pateelhs

# clustering.py
from sklearn.cluster import DBSCAN

def cluster_tickets_advanced(tfidf_matrix, min_samples=5, eps=0.5):
    dbscan = DBSCAN(eps=eps, min_samples=min_samples, metric='cosine')
    clusters = dbscan.fit_predict(tfidf_matrix)
    return clusters

pateelhs

import numpy as np
from sklearn.cluster import KMeans

def cluster_tickets(tfidf_matrix, num_clusters=10):
    kmeans = KMeans(n_clusters=num_clusters, random_state=42)
    clusters = kmeans.fit_predict(tfidf_matrix)
    return clusters

pateelhs

import pandas as pd
import numpy as np
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

# Module 1: Data Processing
def preprocess_text(text):
    stop_words = set(stopwords.words('english'))