# main.py

# A demonstration of hierarchical clustering using SciPy and Matplotlib.

#

# Before running, you may need to install scipy, scikit-learn, and matplotlib:

# pip install scipy scikit-learn matplotlib

import numpy as np

import matplotlib.pyplot as plt

import os

from sklearn.datasets import make_blobs

from scipy.cluster.hierarchy import dendrogram, linkage

print("--- Starting Hierarchical Clustering Demonstration with SciPy ---")

# --- Section 1: Generate Sample Dataset ---

# We will create a small dataset to make the dendrogram easy to interpret.

print("\n--- 1. Generating Sample Dataset ---")

# Create 15 data points in 3 loose clusters

X, y = make_blobs(n_samples=15, centers=3, n_features=2, random_state=42)

print("Sample data has been generated.")

# --- Section 2: Perform Hierarchical Clustering ---

# We use the 'linkage' function from SciPy to perform agglomerative clustering.

# 'ward' is a method that minimizes the variance of the clusters being merged.

print("\n--- 2. Performing Agglomerative Hierarchical Clustering ---")

linked = linkage(X, method='ward')

print("Linkage matrix has been created.")

# --- Section 3: Visualize the Dendrogram ---

# A dendrogram is a tree diagram that shows the hierarchical relationship

# between clusters. It illustrates the order in which data points and

# clusters were merged.

print("\n--- 3. Visualizing the Results as a Dendrogram ---")

try:

    plt.figure(figsize=(12, 8))

    dendrogram(

        linked,

        orientation='top',

        labels=range(1, len(X) + 1), # Label each point from 1 to 15

        distance_sort='descending',

        show_leaf_counts=True

    )

    plt.title('Hierarchical Clustering Dendrogram')

    plt.xlabel('Data Point Index')

    plt.ylabel('Euclidean Distance (Cluster Dissimilarity)')

    plt.grid(axis='y', linestyle='--')

    # Save the plot to a file

    plot_filename = 'hierarchical_dendrogram.png'

    plt.savefig(plot_filename)

    print(f"\nDendrogram saved as '{plot_filename}'")

    plt.show() # Display the plot

    plt.close()

except Exception as e:

    print(f"An error occurred during visualization: {e}")

# --- Clean up the created image file ---

finally:

    print("\n--- Cleaning up created image file ---")

    if 'plot_filename' in locals() and os.path.exists(plot_filename):

        os.remove(plot_filename)

        print(f"Removed '{plot_filename}'")

print("\n--- End of Demonstration ---")