# Always suppress warnings to keep output tidy
import warnings; warnings.filterwarnings('ignore')
import numpy as np
np.random.seed(42)

# 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))

# List Titanic columns and their data types
print(df.dtypes)

# How many passengers survived?
survived_count = df['Survived'].value_counts()
print(survived_count)

# Calculate the survival rate
rate = df['Survived'].mean()
print(f'Survival rate: {rate:.2%}')

# Count missing values in each column
print(df.isnull().sum())

# Fill missing ages with the median value
median_age = df['Age'].median()
df['Age'].fillna(median_age, inplace=True)
print(df['Age'].isnull().sum())

# Drop columns we do not need for a simple analysis
cols_to_drop = ['Cabin', 'Ticket', 'Name']
df.drop(columns=cols_to_drop, inplace=True)
print(df.columns)

# What percent of women survived?
female_survival = df[df['Sex'] == 'female']['Survived'].mean()
print(f'Female survival rate: {female_survival:.2%}')

# What percent of children under 16 survived?
children_survival = df[df['Age'] < 16]['Survived'].mean()
print(f'Child survival rate (age < 16): {children_survival:.2%}')

# Comparing survival by passenger class
print(df.groupby('Pclass')['Survived'].mean())

# Mini visualization: survival rate by sex
import matplotlib.pyplot as plt
df.groupby('Sex')['Survived'].mean().plot(kind='bar')
plt.title('Survival Rate by Sex')
plt.ylabel('Survival Rate')
plt.show()

# Which family groupings had the most survivors?
df['FamilySize'] = df['SibSp'] + df['Parch'] + 1
print(df.groupby('FamilySize')['Survived'].sum().sort_values(ascending=False).head())

# Create a new feature: Was the fare high?
df['HighFare'] = df['Fare'] > 100
print(df['HighFare'].value_counts())

# Challenge: Try this yourself!
avg_fare_women_firstclass = df[(df['Sex'] == 'female') & (df['Pclass'] == 1)]['Fare'].mean()
print(f'Average fare paid by women in first class: {avg_fare_women_firstclass:.2f}')