kmeans_(pie_chart) EXTERNAL

# Import required libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler, MinMaxScaler
from sklearn.cluster import KMeans

# Given Data
data = {
    'Feature1': [10, 20, 30, 40, 50],
    'Feature2': [100, 200, 300, 400, 500]
}

# Step 1: Create a DataFrame
df = pd.DataFrame(data)

# Step 1.1: Apply Standard Scaler
scaler_standard = StandardScaler()
df_standard = scaler_standard.fit_transform(df)

# Step 1.2: Apply Min-Max Scaler
scaler_minmax = MinMaxScaler()
df_minmax = scaler_minmax.fit_transform(df)

# Step 2: Apply KMeans Clustering (2 clusters for demonstration)
kmeans = KMeans(n_clusters=2, random_state=42)

# Fitting KMeans on both scaled datasets
kmeans_standard = kmeans.fit_predict(df_standard)
kmeans_minmax = kmeans.fit_predict(df_minmax)

# Step 3: Pie Chart Visualization for KMeans (using standard scaled data as an example)
# Count the occurrences of each cluster
labels_standard = pd.Series(kmeans_standard).value_counts()

# Plot the pie chart
plt.figure(figsize=(6, 6))
plt.pie(labels_standard, labels=[f"Cluster {i}" for i in labels_standard.index], autopct='%1.1f%%', startangle=90)
plt.title('Pie Chart of KMeans Clusters (Standard Scaled Data)')
plt.show()