generate_test_data.py

#!/usr/bin/env python3
"""
Generate test Excel file for MushLog import testing
"""

import pandas as pd
import os
from datetime import datetime, timedelta
import random

def generate_test_data():
    """Generate sample mycology data for testing"""
    
    # Sample data
    data = []
    
    # Generate 10 sample specimens
    for i in range(1, 11):
        # Generate a random date within the last 6 months
        days_ago = random.randint(0, 180)
        date = (datetime.now() - timedelta(days=days_ago)).strftime("%Y-%m-%d")
        
        specimen = {
            'id': f"ML{i:04d}",
            'date': date,
            'state': random.choice(['California', 'Oregon', 'Washington', 'Colorado']),
            'county': random.choice(['Marin', 'Sonoma', 'Mendocino', 'Humboldt', 'Jefferson']),
            'city': random.choice(['San Francisco', 'Oakland', 'Berkeley', 'Arcata', 'Eureka']),
            'site_name': random.choice(['Redwood Regional Park', 'Muir Woods', 'Point Reyes', 'Golden Gate Park', 'Tilden Regional Park']),
            'species': random.choice([
                'Amanita muscaria',
                'Boletus edulis',
                'Cantharellus cibarius',
                'Lactarius deliciosus',
                'Russula emetica',
                'Pleurotus ostreatus',
                'Agaricus bisporus',
                'Coprinus comatus',
                'Morchella esculenta',
                'Gyromitra esculenta'
            ]),
            'field_photo': random.choice(['Yes', 'No']),
            'nearby_trees': random.choice(['Oak', 'Pine', 'Redwood', 'Douglas Fir', 'Mixed']),
            'substrate': random.choice(['Soil', 'Wood', 'Leaf litter', 'Moss', 'Grass']),
            'habit': random.choice(['Solitary', 'Scattered', 'Clustered', 'Gregarious']),
            'odor': random.choice(['None', 'Mild', 'Strong', 'Pleasant', 'Unpleasant']),
            'taste': random.choice(['None', 'Mild', 'Bitter', 'Sweet', 'Nutty']),
            'inat_id': str(random.randint(1000000, 9999999)) if random.random() > 0.3 else 'None',
            'collected_by': random.choice(['John Smith', 'Jane Doe', 'Bob Wilson', 'Alice Brown', 'Charlie Davis'])
        }
        
        data.append(specimen)
    
    return data

def create_test_excel():
    """Create test Excel file"""
    
    # Generate data
    data = generate_test_data()
    
    # Create DataFrame
    df = pd.DataFrame(data)
    
    # Create filename with timestamp
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    filename = f"mushlog_test_data_{timestamp}.xlsx"
    
    # Save to Excel
    df.to_excel(filename, index=False, engine='openpyxl')
    
    print(f"✅ Test Excel file created: {filename}")
    print(f"📊 Contains {len(data)} sample specimens")
    print(f"📁 File location: {os.path.abspath(filename)}")
    print("\n📋 Sample data preview:")
    print(df.head(3).to_string(index=False))
    
    return filename

if __name__ == "__main__":
    try:
        filename = create_test_excel()
        print(f"\n🎯 You can now use '{filename}' to test the import tool!")
        print("💡 Try both 'Replace Database' and 'Merge Data' modes")
    except Exception as e:
        print(f"❌ Error creating test file: {e}")
        print("💡 Make sure you have pandas and openpyxl installed:")
        print("   pip install pandas openpyxl")