Day 45: Cluster Plot in Python

 

Day 45: Cluster Plot in Python (K-Means Explained Simply)

Today we’re visualizing how machines group data automatically using K-Means clustering.

No labels.
No supervision.
Just patterns.

Let’s break it down 👇

---

🧠 What is Clustering?

Clustering is an unsupervised learning technique where the algorithm groups similar data points together.

Imagine:

• Customers with similar buying habits

• Students with similar scores

• Products with similar features

The machine finds patterns without being told the answers.

---

🔍 What is K-Means?

K-Means is one of the most popular clustering algorithms.

It works in 4 simple steps:

1. Choose number of clusters (K)

2. Randomly place K centroids

3. Assign points to nearest centroid

4. Move centroids to the average of assigned points

5. Repeat until stable

That’s it.

---

📌 What This Code Does

1️⃣ Import Libraries

• numpy → create data

• matplotlib → visualization

• KMeans from sklearn → clustering algorithm

---

2️⃣ Generate Random Data

X = np.random.rand(100, 2)

This creates:

• 100 data points

• 2 features (x and y coordinates)

So we get 100 dots on a 2D plane.

---

3️⃣ Create K-Means Model

kmeans = KMeans(n_clusters=3, random_state=42)

We tell the model:

👉 Create 3 clusters.

---

4️⃣ Train the Model

kmeans.fit(X)

Now the algorithm:

• Finds patterns

• Groups points

• Calculates cluster centers

---

5️⃣ Get Results

labels = kmeans.labels_
centroids = kmeans.cluster_centers_

• labels → Which cluster each point belongs to

• centroids → Center of each cluster

---

6️⃣ Visualize the Clusters

plt.scatter(X[:, 0], X[:, 1], c=labels)

Each cluster gets a different color.

Then we plot centroids using:

marker='X', s=200

Big X marks = cluster centers.

---

📊 What the Graph Shows

• Different colors → Different clusters

• Big X → Center of each cluster

• Points closer to a centroid belong to that cluster

The algorithm has automatically discovered structure in random data.

That’s powerful.

---

🧠 Core Learning From This

Don’t memorize the code.

Understand the pattern:

Create Data 
Choose K
Fit Model 
Get Labels
Visualize

That’s the real workflow.

---

🚀 Where K-Means Is Used in Real Life

• Customer segmentation

• Image compression

• Market basket analysis

• Recommendation systems

• Anomaly detection

---

💡 Why This Matters

Clustering is one of the first steps into Machine Learning.

If you understand this:
You’re no longer just plotting charts.
You’re analyzing patterns.