File size: 6,297 Bytes
486eff6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 |
#!/usr/bin/env python3
"""
Word Similarity Engine using Dictionary Embeddings
Reads dictionary from CSV, creates embeddings for all words,
and provides similarity search functionality.
"""
import os
import csv
import numpy as np
from typing import List, Tuple
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
class WordSimilarityEngine:
def __init__(self, cache_dir: str = None):
"""Initialize the word similarity engine.
Args:
cache_dir: Directory to cache the embedding model
"""
if cache_dir is None:
cache_dir = os.path.join(os.path.dirname(__file__), 'model_cache')
self.cache_dir = cache_dir
os.makedirs(cache_dir, exist_ok=True)
# Load embedding model with caching
print("Loading embedding model...")
self.model = SentenceTransformer(
'sentence-transformers/all-mpnet-base-v2',
cache_folder=cache_dir
)
print("Model loaded successfully.")
# Load dictionary and create embeddings
self.words = self._load_dictionary()
print(f"Loaded {len(self.words)} words from dictionary.")
print("Creating embeddings for all words...")
self.embeddings = self._create_embeddings()
print("Embeddings created successfully.")
def _load_dictionary(self) -> List[str]:
"""Load words from the dictionary CSV file."""
dict_path = os.path.join(os.path.dirname(__file__), 'dict-words', 'dict.csv')
words = []
try:
with open(dict_path, 'r', encoding='utf-8') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
word = row['word'].strip().lower()
if word and len(word) > 1: # Include words with 2+ characters
words.append(word)
except FileNotFoundError:
raise Exception(f"Dictionary file not found: {dict_path}")
except Exception as e:
raise Exception(f"Error reading dictionary: {e}")
return words
def _create_embeddings(self) -> np.ndarray:
"""Create embeddings for all dictionary words."""
# Create embeddings in batches for efficiency
batch_size = 256
all_embeddings = []
for i in range(0, len(self.words), batch_size):
batch_words = self.words[i:i + batch_size]
batch_embeddings = self.model.encode(
batch_words,
convert_to_tensor=False,
show_progress_bar=True if i == 0 else False
)
all_embeddings.append(batch_embeddings)
return np.vstack(all_embeddings)
def find_similar_words(self, word: str, top_k: int = 10, min_similarity: float = 0.3) -> List[Tuple[str, float]]:
"""Find words similar to the input word.
Args:
word: Input word to find similarities for
top_k: Number of similar words to return
min_similarity: Minimum similarity threshold
Returns:
List of tuples (word, similarity_score) sorted by similarity
"""
word = word.strip().lower()
# Check if word exists in our dictionary
if word not in self.words:
print(f"Warning: '{word}' not found in dictionary. Computing similarity anyway...")
# Get embedding for input word
input_embedding = self.model.encode([word])
# Compute similarities with all dictionary words
similarities = cosine_similarity(input_embedding, self.embeddings)[0]
# Get indices of most similar words
similar_indices = np.argsort(similarities)[::-1]
# Filter and format results
results = []
for idx in similar_indices:
similarity_score = similarities[idx]
similar_word = self.words[idx]
# Skip the input word itself and apply minimum threshold
if similar_word != word and similarity_score >= min_similarity:
results.append((similar_word, similarity_score))
if len(results) >= top_k:
break
return results
def get_word_embedding(self, word: str) -> np.ndarray:
"""Get embedding for a specific word."""
return self.model.encode([word.strip().lower()])[0]
def main():
"""Demo the word similarity functionality."""
# Initialize the engine
engine = WordSimilarityEngine()
# Test words
test_words = ["cat", "science", "computer", "ocean", "music"]
print("\n" + "="*60)
print("WORD SIMILARITY DEMO")
print("="*60)
for test_word in test_words:
print(f"\nWords similar to '{test_word}':")
print("-" * 30)
similar_words = engine.find_similar_words(test_word, top_k=8)
if similar_words:
for word, score in similar_words:
print(f" {word:<15} (similarity: {score:.3f})")
else:
print(" No similar words found.")
# Interactive mode
print("\n" + "="*60)
print("INTERACTIVE MODE (type 'quit' to exit)")
print("="*60)
while True:
try:
user_word = input("\nEnter a word to find similar words: ").strip()
if user_word.lower() == 'quit':
break
if not user_word:
continue
print(f"\nWords similar to '{user_word}':")
print("-" * 30)
similar_words = engine.find_similar_words(user_word, top_k=50)
if similar_words:
for word, score in similar_words:
print(f" {word:<15} (similarity: {score:.3f})")
else:
print(" No similar words found.")
except KeyboardInterrupt:
break
except Exception as e:
print(f"Error: {e}")
print("\nGoodbye!")
if __name__ == "__main__":
main()
|