👀 Views: 1 💬 Answers: 1 📅 Created: 2025-06-08

python k-means machine-learning Python

I'm stuck trying to I keep running into I've tried everything I can think of but I'm trying to figure out I've looked through the documentation and I'm still confused about I'm working with an scenario with my K-Means clustering implementation in Python using the `scikit-learn` library... I have a dataset of 5,000 points with 2 features, and I notice that each time I run the algorithm with the same parameters, I get different cluster assignments even with the same random seed. I'm using `KMeans` from `sklearn.cluster` and setting the number of clusters to 3. Here’s a simplified version of my code: ```python import numpy as np import matplotlib.pyplot as plt from sklearn.cluster import KMeans # Generate random data np.random.seed(42) data = np.random.rand(5000, 2) # K-Means clustering kmeans = KMeans(n_clusters=3, random_state=42) labels = kmeans.fit_predict(data) # Visualize the clusters plt.scatter(data[:, 0], data[:, 1], c=labels, cmap='viridis') plt.title('K-Means Clustering') plt.show() ``` I expected the clusters to be consistent on re-runs, but the clusters seem to change significantly each time. I tried fixing the `random_state`, but the assignments still vary. I also checked the convergence warning: ``` ConvergenceWarning: Number of distinct clusters (2) found smaller than n_clusters (3). Possibly due to duplicate points in X. ``` This warning leads me to think that I might have duplicate points in my dataset, but I’ve confirmed that the dataset is diverse. Is it possible that the K-Means algorithm is sensitive to input data in this way, and how can I ensure more consistent results? Any advice or best practices would be greatly appreciated. I'm on macOS using the latest version of Python. What would be the recommended way to handle this? This issue appeared after updating to Python 3.10. Thanks for taking the time to read this! What am I doing wrong? For context: I'm using Python on CentOS.