The Titanic, with over 2000 passengers on board, including hundreds of emigrants to the US, as well as some of the world's richest, sank in 1912. The `seaborn`

library provides a smaller-sized, anonymized data set of Titanic's passengers. Without identifying information, we can't tell the poor immigrant from the wealthy, yet the data manages to tell a story in other ways. Your task in this exercise is to answer a series of questions from the data, beginning with the mundane and ending with who survived.

In [1]:

```
import numpy as np
import pandas as pd
import seaborn
```

In [2]:

```
t = seaborn.load_dataset('titanic')
t.head()
```

Out[2]:

**Tasks:** The exercise is to answer the following questions.

- How many passengers are described in the data set?

- How many distinct values are in
`who`

column?

- How many missing values do you find in each data column?

- Does the data contain passengers over 60 old? How many?

- What is the passenger age distribution? (Plot it.)

- What are the 3-quantiles of the passenger age distribution?

(Finite samples are divided into $q$ subsets of nearly equal sizes by $q$-quantiles. The 2-quantile is the median.)

- How will you drop all passengers with no
`embarked`

data?

- What is the average, minimum, and maximum fares paid by the passengers?

- What are the proportions of passengers in different classes?

- What is the female to male ratio in each travel class?

- What fraction survived?

(This fraction is sometimes called the *survival rate* - although it is an improper name in the sense that there is no "rate" to speak of here; the question is to compute a dimensionless fraction.)

- Are the survival rates of male and female passengers different?

- Are the survival rates of first, second, and third class passengers different?

- How can one print a table of survival rate dependencies on class and gender?

- How can one print a table with number of survivors and average fare for each gender and cabin?