kmeans.py

from matplotlib import pyplot as plt
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score


def calculate_wcss(data):
    wcss = []
    for i in range(1, 11):
        kmeans = KMeans(n_clusters=i, init='k-means++', max_iter=300, n_init=10, random_state=0)
        kmeans.fit(data)
        wcss.append(kmeans.inertia_)
    return wcss

def calculate_silhouette_scores(data):
    scores = []
    range_values = range(2, 11)
    for i in range_values:
        kmeans = KMeans(n_clusters=i, init='k-means++', max_iter=300, n_init=10, random_state=0)
        kmeans.fit(data)
        score = silhouette_score(data, kmeans.labels_, metric='euclidean')
        scores.append(score)
    return scores

def plot_elbow(wcss):
    plt.plot(range(1, 11), wcss)
    plt.title('Elbow Method')
    plt.xlabel('Number of clusters')
    plt.ylabel('WCSS')
    plt.show()

def get_optimal_clusters_silhouette(scores):
    optimal_clusters = scores.index(max(scores)) + 2 # +2 because range_values starts from 2
    print(f"Optimal number of clusters: {optimal_clusters}")
    return optimal_clusters

def fit_kmeans(data, n_clusters):
    kmeans = KMeans(n_clusters=n_clusters, random_state=0)
    clusters = kmeans.fit_predict(data)
    data['cluster'] = clusters
    return kmeans, data