Spaces:
Sleeping
Sleeping
File size: 5,813 Bytes
a318724 beeb862 18ec5e9 a318724 18ec5e9 cf30a67 18ec5e9 cf30a67 18ec5e9 ba66486 18ec5e9 beeb862 18ec5e9 beeb862 18ec5e9 a318724 ba66486 18ec5e9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 |
import pickle
import json
import os
class SafeProgress:
"""Wrapper for progress tracking that handles None gracefully"""
def __init__(self, progress_obj=None):
self.progress = progress_obj
def __call__(self, value, desc=""):
if self.progress is not None:
try:
self.progress(value, desc=desc)
except:
print(f"Progress {value}: {desc}")
else:
print(f"Progress {value}: {desc}")
def load_embeddings(embeddings_path):
"""Load ingredient embeddings from pickle file"""
print(f"Loading ingredient embeddings from {embeddings_path}")
with open(embeddings_path, "rb") as f:
ingredients_embeddings = pickle.load(f)
print(f"Loaded {len(ingredients_embeddings)} ingredient embeddings")
return ingredients_embeddings
def parse_product_file(file_path):
"""Parse a file containing product data and extract product names"""
try:
with open(file_path, 'r') as f:
try:
products_data = json.load(f)
if isinstance(products_data, list):
# Extract product names if it's a list of objects with 'name' field
if all(isinstance(item, dict) for item in products_data):
product_names = [item.get('name', '') for item in products_data if isinstance(item, dict)]
else:
# If it's just a list of strings
product_names = [str(item) for item in products_data if item]
else:
# If it's just a list of product names
product_names = []
except json.JSONDecodeError:
# If not JSON, try reading as text file with one product per line
f.seek(0)
product_names = [line.strip() for line in f.readlines() if line.strip()]
except Exception as e:
raise Exception(f"Error reading file: {str(e)}")
return product_names
def format_categories_html(product, similarities, chicory_result=None):
"""Format the similarities as HTML with bootstrap styling"""
html = f"<div class='product-result'><h3 style='color: #fff;'>{product}</h3>"
# Add Chicory results with enhanced styling
if chicory_result:
html += "<div class='result-section chicory-section' style='background-color: #1a3c6e; color: white; padding: 15px; border-radius: 5px; margin: 10px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);'>"
html += "<h4 style='margin-top: 0; border-bottom: 1px solid rgba(255,255,255,0.3); padding-bottom: 8px;'>Chicory Parser Results</h4>"
if isinstance(chicory_result, dict):
# Extract important fields with better formatting
ingredient = chicory_result.get("ingredient", "Not found")
confidence = chicory_result.get("confidence", 0)
confidence_pct = int(confidence * 100) if confidence else 0
html += f"<div style='display: flex; justify-content: space-between; align-items: center; background-color: rgba(255,255,255,0.1); padding: 10px; border-radius: 4px;'>"
html += f"<span style='font-size: 1.1em;'>{ingredient}</span>"
html += f"<span style='background-color: {get_confidence_bg_color(confidence)}; color: {get_confidence_text_color(confidence)}; padding: 4px 8px; border-radius: 12px; font-weight: bold;'>{confidence_pct}%</span>"
html += "</div>"
html += "</div>"
# Add embedding similarities with matching styling
if similarities:
html += "<div class='result-section embedding-section' style='background-color: #263238; color: white; padding: 15px; border-radius: 5px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);'>"
html += "<h4 style='margin-top: 0; border-bottom: 1px solid rgba(255,255,255,0.3); padding-bottom: 8px;'>Embedding Similarity</h4>"
for i, (ingredient, score) in enumerate(similarities):
confidence_pct = int(score * 100)
html += f"<div style='display: flex; justify-content: space-between; align-items: center; padding: 8px; border-radius: 4px; margin: 4px 0; background-color: rgba(255,255,255,{0.07 + (i * 0.01)});'>"
html += f"<span>{ingredient}</span>"
html += f"<span style='background-color: {get_confidence_bg_color(score)}; color: {get_confidence_text_color(score)}; padding: 4px 8px; border-radius: 12px; font-weight: bold;'>{confidence_pct}%</span>"
html += "</div>"
html += "</div>"
else:
html += "<p style='color: #b0bec5; font-style: italic; padding: 10px; background-color: rgba(255,255,255,0.05); border-radius: 4px; margin: 10px 0;'>No similar ingredients found above the confidence threshold.</p>"
html += "</div>"
return html
def get_confidence_color(score):
"""Get color based on confidence score"""
if score >= 0.8:
return "#1a8a38" # Strong green
elif score >= 0.65:
return "#4caf50" # Medium green
elif score >= 0.5:
return "#8bc34a" # Light green
else:
return "#9e9e9e" # Gray
def get_confidence_bg_color(score):
"""Get background color for confidence badge based on score"""
if score >= 0.8:
return "#2e7d32" # Dark green
elif score >= 0.65:
return "#558b2f" # Medium green
elif score >= 0.5:
return "#9e9d24" # Light green/yellow
else:
return "#757575" # Gray
def get_confidence_text_color(score):
"""Get text color that's readable on the confidence background"""
if score >= 0.5:
return "#ffffff" # White text on dark backgrounds
else:
return "#f5f5f5" # Light gray on gray background |