import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

data = load_iris()

X = pd.DataFrame(data['data'], columns=data['feature_names'])
y = data['target']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

km = KMeans(n_clusters=3)
km.fit(X_train)
training_dist = km.transform(X_train)

X_train['dist1'] = training_dist[:,0]
X_train['dist2'] = training_dist[:,1]
X_train['dist3'] = training_dist[:,2]

clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)

# new data
test_dist = km.transform(X_test)

X_test['dist1'] = test_dist[:,0]
X_test['dist2'] = test_dist[:,1]
X_test['dist3'] = test_dist[:,2]

clf.predict(X_test)