实施相似性搜索算法

import pandas as pd   descripciones = [         'all users must reset passwords every 90 days.',         'passwords need to be reset by all users every 90 days.',         'admin access should be restricted.',         'passwords must change for users every 90 days.',         'passwords must change for users every 80 days.'     ]  # cargar el dataset data = pd.dataframe({     'rule_id': range(1, len(descripciones) + 1),     'description': descripciones })  

from sklearn.feature_extraction.text import tfidfvectorizer from sklearn.metrics.pairwise import cosine_similarity  ! # vectorización de las descripciones con tf-idf vectorizer = tfidfvectorizer().fit_transform(data['description'])  # calcular la matriz de similitud de coseno cosine_sim_matrix = cosine_similarity(vectorizer)  # crear un diccionario para almacenar las relaciones sin duplicados def find_related_rules(matrix, rule_ids, threshold=0.8):     related_rules = {}     seen_pairs = set()  # para evitar duplicados de la forma (a, b) = (b, a)      for i in range(len(matrix)):         related = []         for j in range(i + 1, len(matrix)):  # j comienza en i + 1 para evitar duplicados             if matrix[i, j] >= threshold:                 pair = (rule_ids[i], rule_ids[j])                 if pair not in seen_pairs:                     seen_pairs.add(pair)                     related.append((rule_ids[j], round(matrix[i, j], 2)))         if related:             related_rules[rule_ids[i]] = related      return related_rules  # aplicar la función para encontrar reglas relacionadas related_rules = find_related_rules(cosine_sim_matrix, data['rule_id'].tolist(), threshold=0.8)  # mostrar las reglas relacionadas print("reglas relacionadas por similitud:") for rule, relations in related_rules.items():     print(f"rule {rule} es similar a:")     for related_rule, score in relations:         print(f"  - rule {related_rule} con similitud de {score}") 

!pip install sentence-transformers from sentence_transformers import SentenceTransformer, util   # Load the pre-trained model for generating embeddings model = SentenceTransformer('all-MiniLM-L6-v2')  # Generate sentence embeddings for each rule description embeddings = model.encode(data['Description'], convert_to_tensor=True)  # Compute the semantic similarity matrix cosine_sim_matrix = util.cos_sim(embeddings, embeddings).cpu().numpy()  # Function to find related rules based on semantic similarity def find_related_rules(matrix, rule_ids, threshold=0.8):     related_rules = {}     seen_pairs = set()  # To avoid duplicates of the form (A, B) = (B, A)      for i in range(len(matrix)):         related = []         for j in range(i + 1, len(matrix)):  # Only consider upper triangular matrix             if matrix[i, j] >= threshold:                 pair = (rule_ids[i], rule_ids[j])                 if pair not in seen_pairs:                     seen_pairs.add(pair)                     related.append((rule_ids[j], round(matrix[i, j], 2)))         if related:             related_rules[rule_ids[i]] = related      return related_rules  # Apply the function to find related rules related_rules = find_related_rules(cosine_sim_matrix, data['Rule_ID'].tolist(), threshold=0.8)  # Display the related rules print("Reglas relacionadas por similitud semántica:") for rule, relations in related_rules.items():     print(f"Rule {rule} es similar a:")     for related_rule, score in relations:         print(f"  - Rule {related_rule} con similitud de {score}")