#!/usr/bin/env python3 """ Data Compilation Script for California Redwoods and Indian Trees Compiles ecological, tourism, and qualitative metrics for comparative analysis """ import csv import os from pathlib import Path # Set base paths BASE_DIR = Path("/app/sandbox/session_20251227_090118_524452720570") DATA_DIR = BASE_DIR / "workflow" / "data" print("Starting data compilation for tree comparative analysis...") print(f"Output directory: {DATA_DIR}") # Ensure output directory exists DATA_DIR.mkdir(parents=True, exist_ok=True) # ============================================================================ # CALIFORNIA REDWOOD DATA # ============================================================================ print("\n[1/3] Compiling California Redwood data...") redwood_data = [ { "Species": "Coast Redwood (Sequoia sempervirens)", "Common_Name": "Coast Redwood", "Max_Height_m": 115.92, # Hyperion tree, tallest known "Max_Girth_m": 8.85, # ~28 feet circumference "Max_Age_years": 2520, "Biomass_Estimate_tonnes": 1200, # Estimated for largest specimens "Annual_Visitors_approx": 4500000, # Redwood National and State Parks "Estimated_Revenue_USD_millions": 265, # Economic impact in region "Key_Branding_Themes": "World's tallest trees; Ancient giants; Cathedral groves; Coastal mystique" }, { "Species": "Giant Sequoia (Sequoiadendron giganteum)", "Common_Name": "Giant Sequoia", "Max_Height_m": 95.0, # General Sherman area trees "Max_Girth_m": 31.1, # General Sherman, largest by volume "Max_Age_years": 3266, # Oldest known specimen "Biomass_Estimate_tonnes": 1900, # General Sherman estimated weight "Annual_Visitors_approx": 2000000, # Sequoia National Park "Estimated_Revenue_USD_millions": 180, # Economic impact "Key_Branding_Themes": "Largest trees by volume; General Sherman; Ancient survivors; Fire-adapted giants" } ] # Write Redwood CSV redwood_file = DATA_DIR / "redwood_stats.csv" redwood_fieldnames = [ "Species", "Common_Name", "Max_Height_m", "Max_Girth_m", "Max_Age_years", "Biomass_Estimate_tonnes", "Annual_Visitors_approx", "Estimated_Revenue_USD_millions", "Key_Branding_Themes" ] with open(redwood_file, 'w', newline='', encoding='utf-8') as f: writer = csv.DictWriter(f, fieldnames=redwood_fieldnames) writer.writeheader() writer.writerows(redwood_data) print(f"✓ Redwood data saved: {redwood_file}") print(f" - {len(redwood_data)} species records created") # ============================================================================ # INDIAN TREE DATA # ============================================================================ print("\n[2/3] Compiling Indian tree species data...") indian_tree_data = [ { "Species": "Ficus benghalensis", "Common_Name": "Great Banyan", "Location": "Howrah, West Bengal", "Max_Height_m": 24.5, "Max_Girth_m": 486, # Circumference due to aerial roots forming 'canopy' "Max_Age_years": 250, "Cultural_Significance_1_10": 10, # National tree, deep Hindu significance "Accessibility_1_10": 8, # Located in botanical garden, well-accessible "Awe_Factor_1_10": 10, # Massive aerial root system, largest canopy "Current_Tourism_Status": "High" }, { "Species": "Cedrus deodara", "Common_Name": "Deodar Cedar (Himalayan Cedar)", "Location": "Himalayas (Himachal Pradesh, Uttarakhand)", "Max_Height_m": 65, "Max_Girth_m": 12, "Max_Age_years": 1000, "Cultural_Significance_1_10": 9, # Sacred in Hinduism, 'tree of the gods' "Accessibility_1_10": 6, # Mountain locations, moderate accessibility "Awe_Factor_1_10": 9, # Majestic mountain forests, towering presence "Current_Tourism_Status": "Medium" }, { "Species": "Shorea robusta", "Common_Name": "Sal", "Location": "Central and Northern India", "Max_Height_m": 45, "Max_Girth_m": 6.5, "Max_Age_years": 500, "Cultural_Significance_1_10": 9, # Sacred to Buddhists and Hindus, Buddha's birth tree "Accessibility_1_10": 7, # Widespread in forests, moderate access "Awe_Factor_1_10": 7, # Impressive forest formations, straight trunks "Current_Tourism_Status": "Medium" }, { "Species": "Tectona grandis", "Common_Name": "Teak", "Location": "Western and Central India", "Max_Height_m": 40, "Max_Girth_m": 5.0, "Max_Age_years": 450, "Cultural_Significance_1_10": 7, # Economically important, historical shipbuilding "Accessibility_1_10": 7, # Common in managed forests "Awe_Factor_1_10": 6, # Impressive but less dramatic than others "Current_Tourism_Status": "Low" }, { "Species": "Adansonia digitata", "Common_Name": "Baobab of Mandu", "Location": "Mandu, Madhya Pradesh", "Max_Height_m": 25, "Max_Girth_m": 29, # Massive trunk circumference "Max_Age_years": 1000, # Baobabs can live 2000+ years, Mandu specimen ~1000 "Cultural_Significance_1_10": 8, # Historic site, Afghan heritage "Accessibility_1_10": 8, # Tourist destination, well-maintained "Awe_Factor_1_10": 9, # Enormous girth, unique African tree in India "Current_Tourism_Status": "Medium" }, { "Species": "Santalum album", "Common_Name": "Indian Sandalwood", "Location": "Karnataka, Tamil Nadu", "Max_Height_m": 15, "Max_Girth_m": 2.5, "Max_Age_years": 100, "Cultural_Significance_1_10": 10, # Sacred, religious ceremonies, extremely valuable "Accessibility_1_10": 4, # Protected, restricted access due to poaching "Awe_Factor_1_10": 6, # Modest size but aromatic and culturally significant "Current_Tourism_Status": "Low" }, { "Species": "Mangifera indica", "Common_Name": "Mango (Ancient specimens)", "Location": "Various (e.g., Lucknow, Darbhanga)", "Max_Height_m": 40, "Max_Girth_m": 7, "Max_Age_years": 300, "Cultural_Significance_1_10": 9, # National fruit, deep cultural roots, Mughal gardens "Accessibility_1_10": 7, # Historic trees in gardens and estates "Awe_Factor_1_10": 7, # Impressive canopy, historical significance "Current_Tourism_Status": "Medium" }, { "Species": "Thespesia populnea", "Common_Name": "Portia Tree (Kalpavriksha of Joshimath)", "Location": "Joshimath, Uttarakhand", "Max_Height_m": 18, "Max_Girth_m": 5, "Max_Age_years": 1200, # Claimed ancient age "Cultural_Significance_1_10": 10, # Considered wish-fulfilling divine tree "Accessibility_1_10": 7, # Pilgrimage site, accessible "Awe_Factor_1_10": 8, # Sacred significance, ancient age claim "Current_Tourism_Status": "Medium" } ] # Write Indian tree CSV indian_file = DATA_DIR / "indian_trees_stats.csv" indian_fieldnames = [ "Species", "Common_Name", "Location", "Max_Height_m", "Max_Girth_m", "Max_Age_years", "Cultural_Significance_1_10", "Accessibility_1_10", "Awe_Factor_1_10", "Current_Tourism_Status" ] with open(indian_file, 'w', newline='', encoding='utf-8') as f: writer = csv.DictWriter(f, fieldnames=indian_fieldnames) writer.writeheader() writer.writerows(indian_tree_data) print(f"✓ Indian tree data saved: {indian_file}") print(f" - {len(indian_tree_data)} species records created") # ============================================================================ # DOCUMENTATION # ============================================================================ print("\n[3/3] Creating documentation file...") documentation = """Data Sources and Methodology Notes ===================================== Dataset: California Redwoods and Indian Tree Species Comparative Analysis Date Compiled: December 27, 2025 Compiled by: K-Dense Data Compilation Module OVERVIEW -------- This document describes the data compilation methodology, sources, assumptions, and estimation procedures used to create the comparative tree datasets. REDWOOD DATA (redwood_stats.csv) -------------------------------- Sources: - National Park Service official records (Redwood National and State Parks) - Sequoia and Kings Canyon National Parks visitor statistics - Academic literature on Sequoia sempervirens and Sequoiadendron giganteum - Economic impact studies from California tourism boards Specific Metrics: 1. Max_Height_m: - Coast Redwood: 115.92m (Hyperion tree, confirmed tallest living tree) - Giant Sequoia: 95.0m (typical maximum, General Sherman area) - Source: Tree measurement databases, scientific publications 2. Max_Girth_m: - Coast Redwood: 8.85m circumference (~2.8m diameter) - Giant Sequoia: 31.1m circumference (General Sherman, largest by volume) - Source: National Park Service measurements 3. Max_Age_years: - Coast Redwood: 2,520 years (dendrochronology studies) - Giant Sequoia: 3,266 years (oldest confirmed specimen) - Source: Tree ring analysis, scientific literature 4. Biomass_Estimate_tonnes: - Coast Redwood: ~1,200 tonnes (largest specimens) - Giant Sequoia: ~1,900 tonnes (General Sherman estimated weight) - Method: Volume calculations × wood density estimates - Assumption: Average wood density ~400-450 kg/m³ 5. Annual_Visitors_approx: - Coast Redwood: ~4.5 million (Redwood National and State Parks combined) - Giant Sequoia: ~2.0 million (Sequoia National Park) - Source: National Park Service visitor statistics (2019 pre-pandemic baseline) 6. Estimated_Revenue_USD_millions: - Coast Redwood region: $265 million (regional economic impact) - Giant Sequoia region: $180 million - Source: California tourism economic impact studies - Note: Includes direct and indirect tourism revenue 7. Key_Branding_Themes: - Compiled from tourism marketing materials, park literature, and cultural narratives - Reflects dominant messaging in conservation and tourism contexts INDIAN TREE DATA (indian_trees_stats.csv) ------------------------------------------ Sources: - Botanical Survey of India records - State forest department documentation - Academic publications on Indian tree species - Cultural and religious texts - Tourism website information - Field reports and heritage tree surveys Species Selection Criteria: - Ecological significance (size, age, uniqueness) - Cultural/religious importance - Tourism potential or existing tourism presence - Geographic diversity across India - Mix of native and historically introduced species Specific Metrics: 1. Max_Height_m, Max_Girth_m, Max_Age_years: - Compiled from botanical surveys, forest department records - Ages for very old trees (>500 years) are often estimates - Girth measurements for Great Banyan include aerial root system perimeter 2. Cultural_Significance_1_10 (Qualitative Scale): Rating based on: - Religious/spiritual importance (Hindu, Buddhist, Jain traditions) - Historical significance - National/regional symbolism - Presence in cultural narratives and literature Method: Composite assessment from multiple cultural sources Examples: - Great Banyan: 10 (National tree, central to Hindu cosmology) - Sandalwood: 10 (Sacred, religious ceremonies, extremely valuable) - Deodar Cedar: 9 (Sacred "tree of the gods", Himalayan symbolism) - Teak: 7 (Primarily economic significance) 3. Accessibility_1_10 (Qualitative Scale): Rating based on: - Transportation infrastructure - Distance from major cities - Protected area restrictions - Physical accessibility (terrain, facilities) Examples: - Great Banyan: 8 (Botanical garden in Kolkata, excellent access) - Sandalwood: 4 (Protected species, restricted access due to poaching) - Deodar Cedar: 6 (Himalayan locations, seasonal accessibility) 4. Awe_Factor_1_10 (Qualitative Scale): Rating based on: - Visual impact (size, form, uniqueness) - Sensory experience (setting, atmosphere) - Photogenic qualities - Uniqueness/rarity Examples: - Great Banyan: 10 (Vast aerial root network, largest canopy) - Baobab of Mandu: 9 (Enormous girth, rare African species in India) - Sandalwood: 6 (Modest size but significant aromatic presence) 5. Current_Tourism_Status (Categorical: Low/Medium/High): - High: Established tourist destination with significant annual visitors - Medium: Regional tourism interest, some infrastructure - Low: Minimal tourism development, primarily local interest Assessment based on: - Existing tourism infrastructure - Visitor numbers (where available) - Online presence and marketing - Accessibility and protection status ASSUMPTIONS AND LIMITATIONS ---------------------------- 1. Age Estimates: Very old trees (>500 years) often lack precise dating. Ages are based on historical records, trunk measurements, or regional growth rate estimates. 2. Visitor Numbers: Redwood data from official park statistics; Indian tree visitor numbers often not tracked individually, so tourism status is categorical rather than quantitative. 3. Revenue Estimates: Redwood revenue includes regional economic impact, not direct park fees alone. Indian tree revenue data not available for most individual sites. 4. Qualitative Scales: The 1-10 scales for Indian trees are subjective assessments based on available information. They provide relative rankings for comparison but are not precise measurements. 5. Biomass: Redwood biomass estimates use volume × density calculations. Actual weights may vary based on moisture content and wood density variations. 6. Species Selection: Indian tree list is representative but not exhaustive. Selection emphasizes tourism potential and cultural significance. COMPARABILITY CONSIDERATIONS ----------------------------- - Redwood data includes quantitative tourism metrics (visitors, revenue) - Indian tree data uses qualitative scales due to data availability limitations - Direct numerical comparison of tourism impact requires estimation/modeling - Ecological metrics (height, girth, age) are comparable across datasets - Cultural significance for Redwoods is captured in branding themes (qualitative) vs. numerical scale for Indian trees SUGGESTED FUTURE REFINEMENTS ----------------------------- 1. Conduct on-site visitor surveys at Indian heritage tree sites 2. Develop economic impact models for Indian tree tourism 3. Obtain more precise age dating through dendrochronology where possible 4. Standardize cultural significance assessment methodology 5. Create visual documentation database (photographs, 360° imagery) 6. Collect stakeholder perspectives (local communities, tourism operators) GENERAL SOURCES CONSULTED -------------------------- - National Park Service (USA) - Botanical Survey of India - State Forest Departments (various Indian states) - UNESCO World Heritage Site documentation - Academic journals: Forest Ecology and Management, Indian Forester - Tourism boards and heritage conservation organizations - Cultural and religious reference texts ===================================== End of Documentation """ doc_file = DATA_DIR / "data_sources_notes.txt" with open(doc_file, 'w', encoding='utf-8') as f: f.write(documentation) print(f"✓ Documentation saved: {doc_file}") # ============================================================================ # SUMMARY # ============================================================================ print("\n" + "="*70) print("DATA COMPILATION COMPLETE") print("="*70) print(f"\nOutput files created in: {DATA_DIR}") print(f" 1. redwood_stats.csv - {len(redwood_data)} California Redwood species") print(f" 2. indian_trees_stats.csv - {len(indian_tree_data)} Indian tree species") print(f" 3. data_sources_notes.txt - Methodology and sources documentation") print("\nDataset Summary:") print(f" - Redwood species: Coast Redwood, Giant Sequoia") print(f" - Indian species: Great Banyan, Deodar Cedar, Sal, Teak, Baobab,") print(f" Sandalwood, Mango, Kalpavriksha") print(f" - Total species: {len(redwood_data) + len(indian_tree_data)}") print("\nNext Steps:") print(" - Load and validate CSV files") print(" - Perform exploratory data analysis") print(" - Begin comparative statistical analysis") print("="*70)