NICAR2024.Rmd

---
title: "Baby Names"
author: "Lucia Walinchus"
date: "6/23/2020"
output: html_document
---

Bringing in required packages

```{r}
library(ggplot2)
library(tidyverse) #includes dplyr
library(DT)
library(babynames)
```

## Baby Names


The babynames package brings in names from the [Social Security Administration](https://www.ssa.gov/oact/babynames/limits.html)

Alternatively, you can download this file yourself which I prefer as it's more current. 


Bringing in the dataframe

```{r}
US_Names <- babynames

summary(US_Names)

```


Learning count

```{r}
US_Names %>% 
  count(name)
```

Learning arrange
```{r}
US_Names %>% 
  count(name) %>% 
  arrange(desc(n))
```


Learning filter (and datatable)

```{r}
US_Names %>% 
  filter(year==2010) %>% 
  datatable()
```


Learning select

```{r}
US_Names %>% 
  select(name,prop) %>% 
  arrange(desc(prop))
```


Learning mutate

```{r}
popularity <- US_Names %>% 
  mutate(popularity=rank(-n, ties.method= "first")) %>% 
  arrange(popularity)

head(popularity)
```


Learning summarize/group_by
```{r}
top_names <- US_Names %>% 
  group_by(name) %>% 
  summarize(total=sum(n)) %>% 
  arrange(desc(total))

datatable(top_names)
```


The real power of R: grouping and ungrouping these

Learning summarize/group_by
```{r}
top_names_by_sex <- US_Names %>% 
  group_by(name,sex) %>% 
  summarize(total=sum(n)) %>% 
  ungroup() %>% 
  group_by(name) %>% 
  mutate(percent=total/sum(total))
  

datatable(top_names_by_sex)
```


How many male versus female Averys?

```{r}
top_names_by_sex %>% 
  filter(name=="Avery") %>% 
  ggplot( aes(x=sex, y=percent, fill=sex))+
  geom_col(stat="identity")
```






Basics of ggplot

```{r}
top_names %>% 
  slice_head(n= 10) %>% 
ggplot( aes(x= reorder(name, -total), y=total))+ #NOT %>%   
  geom_col()
```


```{r}
Marys <- US_Names %>% 
  filter(name=="Mary" & sex == "F")

ggplot(Marys, aes(year, n))+
  geom_point()+
  theme(axis.text.x = element_text(angle = 45, vjust =1.2, hjust = 1.1))+
  labs(title = "Children Named 'Mary' in the \n United States per Year", )

```


```{r}
Leslies <- US_Names %>% 
  filter(name=="Leslie")

ggplot(Leslies, aes(year, n, fill = sex))+
  geom_bar(stat = "identity")+
  theme(axis.text.x = element_text(angle = 45, vjust =1.2, hjust = 1.1))+
  labs(title = "Children Named 'Leslie' in the United States per Year")

```

```{r}
LuciaLucy <- US_Names %>% 
  filter(name=="Lucia"| name=="Lucy"& sex=="F")

ggplot(LuciaLucy, aes(year, n, color = name))+
  geom_point(stat = "identity")+
  theme(axis.text.x = element_text(angle = 45, vjust =1.2, hjust = 1.1))+
  labs(title = "Children Named 'Lucy' and 'Lucia' in the United States per Year")
```


```{r}
ManyNames <- US_Names %>% 
  filter(name=="Tyrion" |
           name=="Kaleesi"|
           name=="Shae"|
           name=="Arya"|
           name=="Bran"|
           name=="Catelyn"|
           name=="Joffrey"|
           name=="Sansa"|
           name=="Brienne")

ggplot(ManyNames, aes(year, n, fill=name))+
  geom_bar(stat = "identity")+
  facet_wrap(~name, scales = "free")+
  theme(axis.text.x = element_text(angle = 45, vjust =1.2, hjust = 1.1))+
  labs(title = "US Baby Names",subtitle = "Sample of 9 popular baby names in the US per year")

```




Your turn: use your own name! 

```{r}
Lucias <- US_Names %>% 
  filter(name=="Lucia"& sex == "F")

ggplot(Lucias, aes(year, n))+
  geom_point()+
  theme(axis.text.x = element_text(angle = 45, vjust =1.2, hjust = 1.1))+
  labs(title = "Number of Lucias born each year", caption="I am having so much fun learning R")

#ggsave("Lucia.jpg", plot=last_plot())
```