26/03/2024, 22:11 Clustering assignment - Colaboratory
Q1. Read aggregation data and display the first five rows of the data set
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')
from pandas import Series, DataFrame
data = pd.read_excel('Clustering_Assignment_dataset.xlsx')
print(data.head())
x y c
0 15.55 28.65 2
1 14.90 27.55 2
2 14.45 28.35 2
3 14.15 28.80 2
4 13.75 28.05 2
Q2. Plot the data with different colors different labels
from matplotlib.colors import ListedColormap
import pandas as pd
import matplotlib.pyplot as plt
plt.figure(figsize=(10, 6))
plt.scatter(data['x'], data['y'], c=data['c'], cmap='viridis')
plt.xlabel('X')
plt.ylabel('Y')
plt.title('Scatter Plot with Different Labels')
plt.colorbar(label='Intensity')
plt.show()
Q3. Find the labels using k means
https://colab.research.google.com/drive/1u1Ez1GFA_I2X5Lec-lac8A5fhF8BWZqt?usp=sharing#scrollTo=4GWVpJAnkF-h&printMode=true 1/3
26/03/2024, 22:12 Clustering assignment - Colaboratory
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
kmeans = KMeans(n_clusters=3, random_state=42)
kmeans.fit(data)
labels = kmeans.labels_
kmeans.labels_
array([2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 2, 2, 0, 2, 2,
2, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], dtype=int32)
Q4. Find the cluster centre
import pandas as pd
from sklearn.cluster import KMeans
kmeans = KMeans(n_clusters=3, random_state=42)
kmeans.fit(data)
cluster_centers = kmeans.cluster_centers_
print("Cluster Centers:")
print(cluster_centers)
Cluster Centers:
[[32.63702929 16.35020921 4.57322176]
[15.32228739 7.27903226 4.39882698]
[11.50721154 22.96875 1.81730769]]
Q5. Find the number of data in each cluster. Create plots for clusters
import pandas as pd import matplotlib.pyplot as plt from sklearn.cluster import KMeans
kmeans = KMeans(n_clusters=3, random_state=42) kmeans.fit(data)
labels = kmeans.labels_
unique, counts = np.unique(labels, return_counts=True) cluster_counts = dict(zip(unique, counts))
print("Number of data points in each cluster:") print(cluster_counts)
https://colab.research.google.com/drive/1u1Ez1GFA_I2X5Lec-lac8A5fhF8BWZqt?usp=sharing#scrollTo=4GWVpJAnkF-h&printMode=true 2/3
26/03/2024, 22:12 Clustering assignment - Colaboratory
plt.figure(figsize=(12, 8))
for i in range(len(cluster_centers)): cluster_data = data[labels == i] plt.scatter(cluster_data.iloc[:, 0], cluster_data.iloc[:, 1], label=f'Cluster {i+1}')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=300, c='black', marker='*', label='Centroids') plt.title('Clusters')
plt.xlabel('X Axis') plt.ylabel('Y Axis') plt.legend() plt.grid(True) plt.show()
Could not connect to the reCAPTCHA service. Please check your internet connection and reload to get a reCAPTCHA challenge.
https://colab.research.google.com/drive/1u1Ez1GFA_I2X5Lec-lac8A5fhF8BWZqt?usp=sharing#scrollTo=4GWVpJAnkF-h&printMode=true 3/3
