Librairies utilisées¶
In [1]:
import pandas
import numpy
import matplotlib.pyplot as plt
import seaborn
seaborn.set_style("white")
from sklearn.cluster import AgglomerativeClustering
from sklearn.preprocessing import scale
Données utilisées¶
In [2]:
iris = pandas.read_table("https://fxjollois.github.io/donnees/Iris.txt", sep = "\t")
iris.head()
Out[2]:
| Sepal Length | Sepal Width | Petal Length | Petal Width | Species | |
|---|---|---|---|---|---|
| 0 | 5.1 | 3.5 | 1.4 | 0.2 | setosa |
| 1 | 4.9 | 3.0 | 1.4 | 0.2 | setosa |
| 2 | 4.7 | 3.2 | 1.3 | 0.2 | setosa |
| 3 | 4.6 | 3.1 | 1.5 | 0.2 | setosa |
| 4 | 5.0 | 3.6 | 1.4 | 0.2 | setosa |
In [3]:
iris2 = iris.drop("Species", axis = 1)
iris2.head()
Out[3]:
| Sepal Length | Sepal Width | Petal Length | Petal Width | |
|---|---|---|---|---|
| 0 | 5.1 | 3.5 | 1.4 | 0.2 |
| 1 | 4.9 | 3.0 | 1.4 | 0.2 |
| 2 | 4.7 | 3.2 | 1.3 | 0.2 |
| 3 | 4.6 | 3.1 | 1.5 | 0.2 |
| 4 | 5.0 | 3.6 | 1.4 | 0.2 |
Réalisation de la CAH¶
In [4]:
hac = AgglomerativeClustering(distance_threshold=0, n_clusters=None)
hac.fit(scale(iris2))
Out[4]:
AgglomerativeClustering(distance_threshold=0, n_clusters=None)
Réalisation du dendrogramme¶
Création d'une fonction en se basant sur cette page (avec quelques modifications)
In [5]:
from scipy.cluster.hierarchy import dendrogram
def plot_dendrogram(model, **kwargs):
# Create linkage matrix and then plot the dendrogram
# create the counts of samples under each node
counts = numpy.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 # leaf node
else:
current_count += counts[child_idx - n_samples]
counts[i] = current_count
linkage_matrix = numpy.column_stack([model.children_, model.distances_, counts]).astype(float)
# Plot the corresponding dendrogram
dendrogram(linkage_matrix, **kwargs)
Dendrogramme¶
In [11]:
plt.figure(figsize = (16, 8))
plt.title("CAH (Ward)")
plot_dendrogram(hac)
plt.axhline(y = 20, linewidth = .5, color = "dimgray", linestyle = "--")
plt.axhline(y = 10, linewidth = .5, color = "dimgray", linestyle = "--")
plt.show()
Avec proposition du nombre de classes¶
In [7]:
hac2 = AgglomerativeClustering()
hac2.fit(scale(iris2))
Out[7]:
AgglomerativeClustering()
In [8]:
hac2.labels_
Out[8]:
array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1,
1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
Avec recherche du nombre de classes demandé¶
In [9]:
hac3 = AgglomerativeClustering(n_clusters = 3)
hac3.fit(scale(iris2))
Out[9]:
AgglomerativeClustering(n_clusters=3)
In [10]:
hac3.labels_
Out[10]:
array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1,
1, 1, 1, 1, 1, 1, 0, 0, 0, 2, 0, 2, 0, 2, 0, 2, 2, 0, 2, 0, 2, 0,
2, 2, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 2, 2, 0, 2, 0, 0, 2,
2, 2, 2, 0, 2, 2, 2, 2, 2, 0, 2, 2, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])