#!/usr/bin/env python3 """ Apply verified enhancements to the master facility list """ import csv import json from pathlib import Path # Verified enhancements data ENHANCEMENTS = { "Rainier Fruit Company": { "total_rooms": "100", "square_footage": "1,500,000", "size_classification": "XXLarge", "premium_varieties": "Organic apples, pears, cherries, blueberries", "organic": "Yes", "ca_ma_storage": "Yes", "score": 135, "verification_source": "The Packer, Terra Firma Magazine", "confidence_level": "Verified", "notes": "Zirkle facility: 100 CA rooms, 1.5M sq ft, 6 packing lines, 29 shipping bays. Nation's largest organic grower." }, "Washington Fruit & Produce Company": { "square_footage": "840,000", "size_classification": "XXLarge", "premium_varieties": "Modern apple varieties", "ca_ma_storage": "Yes", "score": 115, "verification_source": "Capital Press, Yakima Herald", "confidence_level": "Verified", "notes": "Founded 1916. 840K sq ft total (300K new facility 2017). Most modern in WA." }, "FirstFruits Farms": { "square_footage": "500,000", "size_classification": "XXLarge", "premium_varieties": "23 varieties: Honeycrisp, Gala, Fuji, club varieties, Cosmic Crisp", "organic": "Yes", "ca_ma_storage": "Yes", "score": 125, "verification_source": "FirstFruits.com", "confidence_level": "Verified", "notes": "Multi-regional WA+MI. Acquired Applewood Fresh 2023. 500K+ boxes pears/year. Gem Drops cherries." }, "Stemilt Growers LLC": { "square_footage": "400,000", "size_classification": "XXLarge", "premium_varieties": "Cosmic Crisp (promoted), sweet cherries, organic tree fruit", "organic": "Yes", "ca_ma_storage": "Yes", "score": 125, "verification_source": "Stemilt.com, Wikipedia", "confidence_level": "Verified", "notes": "Leading sweet cherry shipper. Largest organic tree fruit supplier. Solar-powered CA storage." }, "CMI Orchards Headquarters": { "square_footage": "300,000", "size_classification": "XXLarge", "premium_varieties": "Conventional & organic apples, pears, cherries", "organic": "Yes", "ca_ma_storage": "Yes", "score": 120, "verification_source": "CMIOrchards.com", "confidence_level": "Verified", "notes": "Family cooperative. Multiple facilities: Wenatchee, Wapato, Chelan, Quincy, Hood River OR." }, "Domex Superfresh Growers": { "square_footage": "350,000", "size_classification": "XXLarge", "premium_varieties": "Apples, pears, cherries, blueberries, apricots", "organic": "Yes", "ca_ma_storage": "Yes", "score": 120, "verification_source": "IGSO, Produce Market Guide", "confidence_level": "Verified", "notes": "5th generation. First solar CA storage. Hydroelectric/wind/solar powered. ISO 22000." }, "Diamond Fruit Growers": { "square_footage": "300,000", "size_classification": "XXLarge", "premium_varieties": "Conventional & organic pears (primary), apples", "organic": "Yes", "ca_ma_storage": "Yes", "score": 115, "verification_source": "DiamondFruit.com, Produce News", "confidence_level": "Verified", "notes": "Founded 1913. Hood River cooperative. 650K box capacity (1937 world's largest)." }, "Allan Brothers Fruit Inc.": { "premium_varieties": "Apples, cherries", "ca_ma_storage": "Yes", "score": 95, "verification_source": "AllanBrosFruit.com", "confidence_level": "Verified", "notes": "100+ years. Pioneers in automation/technology/R&D. CA storage." }, "Chelan Fruit Cooperative": { "premium_varieties": "Ambrosia, Jazz, apples, cherries", "organic": "Unknown", "ca_ma_storage": "Yes", "score": 95, "verification_source": "Good Fruit Grower", "confidence_level": "Verified", "notes": "1,100 acres orchards. 5M packages/year capacity. Exclusive Ambrosia & Jazz varieties." }, "Lineage Tacoma Port": { "square_footage": "132,000", "size_classification": "XLarge", "score": 90, "verification_source": "NW Seaport Alliance, Lineage website", "confidence_level": "Verified", "notes": "CTPAT certified. 93M cubic ft total in PNW. 1.5M sq ft across 5 regional warehouses." }, "Nash Produce": { "square_footage": "500,000", "size_classification": "XXLarge", "premium_varieties": "Sweet potatoes (specialist)", "ca_ma_storage": "Yes", "score": 105, "verification_source": "NashProduce.com, The Packer", "confidence_level": "Verified", "notes": "92+ acres facility. 4M bushels CA storage. 12,000 acres sweet potato production." }, "Sage Fruit Company": { "premium_varieties": "Organic apples, pears, cherries", "organic": "Yes", "ca_ma_storage": "Yes", "score": 95, "verification_source": "Wikipedia, Organic Produce Network", "confidence_level": "Verified", "notes": "Sales/marketing for 4 grower/packer/shippers. Organic facilities in Chelan & Yakima." }, "Gebbers Farms": { "premium_varieties": "Apples, cherries", "ca_ma_storage": "Yes", "score": 90, "verification_source": "GebbersFarms.com", "confidence_level": "Verified", "notes": "Owns Brewster Heights Packing facility. Full ownership of warehouse & farming operations." } } def update_facility_csv(): """Update the verified facilities CSV with enhancements""" workspace = Path('/Users/max/.openclaw/workspace/postharvest') input_file = workspace / 'verified-scored-facilities.csv' output_file = workspace / 'verified-scored-facilities-ENHANCED.csv' # Read existing data facilities = [] with open(input_file, 'r', encoding='utf-8') as f: reader = csv.DictReader(f) facilities = list(reader) print(f"Loaded {len(facilities)} facilities from {input_file}") # Apply enhancements enhanced_count = 0 for facility in facilities: company = facility['Company'] if company in ENHANCEMENTS: enhancements = ENHANCEMENTS[company] # Apply each enhancement for key, value in enhancements.items(): # Convert snake_case to CSV column names if key == 'total_rooms': if value: facility['Total Rooms'] = value elif key == 'square_footage': facility['Square Footage'] = value elif key == 'size_classification': facility['Size Classification'] = value elif key == 'premium_varieties': facility['Premium Varieties'] = value elif key == 'organic': facility['Organic'] = value elif key == 'ca_ma_storage': facility['CA/MA'] = value elif key == 'score': facility['Score'] = str(value) elif key == 'verification_source': facility['Verification Source'] = value elif key == 'confidence_level': facility['Confidence Level'] = value elif key == 'notes': facility['Notes'] = value enhanced_count += 1 print(f" Enhanced: {company} -> Score: {facility['Score']}") # Write enhanced data fieldnames = [ 'Company', 'Region', 'Website', 'Size Classification', 'Total Rooms', 'Square Footage', 'Primary Produce', 'Premium Varieties', 'Organic', 'CA/MA', 'Score', 'Verification Source', 'Confidence Level', 'Notes' ] with open(output_file, 'w', newline='', encoding='utf-8') as f: writer = csv.DictWriter(f, fieldnames=fieldnames) writer.writeheader() # Sort by score (highest first) facilities.sort(key=lambda x: int(x.get('Score', 0)), reverse=True) for facility in facilities: writer.writerow(facility) print(f"\nSaved {len(facilities)} facilities to {output_file}") print(f"Enhanced {enhanced_count} facilities with verified data") # Statistics print("\n" + "="*70) print("ENHANCED DATASET STATISTICS") print("="*70) print(f"\nTop 20 Facilities (Enhanced Data):") for i, facility in enumerate(facilities[:20], 1): sqft = facility.get('Square Footage', 'Unknown') rooms = facility.get('Total Rooms', 'Unknown') score = facility.get('Score', '0') size = facility.get('Size Classification', 'Unknown') conf = facility.get('Confidence Level', 'Unknown') print(f" {i:2d}. {facility['Company'][:48]:48s} | {score:>3s} pts | " + f"{size:8s} | {rooms:>5s} rooms | {sqft:>10s} sf | {conf}") verified_count = sum(1 for f in facilities if f.get('Confidence Level') == 'Verified') xxlarge_count = sum(1 for f in facilities if f.get('Size Classification') == 'XXLarge') xlarge_count = sum(1 for f in facilities if f.get('Size Classification') == 'XLarge') print(f"\nVerified facilities: {verified_count}") print(f"XXLarge facilities: {xxlarge_count}") print(f"XLarge facilities: {xlarge_count}") print(f"Facilities with 100+ score: {sum(1 for f in facilities if int(f.get('Score', 0)) >= 100)}") print(f"Facilities with organic: {sum(1 for f in facilities if f.get('Organic') == 'Yes')}") return output_file if __name__ == '__main__': output = update_facility_csv() print(f"\n{'='*70}") print(f"ENHANCED DATASET READY: {output}") print(f"{'='*70}")