loc='lower right')
	ax2.get_yaxis().get_major_formatter().set_scientific(False)

	# Estimated percentage for herd immunity
	#ax2.axline((0, einwohner_deutschland * 0.7), slope=0, color='green')

	ax2.set_ylabel('Kumulierte Impfungen')

	plt.savefig(archive_plot_filename + '.pdf')
	plt.savefig(archive_plot_filename + '.png')
	plt.savefig(latest_plot_filename + '.pdf')
	plt.savefig(latest_plot_filename + '.png')
	plt.close()

	print('Created plot {} as pdf and png'.format(archive_plot_filename))


plot_extrapolation_portion(0.1)
#plot_extrapolation_portion(0.7)
plot_extrapolation_portion(1.0)



def plot_vaccination_bar_graph_total_time():

	archive_plot_filename = '{}/vaccination_bar_graph_total_time'.format(archive_folder)
	latest_plot_filename = '{}/vaccination_bar_graph_total_time'.format(site_folder)

	if os.path.isfile(archive_plot_filename + '.pdf'):
		print('Plot {} already exists'.format(archive_plot_filename))
		return

	fig, ax = plt.subplots(1)


	plt.title(
		'Tägliche Impfrate (Erst- und Zweitimpfung)\n'
			'Datenquelle: RKI, Stand: {}. Erstellung: {}, Ersteller: Benedikt Bastin, Lizenz: CC BY-SA 4.0\n'.format(
			print_stand, print_today
		)
	)

	ax.grid()

	ax.bar(dates, data_first_vaccination['daily'], label='Tägliche Erstimpfungen', color='blue')
	ax.bar(dates, data_second_vaccination['daily'], label='Tägliche Zweitimpfungen', color='lightblue', bottom=data_first_vaccination['daily'])

	ax.set_ylim([0, np.max(data_first_vaccination['daily']) + np.max(data_second_vaccination['daily'])])

	ax.legend(loc='upper left')
	ax.get_yaxis().get_major_formatter().set_scientific(False)

	ax.set_xlabel('Datum')
	ax.set_ylabel('Tägliche Impfungen')


	plt.savefig(archive_plot_filename + '.pdf')
	plt.savefig(archive_plot_filename + '.png')
	plt.savefig(latest_plot_filename + '.pdf')
	plt.savefig(latest_plot_filename + '.png')
	plt.close()

	print('Created plot {} as pdf and png'.format(archive_plot_filename))

plot_vaccination_bar_graph_total_time()

def render_dashboard():
	dashboard_filename = 'site/index.xhtml'
	dashboard_archive_filename = 'site/archive/{}/index.xhtml'.format(filename_stand)
	stylesheet_filename = 'site/rki-dashboard.css'
	stylesheet_archive_filename = 'site/archive/{}/rki-dashboard.css'.format(filename_stand)

	if os.path.isfile(dashboard_archive_filename):
		print('Dashboard {} already exists'.format(dashboard_archive_filename))
		return

	from jinja2 import Template, Environment, FileSystemLoader, select_autoescape
	env = Environment(
		loader=FileSystemLoader('./'),
		autoescape=select_autoescape(['html', 'xml', 'xhtml'])
	)

	german_text_date_format = '%d. %B %Y'
	df = german_text_date_format

	german_text_datetime_format = '%d. %B %Y, %H:%M:%S Uhr'
	dtf = german_text_datetime_format

	latest_dashboard_filename = site_folder + 'index.xhtml'
	archive_dashboard_filename = archive_folder

	template = env.get_template('dashboard_template.xhtml')
	template.stream(
		stand = stand_date.strftime(dtf),
		filename_stand = filename_stand,
		einwohner_deutschland = '{:n}'.format(einwohner_deutschland).replace('.', ' '),
		herd_immunity = '{:n}'.format(int(herd_immunity * 100)),
		data_first_vaccination = data_first_vaccination,
		data_second_vaccination = data_second_vaccination,
		#details_per_land = dict(sorted(details_per_land_formatted.items(), key=lambda item: item[0])),
		#details_total = details_total_formatted
	).dump('site/index.xhtml')

	shutil.copyfile(dashboard_filename, dashboard_archive_filename)
	shutil.copyfile(stylesheet_filename, stylesheet_archive_filename)

	print('Created dashboard')

render_dashboard()