Python Code Editor

Write and execute Python code with data science libraries

Code Templates

Quick start with pre-built templates

Code Editor

Write your Python code here

Python 3.11

NumPy

Pandas

Matplotlib

Seaborn

# Welcome to the Python Code Editor
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

# Example: Comprehensive Data Analysis
def comprehensive_analysis():
    # Create sample dataset
    np.random.seed(42)
    n_samples = 1000
    
    data = {
        'sales': np.random.normal(5000, 1500, n_samples),
        'marketing_spend': np.random.normal(1000, 300, n_samples),
        'customer_satisfaction': np.random.uniform(1, 10, n_samples),
        'region': np.random.choice(['North', 'South', 'East', 'West'], n_samples),
        'product_category': np.random.choice(['Electronics', 'Clothing', 'Books', 'Home'], n_samples)
    }
    
    # Add some correlation
    data['sales'] = data['sales'] + data['marketing_spend'] * 0.5 + np.random.normal(0, 200, n_samples)
    
    df = pd.DataFrame(data)
    
    print("=== COMPREHENSIVE DATA ANALYSIS ===")
    print(f"Dataset shape: {df.shape}")
    print("\nFirst 5 rows:")
    print(df.head())
    
    print("\nBasic Statistics:")
    print(df.describe())
    
    print("\nCorrelation Matrix:")
    numeric_cols = df.select_dtypes(include=[np.number]).columns
    correlation_matrix = df[numeric_cols].corr()
    print(correlation_matrix)
    
    # Regional Analysis
    print("\nSales by Region:")
    regional_stats = df.groupby('region')['sales'].agg(['mean', 'sum', 'count'])
    print(regional_stats)
    
    # Create visualizations
    create_advanced_visualizations(df)
    
    return df

def create_advanced_visualizations(df):
    """Create multiple publication-ready visualizations"""
    
    # Set style for better-looking plots
    plt.style.use('seaborn-v0_8')
    
    # 1. Sales Distribution
    plt.figure(figsize=(12, 8))
    
    plt.subplot(2, 2, 1)
    plt.hist(df['sales'], bins=30, alpha=0.7, color='skyblue', edgecolor='black')
    plt.title('Sales Distribution', fontsize=14, fontweight='bold')
    plt.xlabel('Sales ($)')
    plt.ylabel('Frequency')
    plt.grid(True, alpha=0.3)
    
    # 2. Sales vs Marketing Spend Scatter Plot
    plt.subplot(2, 2, 2)
    plt.scatter(df['marketing_spend'], df['sales'], alpha=0.6, color='coral')
    plt.title('Sales vs Marketing Spend', fontsize=14, fontweight='bold')
    plt.xlabel('Marketing Spend ($)')
    plt.ylabel('Sales ($)')
    plt.grid(True, alpha=0.3)
    
    # Add trend line
    z = np.polyfit(df['marketing_spend'], df['sales'], 1)
    p = np.poly1d(z)
    plt.plot(df['marketing_spend'], p(df['marketing_spend']), "r--", alpha=0.8)
    
    # 3. Sales by Region Box Plot
    plt.subplot(2, 2, 3)
    regions = df['region'].unique()
    sales_by_region = [df[df['region'] == region]['sales'] for region in regions]
    plt.boxplot(sales_by_region, labels=regions)
    plt.title('Sales Distribution by Region', fontsize=14, fontweight='bold')
    plt.ylabel('Sales ($)')
    plt.xticks(rotation=45)
    plt.grid(True, alpha=0.3)
    
    # 4. Customer Satisfaction vs Sales
    plt.subplot(2, 2, 4)
    plt.scatter(df['customer_satisfaction'], df['sales'], alpha=0.6, color='lightgreen')
    plt.title('Customer Satisfaction vs Sales', fontsize=14, fontweight='bold')
    plt.xlabel('Customer Satisfaction (1-10)')
    plt.ylabel('Sales ($)')
    plt.grid(True, alpha=0.3)
    
    plt.tight_layout()
    plt.savefig('comprehensive_analysis.png', dpi=300, bbox_inches='tight')
    plt.close()
    
    # Create a separate correlation heatmap
    plt.figure(figsize=(10, 8))
    numeric_cols = df.select_dtypes(include=[np.number]).columns
    correlation_matrix = df[numeric_cols].corr()
    
    # Create heatmap
    mask = np.triu(np.ones_like(correlation_matrix, dtype=bool))
    plt.imshow(correlation_matrix, cmap='RdYlBu_r', aspect='auto', vmin=-1, vmax=1)
    
    # Add labels and values
    plt.xticks(range(len(numeric_cols)), numeric_cols, rotation=45, ha='right')
    plt.yticks(range(len(numeric_cols)), numeric_cols)
    
    # Add correlation values
    for i in range(len(numeric_cols)):
        for j in range(len(numeric_cols)):
            plt.text(j, i, f'{correlation_matrix.iloc[i, j]:.2f}',
                    ha="center", va="center", 
                    color="white" if abs(correlation_matrix.iloc[i, j]) > 0.5 else "black",
                    fontweight='bold')
    
    plt.title('Correlation Heatmap', fontsize=16, fontweight='bold', pad=20)
    plt.colorbar(label='Correlation Coefficient')
    plt.tight_layout()
    plt.savefig('correlation_heatmap.png', dpi=300, bbox_inches='tight')
    plt.close()
    
    print("\n📊 Visualizations created:")
    print("  - comprehensive_analysis.png")
    print("  - correlation_heatmap.png")

# Run the comprehensive analysis
if __name__ == "__main__":
    print("🚀 Starting comprehensive data analysis...")
    df = comprehensive_analysis()
    
    print("\n✅ Analysis complete!")
    print("📈 Check the generated PNG files for detailed visualizations.")
    print(f"📋 Dataset saved with {len(df)} records and {len(df.columns)} columns.")

Output Console

Code execution results and logs

Click "Run Code" to see output here...

Available Libraries

Pre-installed Python libraries for data science and analysis

Data Processing

pandas

numpy

scipy

Visualization

matplotlib

seaborn

plotly

Machine Learning

scikit-learn

tensorflow

pytorch

Utilities

requests

beautifulsoup4

pillow