# Suppress Warnings For a Clean 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'
titanic = pd.read_csv(url)
print(titanic.shape)
print(titanic.head(3))

# Data setup (Iris Dataset)
url = 'https://raw.githubusercontent.com/uiuc-cse/data-fa14/gh-pages/data/iris.csv'
iris = pd.read_csv(url)
print(iris.shape)
print(iris.head(3))

# Look for missing values in Titanic
titanic.isnull().sum()

# Look for missing values in Iris
iris.isnull().sum()

# Fill missing ages in Titanic with median age
titanic['Age'] = titanic['Age'].fillna(titanic['Age'].median())

# Fill missing embarked values with most common port
titanic['Embarked'] = titanic['Embarked'].fillna(titanic['Embarked'].mode()[0])

# Confirm there are no more missing values
titanic.isnull().sum()

# Quick summary statistics for Titanic
titanic.describe()

# Count flower species in Iris dataset
iris['species'].value_counts()

# Plot survival rate by sex in Titanic
import seaborn as sns
import matplotlib.pyplot as plt
sns.barplot(x='Sex', y='Survived', data=titanic)
plt.title('Survival Rate by Sex')
plt.show()

# Encode Sex as 0 for male, 1 for female
titanic['Sex'] = titanic['Sex'].map({'male': 0, 'female': 1})
titanic[['Sex']].head(3)

# One-hot encode the Embarked column
titanic = pd.get_dummies(titanic, columns=['Embarked'], drop_first=True)
titanic.head(3)

# Create a child flag: 1 if Age < 13, else 0
titanic['Child'] = (titanic['Age'] < 13).astype(int)
titanic[['Age', 'Child']].head(5)

# Practice interactive input: Guess a survivor
name = input("Type the name of a passenger from the preview above (e.g., Allen, Miss. Elisabeth Walton): ")
survived = titanic.loc[titanic['Name'].str.contains(name), 'Survived']
if not survived.empty:
    print("Survived:" if survived.values[0] == 1 else "Did not survive.")
else:
    print("Name not found.")