37 lines
1.0 KiB
Python
37 lines
1.0 KiB
Python
|
from sklearn.cluster import AgglomerativeClustering
|
||
|
|
from scipy.cluster.hierarchy import dendrogram
|
||
|
|
import matplotlib.pyplot as plt
|
||
|
|
import pandas as pd
|
||
|
|
import numpy as np
|
||
|
|
|
||
|
|
FILE_PATH = "boston.csv"
|
||
|
|
FEATURES = ['LSTAT', 'CRIM']
|
||
|
|
|
||
|
|
def plot_dendrogram(model, **kwargs):
|
||
|
|
counts = np.zeros(model.children_.shape[0])
|
||
|
|
n_samples = len(model.labels_)
|
||
|
|
for i, merge in enumerate(model.children_):
|
||
|
|
current_count = 0
|
||
|
|
for child_idx in merge:
|
||
|
|
if child_idx < n_samples:
|
||
|
|
current_count += 1
|
||
|
|
else:
|
||
|
|
current_count += counts[child_idx - n_samples]
|
||
|
|
counts[i] = current_count
|
||
|
|
|
||
|
|
linkage_matrix = np.column_stack(
|
||
|
|
[model.children_, model.distances_, counts]
|
||
|
|
).astype(float)
|
||
|
|
|
||
|
|
dendrogram(linkage_matrix, **kwargs)
|
||
|
|
|
||
|
|
|
||
|
|
data = pd.read_csv(FILE_PATH)
|
||
|
|
X = data[FEATURES]
|
||
|
|
model = AgglomerativeClustering(distance_threshold=0, n_clusters=None)
|
||
|
|
model = model.fit(X)
|
||
|
|
plt.title("Hierarchical Clustering Dendrogram for Boston House Prices")
|
||
|
|
|
||
|
|
plot_dendrogram(model, truncate_mode="level", p=2)
|
||
|
|
plt.show()
|