w12_PrgL.qmd

---
title: "TidyTuesday 2023 w12 Programming Languages"
author: "Federica Gazzelloni"
execute:  
  comments: ""
  eval: true
  echo: true
  warning: false
  message: false
---

```{r}
library(tidyverse)
tuesdata <- tidytuesdayR::tt_load(2023, week = 12)
```
```{r}
languages <- tuesdata$languages
```

```{r}
write_csv(languages,"languages.csv")
```



```{r}
languages%>%head
```

```{r}
languages%>%names
```

```{r}
df <- languages%>%
  arrange(appeared)%>%
  select(pldb_id,appeared,type,language_rank,number_of_users)
df
```


```{r}
ggplot(df,aes(appeared,language_rank))+
  geom_point()
```

```{r}
df %>%
  filter(appeared>1900)%>%
ggplot(aes(appeared,language_rank))+
  geom_point()+
  scale_y_reverse()
```

```{r}
df %>%
  count(type,sort = TRUE)%>%
  mutate(pct=round(n/sum(n)*100,2))
```


```{r}
df %>%
  arrange(-appeared)%>%
  filter(between(appeared,2021,2023))%>%#count(type)
  mutate(appeared=as.factor(appeared))
```


```{r}
df %>%
  arrange(-appeared)%>%
  filter(between(appeared,2021,2023))%>%#count(type)
  mutate(appeared=as.factor(appeared))%>%
  ggplot(aes(appeared,number_of_users,fill=type))+
  geom_col()+
  labs(title="New Language tools")
```
```{r}
df%>%
  group_by(appeared)%>%
  reframe(n_languages=n(),pldb_id,type,avg=mean(number_of_users))%>%
  filter(between(appeared,2000,2023)) %>%
  ggplot(aes(appeared,n_languages))+
  geom_point()+
  geom_line()+
  geom_segment(aes(x=appeared,xend=appeared,y=0,yend=n_languages,
                   color=n_languages),
               size=6)+
  geom_text(aes(label=type),check_overlap = TRUE,vjust=-0.5)
```