quick_start.py

#!/usr/bin/env python3
"""
Quick Start Script for Datasets Repository

This script provides a quick demonstration of loading and exploring all datasets
in the repository. Run this to get started quickly!

Usage:
    python quick_start.py
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from pathlib import Path
import warnings
warnings.filterwarnings('ignore')

def main():
    """Main function to demonstrate dataset usage"""
    
    print("🚀 Datasets Repository Quick Start")
    print("=" * 50)
    
    # Check if datasets exist
    datasets_path = Path(".")
    csv_files = list(datasets_path.glob("*.csv"))
    
    if not csv_files:
        print("❌ No CSV files found in current directory!")
        print("Please run this script from the datasets directory.")
        return
    
    print(f"📊 Found {len(csv_files)} datasets:")
    for file in csv_files:
        print(f"   - {file.name}")
    
    print("\n" + "=" * 50)
    
    # Load and explore each dataset
    explore_datasets(csv_files)
    
    print("\n✅ Quick start completed!")
    print("📚 Check the docs/ folder for detailed examples and usage patterns.")

def explore_datasets(csv_files):
    """Explore each dataset and show basic information"""
    
    for i, csv_file in enumerate(csv_files):
        print(f"\n🔍 Dataset {i+1}: {csv_file.name}")
        print("-" * 40)
        
        try:
            # Load dataset
            df = pd.read_csv(csv_file)
            
            # Basic info
            print(f"Shape: {df.shape}")
            print(f"Memory usage: {df.memory_usage(deep=True).sum() / 1024 / 1024:.2f} MB")
            
            # Data types
            numeric_cols = df.select_dtypes(include=[np.number]).columns
            categorical_cols = df.select_dtypes(include=['object']).columns
            
            print(f"Numerical columns: {len(numeric_cols)}")
            print(f"Categorical columns: {len(categorical_cols)}")
            
            # Missing values
            missing_count = df.isnull().sum().sum()
            if missing_count > 0:
                print(f"Missing values: {missing_count}")
            else:
                print("Missing values: None")
            
            # Sample data
            print("\nFirst 3 rows:")
            print(df.head(3).to_string())
            
            # Basic statistics for numerical columns
            if len(numeric_cols) > 0:
                print(f"\nNumerical columns statistics:")
                print(df[numeric_cols].describe().round(2))
            
            # Categorical value counts (show top 5)
            if len(categorical_cols) > 0:
                print(f"\nCategorical columns sample values:")
                for col in categorical_cols[:3]:  # Limit to 3 columns
                    unique_vals = df[col].nunique()
                    if unique_vals <= 10:
                        print(f"{col}: {df[col].value_counts().head().to_dict()}")
                    else:
                        print(f"{col}: {unique_vals} unique values")
            
        except Exception as e:
            print(f"❌ Error loading {csv_file.name}: {str(e)}")
        
        print("-" * 40)

def show_dataset_summary():
    """Show a summary table of all datasets"""
    
    print("\n📋 Dataset Summary Table")
    print("=" * 80)
    
    summary_data = []
    
    for csv_file in Path(".").glob("*.csv"):
        try:
            df = pd.read_csv(csv_file)
            file_size = csv_file.stat().st_size / 1024 / 1024  # MB
            
            summary_data.append({
                'Dataset': csv_file.name,
                'Rows': df.shape[0],
                'Columns': df.shape[1],
                'Size (MB)': f"{file_size:.2f}",
                'Numerical': len(df.select_dtypes(include=[np.number]).columns),
                'Categorical': len(df.select_dtypes(include=['object']).columns),
                'Missing Values': df.isnull().sum().sum()
            })
        except:
            continue
    
    if summary_data:
        summary_df = pd.DataFrame(summary_data)
        print(summary_df.to_string(index=False))
    
    print("=" * 80)

if __name__ == "__main__":
    try:
        main()
        show_dataset_summary()
    except KeyboardInterrupt:
        print("\n\n⏹️  Script interrupted by user")
    except Exception as e:
        print(f"\n❌ Unexpected error: {str(e)}")
        print("Please check that all required packages are installed:")
        print("pip install -r requirements.txt")