Spectral

class geoanalytics.clustering.Spectral.Spectral(dataframe)

Bases: object

About this algorithm

Description:

Spectral Clustering uses graph-based methods to cluster points based on the eigenvalues of a similarity matrix. It’s particularly effective for complex cluster shapes that traditional methods like KMeans may not detect.

Parameters:

• dataframe (pd.DataFrame) – Input dataset where the first two columns are assumed to be spatial (‘x’, ‘y’) and all remaining columns are used for clustering.

Attributes:

• df (pd.DataFrame) – Cleaned and formatted input data.

• labelsDF (pd.DataFrame) – Output containing ‘x’, ‘y’, and assigned cluster labels.

Execution methods

import pandas as pd

from goeAnalytics.clustering import Spectral

df = pd.read_csv("data.csv")

obj = Spectral(df)

obj.clustering(n_clusters=4)

labels_df = output[0]

obj.save(outputFile="SpectralLabels.csv")

Credits

This implementation was created and revised under the guidance of Professor Rage Uday Kiran.

getMemoryRSS()

Prints the memory usage (RSS) of the process in kilobytes.

getMemoryUSS()

Prints the memory usage (USS) of the process in kilobytes.

getRuntime()

Prints the total runtime of the clustering algorithm.

run(n_clusters=8, assign_labels='discretize')

Applies Spectral Clustering to the dataset.

Parameters:

• n_clusters – Number of clusters to form.

• assign_labels – Method for assigning labels after clustering (‘kmeans’ or ‘discretize’).

Returns:

A DataFrame containing x, y, and assigned labels.

save(outputFile='SpectralLabels.csv')

Saves the clustering results to a CSV file.

Parameters:

outputFile – Filename to save the resulting DataFrame.