gistfile1.txt

from sklearn.cluster import KMeans
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder

gistfile2.txt

k_rng = range(1,10)
sse =[]
for k in k_rng:
  km = KMeans(n_clusters = k)
  km.fit(salary_story[['Total Salary Paid Rescaled', 'Home Price Rescaled']])
  sse.append(km.inertia_)

gistfile3.txt

plt.xlabel('K')
plt.ylabel('Sum of squared error')
plt.plot(k_rng, sse)