-
-
Save kuchaale/db5aff34ce934604458fb0ac1030f269 to your computer and use it in GitHub Desktop.
[scikit-learn/sklearn, pandas] Plot percent of variance explained for KMeans (Elbow Method)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import matplotlib.pyplot as plt | |
import seaborn | |
from sklearn.cluster import KMeans | |
import numpy as np | |
from scipy.spatial.distance import cdist, pdist | |
def eblow(df, n): | |
kMeansVar = [KMeans(n_clusters=k).fit(df.values) for k in range(1, n)] | |
centroids = [X.cluster_centers_ for X in kMeansVar] | |
k_euclid = [cdist(df.values, cent) for cent in centroids] | |
dist = [np.min(ke, axis=1) for ke in k_euclid] | |
wcss = [sum(d**2) for d in dist] | |
tss = sum(pdist(df.values)**2)/df.values.shape[0] | |
bss = tss - wcss | |
plt.plot(bss) | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment