K-Means
from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
import pandas as pd
import matplotlib.pyplot as plt
iris = load_iris()
# Criação do DataFrame para facilitar a análise
df = pd.DataFrame( iris.data, columns=iris.feature_names)
display(df)
X = df[["petal length (cm)", "petal width (cm)"]]
kmeans = KMeans(n_clusters=3, random_state=42, n_init=10)
clusters = kmeans.fit_predict(X)
# Adiciona o cluster encontrado ao DataFrame
df["Cluster"] = clusters
display(df)
# Coordenadas dos centróides
centroides = kmeans.cluster_centers_
plt.figure(figsize=(8, 6))
plt.scatter(
X["petal length (cm)"],
X["petal width (cm)"],
c=clusters,
cmap="viridis",
s=60,
alpha=0.8,
label="Flores"
)
# Desenha os centróides
plt.scatter(
centroides[:, 0],
centroides[:, 1],
marker="X",
s=250,
color="red",
label="Centróides"
)
plt.title("Clusterização do Dataset Iris com K-Means")
plt.xlabel("Comprimento da Pétala (cm)")
plt.ylabel("Largura da Pétala (cm)")
plt.legend()
plt.grid(True)
plt.show()
print(df["Cluster"].value_counts().sort_index())
Agrupamento HIerarquico
rom sklearn.datasets import load_iris
import scipy.cluster.hierarchy as sch
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
# Carregar o dataset Iris
iris = load_iris()
X = iris.data
# Normalizar os dados para melhorar a performance do clustering
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
# Criar o dendrograma
plt.figure(figsize=(10, 5))
sch.dendrogram(sch.linkage(X_scaled, method='ward'))
plt.title("Dendrograma do Agrupamento Hierárquico")
plt.xlabel("Amostras")
plt.ylabel("Distância Euclidiana")
plt.show()
from sklearn.cluster import AgglomerativeClustering
# Aplicar Hierarchical Clustering definindo 3 grupos
hc = AgglomerativeClustering(n_clusters=3, metric='euclidean', linkage='ward')
clusters = hc.fit_predict(X_scaled)
# Visualizar os clusters
plt.scatter(X[:, 0], X[:, 1], c=clusters, cmap='viridis')
plt.title("Agrupamento com Hierarchical Clustering")
plt.xlabel("Característica 1")
plt.ylabel("Característica 2")
plt.show()
PCA
from sklearn.datasets import load_iris
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
# Carregar dados
iris = load_iris()
X = iris.data
# Padronizar
X_scaled = StandardScaler().fit_transform(X)
# Reduzir de 4 para 2 dimensões
X_pca = PCA(n_components=2).fit_transform(X_scaled)
# Aplicar K-Means nos dados reduzidos
kmeans = KMeans(n_clusters=3, random_state=42)
clusters = kmeans.fit_predict(X_pca)
# Visualizar clusters
plt.figure(figsize=(8,5))
plt.scatter(X_pca[:, 0], X_pca[:, 1], c=clusters)
plt.scatter(
kmeans.cluster_centers_[:, 0],
kmeans.cluster_centers_[:, 1],
marker='X',
s=200
)
plt.xlabel("PC1")
plt.ylabel("PC2")
plt.title("K-Means após PCA")
plt.show()
