import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
from scipy.cluster.hierarchy import dendrogram, linkage
import pandas as pd
iris = load_iris()
X = iris.data
y = iris.target
df = pd.DataFrame(X, columns=iris.feature_names)
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X)
kmeans = KMeans(n_clusters=3, random_state=42)
clusters = kmeans.fit_predict(X)
plt.figure(figsize=(8,6))
plt.scatter(X_pca[:,0], X_pca[:,1], c=clusters, cmap='viridis', alpha=0.7)
plt.title("Clusters com K-Means (visualização PCA)")
plt.xlabel("Componente Principal 1")
plt.ylabel("Componente Principal 2")
plt.show()
linked = linkage(X, 'ward')
plt.figure(figsize=(10,6))
dendrogram(linked, orientation='top', distance_sort='descending', show_leaf_counts=False)
plt.title("Dendrograma - Hierarchical Clustering")
plt.show()
