# Run the kmeans model on scaled data
kmeans = KMeans(n_clusters=6, random_state=42).fit(X_scaled)

# Get the cluster number for each datapoint
X_clusters = kmeans.predict(X_scaled)

# Save the cluster centroids
X_clusters_centers = kmeans.cluster_centers_

# Calculate the distance to the cluster centroid for each point
dist = [np.linalg.norm(x-y) for x,y in zip(X_scaled,
X_clusters_centers[X_clusters])]

# Create predictions based on distance
km_y_pred = np.array(dist)
km_y_pred[dist>=np.percentile(dist, 93)] = 1
km_y_pred[dist<np.percentile(dist, 93)] = 0