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))

# Check for missing values
df.isnull().sum()

# Fill missing 'Age' values with the median
df['Age'].fillna(df['Age'].median(), inplace=True)

# See unique passenger classes
print(df['Pclass'].unique())

# Group by 'Pclass' and get mean age
pclass_age = df.groupby('Pclass')['Age'].mean()
print(pclass_age)

# Group by 'Sex' and see survival rate
survival_rate = df.groupby('Sex')['Survived'].mean()
print(survival_rate)

# Group by multiple columns: class and sex
survival_by_group = df.groupby(['Pclass', 'Sex'])['Survived'].mean()
print(survival_by_group)

# Find mean, median, and max fare by class
fare_stats = df.groupby('Pclass')['Fare'].agg(['mean', 'median', 'max'])
print(fare_stats)

# Group by 'Embarked' and 'Pclass', counting survivors per group
survivor_counts = df.groupby(['Embarked', 'Pclass'])['Survived'].sum().unstack()
print(survivor_counts)

# Group by 'Sex' and describe ages
age_stats = df.groupby('Sex')['Age'].describe()
print(age_stats)

# Custom aggregation: average fare per survival status and class
def mean_fare(x):
    return round(x.mean(), 2)

fare_grouped = df.groupby(['Survived', 'Pclass'])['Fare'].agg(mean_fare)
print(fare_grouped)

# Filter: Only show groups with more than 100 passengers
sizes = df.groupby('Pclass').filter(lambda x: len(x) > 100)
print(sizes['Pclass'].value_counts())

# Pivot table recreation: survival rate by class and gender
pivot = df.pivot_table(values='Survived', index='Pclass', columns='Sex', aggfunc='mean')
print(pivot)

# Visualize groupby: average age by class
import matplotlib.pyplot as plt
grouped_avg_age = df.groupby('Pclass')['Age'].mean()
grouped_avg_age.plot(kind='bar', color='skyblue')
plt.ylabel('Average Age')
plt.title('Average Age by Passenger Class')
plt.show()

# Youngest and oldest survivor per class
survivors = df[df['Survived'] == 1]
result = survivors.groupby('Pclass')['Age'].agg(['min', 'max'])
print(result)