# In[59]:
df = kmeans.labels_
df = pd.DataFrame(df)
df2 = pd.concat([df, data1], axis=1)
df2
# In[40]:
cluster = pd.read_csv('cluster.csv')
# In[ ]:
# In[41]:
np.sum(cluster.isnull())
# In[42]:
kmeans.set_params(n_clusters=10)
kmeans.fit(cluster)
# In[29]:
kmeans.cluster_centers_
# In[30]:
plt.scatter(cluster['Rev_growth'], cluster['ROE'], c=kmeans.labels_, alpha=0.8)
#plt.scatter(kmeans.cluster_centers_['EV_ebitda_ttm'], kmeans.cluster_centers_['ROA'], marker="+", s=1000, c=[0, 1, 2])
plt.xlabel('Rev_growth')
