DAY2HW

train <- read.csv("~/Downloads/train.csv")
library(visdat)
vis_dat(train)

stargazer(
  train[, -c(1, 2)],                             # drop PassengerId & Survived
  type             = "text",
  title            = "Table 1: Titanic Summary Statistics",
  summary.stat     = c("n", "mean", "sd", "min", "max"),
  column.labels    = c("N", "Mean", "SD", "Min", "Max"),
  covariate.labels = c(
    "Passenger Class (1 = 1st, 2 = 2nd, 3 = 3rd)",
    "Age (years)",
    "Siblings/Spouses Aboard",
    "Parents/Children Aboard",
    "Fare (£)"
  ),
  digits           = 2,
  align            = TRUE,
  no.space         = TRUE,
  add.lines        = list(
    c("Missing Age", sum(is.na(train$Age))),
    c("Missing Cabin", sum(is.na(train$Cabin)))
  ),
  notes            = "Source: Kaggle Titanic dataset (N = 891)."
)

Table 1: Titanic Summary Statistics
==========================================================================
Statistic                                    N  Mean  St. Dev. Min   Max  
--------------------------------------------------------------------------
Passenger Class (1 = 1st, 2 = 2nd, 3 = 3rd) 891 2.31    0.84    1     3   
Age (years)                                 714 29.70  14.53   0.42 80.00 
Siblings/Spouses Aboard                     891 0.52    1.10    0     8   
Parents/Children Aboard                     891 0.38    0.81    0     6   
Fare (£)                                    891 32.20  49.69   0.00 512.33
--------------------------------------------------------------------------
Source: Kaggle Titanic dataset (N = 891).