UofT-DSI | LCR - Assignment 3

[akorade]

What changes are you trying to make? (e.g. Adding or removing code, refactoring existing code, adding reports)

I completed Assignment 3 by implementing clustering and bootstrapping analysis on the Wine dataset from scikit-learn. The changes include:

Data Inspection: Loaded the Wine dataset and examined its structure (178 observations, 13 features)
Data Visualization: Created scatter plots to explore relationships between chemical properties
Data Standardization: Applied StandardScaler to normalize feature scales before clustering
K-Means Clustering: Implemented K-Means with k=3 clusters and visualized the results
Bootstrapping Analysis: Generated 10,000 bootstrap samples of color intensity mean and calculated a 90% confidence interval
Interpretation: Provided answers to conceptual questions about standardization, clustering methods, and bootstrap reliability

What did you learn from the changes you have made?

Feature Scaling Importance: Understanding how K-Means relies on distance metrics and why standardization is critical to prevent high-variance features (like Proline) from dominating the clustering results
Elbow Method: Recognized that determining optimal cluster numbers requires visual analysis of inertia plots to identify diminishing returns
Bootstrap Confidence: Learned that bootstrap resampling provides empirical estimates of sampling distributions without strong parametric assumptions
Variability Assessment: Discovered that a narrow confidence interval indicates reliable and stable estimates of population parameters

Was there another approach you were thinking about making? If so, what approach(es) were you thinking of?

NA

Were there any challenges? If so, what issue(s) did you face? How did you overcome it?

NA

How were these changes tested?

Locally on visual studio code

A reference to a related issue in your repository (if applicable)

NA

Checklist

• I can confirm that my changes are working as intended

[Aditya-k-23]

Well written code and complete submission. Well done!