# Suppress warnings for cleaner output
import warnings
import numpy as np
np.random.seed(42)
warnings.filterwarnings("ignore")
 
 

# Data setup (Titanic Dataset)
import pandas as pd
url = 'https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv'
df = pd.read_csv(url)
print(df.shape)
print(df.head(3))

# Basic pivot: mean age by passenger class
pivot_simple = df.pivot_table(values='Age', index='Pclass', aggfunc='mean')
print(pivot_simple)

# Multiple aggregations: survival rate and average fare by gender
pivot_mult = df.pivot_table(values=['Survived', 'Fare'], index='Sex',
                            aggfunc={'Survived': 'mean', 'Fare': 'mean'})
print(pivot_mult)

# Pivot with both index and columns
pivot_grid = df.pivot_table(values='Survived', index='Sex', columns='Pclass', aggfunc='mean')
print(pivot_grid)

# Filling missing values with zeros
pivot_nas = df.pivot_table(values='Survived', index='Sex', columns='Embarked', aggfunc='mean', fill_value=0)
print(pivot_nas)

# Counting passengers per class and gender
pivot_count = df.pivot_table(values='Name', index='Pclass', columns='Sex', aggfunc='count')
print(pivot_count)

# Custom aggregation: minimum and maximum ages by embarked port
pivot_custom = df.pivot_table(values='Age', index='Embarked', aggfunc=['min', 'max'])
print(pivot_custom)

# Basic crosstab: count of passengers by class and gender
ctab = pd.crosstab(index=df['Pclass'], columns=df['Sex'])
print(ctab)

# Crosstab with proportions instead of counts
ctab_prop = pd.crosstab(df['Sex'], df['Pclass'], normalize='index')
print(ctab_prop.round(2))

# Pivot table with multiple values: survival by class and embark port
pivot_combined = df.pivot_table(values='Survived', index='Pclass', columns='Embarked', aggfunc='mean')
print(pivot_combined.round(2))

# Crosstab for family size: groups based on siblings/spouse count
ctab_family = pd.crosstab(df['SibSp'], df['Survived'])
print(ctab_family)

# Quick visualization of a pivot table
import matplotlib.pyplot as plt
pivot_grid.plot(kind='bar')
plt.title('Survival Rate by Gender and Class')
plt.xlabel('Sex')
plt.ylabel('Survival Rate')
plt.legend(title='Pclass')
plt.tight_layout()
plt.show()