# Data setup (Titanic Dataset)
import warnings; warnings.filterwarnings('ignore')
import pandas as pd
import numpy as np
np.random.seed(42)
url = 'https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv'
df = pd.read_csv(url)
print(df.shape)
print(df.head(3))

# Checking columns in our Titanic DataFrame
print(df.columns.tolist())

# Applying a built-in function to a column: get the length of each passenger's name
df['name_length'] = df['Name'].apply(len)
df[['Name', 'name_length']].head(3)

# Using apply with a custom function: check if a passenger is a child (under 16)
def is_child(age):
    if pd.isnull(age):
        return None
    return age < 16

df['is_child'] = df['Age'].apply(is_child)
df[['Name', 'Age', 'is_child']].head(5)

# Quickly check who paid over $50 for a ticket using lambda
df['BigSpender'] = df['Fare'].apply(lambda x: x > 50 if pd.notnull(x) else False)
df[['Fare', 'BigSpender']].head(8)

# Apply a function across several columns using axis=1
def family_size(row):
    return row['SibSp'] + row['Parch'] + 1  # Include self

df['FamilySize'] = df.apply(family_size, axis=1)
df[['Name', 'SibSp', 'Parch', 'FamilySize']].head(5)

# Using applymap: Apply a function to every element in a DataFrame
df2 = df[['SibSp', 'Parch']].copy()
df2_applied = df2.applymap(lambda x: x * 10)
print(df2_applied.head())

# Using agg to summarize with multiple functions
df[['Fare', 'Age']].agg(['min', 'max', 'mean'])

# Using transform to scale the Fare column
fare_mean = df['Fare'].mean()
fare_std = df['Fare'].std()
df['Fare_zscore'] = df['Fare'].transform(lambda x: (x - fare_mean) / fare_std)
df[['Fare', 'Fare_zscore']].head(5)

# Combining apply with filtering: find the longest name among survivors
survivors = df[df['Survived'] == 1]
longest_name = survivors['Name'].apply(len).max()
name_row = survivors[survivors['Name'].apply(len) == longest_name][['Name', 'Survived']]
print(name_row)

# Challenge: Prompt user to type a minimum fare and flag passengers above it
min_fare = float(input('Enter a minimum fare: '))
df['BigSpenderCustom'] = df['Fare'].apply(lambda f: f > min_fare if pd.notnull(f) else False)
print(df[['Fare', 'BigSpenderCustom']].head())

# Real-world use: flag cabin letters (A, B, etc.) with apply and lambda
def cabin_letter(cabin):
    if pd.isnull(cabin):
        return None
    return str(cabin)[0]

df['CabinLetter'] = df['Cabin'].apply(cabin_letter)
df[['Cabin', 'CabinLetter']].head(8)

# Common error demonstration: applying a function the wrong way
try:
    df.apply(len)
except Exception as e:
    print('Caught:', e)
    

# Best Practice: Use vectorized pandas methods when possible
df['name_length_vec'] = df['Name'].str.len()
df[['Name', 'name_length_vec', 'name_length']].head(3)

# Who survived with a large family? Using our FamilySize feature
print(df.groupby('Survived')['FamilySize'].mean())

# Combining multiple apply-created features in a scatter plot
import matplotlib.pyplot as plt
plt.figure(figsize=(7,4))
plt.scatter(df['FamilySize'], df['Fare'], c=df['Survived'], cmap='coolwarm', alpha=0.5)
plt.xlabel('Family Size')
plt.ylabel('Fare')
plt.title('Fare vs Family Size (Color: Survived)')
plt.show()