CSC310-fall25/seeds-clustering

Model description

K-Means clustering model trained on wheat seeds dataset to identify 3 types of wheat seeds based on 7 morphological features. The model groups seeds into clusters that correspond to different wheat varieties.

Intended uses & limitations

[More Information Needed]

Training Procedure

[More Information Needed]

Hyperparameters

Click to expand

Hyperparameter	Value
algorithm	lloyd
copy_x	True
init	k-means++
max_iter	300
n_clusters	3
n_init	auto
random_state	80
tol	0.0001
verbose	0

Model Plot

KMeans(n_clusters=3, random_state=80)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Evaluation Results

[More Information Needed]

How to Get Started with the Model

from huggingface_hub import hf_hub_download
import skops.io as sio
import pandas as pd

# Download model and test data
hf_hub_download(repo_id='CSC310-fall25/seeds-clustering', filename='model.pkl', local_dir='.')
hf_hub_download(repo_id='CSC310-fall25/seeds-clustering', filename='test_data.csv', local_dir='.')

# Load model and data
model = sio.load('model.pkl')
test_data = pd.read_csv('test_data.csv')

# Prepare features (exclude wheat_type for clustering)
X_test = test_data.drop('wheat_type', axis=1)

# Make cluster predictions
cluster_labels = model.predict(X_test)

Model Card Authors

Christian Romualdo

Model Card Contact

[email protected]

Citation

Wheat Seeds Dataset from UCI Machine Learning Repository

Intended uses & limitations

This clustering model is made for educational purposes and identifies 3 wheat seed types. Performance depends on feature scaling and random initialization.

Training Procedure

Trained K-Means with 3 clusters on wheat seeds morphological data. Used 80% of data for training, 20% for testing. Evaluation metrics: Silhouette Score and Adjusted Mutual Information (AMI).

Evaluation Results

Training Silhouette Score: 0.480 Adjusted Mutual Information: 0.722 The model shows good separation between wheat types, with clusters aligning well with true labels as shown in the confusion matrix and scatter plots.