library(tidyverse)
## -- Attaching packages ------------------------------------------------------- tidyverse 1.2.1 --
## v ggplot2 3.1.0     v purrr   0.2.5
## v tibble  1.4.2     v dplyr   0.7.6
## v tidyr   0.8.2     v stringr 1.3.1
## v readr   1.1.1     v forcats 0.3.0
## -- Conflicts ---------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(titanic)
library(ggplot2)
library(dplyr)
df <- dplyr::bind_rows(titanic::titanic_test,
                 titanic::titanic_train)

df <- as_tibble(df)


filter(df, Survived == 1)
## # A tibble: 342 x 12
##    PassengerId Pclass Name  Sex     Age SibSp Parch Ticket  Fare Cabin
##          <int>  <int> <chr> <chr> <dbl> <int> <int> <chr>  <dbl> <chr>
##  1           2      1 Cumi~ fema~    38     1     0 PC 17~ 71.3  C85  
##  2           3      3 Heik~ fema~    26     0     0 STON/~  7.92 ""   
##  3           4      1 Futr~ fema~    35     1     0 113803 53.1  C123 
##  4           9      3 John~ fema~    27     0     2 347742 11.1  ""   
##  5          10      2 Nass~ fema~    14     1     0 237736 30.1  ""   
##  6          11      3 Sand~ fema~     4     1     1 PP 95~ 16.7  G6   
##  7          12      1 Bonn~ fema~    58     0     0 113783 26.6  C103 
##  8          16      2 "Hew~ fema~    55     0     0 248706 16    ""   
##  9          18      2 Will~ male     NA     0     0 244373 13    ""   
## 10          20      3 Mass~ fema~    NA     0     0 2649    7.22 ""   
## # ... with 332 more rows, and 2 more variables: Embarked <chr>,
## #   Survived <int>
total_vivos <- filter(df, Survived == 1)

filter(df, Age < 15)
## # A tibble: 109 x 12
##    PassengerId Pclass Name  Sex     Age SibSp Parch Ticket   Fare Cabin
##          <int>  <int> <chr> <chr> <dbl> <int> <int> <chr>   <dbl> <chr>
##  1         897      3 Sven~ male     14     0     0 7538     9.22 ""   
##  2         913      3 Olse~ male      9     0     1 C 173~   3.17 ""   
##  3         947      3 Rice~ male     10     4     1 382652  29.1  ""   
##  4         956      1 Ryer~ male     13     2     2 PC 17~ 262.   B57 ~
##  5         972      3 Boul~ male      6     1     1 2678    15.2  ""   
##  6         981      2 Well~ male      2     1     1 29103   23    ""   
##  7        1009      3 Sand~ fema~     1     1     1 PP 95~  16.7  G6   
##  8        1012      2 Watt~ fema~    12     0     0 C.A. ~  15.8  ""   
##  9        1032      3 Good~ fema~    10     5     2 CA 21~  46.9  ""   
## 10        1046      3 Aspl~ male     13     4     2 347077  31.4  ""   
## # ... with 99 more rows, and 2 more variables: Embarked <chr>,
## #   Survived <int>
niñes_total <- filter(df, Age < 15)

filter (df, Sex == "female")
## # A tibble: 466 x 12
##    PassengerId Pclass Name  Sex     Age SibSp Parch Ticket  Fare Cabin
##          <int>  <int> <chr> <chr> <dbl> <int> <int> <chr>  <dbl> <chr>
##  1         893      3 Wilk~ fema~    47     1     0 363272  7    ""   
##  2         896      3 Hirv~ fema~    22     1     1 31012~ 12.3  ""   
##  3         898      3 Conn~ fema~    30     0     0 330972  7.63 ""   
##  4         900      3 Abra~ fema~    18     0     0 2657    7.23 ""   
##  5         904      1 Snyd~ fema~    23     1     0 21228  82.3  B45  
##  6         906      1 Chaf~ fema~    47     1     0 W.E.P~ 61.2  E31  
##  7         907      2 del ~ fema~    24     1     0 SC/PA~ 27.7  ""   
##  8         910      3 Ilma~ fema~    27     1     0 STON/~  7.92 ""   
##  9         911      3 "Ass~ fema~    45     0     0 2696    7.22 ""   
## 10         914      1 Fleg~ fema~    NA     0     0 PC 17~ 31.7  ""   
## # ... with 456 more rows, and 2 more variables: Embarked <chr>,
## #   Survived <int>
mujeres_total <- filter (df, Sex == "female")

En el barco iban

ggplot(df) +
  geom_count(mapping = aes(x = Sex, y = factor (Pclass), color = factor (..n..))) +
ggtitle("Total de pasajeros por sexo y clase")

ggplot(df) +
  geom_jitter(mapping = aes(x = Fare, y = Sex, color = factor(Survived))) +
  ggtitle("Muertos y sobrevivientes según precio del ticket y sexo")
## Warning: Removed 1 rows containing missing values (geom_point).

ggplot(df) +
geom_jitter(mapping = aes(x = Sex, y = Pclass, color = factor (Survived))) + 
  ggtitle("Sobrevivientes y muertos por clase y sexo")

ggplot(mujeres_total) +
  geom_count(mapping = aes(x = factor (Survived) , y =  factor (Pclass), color = factor (..n..))) +
ggtitle("Mujeres vivas y muertas por clase")

ggplot(niñes_total) +
  geom_bar(mapping = aes(x = factor (Survived), fill = factor(Pclass))) +
  ggtitle("Sobrevivientes y muertos menores de 15 años por clase")

ggplot(data = df, mapping = aes(x = Pclass, fill = factor (Sex))) +
  geom_bar() +
  facet_wrap(~ Survived) +
ggtitle("Cantidad de muertos y sobrevivientes según sexo y clase")