# --- Import Required Libraries ---
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_iris
from sklearn.cluster import KMeans

# --- Load the Iris Dataset ---
data = load_iris()
X = pd.DataFrame(data.data, columns=data.feature_names)

# --- Apply K-Means Clustering ---
kmeans = KMeans(n_clusters=3, random_state=42)
kmeans.fit(X)

# --- Add Predicted Cluster Labels to the DataFrame ---
X['Cluster'] = kmeans.labels_

# --- Add Actual Species Names for Comparison ---
X['Actual'] = [data.target_names[i] for i in data.target]

# --- Display the First Few Rows of the Dataset ---
print("Sample of clustered data:")
print(X.head())
print("\nCluster Centers:")
print(kmeans.cluster_centers_)

# --- Visualization 1: K-Means Clusters ---
plt.figure(figsize=(8, 6))
sns.scatterplot(
    data=X,
    x='petal length (cm)',
    y='petal width (cm)',
    hue='Cluster',
    palette='viridis',
    s=80
)
plt.title("K-Means Clustering on Iris Dataset", fontsize=14)
plt.xlabel("Petal Length (cm)")
plt.ylabel("Petal Width (cm)")
plt.legend(title="Cluster", loc="upper left")
plt.show()

# --- Visualization 2: Actual Species ---
plt.figure(figsize=(8, 6))
sns.scatterplot(
    data=X,
    x='petal length (cm)',
    y='petal width (cm)',
    hue='Actual',
    palette='Set2',
    s=80
)
plt.title("Actual Iris Species", fontsize=14)
plt.xlabel("Petal Length (cm)")
plt.ylabel("Petal Width (cm)")
plt.legend(title="Species", loc="upper left")
plt.show()

        __
        __