---
title: "Exercice 2 Module 3"
author: "Da Mota Mégane"
date: "02/03/2022"
output: html_document
---


```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

## Préparation des données : 
Etude de la varicelle, étude des données du réseau sentinelle. L'URL est :

```{r}
data_url = "http://www.sentiweb.fr/datasets/incidence-PAY-7.csv"
```

## Téléchargement :
```{r}
data = read.csv(data_url, skip=1)
```

```{r}
head(data)
tail(data)
```

```{r}
na_records = apply(data, 1, function (x) any(is.na(x)))
data[na_records,]
```

```{r}
class(data$week)
class(data$inc)
```

```{r}
library(parsedate)
```

```{r}
convert_week = function(w) {
	ws = paste(w)
	iso = paste0(substring(ws, 1, 4), "-W", substring(ws, 5, 6))
	as.character(parse_iso_8601(iso))
}
```

```{r}
data$date = as.Date(convert_week(data$week))
```

```{r}
class(data$date)
```

```{r}
data = data[order(data$date),]
```

```{r}
all(diff(data$date) == 7)
```

```{r}
plot(data$date, data$inc, type="l", xlab="Date", ylab="Incidence hebdomadaire")
```
```{r}
with(tail(data, 200), plot(date, inc, type="l", xlab="Date", ylab="Incidence hebdomadaire"))
```
```{r}
pic_annuel = function(annee) {
      debut = paste0(annee-1,"-09-01")
      fin = paste0(annee,"-09-01")
      semaines = data$date > debut & data$date <= fin
      sum(data$inc[semaines], na.rm=TRUE)
      }
```

```{r}
annees = 1991:2021
```

```{r}
inc_annuelle = data.frame(annee = annees,
                          incidence = sapply(annees, pic_annuel))
head(inc_annuelle)
```

```{r}
plot(inc_annuelle, type="p", xlab="Année", ylab="Incidence annuelle")
```

```{r}
head(inc_annuelle[order(-inc_annuelle$incidence),])
```