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

# 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)  # rows and columns
print(df.head(3))  # a quick look at the data

# Check total and percentage of missing values per column
missing_counts = df.isnull().sum()
missing_percent = (missing_counts / len(df)) * 100
missing_summary = pd.DataFrame({'MissingCount': missing_counts, 'Percent': missing_percent.round(2)})
print(missing_summary[missing_summary.MissingCount > 0])

# Visualize missing values using a heatmap
import seaborn as sns
import matplotlib.pyplot as plt
plt.figure(figsize=(8, 4))
sns.heatmap(df.isnull(), cbar=False, cmap='viridis')
plt.title('Where is data missing?')
plt.show()

# Fill missing Age with median (safer for skewed data)
age_median = df['Age'].median()
df['Age'].fillna(age_median, inplace=True)
print(f"Filled missing Age with: {age_median}")

# Fill missing Embarked values with the most common (mode)
mode_embarked = df['Embarked'].mode()[0]
df['Embarked'].fillna(mode_embarked, inplace=True)
print(f"Filled missing Embarked with: {mode_embarked}")

# Drop the Cabin column (too many missing values)
df.drop('Cabin', axis=1, inplace=True)
print('Cabin column dropped. Too much missing data.')

# Boxplot to visualize outliers for Age and Fare
plt.figure(figsize=(10, 4))
plt.subplot(1, 2, 1)
sns.boxplot(x=df['Age'])
plt.title('Age Boxplot')
plt.subplot(1, 2, 2)
sns.boxplot(x=df['Fare'])
plt.title('Fare Boxplot')
plt.tight_layout()
plt.show()

# Find outliers in Fare using the interquartile range (IQR) rule
Q1 = df['Fare'].quantile(0.25)
Q3 = df['Fare'].quantile(0.75)
IQR = Q3 - Q1
fare_lower = Q1 - 1.5 * IQR
fare_upper = Q3 + 1.5 * IQR
outliers = df[(df['Fare'] < fare_lower) | (df['Fare'] > fare_upper)]
print(f"Number of Fare outliers: {len(outliers)}")

# Bin Age into categories (child, teen, adult, senior)
bins = [0, 12, 18, 59, 120]
labels = ['child', 'teen', 'adult', 'senior']
df['AgeGroup'] = pd.cut(df['Age'], bins=bins, labels=labels)
print(df[['Age', 'AgeGroup']].head(8))

# Preview cleaned data
print(df.head(5))

# Practice: Enter a custom Age for a missing spot
df.loc[df.index[1], 'Age'] = np.nan
missing_index = df['Age'].isnull().idxmax() if df['Age'].isnull().sum() > 0 else None
if missing_index is not None:
    new_age = input("Enter a value to fill in the missing Age: ")
    df.loc[missing_index, 'Age'] = float(new_age)
    print(f"Age at index {missing_index} set to {new_age}")
else:
    print("No missing Age value left. Well done!")