import pandas as pd

# Sample dataset with mixed types
employees = pd.DataFrame({
    'name': ['Alice', 'Bob', 'Charlie'],
    'age': [25, 30, 35],
    'salary': [50000.0, 60000.5, 55000.0],
    'active': [True, False, True],
    'department': ['Sales', 'IT', 'Marketing']
})

print("📊 Employee Data:")
print(employees)
print()

print("🔍 Column Information:")
print(employees.info())
print()

print("🏷️ Data Types:")
print(employees.dtypes)

import pandas as pd

# Numerical data
sales = pd.DataFrame({
    'product': ['A', 'B', 'C'],
    'price': [10.99, 25.50, 15.75],
    'quantity': [5, 3, 8]
})

print("Sales Data:")
print(sales)
print()

print("💰 Price Column Analysis:")
print(f"Type: {sales['price'].dtype}")
print(f"Average: ${sales['price'].mean():.2f}")
print(f"Total: ${sales['price'].sum():.2f}")
print()

print("📦 Quantity Column Analysis:")
print(f"Type: {sales['quantity'].dtype}")
print(f"Total quantity: {sales['quantity'].sum()}")
print(f"Max quantity: {sales['quantity'].max()}")

import pandas as pd

# Text data
customers = pd.DataFrame({
    'name': ['Alice Johnson', 'Bob Smith', 'Charlie Brown'],
    'city': ['New York', 'Los Angeles', 'Chicago'],
    'email': ['alice@email.com', 'bob@email.com', 'charlie@email.com']
})

print("Customer Data:")
print(customers)
print()

print("📧 Email Column Analysis:")
print(f"Type: {customers['email'].dtype}")
print(f"Unique emails: {customers['email'].nunique()}")
print("Email domains:")
for email in customers['email']:
    domain = email.split('@')[1]
    print(f"  {domain}")
print()

print("🏙️ City Column Analysis:")
print(customers['city'].value_counts())

import pandas as pd

# Boolean data
survey = pd.DataFrame({
    'respondent': [1, 2, 3, 4],
    'satisfied': [True, False, True, True],
    'will_recommend': [True, False, False, True]
})

print("Survey Data:")
print(survey)
print()

print("😊 Satisfaction Analysis:")
print(f"Type: {survey['satisfied'].dtype}")
print(f"Satisfied customers: {survey['satisfied'].sum()}")
print(f"Satisfaction rate: {survey['satisfied'].mean():.2%}")
print()

print("👍 Recommendation Analysis:")
print(f"Will recommend: {survey['will_recommend'].sum()}")
print(f"Recommendation rate: {survey['will_recommend'].mean():.2%}")

import pandas as pd

# Mixed dataset
products = pd.DataFrame({
    'product_name': ['Laptop', 'Mouse', 'Keyboard', 'Monitor'],
    'price': [999.99, 24.99, 74.99, 299.99],
    'in_stock': [True, True, False, True],
    'category': ['Computer', 'Accessory', 'Accessory', 'Computer']
})

print("Product Data:")
print(products)
print()

# Analyze each column
for column in products.columns:
    print(f"📊 {column.upper()} Column:")
    print(f"   Type: {products[column].dtype}")
    print(f"   Unique values: {products[column].nunique()}")
    print(f"   Non-null count: {products[column].count()}")
    
    if products[column].dtype in ['int64', 'float64']:
        print(f"   Range: {products[column].min()} to {products[column].max()}")
    elif products[column].dtype == 'bool':
        print(f"   True count: {products[column].sum()}")
    else:
        print(f"   Sample values: {products[column].unique()[:3]}")
    print()

import pandas as pd

# Data with type issues
messy_data = pd.DataFrame({
    'age': ['25', '30', 'unknown', '35'],  # Should be numbers
    'price': ['$10.99', '$25.50', 'free', '$15.75'],  # Has symbols
    'active': ['yes', 'no', 'true', 'false']  # Should be boolean
})

print("❌ Messy Data:")
print(messy_data)
print()

print("🔍 Type Problems:")
print(messy_data.dtypes)
print()

print("🎯 What Should Be Fixed:")
print("- Age column: Contains 'unknown', should be numbers")
print("- Price column: Has '$' symbols and 'free'")
print("- Active column: Text instead of True/False")
print()

print("✅ After cleaning (example):")
# This is what you'd do after cleaning
clean_data = pd.DataFrame({
    'age': [25, 30, None, 35],  # Proper numbers with NaN
    'price': [10.99, 25.50, 0.0, 15.75],  # Clean numbers
    'active': [True, False, True, False]  # Proper booleans
})
print(clean_data)
print(clean_data.dtypes)

import pandas as pd

# Dataset to check
data = pd.DataFrame({
    'product': ['Laptop', 'Mouse', None, 'Monitor'],
    'price': [999, 25, 75, None],
    'rating': [4.5, 4.2, 5.0, 4.8]
})

print("Data Quality Check:")
print(data)
print()

print("🔍 Column-by-Column Analysis:")
for col in data.columns:
    print(f"\n{col.upper()}:")
    print(f"  Type: {data[col].dtype}")
    print(f"  Missing values: {data[col].isnull().sum()}")
    print(f"  Unique values: {data[col].nunique()}")
    
    if data[col].dtype in ['int64', 'float64']:
        print(f"  Min/Max: {data[col].min()} / {data[col].max()}")
    else:
        unique_vals = data[col].dropna().unique()
        print(f"  Sample values: {unique_vals[:3]}")

import pandas as pd

# Practice dataset
practice = pd.DataFrame({
    'customer_id': [1001, 1002, 1003, 1004],
    'purchase_amount': [99.99, 149.50, 75.25, 200.00],
    'is_member': [True, False, True, True],
    'product_category': ['Electronics', 'Clothing', 'Electronics', 'Books']
})

print("🎯 Column Analysis Practice:")
print(practice)
print()

print("📊 Quick Column Summary:")
for col in practice.columns:
    dtype = practice[col].dtype
    unique = practice[col].nunique()
    missing = practice[col].isnull().sum()
    
    print(f"{col}: {dtype} | {unique} unique | {missing} missing")

print()
print("🔍 Detailed Analysis:")
print(f"💰 Purchase amounts: ${practice['purchase_amount'].min()} - ${practice['purchase_amount'].max()}")
print(f"👥 Member percentage: {practice['is_member'].mean():.1%}")
print(f"📦 Categories: {practice['product_category'].unique()}")