Complete Enhanced Agricultural AI System - All Requirements Met
This commit is contained in:
Aherobo Ovie Victor
+91
-20
@@ -4,6 +4,7 @@ Smart Farm Photo Keyword Tagging AI - Main Processing Script
|
||||
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
import pandas as pd
|
||||
from datetime import datetime
|
||||
import argparse
|
||||
@@ -13,44 +14,61 @@ sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
|
||||
|
||||
from src.data.image_processor import ImageProcessor
|
||||
from src.model.keyword_generator import AgricultureKeywordGenerator
|
||||
from src.utils.validation import KeywordValidator, DataQualityChecker
|
||||
from src.utils.batch_processor import BatchProcessor, estimate_processing_time
|
||||
|
||||
def process_agricultural_photos(input_dir: str = "data/raw", output_dir: str = "outputs"):
|
||||
"""Main function to process agricultural photos and generate keywords"""
|
||||
def process_agricultural_photos(input_dir: str = "data/raw", output_dir: str = "outputs",
|
||||
validate_quality: bool = True, batch_size: int = 500):
|
||||
"""Enhanced function to process agricultural photos with quality validation"""
|
||||
|
||||
print("🚜 Smart Farm Photo Keyword Tagging AI")
|
||||
print("=" * 50)
|
||||
print("🚜 Smart Farm Photo Keyword Tagging AI - Enhanced Version")
|
||||
print("=" * 60)
|
||||
|
||||
# Initialize components
|
||||
print("Initializing image processor...")
|
||||
print("Initializing components...")
|
||||
image_processor = ImageProcessor(input_dir)
|
||||
|
||||
print("Initializing AI keyword generator...")
|
||||
keyword_generator = AgricultureKeywordGenerator()
|
||||
validator = KeywordValidator() if validate_quality else None
|
||||
|
||||
# Process images
|
||||
# Get image files and estimate processing time
|
||||
image_files = image_processor.get_image_files(input_dir)
|
||||
if not image_files:
|
||||
print("No images found to process!")
|
||||
return
|
||||
|
||||
print(f"Found {len(image_files)} images to process")
|
||||
time_estimate = estimate_processing_time(len(image_files))
|
||||
print(f"Estimated processing time: {time_estimate['estimate']}")
|
||||
|
||||
# Process images with enhanced error handling
|
||||
print(f"\nProcessing images from: {input_dir}")
|
||||
image_df = image_processor.batch_process_images(input_dir)
|
||||
|
||||
if image_df.empty:
|
||||
print("No images found to process!")
|
||||
print("No valid images found to process!")
|
||||
return
|
||||
|
||||
print(f"Found {len(image_df)} images to process")
|
||||
|
||||
# Generate keywords for each image
|
||||
# Generate keywords for each image with quality validation
|
||||
results = []
|
||||
quality_scores = []
|
||||
processing_start = time.time()
|
||||
|
||||
for idx, row in image_df.iterrows():
|
||||
if 'error' in row:
|
||||
print(f"Skipping {row['filename']} due to error: {row['error']}")
|
||||
continue
|
||||
|
||||
print(f"Processing {row['filename']}...")
|
||||
print(f"Processing {row['filename']}... ({idx+1}/{len(image_df)})")
|
||||
|
||||
try:
|
||||
# Generate keywords and title
|
||||
ai_results = keyword_generator.generate_keywords(row['filepath'])
|
||||
|
||||
# Create result row
|
||||
# Validate quality if enabled
|
||||
keyword_validation = validator.validate_keywords(ai_results['keywords']) if validator else None
|
||||
title_validation = validator.validate_title(ai_results['title']) if validator else None
|
||||
|
||||
# Create result row with enhanced data
|
||||
result = {
|
||||
'filename': row['filename'],
|
||||
'human_keywords': '', # Placeholder for human keywords
|
||||
@@ -60,14 +78,28 @@ def process_agricultural_photos(input_dir: str = "data/raw", output_dir: str = "
|
||||
'caption': ai_results['caption']
|
||||
}
|
||||
|
||||
# Add quality scores if validation enabled
|
||||
if validate_quality and keyword_validation and title_validation:
|
||||
result.update({
|
||||
'keyword_quality_score': keyword_validation['score'],
|
||||
'title_quality_score': title_validation['score'],
|
||||
'quality_issues': '; '.join(keyword_validation['issues'] + title_validation['issues'])
|
||||
})
|
||||
quality_scores.append(keyword_validation['score'])
|
||||
|
||||
results.append(result)
|
||||
print(f" ✓ Generated {len(ai_results['keywords'])} keywords")
|
||||
print(f" ✓ Generated {len(ai_results['keywords'])} keywords" +
|
||||
(f" (Quality: {keyword_validation['score']:.1f})" if validate_quality and keyword_validation else ""))
|
||||
|
||||
except Exception as e:
|
||||
print(f" ✗ Error processing {row['filename']}: {e}")
|
||||
continue
|
||||
|
||||
# Create output DataFrame
|
||||
# Create output DataFrame and save results
|
||||
if not results:
|
||||
print("No images were successfully processed!")
|
||||
return None
|
||||
|
||||
results_df = pd.DataFrame(results)
|
||||
|
||||
# Save to CSV
|
||||
@@ -77,11 +109,29 @@ def process_agricultural_photos(input_dir: str = "data/raw", output_dir: str = "
|
||||
|
||||
results_df.to_csv(output_file, index=False)
|
||||
|
||||
# Calculate processing statistics
|
||||
processing_time = time.time() - processing_start
|
||||
avg_time_per_image = processing_time / len(results) if results else 0
|
||||
|
||||
print(f"\n✅ Processing complete!")
|
||||
print(f"Results saved to: {output_file}")
|
||||
print(f"Processed {len(results_df)} images successfully")
|
||||
print(f"Total processing time: {processing_time/60:.1f} minutes")
|
||||
print(f"Average time per image: {avg_time_per_image:.1f} seconds")
|
||||
|
||||
# Display sample results
|
||||
# Quality statistics if validation was enabled
|
||||
if validate_quality and quality_scores:
|
||||
avg_quality = sum(quality_scores) / len(quality_scores)
|
||||
print(f"Average keyword quality score: {avg_quality:.1f}/100")
|
||||
|
||||
# Validate CSV output
|
||||
csv_validation = DataQualityChecker.validate_csv_output(output_file)
|
||||
if csv_validation['valid']:
|
||||
print(f"✅ CSV validation passed - {csv_validation['completion_rate']['keywords']}% keyword completion")
|
||||
else:
|
||||
print(f"⚠️ CSV validation issues: {csv_validation['error']}")
|
||||
|
||||
# Display enhanced sample results
|
||||
print("\n📊 Sample Results:")
|
||||
print("-" * 80)
|
||||
for idx, row in results_df.head(3).iterrows():
|
||||
@@ -89,20 +139,41 @@ def process_agricultural_photos(input_dir: str = "data/raw", output_dir: str = "
|
||||
print(f"Title: {row['ai_title']}")
|
||||
print(f"Keywords: {row['ai_keywords']}")
|
||||
print(f"Location: {row['location'] if row['location'] else 'Not available'}")
|
||||
if validate_quality and 'keyword_quality_score' in row:
|
||||
print(f"Quality Score: {row['keyword_quality_score']}/100")
|
||||
print("-" * 80)
|
||||
|
||||
# Performance projections
|
||||
print(f"\n🚀 Performance Projections:")
|
||||
print(f"Time for 500 images: {(avg_time_per_image * 500)/60:.1f} minutes")
|
||||
print(f"Time for 1000 images: {(avg_time_per_image * 1000)/60:.1f} minutes")
|
||||
|
||||
return output_file
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description='Process agricultural photos for keyword tagging')
|
||||
parser = argparse.ArgumentParser(description='Enhanced Agricultural Photo Keyword Tagging AI')
|
||||
parser.add_argument('--input', '-i', default='data/raw', help='Input directory with images')
|
||||
parser.add_argument('--output', '-o', default='outputs', help='Output directory for results')
|
||||
parser.add_argument('--no-validation', action='store_true', help='Skip quality validation')
|
||||
parser.add_argument('--batch-size', type=int, default=500, help='Batch size for processing')
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
output_file = process_agricultural_photos(args.input, args.output)
|
||||
print(f"\n🎉 Success! Check your results in: {output_file}")
|
||||
output_file = process_agricultural_photos(
|
||||
args.input,
|
||||
args.output,
|
||||
validate_quality=not args.no_validation,
|
||||
batch_size=args.batch_size
|
||||
)
|
||||
|
||||
if output_file:
|
||||
print(f"\n🎉 Success! Check your results in: {output_file}")
|
||||
else:
|
||||
print(f"\n⚠️ Processing completed but no results generated")
|
||||
|
||||
except Exception as e:
|
||||
print(f"\n❌ Error: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
sys.exit(1)
|
||||
Reference in New Issue
Block a user