# Let us start by importing the libraries we will use
import warnings
warnings.filterwarnings("ignore")
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# These tools help you load, analyze, and display data

# Data setup
# Let us load the Titanic dataset. It has both categorical and numerical data.
titanic = sns.load_dataset("titanic")
print("Rows, Columns:", titanic.shape)
titanic.head()

# Let us check which columns are categorical
categorical_cols = titanic.select_dtypes(include=["object", "category"]).columns
print("Categorical columns:", list(categorical_cols))

# Let us see which columns are numerical
numerical_cols = titanic.select_dtypes(include=["int", "float"]).columns
print("Numerical columns:", list(numerical_cols))

# Let us peek at the data types for each column
titanic.dtypes

# Let us count the unique values for 'sibsp' and 'parch'
print("sibsp unique values:", titanic['sibsp'].unique())
print("parch unique values:", titanic['parch'].unique())

# Let us check some age and fare values
print("Age samples:", titanic['age'].dropna().unique()[:10])
print("Fare samples:", titanic['fare'].unique()[:10])

# Plotting a bar chart for passenger class (categorical)
sns.countplot(data=titanic, x='pclass')
plt.title('Passenger Count by Class')
plt.xlabel('Class')
plt.ylabel('Number of Passengers')
plt.show()

# Plotting a histogram for passenger age (numerical, continuous)
sns.histplot(data=titanic, x='age', bins=30, kde=True)
plt.title('Distribution of Passenger Ages')
plt.xlabel('Age')
plt.ylabel('Frequency')
plt.show()

# Practice: What type of data is 'sex'?
answer = input("Is 'sex' categorical, discrete, or continuous? ")
if answer.lower() == "categorical":
    print("Correct! 'sex' is categorical.")
else:
    print("Try again: Categorical means labels like male or female.")
    

# Visual summary: Counts per embarkation port (categorical)
sns.countplot(data=titanic, x='embarked')
plt.title('Passengers by Embarkation Port')
plt.xlabel('Embarked Port')
plt.ylabel('Number of Passengers')
plt.show()

# Now, let us see how fare (continuous number) looks by class (categorical group)
sns.boxplot(data=titanic, x='pclass', y='fare')
plt.title('Fare by Passenger Class')
plt.xlabel('Class')
plt.ylabel('Fare')
plt.show()

# Show missing values for categorical and numerical columns
print(titanic[categorical_cols].isnull().sum())
print(titanic[numerical_cols].isnull().sum())