minibatch.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()
from sklearn.cluster import MiniBatchKMeans

data = pd.read_csv("https://raw.githubusercontent.com/ageron/handson-ml/master/datasets/housing/housing.csv")

data = data.loc[:, ["median_income", "latitude", "longitude"]]

kmeans = MiniBatchKMeans(n_clusters=6, random_state=0, batch_size=6)
data["Cluster"] = kmeans.fit_predict(data)
data["Cluster"] = data["Cluster"].astype("int")
print(data.head())


plt.style.use('seaborn-whitegrid')
plt.rc("figure", autolayout=True)
plt.rc("axes", labelweight='bold', labelsize='large', titleweight='bold', titlesize=14, titlepad=10)
sns.relplot(x='longitude', y='latitude', hue='Cluster', data=data, height=6)
plt.show()