library(tidyverse)

## ── Attaching packages ──────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.0.0     ✔ purrr   0.2.5
## ✔ tibble  1.4.2     ✔ dplyr   0.7.6
## ✔ tidyr   0.8.1     ✔ stringr 1.3.1
## ✔ readr   1.1.1     ✔ forcats 0.3.0

## ── Conflicts ─────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(dplyr)

library("babynames", lib.loc="~/R/x86_64-pc-linux-gnu-library/3.5")
str(babynames)

## Classes 'tbl_df', 'tbl' and 'data.frame':    1858689 obs. of  5 variables:
##  $ year: num  1880 1880 1880 1880 1880 1880 1880 1880 1880 1880 ...
##  $ sex : chr  "F" "F" "F" "F" ...
##  $ name: chr  "Mary" "Anna" "Emma" "Elizabeth" ...
##  $ n   : int  7065 2604 2003 1939 1746 1578 1472 1414 1320 1288 ...
##  $ prop: num  0.0724 0.0267 0.0205 0.0199 0.0179 ...

summary(babynames)

##       year          sex                name                 n          
##  Min.   :1880   Length:1858689     Length:1858689     Min.   :    5.0  
##  1st Qu.:1950   Class :character   Class :character   1st Qu.:    7.0  
##  Median :1983   Mode  :character   Mode  :character   Median :   12.0  
##  Mean   :1973                                         Mean   :  183.4  
##  3rd Qu.:2002                                         3rd Qu.:   32.0  
##  Max.   :2015                                         Max.   :99680.0  
##       prop          
##  Min.   :2.260e-06  
##  1st Qu.:3.900e-06  
##  Median :7.350e-06  
##  Mean   :1.391e-04  
##  3rd Qu.:2.324e-05  
##  Max.   :8.155e-02

babynames %>%
  filter(name == 'Mary') -> m
str(m)

## Classes 'tbl_df', 'tbl' and 'data.frame':    266 obs. of  5 variables:
##  $ year: num  1880 1880 1881 1881 1882 ...
##  $ sex : chr  "F" "M" "F" "M" ...
##  $ name: chr  "Mary" "Mary" "Mary" "Mary" ...
##  $ n   : int  7065 27 6919 29 8148 30 8012 32 9217 36 ...
##  $ prop: num  0.072384 0.000228 0.069991 0.000268 0.070426 ...

 m %>% ggplot(aes(x=year,y=n)) +
   geom_point()

babynames %>%
  filter(name == 'Ibrahim') -> i
str(i)

## Classes 'tbl_df', 'tbl' and 'data.frame':    52 obs. of  5 variables:
##  $ year: num  1954 1961 1963 1964 1967 ...
##  $ sex : chr  "M" "M" "M" "M" ...
##  $ name: chr  "Ibrahim" "Ibrahim" "Ibrahim" "Ibrahim" ...
##  $ n   : int  5 5 6 10 9 6 10 13 12 27 ...
##  $ prop: num  2.42e-06 2.32e-06 2.90e-06 4.93e-06 5.06e-06 ...

 i %>% ggplot(aes(x=year,y=n)) +
   geom_point()

babynames %>%
  filter(name == 'Jordan') -> j
str(j)

## Classes 'tbl_df', 'tbl' and 'data.frame':    194 obs. of  5 variables:
##  $ year: num  1880 1881 1882 1883 1884 ...
##  $ sex : chr  "M" "M" "M" "M" ...
##  $ name: chr  "Jordan" "Jordan" "Jordan" "Jordan" ...
##  $ n   : int  23 18 12 17 25 17 9 12 18 7 ...
##  $ prop: num  1.94e-04 1.66e-04 9.83e-05 1.51e-04 2.04e-04 ...

 j %>% ggplot(aes(x=year,y=n)) +
   geom_point()

 j %>% ggplot(aes(x=year,y=n,color=sex)) +
   geom_point()

babynames %>%
  filter(name == 'Harold') -> h
str(h)

## Classes 'tbl_df', 'tbl' and 'data.frame':    230 obs. of  5 variables:
##  $ year: num  1880 1881 1882 1883 1884 ...
##  $ sex : chr  "M" "M" "M" "M" ...
##  $ name: chr  "Harold" "Harold" "Harold" "Harold" ...
##  $ n   : int  113 120 127 108 191 201 224 279 298 340 ...
##  $ prop: num  0.000954 0.001108 0.001041 0.00096 0.001556 ...

 h %>% ggplot(aes(x=year,y=n,color=sex)) +
   geom_point()