Média Móvel Brasil

Carregando os pacotes

library(magrittr) 
library(lubridate)
library(tidyverse)
library(gridExtra)
library(ggforce) 
library(kableExtra) 
library(leaflet) 
library(plotly)
library(zoo)
library(forecast)
options(knitr.kable.NA = '')

Carregando os dados

raw.data.confirmed <- read.csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv')
raw.data.deaths <- read.csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv')
raw.data.recovered <- read.csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_recovered_global.csv')

n.col <- ncol(raw.data.confirmed)
dates <- names(raw.data.confirmed)[5:n.col] %>% substr(2,8) %>% mdy()

Conferindo as datas

range(dates)

[1] "2020-01-22" "2020-07-15"

min.date <- min(dates)
max.date <- max(dates)
min.date.txt <- min.date %>% format('%d %b %Y')
max.date.txt <- max.date %>% format('%d %b %Y')

cleanData <- function(data) {
  data %<>% select(-c(Province.State, Lat, Long)) %>% rename(country=Country.Region)
  data %<>% gather(key=date, value=count, -country)
  data %<>% mutate(date = date %>% substr(2,8) %>% mdy())
  data %<>% group_by(country, date) %>% summarise(count=sum(count, na.rm=T)) %>% as.data.frame()
  return(data)
}

data.confirmed <- raw.data.confirmed %>% cleanData() %>% rename(confirmed=count)
data.deaths <- raw.data.deaths %>% cleanData() %>% rename(deaths=count)
data.recovered <- raw.data.recovered %>% cleanData() %>% rename(recovered=count)
data <- data.confirmed %>% merge(data.deaths, all=T) %>% merge(data.recovered, all=T)

library(wpp2019)
data(pop)

popz <- pop[c(2,17)]

popz$name <- as.factor(popz$name)

names(popz) <- c("country", "pop")
levels(popz$country)[233] <- "US"

#subset(popz, country == "US")
data <- merge(popz,data)



data %<>% arrange(country, date)
n <- nrow(data)
day1 <- min(data$date)
data %<>% mutate(new.confirmed = ifelse(date == day1, NA, confirmed - lag(confirmed, n=1)),
                 new.deaths = ifelse(date == day1, NA, deaths - lag(deaths, n=1)),
                 new.recovered = ifelse(date == day1, NA, recovered - lag(recovered, n=1)))
data %<>% mutate(new.confirmed = ifelse(new.confirmed < 0, 0, new.confirmed),
                 new.deaths = ifelse(new.deaths < 0, 0, new.deaths),
                 new.recovered = ifelse(new.recovered < 0, 0, new.recovered))


db <- data

Selecionando o País

brz <- db %>% arrange((date)) %>% filter(country=='Brazil') 

brz %>% kable("pandoc")

country	pop	date	confirmed	deaths	recovered	new.confirmed	new.deaths	new.recovered
Brazil	212559.4	2020-01-22	0	0	0
Brazil	212559.4	2020-01-23	0	0	0	0	0	0
Brazil	212559.4	2020-01-24	0	0	0	0	0	0
Brazil	212559.4	2020-01-25	0	0	0	0	0	0
Brazil	212559.4	2020-01-26	0	0	0	0	0	0
Brazil	212559.4	2020-01-27	0	0	0	0	0	0
Brazil	212559.4	2020-01-28	0	0	0	0	0	0
Brazil	212559.4	2020-01-29	0	0	0	0	0	0
Brazil	212559.4	2020-01-30	0	0	0	0	0	0
Brazil	212559.4	2020-01-31	0	0	0	0	0	0
Brazil	212559.4	2020-02-01	0	0	0	0	0	0
Brazil	212559.4	2020-02-02	0	0	0	0	0	0
Brazil	212559.4	2020-02-03	0	0	0	0	0	0
Brazil	212559.4	2020-02-04	0	0	0	0	0	0
Brazil	212559.4	2020-02-05	0	0	0	0	0	0
Brazil	212559.4	2020-02-06	0	0	0	0	0	0
Brazil	212559.4	2020-02-07	0	0	0	0	0	0
Brazil	212559.4	2020-02-08	0	0	0	0	0	0
Brazil	212559.4	2020-02-09	0	0	0	0	0	0
Brazil	212559.4	2020-02-10	0	0	0	0	0	0
Brazil	212559.4	2020-02-11	0	0	0	0	0	0
Brazil	212559.4	2020-02-12	0	0	0	0	0	0
Brazil	212559.4	2020-02-13	0	0	0	0	0	0
Brazil	212559.4	2020-02-14	0	0	0	0	0	0
Brazil	212559.4	2020-02-15	0	0	0	0	0	0
Brazil	212559.4	2020-02-16	0	0	0	0	0	0
Brazil	212559.4	2020-02-17	0	0	0	0	0	0
Brazil	212559.4	2020-02-18	0	0	0	0	0	0
Brazil	212559.4	2020-02-19	0	0	0	0	0	0
Brazil	212559.4	2020-02-20	0	0	0	0	0	0
Brazil	212559.4	2020-02-21	0	0	0	0	0	0
Brazil	212559.4	2020-02-22	0	0	0	0	0	0
Brazil	212559.4	2020-02-23	0	0	0	0	0	0
Brazil	212559.4	2020-02-24	0	0	0	0	0	0
Brazil	212559.4	2020-02-25	0	0	0	0	0	0
Brazil	212559.4	2020-02-26	1	0	0	1	0	0
Brazil	212559.4	2020-02-27	1	0	0	0	0	0
Brazil	212559.4	2020-02-28	1	0	0	0	0	0
Brazil	212559.4	2020-02-29	2	0	0	1	0	0
Brazil	212559.4	2020-03-01	2	0	0	0	0	0
Brazil	212559.4	2020-03-02	2	0	0	0	0	0
Brazil	212559.4	2020-03-03	2	0	0	0	0	0
Brazil	212559.4	2020-03-04	4	0	0	2	0	0
Brazil	212559.4	2020-03-05	4	0	0	0	0	0
Brazil	212559.4	2020-03-06	13	0	0	9	0	0
Brazil	212559.4	2020-03-07	13	0	0	0	0	0
Brazil	212559.4	2020-03-08	20	0	0	7	0	0
Brazil	212559.4	2020-03-09	25	0	0	5	0	0
Brazil	212559.4	2020-03-10	31	0	0	6	0	0
Brazil	212559.4	2020-03-11	38	0	0	7	0	0
Brazil	212559.4	2020-03-12	52	0	0	14	0	0
Brazil	212559.4	2020-03-13	151	0	0	99	0	0
Brazil	212559.4	2020-03-14	151	0	0	0	0	0
Brazil	212559.4	2020-03-15	162	0	0	11	0	0
Brazil	212559.4	2020-03-16	200	0	1	38	0	1
Brazil	212559.4	2020-03-17	321	1	2	121	1	1
Brazil	212559.4	2020-03-18	372	3	2	51	2	0
Brazil	212559.4	2020-03-19	621	6	2	249	3	0
Brazil	212559.4	2020-03-20	793	11	2	172	5	0
Brazil	212559.4	2020-03-21	1021	15	2	228	4	0
Brazil	212559.4	2020-03-22	1546	25	2	525	10	0
Brazil	212559.4	2020-03-23	1924	34	2	378	9	0
Brazil	212559.4	2020-03-24	2247	46	2	323	12	0
Brazil	212559.4	2020-03-25	2554	59	2	307	13	0
Brazil	212559.4	2020-03-26	2985	77	6	431	18	4
Brazil	212559.4	2020-03-27	3417	92	6	432	15	0
Brazil	212559.4	2020-03-28	3904	111	6	487	19	0
Brazil	212559.4	2020-03-29	4256	136	6	352	25	0
Brazil	212559.4	2020-03-30	4579	159	120	323	23	114
Brazil	212559.4	2020-03-31	5717	201	127	1138	42	7
Brazil	212559.4	2020-04-01	6836	240	127	1119	39	0
Brazil	212559.4	2020-04-02	8044	324	127	1208	84	0
Brazil	212559.4	2020-04-03	9056	359	127	1012	35	0
Brazil	212559.4	2020-04-04	10360	445	127	1304	86	0
Brazil	212559.4	2020-04-05	11130	486	127	770	41	0
Brazil	212559.4	2020-04-06	12161	564	127	1031	78	0
Brazil	212559.4	2020-04-07	14034	686	127	1873	122	0
Brazil	212559.4	2020-04-08	16170	819	127	2136	133	0
Brazil	212559.4	2020-04-09	18092	950	173	1922	131	46
Brazil	212559.4	2020-04-10	19638	1057	173	1546	107	0
Brazil	212559.4	2020-04-11	20727	1124	173	1089	67	0
Brazil	212559.4	2020-04-12	22192	1223	173	1465	99	0
Brazil	212559.4	2020-04-13	23430	1328	173	1238	105	0
Brazil	212559.4	2020-04-14	25262	1532	3046	1832	204	2873
Brazil	212559.4	2020-04-15	28320	1736	14026	3058	204	10980
Brazil	212559.4	2020-04-16	30425	1924	14026	2105	188	0
Brazil	212559.4	2020-04-17	33682	2141	14026	3257	217	0
Brazil	212559.4	2020-04-18	36658	2354	14026	2976	213	0
Brazil	212559.4	2020-04-19	38654	2462	22130	1996	108	8104
Brazil	212559.4	2020-04-20	40743	2587	22130	2089	125	0
Brazil	212559.4	2020-04-21	43079	2741	22991	2336	154	861
Brazil	212559.4	2020-04-22	45757	2906	25318	2678	165	2327
Brazil	212559.4	2020-04-23	50036	3331	26573	4279	425	1255
Brazil	212559.4	2020-04-24	54043	3704	27655	4007	373	1082
Brazil	212559.4	2020-04-25	59324	4057	29160	5281	353	1505
Brazil	212559.4	2020-04-26	63100	4286	30152	3776	229	992
Brazil	212559.4	2020-04-27	67446	4603	31142	4346	317	990
Brazil	212559.4	2020-04-28	73235	5083	32544	5789	480	1402
Brazil	212559.4	2020-04-29	79685	5513	34132	6450	430	1588
Brazil	212559.4	2020-04-30	87187	6006	35935	7502	493	1803
Brazil	212559.4	2020-05-01	92202	6412	38039	5015	406	2104
Brazil	212559.4	2020-05-02	97100	6761	40937	4898	349	2898
Brazil	212559.4	2020-05-03	101826	7051	42991	4726	290	2054
Brazil	212559.4	2020-05-04	108620	7367	45815	6794	316	2824
Brazil	212559.4	2020-05-05	115455	7938	48221	6835	571	2406
Brazil	212559.4	2020-05-06	126611	8588	51370	11156	650	3149
Brazil	212559.4	2020-05-07	135773	9190	55350	9162	602	3980
Brazil	212559.4	2020-05-08	146894	10017	59297	11121	827	3947
Brazil	212559.4	2020-05-09	156061	10656	61685	9167	639	2388
Brazil	212559.4	2020-05-10	162699	11123	64957	6638	467	3272
Brazil	212559.4	2020-05-11	169594	11653	67384	6895	530	2427
Brazil	212559.4	2020-05-12	178214	12461	72597	8620	808	5213
Brazil	212559.4	2020-05-13	190137	13240	78424	11923	779	5827
Brazil	212559.4	2020-05-14	203165	13999	79479	13028	759	1055
Brazil	212559.4	2020-05-15	220291	14962	84970	17126	963	5491
Brazil	212559.4	2020-05-16	233511	15662	89672	13220	700	4702
Brazil	212559.4	2020-05-17	241080	16118	94122	7569	456	4450
Brazil	212559.4	2020-05-18	255368	16853	100459	14288	735	6337
Brazil	212559.4	2020-05-19	271885	17983	106794	16517	1130	6335
Brazil	212559.4	2020-05-20	291579	18859	116683	19694	876	9889
Brazil	212559.4	2020-05-21	310087	20047	125960	18508	1188	9277
Brazil	212559.4	2020-05-22	330890	21048	135430	20803	1001	9470
Brazil	212559.4	2020-05-23	347398	22013	142587	16508	965	7157
Brazil	212559.4	2020-05-24	363211	22666	149911	15813	653	7324
Brazil	212559.4	2020-05-25	374898	23473	153833	11687	807	3922
Brazil	212559.4	2020-05-26	391222	24512	158593	16324	1039	4760
Brazil	212559.4	2020-05-27	411821	25598	166647	20599	1086	8054
Brazil	212559.4	2020-05-28	438238	26754	177604	26417	1156	10957
Brazil	212559.4	2020-05-29	465166	27878	189476	26928	1124	11872
Brazil	212559.4	2020-05-30	498440	28834	200892	33274	956	11416
Brazil	212559.4	2020-05-31	514849	29314	206555	16409	480	5663
Brazil	212559.4	2020-06-01	526447	29937	211080	11598	623	4525
Brazil	212559.4	2020-06-02	555383	31199	223638	28936	1262	12558
Brazil	212559.4	2020-06-03	584016	32548	238617	28633	1349	14979
Brazil	212559.4	2020-06-04	614941	34021	254963	30925	1473	16346
Brazil	212559.4	2020-06-05	645771	35026	266940	30830	1005	11977
Brazil	212559.4	2020-06-06	672846	35930	277149	27075	904	10209
Brazil	212559.4	2020-06-07	691758	36455	283952	18912	525	6803
Brazil	212559.4	2020-06-08	707412	37134	378257	15654	679	94305
Brazil	212559.4	2020-06-09	739503	38406	396737	32091	1272	18480
Brazil	212559.4	2020-06-10	772416	39680	413916	32913	1274	17179
Brazil	212559.4	2020-06-11	802828	40919	429965	30412	1239	16049
Brazil	212559.4	2020-06-12	828810	41828	445123	25982	909	15158
Brazil	212559.4	2020-06-13	850514	42720	459436	21704	892	14313
Brazil	212559.4	2020-06-14	867624	43332	469141	17110	612	9705
Brazil	212559.4	2020-06-15	888271	43959	477709	20647	627	8568
Brazil	212559.4	2020-06-16	923189	45241	490005	34918	1282	12296
Brazil	212559.4	2020-06-17	955377	46510	521046	32188	1269	31041
Brazil	212559.4	2020-06-18	978142	47748	534580	22765	1238	13534
Brazil	212559.4	2020-06-19	1032913	48954	551631	54771	1206	17051
Brazil	212559.4	2020-06-20	1067579	49976	576779	34666	1022	25148
Brazil	212559.4	2020-06-21	1083341	50591	588118	15762	615	11339
Brazil	212559.4	2020-06-22	1106470	51271	601736	23129	680	13618
Brazil	212559.4	2020-06-23	1145906	52645	627963	39436	1374	26227
Brazil	212559.4	2020-06-24	1188631	53830	660469	42725	1185	32506
Brazil	212559.4	2020-06-25	1228114	54971	679524	39483	1141	19055
Brazil	212559.4	2020-06-26	1274974	55961	702399	46860	990	22875
Brazil	212559.4	2020-06-27	1313667	57070	727715	38693	1109	25316
Brazil	212559.4	2020-06-28	1344143	57622	746018	30476	552	18303
Brazil	212559.4	2020-06-29	1368195	58314	757811	24052	692	11793
Brazil	212559.4	2020-06-30	1402041	59594	788318	33846	1280	30507
Brazil	212559.4	2020-07-01	1448753	60632	817642	46712	1038	29324
Brazil	212559.4	2020-07-02	1496858	61884	957692	48105	1252	140050
Brazil	212559.4	2020-07-03	1539081	63174	984615	42223	1290	26923
Brazil	212559.4	2020-07-04	1577004	64265	990731	37923	1091	6116
Brazil	212559.4	2020-07-05	1603055	64867	1029045	26051	602	38314
Brazil	212559.4	2020-07-06	1623284	65487	1062542	20229	620	33497
Brazil	212559.4	2020-07-07	1668589	66741	1107012	45305	1254	44470
Brazil	212559.4	2020-07-08	1713160	67964	1139844	44571	1223	32832
Brazil	212559.4	2020-07-09	1755779	69184	1171447	42619	1220	31603
Brazil	212559.4	2020-07-10	1800827	70398	1217361	45048	1214	45914
Brazil	212559.4	2020-07-11	1839850	71469	1244088	39023	1071	26727
Brazil	212559.4	2020-07-12	1864681	72100	1264843	24831	631	20755
Brazil	212559.4	2020-07-13	1884967	72833	1291251	20286	733	26408
Brazil	212559.4	2020-07-14	1926824	74133	1323425	41857	1300	32174
Brazil	212559.4	2020-07-15	1966748	75366	1350098	39924	1233	26673

Criando a média movel com os dados diários

Infectados <- c(brz$new.deaths)
inicio <- min(brz$date)
dia <- 1:(length(Infectados))
Day <- inicio+dia

ab <- zoo(Infectados, seq(from = (inicio), to = last(brz$date), by = 1))
sm <- ma(ab,order=7) # 7 dias

brz$mm <- sm
names(brz)[10] <- "mm"

Gráfico da Média Móvel

brz %>% ggplot() + geom_bar(aes(x=date, y=new.deaths, fill="Casos"), stat = "identity", position = position_dodge(1))+
  ggtitle(paste(brz$country[1])) +
  labs(subtitle = paste("Média móvel de 7 dias = ",round(last(na.omit(sm)),0), "óbitos")) +
  geom_line(aes(x=date,y=mm, fill="Média Movel"), color="blue", size=1.5) + 
#  ylim(0, 150)+
  ylab("Óbitos") + 
  xlab("")+
  scale_x_date(
    date_minor_breaks = "1 day",
    breaks = "2 week",
    date_labels = "%d-%b-%Y") + 
  theme_classic() + 
  theme(legend.position = "none",
    text = element_text(size = 10),
        axis.text.x = element_text(angle = 45, hjust = 1)) 

Baixar dados COVID-BR

get_cor <- function (dir = "outputs", filename = "corona_brasil", 
                     cidade = NULL, uf = NULL, ibge_cod = NULL, by_uf = FALSE, 
                     save = TRUE) 
{
  res <- readr::read_csv("https://data.brasil.io/dataset/covid19/caso_full.csv.gz")
  res$date <- as.Date(res$date)
  metadado <- data.frame(intervalo = paste(range(res$date), 
                                           collapse = ";"), fonte = "https://data.brasil.io/dataset/covid19/", 
                         acesso_em = Sys.Date())
  if (!is.null(cidade) & is.null(uf)) {
    stop("Precisa fornecer um estado para evitar ambiguidade")
  }
  if (!is.null(cidade)) {
    if (sum(!cidade %in% unique(res$city)) > 0) {
      stop("algum nome de municipio em 'city' invalido ou ainda nao ha dados/casos para essa cidade")
    }
    if (sum(!uf %in% unique(res$state) > 0)) {
      stop("algum nome de estado em 'state' invalido ou ainda nao ha dados/casos para essa cidade")
    }
    if (!is.null(cidade) & !is.null(uf)) {
      res <- res %>% dplyr::filter(.data$state %in% uf & 
                                     .data$city %in% cidade)
    }
  }
  else {
    res <- res
  }
  if (!is.null(ibge_cod)) {
    if (sum(!ibge_cod %in% unique(res$city_ibge_code)) > 
        0) {
      stop("algum codigo de municipio ou estado 'ibge_code' invalido")
    }
    else {
      res <- res %>% dplyr::filter(.data$city_ibge_code %in% 
                                     ibge_cod)
    }
  }
  else {
    res <- res
  }
  if (is.null(cidade) & is.null(ibge_cod) & !is.null(uf)) {
    res <- res %>% dplyr::filter(.data$state %in% uf)
  }
  if (is.null(cidade) & is.null(ibge_cod) & is.null(uf)) {
    res <- res
  }
  if (by_uf == TRUE) {
    res <- res %>% filter(.data$place_type == "state")
  }
  res$date <- as.Date(res$date)
  res$state <- as.factor(res$state)
  if (save) {
    message(paste0("salvando ", filename, ".csv em ", 
                   dir))
    if (!dir.exists(dir)) 
      dir.create(dir)
    utils::write.csv(res, paste0(dir, "/", filename, 
                                 ".csv"), row.names = FALSE)
    utils::write.csv(metadado, paste0(dir, "/", filename, 
                                      "_metadado", ".csv"), row.names = FALSE)
  }
  return(res)
}

dad <- get_cor()

Selecionando o Estado

st2 <- subset(dad, place_type == "state")
st2$state <- iconv(st2$state, "UTF-8")


st2 %<>% group_by(state) %>% mutate(cum_cases = cumsum(last_available_confirmed))

BA <- st2 %>% filter(state == "BA") %>% arrange(date)
BAn <-  BA %>%
  select(c(state, date, new_deaths)) %>% arrange(date) %>%
  gather(key=type, value=count, -c(state, date))


Infectados <- BAn$count
inicio <- min(BAn$date)
dia <- 1:(length(Infectados))
Day <- inicio+dia


ab <- zoo(Infectados, seq(from = inicio, to = last(BAn$date), by = 1))

sm <- ma(ab,order=7)
BAn$mm <- sm
names(BAn)[5] <- "mm"

Gráfico da Média Móvel do Estado

BAn %>% ggplot() + geom_bar(aes(x=date, y=count, fill="Casos"), stat = "identity", position = position_dodge(1))+
  ggtitle(paste(BAn$state[1])) +
  labs(subtitle = paste("Média móvel de 7 dias = ",round(last(na.omit(sm)),0), "óbitos")) +
  geom_line(aes(x=date,y=mm, fill="Média Movel"), color="blue", size=1.5) + 
  #  ylim(0, 150)+
  ylab("Óbitos") + 
  xlab("")+
  scale_x_date(
    date_minor_breaks = "1 day",
    breaks = "2 week",
    date_labels = "%d-%b-%Y") + 
  theme_classic() + 
  theme(legend.position = "none",
        text = element_text(size = 10),
        axis.text.x = element_text(angle = 45, hjust = 1)) 

Selecionando o Município

ios2 <- dad %>% filter(city == "Ilhéus") %>% arrange(date)

iosn <-  ios2 %>%
  select(c(city, date, new_confirmed)) %>% arrange(date) %>%
  gather(key=type, value=count, -c(city, date))

Infectados <- iosn$count
inicio <- min(iosn$date)
dia <- 1:(length(Infectados))
Day <- inicio+dia


ab <- zoo(Infectados, seq(from = inicio, to = last(iosn$date), by = 1))

sm <- ma(ab,order=7)

iosn$mm <- sm
names(iosn)[5] <- "mm"

Gráfico da Média Móvel de Ilhéus

iosn %>% ggplot() + geom_bar(aes(x=date, y=count, fill="Casos"), stat = "identity", position = position_dodge(1))+
  ggtitle(paste(iosn$city[1])) +
  labs(subtitle = paste("Média móvel de 7 dias = ",round(last(na.omit(sm)),0), "casos"),
       caption = paste("Cid Póvoas @cidedson \n Fonte: Secretaria de Saúde do Estado - ", ios2$state)) +
  geom_line(aes(x=date,y=mm, fill="Média Movel"), color="blue", size=1.5) + 
  ylim(0, round(max(iosn$count, na.rm=T),0))+
  ylab("Casos") + 
  xlab("")+
  scale_x_date(
    date_minor_breaks = "1 day",
    breaks = "2 week",
    date_labels = "%d-%b-%Y") + 
  theme_classic() + 
  theme(legend.position = "none",
        text = element_text(size = 10),
        axis.text.x = element_text(angle = 45, hjust = 1))