
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from datetime import date,datetime,timedelta
from matplotlib.ticker import ScalarFormatter
import numpy as np
from matplotlib.colors import LinearSegmentedColormap, to_rgba_array


gemeentes = pd.read_csv('https://data.rivm.nl/covid-19/COVID-19_aantallen_gemeente_cumulatief.csv', parse_dates=['Date_of_report', 'Date_of_publication'], sep=';').drop(columns=['Hospital_admission', 'Deceased', 'Version'])
gemeentes.loc[gemeentes.Municipality_code.isnull(), 'Municipality_code'] = 'Onbekend'
gemeentes.loc[gemeentes.Province.isnull(), 'Province'] = 'Onbekend'
gemeentes.loc[gemeentes.Province == 'Friesland', 'Province'] = 'Fryslân'
gemeentes = gemeentes.fillna(0)
gemeentes.Date_of_report = gemeentes.Date_of_publication
gemeentes


totalPositiveTestRatio = pd.read_csv('https://raw.githubusercontent.com/mzelst/covid-19/master/data-dashboards/percentage-positive-daily-national.csv', parse_dates=['date'])
totalPositiveTestRatio['infected_percentage_7d'] =  totalPositiveTestRatio['values.infected_percentage'].rolling(7).mean()
totalPositiveTestRatio['total_7d'] =  totalPositiveTestRatio['values.tested_total'].rolling(7).mean()
totalPositiveTestRatio['positive_7d'] =  totalPositiveTestRatio['values.infected'].rolling(7).mean()
totalPositiveTestRatio


sewer_detail = pd.read_csv('https://data.rivm.nl/covid-19/COVID-19_rioolwaterdata.csv', parse_dates=['Date_measurement'], sep=';').drop(columns=['Date_of_report', 'Version', 'RWZI_AWZI_code'])
sewer_detail.rename(columns={'Date_measurement': 'Date', 'RWZI_AWZI_name':'Station'}, inplace=True)
dateOfStatsDetail = sewer_detail.Date.max()
sewer_detail


opnames_nice = pd.read_csv("https://github.com/mzelst/covid-19/raw/master/data-nice/age/leeftijdsverdeling_datum_Klinisch_IC_long.csv", parse_dates=["Datum"])
opnames_nice = opnames_nice[opnames_nice.Type == "Klinisch"].sort_values("Datum")
opnames_nice.drop(columns=['Type'], inplace=True)
opnames_nice.rename(columns={'Datum': 'Date'}, inplace=True)
opnames_nice


#display(pd.read_csv("https://raw.githubusercontent.com/mzelst/covid-19/master/data/lcps_by_day.csv", parse_dates=["date"]))
opnames_lcps = pd.read_csv("https://raw.githubusercontent.com/mzelst/covid-19/master/data/lcps_by_day.csv", parse_dates=["date"])[["date", "kliniek_bezetting_covid", "IC_bezetting_covid"]].sort_values("date")
opnames_lcps


from datetime import datetime
totals = gemeentes.groupby(by=['Date_of_report']).sum().diff().reset_index()
totals['rolling'] = totals.Total_reported.rolling(window=7).mean()
#totals['rolling_100k'] = totals['rolling'] * (100000 / 17454856) 
totals['rolling14'] = totals.Total_reported.rolling(window=14).mean()
#totals['rolling14_100k'] = totals.rolling14 *  (100000 / 17454856)
totals['Growth'] = totals.Total_reported.rolling(window=14).mean().pct_change().rolling(window = 14).mean() * 100
totals


perWeek = totals.copy().drop(columns=['Growth'])
perWeek['week'] = perWeek.Date_of_report.dt.isocalendar().week
perWeek['year'] = perWeek.Date_of_report.dt.isocalendar().year
weekTotals = perWeek.groupby(by=['year', 'week']).mean()
weekTotals.drop(columns=['rolling', 'rolling14'], inplace=True)
weekTotals.rename(columns={'Total_reported': 'WeekTotalReported', 'Hospital_admission': 'WeekHospitalAdmission', 'Deceased' : 'WeekDeceased'}, inplace=True)
perWeek = perWeek.set_index(['year','week']).join(weekTotals).reset_index()
perWeek['Reported_ratio'] = (perWeek.Total_reported / perWeek.WeekTotalReported)

dayOfWeek={0:'Maandag', 1:'Dinsdag', 2:'Woensdag', 3:'Donderdag', 4:'Vrijdag', 5:'Zaterdag', 6:'Zondag'}
perWeek['weekday'] = perWeek.Date_of_report.dt.dayofweek.map(dayOfWeek)
perWeek['month'] = perWeek.Date_of_report.dt.month
perWeek['date'] = pd.to_datetime(perWeek.year.apply(str) + '-W' + perWeek.week.apply(str) + '-7', format='%G-W%V-%u')
display(perWeek)

dayToWeekAvg = totals.copy()
dayToWeekAvg['week'] = dayToWeekAvg.Date_of_report.dt.isocalendar().week
dayToWeekAvg['year'] = dayToWeekAvg.Date_of_report.dt.isocalendar().year
dayToWeekAvg['date'] = pd.to_datetime(dayToWeekAvg.year.apply(str) + '-W' + dayToWeekAvg.week.apply(str) + '-7', format='%G-W%V-%u')
dayToWeekAvg['RatioWeekAvg'] = dayToWeekAvg.Total_reported / dayToWeekAvg['rolling'].shift(1)
dayToWeekAvg['AboveAverage'] = dayToWeekAvg.RatioWeekAvg > 1
dayToWeekAvg['weekday'] = dayToWeekAvg.Date_of_report.dt.dayofweek.map(dayOfWeek)
display(dayToWeekAvg)


sewer_detail_mean = sewer_detail.copy().groupby(by=['Date']).mean().reset_index().rolling(on="Date", window=14).mean()
sewer_detail_mean['RNA_flow_per_100000_Growth_7d'] = sewer_detail_mean.RNA_flow_per_100000.pct_change().replace([np.inf, -np.inf], 0).fillna(0).rolling(window=14).mean() * 100
sewer_detail_mean = sewer_detail_mean.reset_index()
sewer_detail_mean


totalPositiveTestRatio['infected_percentage_14d_growth'] =  totalPositiveTestRatio['values.infected_percentage'].rolling(14).mean().pct_change().rolling(14).mean() * 100
totalPositiveTestRatio


opnames_nice7 = pd.melt(opnames_nice.set_index('Date').diff().reset_index(), id_vars='Date', var_name=['Age'], value_name='Opnames')
opnames_nice7 = opnames_nice7.groupby(by=["Date"]).sum().reset_index()
opnames_nice7 = opnames_nice7.rolling(on="Date", window=14).mean().reset_index()
opnames_nice7['Growth'] = opnames_nice7.Opnames.pct_change().rolling(window= 14).mean() * 100
opnames_nice7


opnames_lcps14 = opnames_lcps.fillna(0).rolling(on="date", window=14).mean()
opnames_lcps14['IC_growth'] = opnames_lcps14.IC_bezetting_covid.pct_change().rolling(window=14).mean() * 100
opnames_lcps14['Kliniek_growth'] = opnames_lcps14.kliniek_bezetting_covid.pct_change().rolling(window=14).mean() * 100
opnames_lcps14


sns.set_style("whitegrid")
sns.set_context("talk", font_scale=1, rc={"lines.linewidth": 3, "font.size":10,"axes.titlesize":24,"axes.labelsize":18})
sns.set_palette(sns.color_palette(['#CC6677', '#332288', '#DDCC77', '#117733', '#88CCEE', \
                    '#882255', '#44AA99', '#999933', '#AA4499', '#DDDDDD', \
                    '#000000']))

def discretemap(colormap, hexclrs):
    """
    Produce a colormap from a list of discrete colors without interpolation.
    """
    clrs = to_rgba_array(hexclrs)
    clrs = np.vstack([clrs[0], clrs, clrs[-1]])
    cdict = {}
    for ki, key in enumerate(('red','green','blue')):
        cdict[key] = [ (i/(len(clrs)-2.), clrs[i, ki], clrs[i+1, ki]) for i in range(len(clrs)-1) ]
    return LinearSegmentedColormap(colormap, cdict)

def __rainbow_WhBr():
    """
    Define colormap 'rainbow_WhBr'.
    """
    clrs = ['#E8ECFB', '#DDD8EF', '#D1C1E1', '#C3A8D1', '#B58FC2',
            '#A778B4', '#9B62A7', '#8C4E99', '#6F4C9B', '#6059A9',
            '#5568B8', '#4E79C5', '#4D8AC6', '#4E96BC', '#549EB3',
            '#59A5A9', '#60AB9E', '#69B190', '#77B77D', '#8CBC68',
            '#A6BE54', '#BEBC48', '#D1B541', '#DDAA3C', '#E49C39',
            '#E78C35', '#E67932', '#E4632D', '#DF4828', '#DA2222',
            '#B8221E', '#95211B', '#721E17', '#521A13']
    return LinearSegmentedColormap.from_list("Rainbo_WhBr", clrs)
    #self.cmap.set_bad('#666666')

def __iridescent():
    """
    Define colormap 'iridescent'.
    """
    clrs = ['#FEFBE9', '#FCF7D5', '#F5F3C1', '#EAF0B5', '#DDECBF',
            '#D0E7CA', '#C2E3D2', '#B5DDD8', '#A8D8DC', '#9BD2E1',
            '#8DCBE4', '#81C4E7', '#7BBCE7', '#7EB2E4', '#88A5DD',
            '#9398D2', '#9B8AC4', '#9D7DB2', '#9A709E', '#906388',
            '#805770', '#684957', '#46353A']
    return LinearSegmentedColormap.from_list("iridescent", clrs)
    #self.cmap.set_bad('#999999')

def __YlOrBr():
    """
    Define colormap 'YlOrBr'.
    """
    clrs = ['#FFFFE5', '#FFF7BC', '#FEE391', '#FEC44F', '#FB9A29',
            '#EC7014', '#CC4C02', '#993404', '#662506']
    return LinearSegmentedColormap.from_list('YlOrBr', clrs)
    #self.cmap.set_bad('#888888')

def __BuRd():
    """
    Define colormap 'BuRd'.
    """
    clrs = ['#2166AC', '#4393C3', '#92C5DE', '#D1E5F0', '#F7F7F7',
            '#FDDBC7', '#F4A582', '#D6604D', '#B2182B']
    return LinearSegmentedColormap.from_list('BuRd', clrs)

def __rainbow_discrete(self, lut=None):
    """
    Define colormap 'rainbow_discrete'.
    """
    clrs = ['#E8ECFB', '#D9CCE3', '#D1BBD7', '#CAACCB', '#BA8DB4',
            '#AE76A3', '#AA6F9E', '#994F88', '#882E72', '#1965B0',
            '#437DBF', '#5289C7', '#6195CF', '#7BAFDE', '#4EB265',
            '#90C987', '#CAE0AB', '#F7F056', '#F7CB45', '#F6C141',
            '#F4A736', '#F1932D', '#EE8026', '#E8601C', '#E65518',
            '#DC050C', '#A5170E', '#72190E', '#42150A']
    indexes = [[9], [9, 25], [9, 17, 25], [9, 14, 17, 25], [9, 13, 14, 17,
            25], [9, 13, 14, 16, 17, 25], [8, 9, 13, 14, 16, 17, 25], [8,
            9, 13, 14, 16, 17, 22, 25], [8, 9, 13, 14, 16, 17, 22, 25, 27],
            [8, 9, 13, 14, 16, 17, 20, 23, 25, 27], [8, 9, 11, 13, 14, 16,
            17, 20, 23, 25, 27], [2, 5, 8, 9, 11, 13, 14, 16, 17, 20, 23,
            25], [2, 5, 8, 9, 11, 13, 14, 15, 16, 17, 20, 23, 25], [2, 5,
            8, 9, 11, 13, 14, 15, 16, 17, 19, 21, 23, 25], [2, 5, 8, 9, 11,
            13, 14, 15, 16, 17, 19, 21, 23, 25, 27], [2, 4, 6, 8, 9, 11,
            13, 14, 15, 16, 17, 19, 21, 23, 25, 27], [2, 4, 6, 7, 8, 9, 11,
            13, 14, 15, 16, 17, 19, 21, 23, 25, 27], [2, 4, 6, 7, 8, 9, 11,
            13, 14, 15, 16, 17, 19, 21, 23, 25, 26, 27], [1, 3, 4, 6, 7, 8,
            9, 11, 13, 14, 15, 16, 17, 19, 21, 23, 25, 26, 27], [1, 3, 4,
            6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 19, 21, 23, 25, 26,
            27], [1, 3, 4, 6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 18, 20,
            22, 24, 25, 26, 27], [1, 3, 4, 6, 7, 8, 9, 10, 12, 13, 14, 15,
            16, 17, 18, 20, 22, 24, 25, 26, 27, 28], [0, 1, 3, 4, 6, 7, 8,
            9, 10, 12, 13, 14, 15, 16, 17, 18, 20, 22, 24, 25, 26, 27, 28]]
    if lut == None or lut < 1 or lut > 23:
        lut = 22
    self.cmap = discretemap(self.cname, [ clrs[i] for i in indexes[lut-1] ])
    if lut == 23:
        self.cmap.set_bad('#777777')
    else:
        self.cmap.set_bad('#FFFFFF')


def tuftefy(ax):
    """Remove spines and tick position markers to reduce ink."""
    # 
    ax.spines["top"].set_visible(False)
    ax.spines["right"].set_visible(False)
    ax.spines["left"].set_visible(False)
    ax.spines["bottom"].set_visible(True)
    ax.spines["bottom"].set_color('grey')

    ax.grid(color="w", alpha=0.5)
    ax.get_yaxis().grid(True)
    ax.get_xaxis().grid(False)

def fancy_titles(t1, t2, ax=None):
  if ax:
    ax.set_title(t1, loc='left', fontsize=18)
    ax.set_title(t2, loc='right', fontsize=13, color='grey')
  else:
    plt.title(t1, loc='left', fontsize=18)
    plt.title(t2, loc='right', fontsize=13, color='grey')


#sns.set_context("talk")
fig = plt.gcf()
fig.set_size_inches(15, 6)
e =sns.violinplot(x="weekday", linewidth=2, y="Reported_ratio", data=perWeek[perWeek.Date_of_report >= '2020-09-01'], order=["Maandag", "Dinsdag", "Woensdag", "Donderdag", "Vrijdag", "Zaterdag", "Zondag"], inner=None, color='#ccc', scale_hue=False, cut=0.5, bw=0.4)
e =sns.stripplot(x="weekday", y="Reported_ratio", data=perWeek[perWeek.Date_of_report >= '2020-09-01'],order=["Maandag", "Dinsdag", "Woensdag", "Donderdag", "Vrijdag", "Zaterdag", "Zondag"], color='black', alpha=0.5)
e.set(ylabel='Verhouding tov weekgemiddelde', title='Verhouding tussen positieve COVID-19 testen en de weekdag', xlabel='')
plt.title("bron: RIVM update " + (totals.Date_of_report.to_list()[-1]).strftime('%Y-%m-%d'), loc='right', fontsize=12, color='grey', y=0.01)
#tuftefy(e)
e.yaxis.grid(True)
sns.despine(bottom=True)


fig = plt.gcf()
fig.set_size_inches(15, 6)
e = sns.countplot(x="weekday", hue="AboveAverage", data=dayToWeekAvg[dayToWeekAvg.Date_of_report >= '2020-09-01'], order=["Maandag", "Dinsdag", "Woensdag", "Donderdag", "Vrijdag", "Zaterdag", "Zondag"])

e.set(ylabel='Aantal weken', title='Aantal keer dag boven week gemiddelde', xlabel='Weekdag')
plt.title("bron: RIVM update " + (totals.Date_of_report.to_list()[-1]).strftime('%Y-%m-%d'), loc='right', fontsize=12, color='grey', y=0.0)
e.yaxis.grid(True)
sns.despine(bottom=True)


fig = plt.gcf()
fig.set_size_inches(15, 6)
ax = sns.lineplot(x='date', y='Reported_ratio', hue='weekday', style='weekday', linewidth=2, hue_order=['Maandag', 'Dinsdag', 'Woensdag', 'Donderdag', 'Vrijdag', 'Zaterdag', 'Zondag'], data=perWeek[perWeek.Date_of_report >= '2021-01-01'])
ax.set_ylim(0.0,2)
plt.axhline(y=0.6, ls=':', c='.8', linewidth=1, zorder=1)
plt.axhline(y=0.8, ls=':', c='.8', linewidth=1, zorder=1)
plt.axhline(y=1.0, ls='-', c='.85', linewidth=1, zorder=1)
plt.axhline(y=1.2, ls=':', c='.8', linewidth=1, zorder=1)
plt.axhline(y=1.6, ls=':', c='.8', linewidth=1, zorder=1)
ax.xaxis.set_major_formatter(mdates.DateFormatter('%V'))
ax.xaxis.set_major_locator(mdates.WeekdayLocator(byweekday=mdates.SUNDAY, interval=3))
ax.set(ylabel='Verhouding tov weekgemiddelde', title='Verhouding tussen positieve COVID-19 testen en de weekdag', xlabel='Week')
plt.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.)
tuftefy(ax)


fig = plt.gcf()
fig.set_size_inches(15, 6)
ax = sns.lineplot(x='date', y='RatioWeekAvg', hue='weekday', style='weekday', linewidth=2, hue_order=['Maandag', 'Dinsdag', 'Woensdag', 'Donderdag', 'Vrijdag', 'Zaterdag', 'Zondag'], data=dayToWeekAvg[dayToWeekAvg.Date_of_report >= '2021-01-01'])
ax.set_ylim(0.3,2)
plt.axhline(y=0.8, ls=':', c='.8', linewidth=1, zorder=1)
plt.axhline(y=1.0, ls='-', c='.85', linewidth=1, zorder=1)
plt.axhline(y=1.2, ls=':', c='.8', linewidth=1, zorder=1)
ax.xaxis.set_major_formatter(mdates.DateFormatter('%V'))
ax.xaxis.set_major_locator(mdates.WeekdayLocator(byweekday=mdates.SUNDAY, interval=3))
ax.set(ylabel='Verhouding tov weekgemiddelde', title='Verhouding tussen positieve COVID-19 testen en de 7d gemiddelde', xlabel='Week')
plt.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.)
tuftefy(ax)


fig = plt.figure()
fig.set_size_inches(15, 10)

#ax = sns.lineplot(data=totalPositiveTestRatio[totalPositiveTestRatio.date >= '2020-08-01'], x='date', y='total_7d', color='#004488', label='Aantal testen')

ax = sns.lineplot(data=totalPositiveTestRatio, x='date', y='total_7d', color='#004488', label='Aantal testen')
plt.legend(bbox_to_anchor=(0.2, 1),borderaxespad=0)
ax2 = ax.twinx()
#sns.lineplot(data=totalPositiveTestRatio[totalPositiveTestRatio.date >= '2020-08-01'], x='date', y='positive_7d', color='#ddaa33', label='Aantal positief', ax = ax2)
sns.lineplot(data=totalPositiveTestRatio, x='date', y='positive_7d', color='#ddaa33', label='Aantal positief', ax = ax2)
plt.legend(bbox_to_anchor=(0.9, 1),borderaxespad=0)
#sns.lineplot(data=totals[totals.Date_of_report > '2020-06-01'], x='Date_of_report',y='rolling', color='red',  ax=ax2)
ax.set_ylabel("Aantal testen")
ax2.set_ylabel("Positieve testen")
ax.set_xlabel("")
ax.set_title('Voortschrijdend gemiddelde (7d) van aantal uitgevoerde en positieve testen', pad=30)
#ax.xaxis.set_major_formatter(mdates.DateFormatter('%V'))
ax.xaxis.set_major_formatter(mdates.ConciseDateFormatter(mdates.AutoDateLocator()))
#ax.xaxis.set_major_locator(mdates.WeekdayLocator(byweekday=mdates.SUNDAY, interval=2))
ax.set(ylim=(0, None))
ax2.set(ylim=(0, None))
#plt.axvline(date(2020,10,14), ls=":", c=".5")
#plt.axvline(date(2020,12,18), ls=":", c=".5")
#plt.axvline(date(2021,2,8), ls=":", c=".5")
#plt.axhline(0.0, ls="-", c=".8", zorder=1)
#g = g.map(plt.axvline, x=date(2020,10,14), ls=":", c=".5")
plt.title("bron: Dashboard data t/m " + (totalPositiveTestRatio.date.to_list()[-1]).strftime('%Y-%m-%d'), loc='right', fontsize=12, color='grey', y=0.0)


tuftefy(ax)
tuftefy(ax2)


fig = plt.figure()
fig.set_size_inches(15, 10)

ax = sns.lineplot(data=sewer_detail_mean, x='Date', y='RNA_flow_per_100000', color='#004488', label='Riooldeeltjes')
plt.legend(bbox_to_anchor=(0.2, 1),borderaxespad=0)
ax2 = ax.twinx()
#sns.lineplot(data=totalPositiveTestRatio[totalPositiveTestRatio.date >= '2020-08-01'], x='date', y='positive_7d', color='#ddaa33', label='Aantal positief', ax = ax2)
sns.lineplot(data=totalPositiveTestRatio, x='date', y='positive_7d', color='#ddaa33', label='Aantal positief', ax = ax2)
plt.legend(bbox_to_anchor=(0.9, 1),borderaxespad=0)
#sns.lineplot(data=totals[totals.Date_of_report > '2020-06-01'], x='Date_of_report',y='rolling', color='red',  ax=ax2)
ax.set_ylabel("Riooldeeltjes per 100.000 inwoners")
ax2.set_ylabel("Positieve testen")
ax.set_xlabel("")
ax.set_title('Voortschrijdend gemiddelde (7d) van positieve testen en riooldeeltjes', pad=30)
#ax.xaxis.set_major_formatter(mdates.DateFormatter('%V'))
ax.xaxis.set_major_formatter(mdates.ConciseDateFormatter(mdates.AutoDateLocator()))
#ax.xaxis.set_major_locator(mdates.WeekdayLocator(byweekday=mdates.SUNDAY, interval=2))
ax.set(ylim=(0, None))
ax2.set(ylim=(0, None))
#plt.axvline(date(2020,10,14), ls=":", c=".5")
#plt.axvline(date(2020,12,18), ls=":", c=".5")
#plt.axvline(date(2021,2,8), ls=":", c=".5")
#plt.axhline(0.0, ls="-", c=".8", zorder=1)
#g = g.map(plt.axvline, x=date(2020,10,14), ls=":", c=".5")
plt.title("bron: Dashboard data t/m " + (totalPositiveTestRatio.date.to_list()[-1]).strftime('%Y-%m-%d'), loc='right', fontsize=12, color='grey', y=0.0)


tuftefy(ax)
tuftefy(ax2)


fig = plt.figure()
fig.set_size_inches(15, 10)

ax = sns.lineplot(data=sewer_detail_mean, x='Date', y='RNA_flow_per_100000', color='#004488', label='Riooldeeltjes')
plt.legend(bbox_to_anchor=(0.2, 1),borderaxespad=0)
ax2 = ax.twinx()
sns.lineplot(data=opnames_nice7, x='Date', y='Opnames', color='#ddaa33', label='Nieuwe opnames', ax = ax2)
plt.legend(bbox_to_anchor=(0.9, 1),borderaxespad=0)
#sns.lineplot(data=totals[totals.Date_of_report > '2020-06-01'], x='Date_of_report',y='rolling', color='red',  ax=ax2)
ax.set_ylabel("Riooldeeltjes per 100.000 inwoners")
ax2.set_ylabel("Nieuwe opnames")
ax.set_xlabel("")
ax.set_title('Voortschrijdend gemiddelde (14d) van opnames en riooldeeltjes', pad=30)
#ax.xaxis.set_major_formatter(mdates.DateFormatter('%V'))
ax.xaxis.set_major_formatter(mdates.ConciseDateFormatter(mdates.AutoDateLocator()))
#ax.xaxis.set_major_locator(mdates.WeekdayLocator(byweekday=mdates.SUNDAY, interval=2))
ax.set(ylim=(0, None))
ax2.set(ylim=(0, None))
#plt.axvline(date(2020,10,14), ls=":", c=".5")
#plt.axvline(date(2020,12,18), ls=":", c=".5")
#plt.axvline(date(2021,2,8), ls=":", c=".5")
#plt.axhline(0.0, ls="-", c=".8", zorder=1)
#g = g.map(plt.axvline, x=date(2020,10,14), ls=":", c=".5")
plt.title("bron: Dashboard data t/m " + (totalPositiveTestRatio.date.to_list()[-1]).strftime('%Y-%m-%d'), loc='right', fontsize=12, color='grey', y=0.0)


tuftefy(ax)
tuftefy(ax2)


from matplotlib.patches import Rectangle

fig = plt.figure()
fig.set_size_inches(15, 10)

#ax = sns.lineplot(data=totalPositiveTestRatio[totalPositiveTestRatio.date >= '2020-08-01'], x='date', y='total_7d', color='#4477AA', label='Aantal testen')

ax = sns.lineplot(data=totals, x='Date_of_report', y='rolling', color='#332288')
#sns.lineplot(data=totals[totals.Date_of_report > '2020-06-01'], x='Date_of_report',y='rolling', color='red',  ax=ax2)
ax.set_ylabel("Positieve testen")
#ax2.set_ylabel("Positieve testen")
ax.set_xlabel("")
ax.set_title('Positieve testen in relatie tot sluiten en openen van basisscholen', pad=30)
#ax.xaxis.set_major_formatter(mdates.DateFormatter('%V'))
ax.xaxis.set_major_formatter(mdates.ConciseDateFormatter(mdates.AutoDateLocator()))
#ax.xaxis.set_major_locator(mdates.WeekdayLocator(byweekday=mdates.SUNDAY, interval=2))
ax.set(ylim=(0, None))
# scholen sluiten
plt.axvline(date(2020,3,16), ls=":", c="#999933")
plt.annotate("Sluiten", xy=(date(2020,3,18), 10000), fontsize="x-large", color="#999933")
plt.axvline(date(2020,12,14), ls=":", c="#999933")
plt.axvline(date(2021,12,20), ls=":", c="#999933")
# scholen open
plt.axvline(date(2020,5,11), ls=":", c="#aa4499")
plt.annotate("Openen", xy=(date(2020,5,13), 10000), fontsize="x-large", color="#aa4499")
plt.axvline(date(2021,2,8), ls=":", c="#aa4499")
plt.axvline(date(2022,1,10), ls=":", c="#aa4499")

#ax.add_patch(Rectangle(date(2020,3,16), date(2020,5,20), color="#228833"))
def add_holiday(start, end):
    plt.axvspan(start, end, color="#117733", alpha=0.1)

plt.annotate("Vakantie", xy=(date(2020,7,9), 10000), fontsize="x-large")
# zomer 2020
add_holiday(date(2020, 7,4), date(2020, 8,16))
add_holiday(date(2020, 7,18), date(2020, 8,30))
add_holiday(date(2020, 7,11), date(2020, 8,23))

# herfst 2020
add_holiday(date(2020, 10,10), date(2020, 10,18))
add_holiday(date(2020, 10,17), date(2020, 10,25))
add_holiday(date(2020, 10,17), date(2020, 10,25))

# kerst 2020
add_holiday(date(2020, 12,19), date(2021, 1,3))
add_holiday(date(2020, 12,19), date(2021, 1,3))
add_holiday(date(2020, 12,19), date(2021, 1,3))

# voorjaar 2021
add_holiday(date(2021, 2,20), date(2021, 2,28))
add_holiday(date(2021, 2,20), date(2021, 2,28))
add_holiday(date(2021, 2,13), date(2021, 2,21))

# mei 2021
add_holiday(date(2021, 5,1), date(2021, 5,9))
add_holiday(date(2021, 5,1), date(2021, 5,9))
add_holiday(date(2021, 5,1), date(2021, 5,9))

# zomer 2021
add_holiday(date(2021, 7,10), date(2021, 8,22))
add_holiday(date(2021, 7,17), date(2021, 8,29))
add_holiday(date(2021, 7,24), date(2021, 9,5))

# herfst 2021
add_holiday(date(2021, 10,16), date(2021, 10,24))
add_holiday(date(2021, 10,16), date(2021, 10,24))
add_holiday(date(2021, 10,23), date(2021, 10,31))

# kerst 2021
add_holiday(date(2021, 12,25), date(2022, 1,9))
add_holiday(date(2021, 12,25), date(2022, 1,9))
add_holiday(date(2021, 12,25), date(2022, 1,9))

def annotate_date(d, labelxpos, txt):
    xval = totals[totals.Date_of_report.dt.date == d]["rolling"].to_list()[0]

    plt.annotate(txt, xy=(d, xval), xytext=(d - timedelta(days=3), labelxpos),
            arrowprops=dict(facecolor='black', shrink=0.05),
            horizontalalignment='center', verticalalignment='top',
            fontsize="x-large", bbox=dict(color='white', alpha=0.8)
            )

annotate_date(date(2021,12,28), 10000, "Omikron\ndominant")
annotate_date(date(2021,6,23), 8000, "Delta\ndominant")
annotate_date(date(2021,7,19), 16000, "Dansen met\nJansen")
#annotate_date(date(2021,1,5), 2000, "Alpha dominant")

#plt.legend(bbox_to_anchor=(0.2, 0.1),borderaxespad=0)
#plt.axvline(date(2020,12,18), ls=":", c=".5")
#plt.axvline(date(2021,2,8), ls=":", c=".5")
#plt.axhline(0.0, ls="-", c=".8", zorder=1)
#g = g.map(plt.axvline, x=date(2020,10,14), ls=":", c=".5")
plt.title("bron: RIVM " + (totals.Date_of_report.to_list()[-1]).strftime('%Y-%m-%d'), loc='right', fontsize=12, color='grey', y=0.0)

tuftefy(ax)


fig = plt.figure()
fig.set_size_inches(15, 10)

since= '2022-01-01'
g = sns.lineplot(data=totals[totals.Date_of_report >= since], x='Date_of_report', y='Growth', label="Positieve testen")
sns.lineplot(data=totalPositiveTestRatio[totalPositiveTestRatio.date >= since], x='date', y='infected_percentage_14d_growth', label="Percentage positief")
sns.lineplot(data=opnames_nice7[opnames_nice7.Date >= since], x='Date', y='Growth', label="Opnames (NICE)")
sns.lineplot(data=opnames_lcps14[opnames_lcps14.date >= since], x='date', y='Kliniek_growth', label="Opnames (LCPS)")
sns.lineplot(data=sewer_detail_mean[sewer_detail_mean.Date >= since], x='Date', y='RNA_flow_per_100000_Growth_7d', label="Riooldeeltjes")

g.set_ylabel("Groei percentage")
g.set_xlabel("")
g.set_title('Groei (14d gemiddelde) van verschillende signaal waardes (14d gemiddelde)', pad=30)
g.xaxis.set_major_formatter(mdates.ConciseDateFormatter(mdates.AutoDateLocator()))
g.set(ylim=(-12.5, 12.5))
plt.axhline(0.0, ls="-", c=".8", zorder=1)
#g = g.map(plt.axvline, x=date(2020,10,14), ls=":", c=".5")
plt.title("bronnen: RIVM/LCSP/NICE data t/m " + opnames_lcps14.date.max().strftime('%Y-%m-%d'), loc='right', fontsize=12, color='grey', y=0.0)


tuftefy(g)

	Date_of_report	Date_of_publication	Municipality_code	Municipality_name	Province	Total_reported
0	2020-03-13 10:00:00	2020-03-13 10:00:00	GM0003	Appingedam	Groningen	0
1	2020-03-13 10:00:00	2020-03-13 10:00:00	GM0010	Delfzijl	Groningen	0
2	2020-03-13 10:00:00	2020-03-13 10:00:00	GM0014	Groningen	Groningen	3
3	2020-03-13 10:00:00	2020-03-13 10:00:00	GM0024	Loppersum	Groningen	0
4	2020-03-13 10:00:00	2020-03-13 10:00:00	GM0034	Almere	Flevoland	1
...	...	...	...	...	...	...
403201	2023-03-31 10:00:00	2023-03-31 10:00:00	Onbekend	0	Overijssel	4871
403202	2023-03-31 10:00:00	2023-03-31 10:00:00	Onbekend	0	Utrecht	4751
403203	2023-03-31 10:00:00	2023-03-31 10:00:00	Onbekend	0	Zeeland	1607
403204	2023-03-31 10:00:00	2023-03-31 10:00:00	Onbekend	0	Zuid-Holland	17335
403205	2023-03-31 10:00:00	2023-03-31 10:00:00	Onbekend	0	Onbekend	139

	date	values.tested_total	values.infected	values.infected_percentage	tests.7d.avg	tests.7d_lagged_7	pos.rate.3d.avg	pos.rate.7d.avg	values.infected_7d.avg	values.infected_7d_lagged	growth_infected	growth_tests	infected_percentage_7d	total_7d	positive_7d
0	2020-06-01	1551	73	4.706641	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	2020-06-02	6821	203	2.976103	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	2020-06-03	8880	165	1.858108	NaN	NaN	2.6	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	2020-06-04	9352	173	1.849872	NaN	NaN	2.2	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	2020-06-05	9478	135	1.424351	NaN	NaN	1.7	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1015	2023-03-13	108	72	66.666667	171.428571	199.571429	62.3	62.3	62.354688	59.827485	104.2	85.9	62.354688	171.428571	106.714286
1016	2023-03-14	98	57	58.163265	154.142857	194.571429	62.1	61.9	61.792233	60.037562	102.9	79.2	61.792233	154.142857	95.428571
1017	2023-03-15	116	77	66.379310	131.142857	200.000000	64.0	63.8	63.074888	60.467193	104.3	65.6	63.074888	131.142857	83.714286
1018	2023-03-16	113	49	43.362832	119.857143	200.428571	56.0	60.7	59.894578	60.998655	98.2	59.8	59.894578	119.857143	72.714286
1019	2023-03-17	144	86	59.722222	106.714286	202.428571	56.8	59.0	59.104290	61.311680	96.4	52.7	59.104290	106.714286	63.000000

	Date	Station	RNA_flow_per_100000
0	2020-03-30	Tilburg	34621959326395
1	2020-03-31	Assen	41199039310795
2	2020-03-31	Garmerwolde	10473596079208
3	2020-03-31	Leeuwarden	11002680177775
4	2020-03-31	Stadskanaal	3802954816430
...	...	...	...
117936	2023-04-19	Asten	14144676039699
117937	2023-04-19	Dinteloord	7575368694212
117938	2023-04-19	Dinther	12578231882919
117939	2023-04-19	Dokhaven	44366369820223
117940	2023-04-16	Nieuw-Vossemeer	10721634301093

	Date	<20	20 - 24	25 - 29	30 - 34	35 - 39	40 - 44	45 - 49	50 - 54	55 - 59	60 - 64	65 - 69	70 - 74	75 - 79	80 - 84	85 - 89	>90
185	2020-11-03	507	151	290	353	440	562	935	1479	1723	1944	1979	2617	2739	2466	1646	657
187	2020-11-04	523	151	290	361	445	568	940	1485	1747	1976	1997	2641	2759	2494	1676	662
189	2020-11-05	531	151	293	363	444	575	953	1494	1759	1994	2007	2687	2799	2532	1697	673
191	2020-11-06	529	151	299	366	448	573	958	1507	1776	2020	2025	2688	2822	2564	1714	678
193	2020-11-07	531	154	299	368	453	585	973	1514	1796	2022	2041	2703	2850	2582	1729	681
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1718	2023-03-22	5013	1233	2102	2874	2923	3201	4557	7127	8949	10111	11460	14676	16520	15338	10986	5361
1720	2023-03-23	5023	1234	2104	2873	2925	3203	4561	7132	8954	10130	11473	14706	16543	15365	11013	5367
1722	2023-03-24	5027	1234	2104	2876	2925	3205	4562	7137	8962	10139	11477	14719	16562	15387	11026	5380
1724	2023-03-27	5034	1236	2105	2882	2926	3205	4566	7144	8969	10155	11497	14762	16612	15427	11054	5400
1726	2023-03-28	5039	1236	2106	2883	2929	3205	4567	7148	8971	10158	11510	14781	16631	15452	11066	5406

	date	kliniek_bezetting_covid	IC_bezetting_covid
844	2021-01-01	1780.0	642.0
843	2021-01-02	1819.0	650.0
842	2021-01-03	1826.0	643.0
841	2021-01-04	1895.0	651.0
840	2021-01-05	1905.0	661.0
...	...	...	...
4	2023-04-21	323.0	23.0
3	2023-04-22	NaN	NaN
2	2023-04-23	NaN	NaN
1	2023-04-24	357.0	22.0
0	2023-04-25	333.0	24.0

Globale trends¶

Data importeren¶

Data voorbereiden¶

Plots configureren¶

Plots¶

Week gemiddeld¶

Totals¶

Groei¶

	Date_of_report	Total_reported	rolling	rolling14	Growth
0	2020-03-13 10:00:00	NaN	NaN	NaN	NaN
1	2020-03-14 10:00:00	155.0	NaN	NaN	NaN
2	2020-03-15 10:00:00	176.0	NaN	NaN	NaN
3	2020-03-16 10:00:00	278.0	NaN	NaN	NaN
4	2020-03-17 10:00:00	292.0	NaN	NaN	NaN
...	...	...	...	...	...
1109	2023-03-27 10:00:00	187.0	286.714286	337.000000	-4.026833
1110	2023-03-28 10:00:00	473.0	264.285714	303.285714	-4.662717
1111	2023-03-29 10:00:00	297.0	251.285714	299.357143	-4.425063
1112	2023-03-30 10:00:00	182.0	236.142857	281.428571	-4.716153
1113	2023-03-31 10:00:00	203.0	219.714286	261.785714	-5.143211

	year	week	Date_of_report	Total_reported	rolling	rolling14	WeekTotalReported	Reported_ratio	weekday	month	date
0	2020	11	2020-03-13 10:00:00	NaN	NaN	NaN	165.500000	NaN	Vrijdag	3	2020-03-15
1	2020	11	2020-03-14 10:00:00	155.0	NaN	NaN	165.500000	0.936556	Zaterdag	3	2020-03-15
2	2020	11	2020-03-15 10:00:00	176.0	NaN	NaN	165.500000	1.063444	Zondag	3	2020-03-15
3	2020	12	2020-03-16 10:00:00	278.0	NaN	NaN	438.428571	0.634083	Maandag	3	2020-03-22
4	2020	12	2020-03-17 10:00:00	292.0	NaN	NaN	438.428571	0.666015	Dinsdag	3	2020-03-22
...	...	...	...	...	...	...	...	...	...	...	...
1109	2023	13	2023-03-27 10:00:00	187.0	286.714286	337.000000	268.400000	0.696721	Maandag	3	2023-04-02
1110	2023	13	2023-03-28 10:00:00	473.0	264.285714	303.285714	268.400000	1.762295	Dinsdag	3	2023-04-02
1111	2023	13	2023-03-29 10:00:00	297.0	251.285714	299.357143	268.400000	1.106557	Woensdag	3	2023-04-02
1112	2023	13	2023-03-30 10:00:00	182.0	236.142857	281.428571	268.400000	0.678092	Donderdag	3	2023-04-02
1113	2023	13	2023-03-31 10:00:00	203.0	219.714286	261.785714	268.400000	0.756334	Vrijdag	3	2023-04-02

	index	Date	RNA_flow_per_100000	RNA_flow_per_100000_Growth_7d
0	0	2020-03-30	NaN	NaN
1	1	2020-03-31	NaN	NaN
2	2	2020-04-01	NaN	NaN
3	3	2020-04-02	NaN	NaN
4	4	2020-04-05	NaN	NaN
...	...	...	...	...
1088	1088	2023-04-16	8.729763e+13	-3.327250
1089	1089	2023-04-17	8.599119e+13	-3.124042
1090	1090	2023-04-18	8.399785e+13	-2.962682
1091	1091	2023-04-19	8.074352e+13	-2.845877
1092	1092	2023-04-20	7.632153e+13	-2.965786