COVID pandemic balance in Spain

ISCII Covid Official Data Analysis (Last update 07 mayo, 2023)

Download data

This document downloads and analyses data providad by “Instituto de la Salud Carlos III” associated with the following data file https://cnecovid.isciii.es/covid19/resources/casos_hosp_uci_def_sexo_edad_provres.csv.

rm(list=ls())

setwd("C:/Users/rominsol/Mi unidad/uc3m/IntroductiontoDataScience/MaterialCurso2022_23/Class14")

print('Download data file https://cnecovid.isciii.es/covid19/resources/casos_hosp_uci_def_sexo_edad_provres.csv')

## [1] "Download data file https://cnecovid.isciii.es/covid19/resources/casos_hosp_uci_def_sexo_edad_provres.csv"

print(paste(c('and storage it in the folder ', getwd())))

## [1] "and storage it in the folder "                                                          
## [2] "C:/Users/rominsol/Mi unidad/uc3m/IntroductiontoDataScience/MaterialCurso2022_23/Class14"

#input('con el nombre dataMOMO.csv');
url ='https://cnecovid.isciii.es/covid19/resources/casos_hosp_uci_def_sexo_edad_provres.csv';
filename = 'dataISCIII.csv';
if(!file.exists(filename)){
  download.file(url, filename)
}
aux=installed.packages()[,"Package"]

#
if(!("lubridate"%in%installed.packages()[,"Package"])){
  install.packages("lubridate", repos="http://cran.rstudio.com/", dependencies=TRUE)  
}
library("lubridate")

## Loading required package: timechange

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

# Load current ISCIII data set 
data = read.csv(filename,
                header=TRUE,
                sep=",",
                dec=".",
                stringsAsFactors=TRUE,
                encoding="UTF-8")

Once the data is available in the environment, we take a look to the structure of the information content. Note that some of the variables are storaged as factor, including the date. The rest of variables correspond to integers:

head(data,15)

##    provincia_iso sexo grupo_edad      fecha num_casos num_hosp num_uci num_def
## 1              A    H        0-9 2020-01-01         0        0       0       0
## 2              A    H      10-19 2020-01-01         0        0       0       0
## 3              A    H      20-29 2020-01-01         0        0       0       0
## 4              A    H      30-39 2020-01-01         0        0       0       0
## 5              A    H      40-49 2020-01-01         0        0       0       0
## 6              A    H      50-59 2020-01-01         0        0       0       0
## 7              A    H      60-69 2020-01-01         0        0       0       0
## 8              A    H      70-79 2020-01-01         0        0       0       0
## 9              A    H        80+ 2020-01-01         0        0       0       0
## 10             A    H         NC 2020-01-01         0        0       0       0
## 11             A    M        0-9 2020-01-01         0        0       0       0
## 12             A    M      10-19 2020-01-01         0        0       0       0
## 13             A    M      20-29 2020-01-01         0        0       0       0
## 14             A    M      30-39 2020-01-01         0        0       0       0
## 15             A    M      40-49 2020-01-01         0        0       0       0

Before starting the exploratory data analysis, we proceed to generate three additional auxiliary variables associated with date, the day of the year and the year information for each record, respectively:

# Create dates
data$date=as.Date(data$fecha)
# Create the days within() the year as a factor and include it in the data frame
data$yearday=as.factor(yday(data$date))
# Create the years within the year as a factor and include it in the data frame
data$year=as.factor(year(data$date))
str(data)

## 'data.frame':    1299030 obs. of  11 variables:
##  $ provincia_iso: Factor w/ 52 levels "A","AB","AL",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ sexo         : Factor w/ 3 levels "H","M","NC": 1 1 1 1 1 1 1 1 1 1 ...
##  $ grupo_edad   : Factor w/ 10 levels "0-9","10-19",..: 1 2 3 4 5 6 7 8 9 10 ...
##  $ fecha        : Factor w/ 817 levels "2020-01-01","2020-01-02",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ num_casos    : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ num_hosp     : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ num_uci      : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ num_def      : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ date         : Date, format: "2020-01-01" "2020-01-01" ...
##  $ yearday      : Factor w/ 366 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ year         : Factor w/ 3 levels "2020","2021",..: 1 1 1 1 1 1 1 1 1 1 ...

Graphs and frequency tables

library("ggplot2")

We initially represent the temporal daily evolution of deaths during pandemic. Since the initial information is distributed by different age groups and sex categories, we need to aggregate the numbers for all possible values of these two categorical variables:

dailydatspain=aggregate(cbind(num_casos=data$num_casos,
                              num_hosp=data$num_hosp,
                              num_uci=data$num_uci,
                              num_def=data$num_def
                              ), 
                        by=list(fecha=data$fecha,
                                yearday=data$yearday,
                                 year=data$year), 
                        FUN=sum)
str(dailydatspain)

## 'data.frame':    817 obs. of  7 variables:
##  $ fecha    : Factor w/ 817 levels "2020-01-01","2020-01-02",..: 1 2 3 4 5 6 7 8 9 10 ...
##  $ yearday  : Factor w/ 366 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
##  $ year     : Factor w/ 3 levels "2020","2021",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ num_casos: int  0 0 0 0 0 0 0 0 1 1 ...
##  $ num_hosp : int  8 75 8 6 7 5 6 4 8 9 ...
##  $ num_uci  : int  0 1 1 0 0 0 1 0 0 0 ...
##  $ num_def  : int  0 0 0 0 0 0 0 0 0 0 ...

f=ggplot(data=dailydatspain)+
  aes(x=fecha)+
  geom_point(aes(y=num_def),shape=23,colour="black",fill="blue")+
  xlab("Date")+
  ylab("COVID deaths")+
  scale_x_discrete(
    breaks=dailydatspain$fecha[seq(1, length(dailydatspain$fecha), by=15)],
    labels = dailydatspain$fecha[seq(1, length(dailydatspain$fecha), by=15)]
    )+
  theme(axis.text.x = element_text(angle = 90,hjust=1),text = element_text(size = 20))

ggsave(gsub(" ",
            "",
            paste("RGraphs/ISCIII_Spain.png"),
            fixed = TRUE),
       width=30,
       height=20,
       units = "cm") 

print(f)

Now we make the same plot but collapsed within one year and using different colors depending on the year of the record:

breaks=as.character(cumsum(c(31,31,28,30,31,30,31,31,30,31,30,32)))
labels = c("Jan",
               "Feb",
               "Mar",
               "Apr",
               "May",
               "Jun",
               "Jul",
               "Aug",
               "Sep",
               "Oct",
               "Nov",
               "Dec")

f=ggplot(data=dailydatspain)+
  aes(x=yearday,colour=year,fill=year)+
  geom_point(aes(y=num_def))+
  xlab("Date")+
  ylab("COVID deaths")+
  scale_x_discrete(
    breaks=breaks,
    labels =labels
  )+
  theme(axis.text.x = element_text(hjust=1))+
  ggtitle(paste("Datos procedentes del ISCII (",Sys.Date(),")"))+
  theme(plot.title = element_text(size=15,hjust = 0.5),text = element_text(size = 15),axis.text = element_text(angle = 45))

ggsave(gsub(" ",
            "",
            paste("RGraphs/ISCIII_Spain2.png"),
            fixed = TRUE),
       width=30,
       height=20,
       units = "cm") 

print(f)

For making two-way or contingency tables, it is convenient to organize the number of deaths by province and age group:

datprovincias=aggregate(list(num_def=data$num_def),
                        by=list(provincias=data$provincia_iso,
                                grupo_edad=data$grupo_edad),
                        FUN=sum)


str(datprovincias)

## 'data.frame':    520 obs. of  3 variables:
##  $ provincias: Factor w/ 52 levels "A","AB","AL",..: 1 2 3 4 5 6 7 8 9 10 ...
##  $ grupo_edad: Factor w/ 10 levels "0-9","10-19",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ num_def   : int  0 1 1 0 2 0 1 0 0 1 ...

With this new information available it is possible to construct the following table:

ctable=matrix(datprovincias$num_def, nrow = length(levels(data$grupo_edad)), byrow = TRUE)
rownames(ctable)=levels(data$grupo_edad)
colnames(ctable)=levels(data$provincia_iso)
ctable=cbind(ctable,apply(ctable,1,sum))
ctable=rbind(ctable,apply(ctable,2,sum))
rownames(ctable)[nrow(ctable)]="All"
colnames(ctable)[ncol(ctable)]="SP"
print(t(ctable))

##    0-9 10-19 20-29 30-39 40-49 50-59 60-69 70-79   80+  NC    All
## A    0     1     3    10    58   160   407   869  1956   0   3464
## AB   1     0     1     1     4    37    86   219   634   0    983
## AL   1     0     7    14    46    80   178   297   526   0   1149
## AV   0     0     1     0     3    17    49    89   416   0    575
## B    2     3    12    27   134   456  1324  3062  9545   0  14565
## BA   0     0     2     5    10    56   130   244   741   1   1189
## BI   1     0     2    14    30    80   246   566  2115   0   3054
## BU   0     0     0     1     7    25    72   182   799   0   1086
## C    0     0     0     3    10    43    96   302   924   0   1378
## CA   1     1     7    14    26   126   274   464   851   0   1764
## CC   1     0     1     0     8    31    94   190   746   0   1071
## CE   0     0     2     0     4     9    42    34    55   0    146
## CO   0     0     1     6    16    49   133   286   829   0   1320
## CR   0     1     5     8    26    60   196   427  1177   0   1900
## CS   0     0     1     1    13    41   105   241   651   0   1053
## CU   0     0     0     1     4    27    58   123   497   0    710
## GC   1     0     1     7    21    50   127   175   317   0    699
## GI   1     0     3     6    22    86   191   371  1177   0   1857
## GR   0     1    10    18    34   105   257   513  1139   0   2077
## GU   0     0     0     1    11    20    54   133   534   0    753
## H    0     0     0     3    11    27    57   128   259   0    485
## HU   0     0     1     4     3    20    55   120   536   4    743
## J    0     2     3     3    23    78   159   286   768   0   1322
## L    0     0     1     3     9    36    84   153   618   0    904
## LE   0     0     1     2     4    28    77   191   808   0   1111
## LO   0     1     0     4    15    24    61   180   627   0    912
## LU   0     0     0     0     1     5    26    42   254   0    328
## M    5     5    21    49   243   760  2045  4527 11278   0  18933
## MA   2     3    16    18    35   150   328   628  1172   0   2352
## ML   0     0     0     2     4    16    21    36    75   0    154
## MU   0     0     1     7    39   105   258   431  1375   0   2216
## NC   0     0     0     2     5    15    22    60   142 184    430
## O    0     0     1     5    17    73   220   485  1802   0   2603
## OR   0     0     0     1     0    14    20    93   417   0    545
## P    0     0     0     1     8    18    66   128   444   0    665
## PM   0     3     2     5    19    53   157   331   807   0   1377
## PO   0     0     1     1     3    38    71   182   651   0    947
## S    0     0     0     1     6    23    53   136   570   0    789
## SA   1     0     1     2     6    24    91   184   879   1   1189
## SE   1     1    10    25    49   203   441   720  1433   0   2883
## SG   0     0     0     0     5    16    51   101   490   0    663
## SO   0     0     0     0     4    12    33    70   370   0    489
## SS   1     0     1     8    17    76   186   413  1349   0   2051
## T    0     2     2     6    14    46   133   311   960   0   1474
## TE   1     1     1     0     6    14    38    71   410   1    543
## TF   2     0     5     8    17    73   122   250   460   0    937
## TO   1     0     4     7    25    96   308   570  1744   0   2755
## V    0     1     4    20    43   174   507  1023  2842   0   4614
## VA   0     1     0     6     7    51   149   353  1316   0   1883
## VI   0     0     3     1    10    23    75   214   585   0    911
## Z    1     1     1    10    26   107   294   603  2305  16   3364
## ZA   0     0     0     1     4    12    57   106   480   0    660
## SP  24    28   139   342  1165  3968 10384 21913 63855 207 102025

If we are just interested in number of deaths per age group regardless of the province:

library("knitr")
prop=prop.table(ctable[1:(nrow(ctable)-1),ncol(ctable)])
prop=cbind(100*prop,100*cumsum(prop),ctable[1:(nrow(ctable)-1),ncol(ctable)],cumsum(ctable[1:(nrow(ctable)-1),ncol(ctable)]))
colnames(prop)=c("% deaths","% Cum deaths","Deaths","Cum deaths")
kable(prop,caption="Proportion of deaths by age group")

Proportion of deaths by age group

	% deaths	% Cum deaths	Deaths	Cum deaths
0-9	0.0235236	0.0235236	24	24
10-19	0.0274443	0.0509679	28	52
20-29	0.1362411	0.1872090	139	191
30-39	0.3352120	0.5224210	342	533
40-49	1.1418770	1.6642980	1165	1698
50-59	3.8892428	5.5535408	3968	5666
60-69	10.1778976	15.7314384	10384	16050
70-79	21.4780691	37.2095075	21913	37963
80+	62.5876011	99.7971086	63855	101818
NC	0.2028914	100.0000000	207	102025

Next we want to show the information storage in the “datprovincias” data frame using a box plot. Note that we have to use a logarithmic scale in the vertical axis:

f=ggplot(data=datprovincias)+
  aes(x=grupo_edad,colour=grupo_edad)+
  geom_boxplot(aes(y=num_def))+
  geom_jitter(aes(y=num_def))+
  xlab("Age group")+
  ylab("COVID deaths by province")+
  scale_y_log10()+
  ggtitle(paste("Official COVID deaths by province and age group (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20),legend.position = "none")

  ggsave(gsub(" ",
            "",
            paste("RGraphs/ISCIII_Boxplot_Age_Province.png"),
            fixed = TRUE),
       width=30,
       height=20,
       units = "cm") 
  
  print(f)

We could present the same data but acumulated by age group:

If we plot the number of deaths by province and splitting the information by age group:

  f=ggplot(data=datprovincias)+
  aes(x=provincias,fill=grupo_edad)+
  geom_bar(aes(y=num_def),stat = "identity")+
  xlab("Province")+
  ylab("Deaths by COVID")+
  labs(fill="Age group")+
  ggtitle(paste("Bar graph of COVID deaths by province and age group (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5,size=20),text = element_text(size = 12),axis.text.x = element_text(angle=90))


ggsave(gsub(" ",
            "",
            paste("RGraphs/ISCIII_Barplot_Age_Province.png"),
            fixed = TRUE),
       width=30,
       height=20,
       units = "cm") 

print(f)

If we show the bars in relative terms we get:

  f=ggplot(data=datprovincias)+
  aes(x=provincias,fill=grupo_edad)+
  geom_bar(aes(y=num_def),stat = "identity",position="fill")+
  xlab("Province")+
  ylab("Deaths by COVID")+
  labs(fill="Age group")+
  ggtitle(paste("Bar graph of COVID deaths by province and age group (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5,size=20),text = element_text(size = 12),axis.text.x = element_text(angle=90))


ggsave(gsub(" ",
            "",
            paste("RGraphs/ISCIII_Bar2plot_Age_Province.png"),
            fixed = TRUE),
       width=30,
       height=20,
       units = "cm") 

print(f)

MoMo Data Analysis (Last update 07 mayo, 2023)

What is MoMo?

MoMo is a system for monitoring daily mortality from all causes in Spain. Its objective is to identify unusual patterns of mortality and estimate the impact on the mortality of the population of any important event to guide action in Public Health.

It is managed by the CNE and uses data from various public administrations.

What data is storaged in MoMo?

MoMo feeds fundamentally on data on daily deaths from all causes from the National Institute of Statistics (INE), up to the year in which they are available, and on civil records that are currently computerized, from that year to the present, and which are received through the Ministry of Justice. The coverage rate by Autonomous Community is provided in the “Notification” tab.

MoMo data might have some delay on reporting date. For example, deaths occurring on day 1 are reported on successive days (2, 3, …). Typically, and in normal periods, practically all the deaths that occurred on day 1 are already available on day 7. Specifically, the deaths observed in recent days, such as those shown highlighted in the blue window, the right of the image, may undergo significant changes in the following days.

Data availability

Data is available in CSV format from https://momo.isciii.es/public/momo/dashboard/momo_dashboard.html#datos with the following information:

• ambito: nacional or ccaa
• cod_ambito: if it is national, it is empty. If it is an autonomous community, it corresponds to the ISO 3166-2 code.
• cod_ine_ambito: Informative column on the autonomous community, if applicable. It is your INE code.
• nombre_ambito: Informative column on the autonomous community, if applicable. It’s his name.
• cod_sexo: INE code of sex. 1 for men, 6 for women. All for both cases.
• nombre_sexo: informative column on sex. Your descriptive name (men, women).
• cod_gedad: Age group code. The possible ones are: “+85”, “0-14”, “15-44”, “45-64”, “65-74”, “75-84” and “all”.
• nombre_gedad: informative column on the age group. Your descriptive name (e.g. age < 65).
• fecha_defuncion: the date to which the indicators described hereinafter refer. It is the date on which the death occurs.
• defunciones_observadas: the number of observed deaths (includes correction for delay and that is the reason why there might be decimal numbers).
• defunciones_atrib_exc_temp: estimated deaths caused by heat waves.
• defunciones_atrib_def_temp: estimated deaths caused by cool waves.
• defunciones_estimadas_base: the number of expected deaths, resulting from the model.
• defunciones_estimadas_base_q01: the lower limit of the confidence interval of the expected deaths, corresponding to the 1st percentile of the distribution.
• defunciones_estimadas_base_q99: equivalently, the upper bound, at the 99th percentile.

Data preparation

MoMo data file is storaged in the following address https://momo.isciii.es/public/momo/dashboard/momo_dashboard.html#datos. It has around 400Mb, before downloading it from the web we check if it is available in our working directory. Once it is in our folder, load it:

print('Download file MOMO https://momo.isciii.es/public/momo/dashboard/momo_dashboard.html#datos')

## [1] "Download file MOMO https://momo.isciii.es/public/momo/dashboard/momo_dashboard.html#datos"

print(paste(c('and storage it in the folder ', getwd())))

## [1] "and storage it in the folder "                                                          
## [2] "C:/Users/rominsol/Mi unidad/uc3m/IntroductiontoDataScience/MaterialCurso2022_23/Class14"

#input('con el nombre dataMOMO.csv');
url ='https://momo.isciii.es/public/momo/data';
filename = 'dataMOMO.csv';
if(!file.exists(filename)){
  download.file(url, filename, timeout = 6000)
}

# Load current MOMO data set 
dataMOMO = read.csv(filename,
                header=TRUE,
                sep=",",
                dec=".",
                stringsAsFactors=TRUE,
                encoding="UTF-8")

We are going to generate additional variables to storage dates as proper dates, the day of the year of each record, the year and even the month. We also drop those levels of factors if we do not have data associated with the corresponding level:

# Create dates
dataMOMO$date_defuncion=as.Date(dataMOMO$fecha_defuncion)
# Create the days within the year as a factor and include it in the data frame
dataMOMO$yearday=as.factor(yday(dataMOMO$date_defuncion))
# Create the years within the year as a factor and include it in the data frame
dataMOMO$year=as.factor(year(dataMOMO$date_defuncion))
# Create the months within the year as a factor and include it in the data frame
dataMOMO$month=as.factor(month(dataMOMO$date_defuncion))

#dataMOMO=dataMOMO[-which(dataMOMO$year%in%c(2015,2016,2017,2018)),]

dataMOMO$defunciones_observadas=as.integer(dataMOMO$defunciones_observadas);

#dataMOMO=na.omit(dataMOMO)
dataMOMO$year=droplevels(dataMOMO$year)

Nationwide chart of death evolution

We initially draw from the global dataset, with national information for both genders and all age groups for each day.

dataMOMO_SP=dataMOMO[dataMOMO$ambito=="nacional" & 
                     dataMOMO$nombre_sexo=="todos" & 
                     dataMOMO$cod_gedad=="all",
                     c("fecha_defuncion",
                       "yearday",
                       "year",
                       "month",
                       "defunciones_observadas",
                       "defunciones_estimadas_base",
                       "defunciones_estimadas_base_q99",
                       "defunciones_estimadas_base_q01")]

dataMOMO_SP=na.omit(dataMOMO_SP)

f=ggplot(data=dataMOMO_SP)+
  aes(x=yearday,y=defunciones_observadas,colour=year)+
  geom_ribbon(
    aes(ymin=defunciones_estimadas_base_q01,
        ymax=defunciones_estimadas_base_q99,
        group=year),
    fill="grey")+
    geom_point(size=5)+
  xlab("Day within year")+
  ylab("Daily deaths for all causes")+
  scale_x_discrete(
    breaks=breaks,
    labels = labels
    )+
  theme(axis.text.x = element_text(hjust=1),text = element_text(size = 20))+
  ggtitle(paste("Data taken from MoMo system (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20))

ggsave(gsub(" ",
            "",
            paste("RGraphs/MOMO_Spain.png"),
            fixed = TRUE),
       width=30,
       height=20,
       units = "cm") 

print(f)

If we plot the same information using box plot, we get the following graph:

# Plot for total Fallecidos in an annual scale including 99% confidence bands
f=ggplot(data=dataMOMO_SP)+
  aes(x=month,y=defunciones_observadas,colour=year)+
  #geom_jitter(aes(shape=year))+
    geom_ribbon(
    aes(ymin=defunciones_estimadas_base_q01,
        ymax=defunciones_estimadas_base_q99,
        group=year),
    fill="grey")+
  geom_boxplot()+
  xlab("Months")+
  ylab("Daily deaths for all causes")+
  scale_x_discrete(
    labels = labels
  )+
  ggtitle(paste("Data taken from MoMo (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20))
ggsave(gsub(" ",
            "",
            paste("RGraphs/MOMO_Boxplot_Spain.png"),
            fixed = TRUE),
       width=30,
       height=20,
       units = "cm") 
print(f)

Next we aggregate deaths by month and plot it using a bar graph:

dataMOMOmesesSP=aggregate(list(num_def=dataMOMO_SP$defunciones_observadas),
                        by=list(year=dataMOMO_SP$year,
                                month=dataMOMO_SP$month),
                        FUN=sum)

#dataMOMOmesesSP=as.data.frame(lapply(dataMOMOmesesSP,function(x)rep(x, as.integer(dataMOMOmesesSP$num_def))))
#dataMOMOmesesSP$num_def=NULL

# Plot for total Fallecidos in an annual scale including 99% confidence bands
f=ggplot(data=dataMOMOmesesSP)+
  aes(x=month,fill=year,y=num_def)+
  #geom_jitter(aes(shape=year))+
  geom_bar(stat="identity",position="dodge")+
  geom_text(aes(label=num_def),position = position_dodge(width = 1),angle=90,hjust=1,size=5)+
  xlab("Months")+
  ylab("Monthly deaths for all causes")+
  scale_x_discrete(
    labels = labels
  )+
  ggtitle(paste("Data taken from MoMo (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20))
ggsave(gsub(" ",
            "",
            paste("RGraphs/MOMO_Barplot_Spain.png"),
            fixed = TRUE),
       width=30,
       height=20,
       units = "cm") 
print(f)                        

Graphs by age group

If we take into consideration the age group we can get the following information:

dataMOMO_SPAge=dataMOMO[dataMOMO$ambito=="nacional" & 
                     dataMOMO$nombre_sexo=="todos",
                     c("fecha_defuncion",
                       "yearday",
                       "year",
                       "month",
                       "cod_gedad",
                       "defunciones_observadas",
                       "defunciones_estimadas_base",
                       "defunciones_estimadas_base_q99",
                       "defunciones_estimadas_base_q01")]



dataMOMO_SPAge$cod_gedad=factor(dataMOMO_SPAge$cod_gedad,levels=c("0-14","15-44","45-64","65-74","75-84","+85","all"  ))

dataMOMO_SPAge=na.omit(dataMOMO_SPAge)

The death evolution throughout different years can be easily displayed:

f=ggplot(data=dataMOMO_SPAge)+
  aes(x=yearday,y=defunciones_observadas,colour=year)+
  geom_ribbon(
    aes(ymin=defunciones_estimadas_base_q01,
        ymax=defunciones_estimadas_base_q99,
        group=year),
    fill="grey")+
  geom_point(size=3)+
  facet_grid(cod_gedad~.,scales="free_y")+
  xlab("Months")+
  ylab("Daily deaths by all causes")+
  scale_x_discrete(
    breaks=breaks,
    labels =labels
    )+
  theme(axis.text.x = element_text(hjust=1))+
  ggtitle(paste("Data taken from MoMo (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20))

ggsave(gsub(" ",
            "",
            paste("RGraphs/MOMO_Ages_Spain.png"),
            fixed = TRUE),
       width=30,
       height=30,
       units = "cm") 

print(f)

Similarly, we group the data by month and display box plots for different years and age groups. This makes it easier to compare the monthly distributions of deaths between different years.

f=ggplot(data=dataMOMO_SPAge)+
  aes(x=month,y=defunciones_observadas,colour=year)+
    geom_ribbon(
    aes(ymin=defunciones_estimadas_base_q01,
        ymax=defunciones_estimadas_base_q99,
        group=year),
    fill="grey")+
  geom_boxplot()+
  facet_grid(cod_gedad~.,scales="free_y")+
  xlab("Months")+
  ylab("Daily deaths for all causes")+
  scale_x_discrete(
    labels =labels
  )+
  ggtitle(paste("Data taken from MoMo system (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20))

  ggsave(gsub(" ",
            "",
            paste("RGraphs/MOMO_AgesBoxplot_Spain.png"),
            fixed = TRUE),
       width=30,
       height=30,
       units = "cm") 
  print(f)

Below we have the information about monthly deceased by agegroups and years:

dataMOMOmesesSPage=aggregate(list(num_def=dataMOMO_SPAge$defunciones_observadas),
                        by=list(year=dataMOMO_SPAge$year,
                                month=dataMOMO_SPAge$month,
                                cod_gedad=dataMOMO_SPAge$cod_gedad),
                        FUN=sum)
# dataMOMOmesesSPage=as.data.frame(lapply(dataMOMOmesesSPage,function(x)rep(x, as.integer(dataMOMOmesesSPage$num_def))))
# dataMOMOmesesSPage$num_def=NULL

# Plot for total Fallecidos in an annual scale including 99% confidence bands

f=ggplot(data=dataMOMOmesesSPage)+
  aes(x=month,fill=year,y=num_def)+
  #geom_jitter(aes(shape=year))+
  geom_bar(stat="identity",position="dodge")+
  geom_text(aes(label=num_def),position = position_dodge(width = 1),angle=90,hjust=1,size=4 )+
  facet_grid(cod_gedad~.,scales="free")+
  xlab("Months")+
  ylab("Monthly deaths for all causes")+
  scale_x_discrete(
    labels = labels
  )+ggtitle(paste("Data taken from MoMo system (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20))

  ggsave(gsub(" ",
            "",
            paste("RGraphs/MOMO_Barplot_SpainEDAD.png"),
            fixed = TRUE),
       width=30,
       height=60,
       units = "cm") 

Graphs by Autonomous Communities

We are going to show the graphs made at the national level but by Autonomous Communities:

dataMOMO_CCAAge=dataMOMO[dataMOMO$ambito=="ccaa" & 
                     dataMOMO$nombre_sexo=="todos",
                     c("fecha_defuncion",
                       "yearday",
                       "year",
                       "month",
                       "cod_gedad",
                       "nombre_ambito",
                       "defunciones_observadas",
                       "defunciones_estimadas_base",
                       "defunciones_estimadas_base_q99",
                       "defunciones_estimadas_base_q01")]
dataMOMO_CCAAge$cod_gedad=factor(dataMOMO_CCAAge$cod_gedad,levels=c("0-14","15-44","45-64","65-74","75-84","+85","all"  ))
dataMOMO_CCAAge$nombre_ambito=droplevels(dataMOMO_CCAAge$nombre_ambito)
ccaas = levels(dataMOMO_CCAAge$nombre_ambito)
#ccaas = c("Andalucía","Aragón","Asturias, Principado de","Balears, Illes","Canarias","Cantabria","Castilla - La Mancha","Castilla y León","Cataluña","Ceuta","Comunitat Valenciana","Extremadura","Galicia","Madrid, Comunidad de","Melilla","Murcia, Región de","Navarra, Comunidad Foral de","País Vasco","Rioja, La")
provincias = list(Andalucía=c("AL","CA","CO","GR","HU","J","MA","SE"),
                  Aragón=c("HU","TE","Z"),
                  "Asturias, Principado de"=c("A"),
                  "Balears, Illes"=c("BA"),
                  Canarias=c("PM","TF"),
                  Cantabria=c("S"),
                  "Castilla - La Mancha"=c("AB","CR","CU","GU","TO"),
                  "Castilla y León"=c("AV","BU","LE","P","SA","SG","SO","VA","ZA"),
                  Cataluña = c("B","GI","L","T"),
                  Ceuta = c("CE"),
                  "Comunitat Valenciana"=c("A","CS","V"),
                  Extremadura = c("BA","CA"),
                  Galicia=c("C","LU","OR","PO"),
                  "Madrid, Comunidad de"= c("M"),
                  Melilla=c("ML"),
                  "Murcia, Región de"=c("MU"),
                  "Navarra, Comunidad Foral de" = c("NC") ,
                  "País Vasco" = c("VI","BI","SS"),
                  "Rioja, La" = c("LO")
                  )


str(dataMOMO_CCAAge)

## 'data.frame':    464208 obs. of  10 variables:
##  $ fecha_defuncion               : Factor w/ 3054 levels "2015-01-01","2015-01-02",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ yearday                       : Factor w/ 366 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ year                          : Factor w/ 9 levels "2015","2016",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ month                         : Factor w/ 12 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ cod_gedad                     : Factor w/ 7 levels "0-14","15-44",..: NA 6 1 2 3 4 5 7 NA 6 ...
##  $ nombre_ambito                 : Factor w/ 19 levels "Andalucía","Aragón",..: 1 1 1 1 1 1 1 1 2 2 ...
##  $ defunciones_observadas        : int  229 104 2 5 41 47 78 279 36 19 ...
##  $ defunciones_estimadas_base    : num  174.87 77.04 1.15 4.62 25.18 ...
##  $ defunciones_estimadas_base_q99: num  206 98 4 10 38 43 84 242 49 30 ...
##  $ defunciones_estimadas_base_q01: num  145 57 0 1 14 18 47 175 22 10 ...

dataMOMO_CCAAge=na.omit(dataMOMO_CCAAge)

dataMOMO_mesesCCAAge=aggregate(list(num_def=dataMOMO_CCAAge$defunciones_observadas),
                        by=list(year=dataMOMO_CCAAge$year,
                                month=dataMOMO_CCAAge$month,
                                cod_gedad=dataMOMO_CCAAge$cod_gedad,
                                nombre_ambito=dataMOMO_CCAAge$nombre_ambito),
                        FUN=sum)

Autonomous Communities

The tables showing official COVID deaths by Autonomous Communities are given below:

for(j in 1:length(ccaas)){

  if(length(provincias[[j]])>1){
    tabla=cbind(apply(ctable[,colnames(ctable)%in%provincias[[j]]],MARGIN=1,FUN=sum),
              cumsum(apply(ctable[,colnames(ctable)%in%provincias[[j]]],MARGIN=1,FUN=sum)))
   tabla[nrow(tabla),ncol(tabla)]="--"
    f=kable(tabla,
        caption=paste("Deceased by age group in ",names(provincias)[j]),
        col.names = c("Deaths","Cum. deaths"),
        align="r")  
    
  }else{
    tabla=cbind(ctable[,colnames(ctable)%in%provincias[[j]]],
              cumsum(ctable[,colnames(ctable)%in%provincias[[j]]]))
    tabla[nrow(tabla),ncol(tabla)]="--"
    f=kable(tabla,
        caption=paste("Deceased by age group in ",names(provincias)[j]),
        col.names = c("Deaths","Cum. deaths"),
        align="r")  
    
  }
  print(f)

}

## 
## 
## Table: Deceased by age group in  Andalucía
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      5|           5|
## |10-19 |      8|          13|
## |20-29 |     55|          68|
## |30-39 |    102|         170|
## |40-49 |    232|         402|
## |50-59 |    811|        1213|
## |60-69 |   1825|        3038|
## |70-79 |   3314|        6352|
## |80+   |   7254|       13606|
## |NC    |      4|       13610|
## |All   |  13610|          --|
## 
## 
## Table: Deceased by age group in  Aragón
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      2|           2|
## |10-19 |      2|           4|
## |20-29 |      3|           7|
## |30-39 |     14|          21|
## |40-49 |     35|          56|
## |50-59 |    141|         197|
## |60-69 |    387|         584|
## |70-79 |    794|        1378|
## |80+   |   3251|        4629|
## |NC    |     21|        4650|
## |All   |   4650|          --|
## 
## 
## Table: Deceased by age group in  Asturias, Principado de
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      1|           1|
## |20-29 |      3|           4|
## |30-39 |     10|          14|
## |40-49 |     58|          72|
## |50-59 |    160|         232|
## |60-69 |    407|         639|
## |70-79 |    869|        1508|
## |80+   |   1956|        3464|
## |NC    |      0|        3464|
## |All   |   3464|          --|
## 
## 
## Table: Deceased by age group in  Balears, Illes
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      0|           0|
## |20-29 |      2|           2|
## |30-39 |      5|           7|
## |40-49 |     10|          17|
## |50-59 |     56|          73|
## |60-69 |    130|         203|
## |70-79 |    244|         447|
## |80+   |    741|        1188|
## |NC    |      1|        1189|
## |All   |   1189|          --|
## 
## 
## Table: Deceased by age group in  Canarias
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      2|           2|
## |10-19 |      3|           5|
## |20-29 |      7|          12|
## |30-39 |     13|          25|
## |40-49 |     36|          61|
## |50-59 |    126|         187|
## |60-69 |    279|         466|
## |70-79 |    581|        1047|
## |80+   |   1267|        2314|
## |NC    |      0|        2314|
## |All   |   2314|          --|
## 
## 
## Table: Deceased by age group in  Cantabria
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      0|           0|
## |20-29 |      0|           0|
## |30-39 |      1|           1|
## |40-49 |      6|           7|
## |50-59 |     23|          30|
## |60-69 |     53|          83|
## |70-79 |    136|         219|
## |80+   |    570|         789|
## |NC    |      0|         789|
## |All   |    789|          --|
## 
## 
## Table: Deceased by age group in  Castilla - La Mancha
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      2|           2|
## |10-19 |      1|           3|
## |20-29 |     10|          13|
## |30-39 |     18|          31|
## |40-49 |     70|         101|
## |50-59 |    240|         341|
## |60-69 |    702|        1043|
## |70-79 |   1472|        2515|
## |80+   |   4586|        7101|
## |NC    |      0|        7101|
## |All   |   7101|          --|
## 
## 
## Table: Deceased by age group in  Castilla y León
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      1|           1|
## |10-19 |      1|           2|
## |20-29 |      3|           5|
## |30-39 |     13|          18|
## |40-49 |     48|          66|
## |50-59 |    203|         269|
## |60-69 |    645|         914|
## |70-79 |   1404|        2318|
## |80+   |   6002|        8320|
## |NC    |      1|        8321|
## |All   |   8321|          --|
## 
## 
## Table: Deceased by age group in  Cataluña
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      3|           3|
## |10-19 |      5|           8|
## |20-29 |     18|          26|
## |30-39 |     42|          68|
## |40-49 |    179|         247|
## |50-59 |    624|         871|
## |60-69 |   1732|        2603|
## |70-79 |   3897|        6500|
## |80+   |  12300|       18800|
## |NC    |      0|       18800|
## |All   |  18800|          --|
## 
## 
## Table: Deceased by age group in  Ceuta
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      0|           0|
## |20-29 |      2|           2|
## |30-39 |      0|           2|
## |40-49 |      4|           6|
## |50-59 |      9|          15|
## |60-69 |     42|          57|
## |70-79 |     34|          91|
## |80+   |     55|         146|
## |NC    |      0|         146|
## |All   |    146|          --|
## 
## 
## Table: Deceased by age group in  Comunitat Valenciana
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      2|           2|
## |20-29 |      8|          10|
## |30-39 |     31|          41|
## |40-49 |    114|         155|
## |50-59 |    375|         530|
## |60-69 |   1019|        1549|
## |70-79 |   2133|        3682|
## |80+   |   5449|        9131|
## |NC    |      0|        9131|
## |All   |   9131|          --|
## 
## 
## Table: Deceased by age group in  Extremadura
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      1|           1|
## |10-19 |      1|           2|
## |20-29 |      9|          11|
## |30-39 |     19|          30|
## |40-49 |     36|          66|
## |50-59 |    182|         248|
## |60-69 |    404|         652|
## |70-79 |    708|        1360|
## |80+   |   1592|        2952|
## |NC    |      1|        2953|
## |All   |   2953|          --|
## 
## 
## Table: Deceased by age group in  Galicia
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      0|           0|
## |20-29 |      1|           1|
## |30-39 |      5|           6|
## |40-49 |     14|          20|
## |50-59 |    100|         120|
## |60-69 |    213|         333|
## |70-79 |    619|         952|
## |80+   |   2246|        3198|
## |NC    |      0|        3198|
## |All   |   3198|          --|
## 
## 
## Table: Deceased by age group in  Madrid, Comunidad de
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      5|           5|
## |10-19 |      5|          10|
## |20-29 |     21|          31|
## |30-39 |     49|          80|
## |40-49 |    243|         323|
## |50-59 |    760|        1083|
## |60-69 |   2045|        3128|
## |70-79 |   4527|        7655|
## |80+   |  11278|       18933|
## |NC    |      0|       18933|
## |All   |  18933|          --|
## 
## 
## Table: Deceased by age group in  Melilla
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      0|           0|
## |20-29 |      0|           0|
## |30-39 |      2|           2|
## |40-49 |      4|           6|
## |50-59 |     16|          22|
## |60-69 |     21|          43|
## |70-79 |     36|          79|
## |80+   |     75|         154|
## |NC    |      0|         154|
## |All   |    154|          --|
## 
## 
## Table: Deceased by age group in  Murcia, Región de
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      0|           0|
## |20-29 |      1|           1|
## |30-39 |      7|           8|
## |40-49 |     39|          47|
## |50-59 |    105|         152|
## |60-69 |    258|         410|
## |70-79 |    431|         841|
## |80+   |   1375|        2216|
## |NC    |      0|        2216|
## |All   |   2216|          --|
## 
## 
## Table: Deceased by age group in  Navarra, Comunidad Foral de
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      0|           0|
## |20-29 |      0|           0|
## |30-39 |      2|           2|
## |40-49 |      5|           7|
## |50-59 |     15|          22|
## |60-69 |     22|          44|
## |70-79 |     60|         104|
## |80+   |    142|         246|
## |NC    |    184|         430|
## |All   |    430|          --|
## 
## 
## Table: Deceased by age group in  País Vasco
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      2|           2|
## |10-19 |      0|           2|
## |20-29 |      6|           8|
## |30-39 |     23|          31|
## |40-49 |     57|          88|
## |50-59 |    179|         267|
## |60-69 |    507|         774|
## |70-79 |   1193|        1967|
## |80+   |   4049|        6016|
## |NC    |      0|        6016|
## |All   |   6016|          --|
## 
## 
## Table: Deceased by age group in  Rioja, La
## 
## |      | Deaths| Cum. deaths|
## |:-----|------:|-----------:|
## |0-9   |      0|           0|
## |10-19 |      1|           1|
## |20-29 |      0|           1|
## |30-39 |      4|           5|
## |40-49 |     15|          20|
## |50-59 |     24|          44|
## |60-69 |     61|         105|
## |70-79 |    180|         285|
## |80+   |    627|         912|
## |NC    |      0|         912|
## |All   |    912|          --|

for(j in 1:length(ccaas)){
  print(ccaas[j])

  f=ggplot(data=dataMOMO_CCAAge[dataMOMO_CCAAge$nombre_ambito==ccaas[j],])+
    aes(x=yearday,y=defunciones_observadas,colour=year)+
    geom_ribbon(
      aes(ymin=defunciones_estimadas_base_q01,
          ymax=defunciones_estimadas_base_q99,
          group=year),
      fill="grey")+
    geom_point(size=3)+
    facet_grid(cod_gedad~.,scales="free_y")+
    xlab("Month")+
    ylab("Daily deaths")+
    scale_x_discrete(
      breaks=breaks,
      labels = labels
    )+
    theme(axis.text.x = element_text(hjust=1))+
    ggtitle(paste("Data from MoMo in ",levels(dataMOMO_CCAAge$nombre_ambito)[j]," (",Sys.Date(),")"))+
    theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20))
  
    dir.create(gsub(" ",
                "",paste("RGraphs/",ccaas[j])))
    
    ggsave(gsub(" ",
                "",
                paste("RGraphs/",ccaas[j],"/MOMO_",substr(ccaas[j], 1, 3),"_byAge.png"),
                fixed = TRUE),
           width=30,
           height=30,
           units = "cm") 
    
    print(f)
    
    f=ggplot(data=dataMOMO_CCAAge[dataMOMO_CCAAge$nombre_ambito==ccaas[j],])+
    aes(x=month,y=defunciones_observadas,colour=year)+
      geom_ribbon(
      aes(ymin=defunciones_estimadas_base_q01,
          ymax=defunciones_estimadas_base_q99,
          group=year),
      fill="grey")+
    geom_boxplot()+
    facet_grid(cod_gedad~.,scales="free_y")+
    xlab("Month")+
    ylab("Daily deaths")+
    scale_x_discrete(
      labels = labels
    )+
    ggtitle(paste("Data from MoMo in ",levels(dataMOMO_CCAAge$nombre_ambito)[j]," (",Sys.Date(),")"))+
    theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20))
  
  ggsave(gsub(" ",
              "",
              paste("RGraphs/",ccaas[j],"/MOMO_Boxplot_",substr(ccaas[j], 1, 3),"_byAge.png"),
              fixed = TRUE),
         width=30,
         height=30,
         units = "cm") 
  
  
  print(f)
  
  f=ggplot(data=dataMOMO_mesesCCAAge[dataMOMO_mesesCCAAge$nombre_ambito==ccaas[j],])+
  aes(x=month,fill=year,y=num_def)+
  #geom_jitter(aes(shape=year))+
  geom_bar(stat="identity",position="dodge")+
  geom_text(aes(label=num_def),position = position_dodge(width = 1),angle=90,hjust=1,size=4 )+
  facet_grid(cod_gedad~.,scales="free")+
  xlab("Months")+
  ylab("Monthly deaths")+
  scale_x_discrete(
    labels =labels
  )+
  ggtitle(paste("Data from MoMo in ",ccaas[j]," (",Sys.Date(),")"))+
  theme(plot.title = element_text(hjust = 0.5),text = element_text(size = 20))
 ggsave(gsub(" ",
            "",
            paste("RGraphs/",ccaas[j],"/MOMO_Barplot.png"),
            fixed = TRUE),
       width=30,
       height=30,
       units = "cm") 

print(f)  
  
}

## [1] "Andalucía"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Andalucía' already exists

## [1] "Aragón"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Aragón' already exists

## [1] "Asturias, Principado de"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Asturias,Principadode' already exists

## [1] "Balears, Illes"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Balears,Illes' already exists

## [1] "Canarias"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Canarias' already exists

## [1] "Cantabria"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Cantabria' already exists

## [1] "Castilla - La Mancha"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Castilla-LaMancha' already exists

## [1] "Castilla y León"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\CastillayLeón' already exists

## [1] "Cataluña"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Cataluña' already exists

## [1] "Ceuta"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Ceuta' already exists

## [1] "Comunitat Valenciana"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\ComunitatValenciana' already exists

## [1] "Extremadura"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Extremadura' already exists

## [1] "Galicia"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Galicia' already exists

## [1] "Madrid, Comunidad de"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Madrid,Comunidadde' already exists

## [1] "Melilla"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Melilla' already exists

## [1] "Murcia, Región de"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Murcia,Regiónde' already exists

## [1] "Navarra, Comunidad Foral de"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Navarra,ComunidadForalde' already exists

## [1] "País Vasco"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\PaísVasco' already exists

## [1] "Rioja, La"

## Warning in dir.create(gsub(" ", "", paste("RGraphs/", ccaas[j]))):
## 'RGraphs\Rioja,La' already exists