Developing Modified KNN Approach

Question

I want to divide the training set into n partitions further besides testing set. How can I do that?

Furthermore, I'm creating these groups in the training set. How can I calculate centroid of each partition ?

Answer 1

If you already know n, you can use cluster module on scikit-learn. Here's a toy example:

# Load libraries
import pandas as pd
from sklearn.datasets import make_blobs 
from sklearn.cluster import KMeans

centers = 3 #here your n should go
# Make simulated feature matrix
features, _ = make_blobs(n_samples = 50,
                             n_features = 2,
                             centers = centers,
                             random_state = 22)

dataframe = pd.DataFrame(features, columns=["feature_1", "feature_2"]) 

# Make k-means clusterer
clusterer = KMeans(3, random_state=0) 
clusterer.fit(features) 

After fitting the model, ou can get the class labels by predict attribute:

clusterer.predict(features)

And each observation centroid is accessible through cluster_centers_:

clusterer.cluster_centers_

You can use scikit-learn documentation on this for more information.