Identifying Groups of climate regions by humidity and sunshine Through K-Means with PCA Visualisation

Project info

• Field of studyMeteorology and Climate
• LevelDoctoral dissertation (S3)
• Method typeClustering
• Estimated build time± 7 working days
• Toolsscikit-learn KMeans, PCA, StandardScaler
• PriceUS$31 - US$197

Research goal

Group region by mean humidity and sunshine duration with K-Means with PCA Visualisation, then interpret the characteristics of each resulting cluster.

Variables

Example result

• 3Clusters k
• 0.569Silhouette
• 85.962Var. explained PC1+PC2 %
• 0.636Davies-Bouldin
• 234.694Calinski-Harabasz
• 0.707ARI vs. true groups

K-Means forms 3 clusters on 6 indicators (silhouette 0.569); the first two principal components hold 86.0% of the variance, enough to visualise the clusters.

Computed from illustrative synthetic data, not from a real study.

About K-Means with PCA Visualisation

K-Means with PCA visualisation clusters high-dimensional data and then projects it onto two principal components so clusters can be seen. It suits presenting multivariate segmentation results in one readable figure.

Steps

1. 1Standardise all features
2. 2Run K-Means in the original feature space
3. 3Compute a two-component PCA and variance ratio
4. 4Project data and cluster centres into PCA space
5. 5Plot points coloured by cluster
6. 6Profile clusters and inspect PCA loadings

Assumptions to check

• Clusters are computed on original features, PCA is only for display
• The first two components retain enough variance so the plot is not misleading
• Features are standardised

Reading and reporting the results

Report the percentage of variance explained by the first two components so readers know how faithful the plot is. Describe clusters through original feature means, not only plot position.

Example Python code

A short starting script with this project's variable names. The delivered version is adapted to your data and fully commented.

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler

X, _ = make_blobs(n_samples=400, n_features=6, centers=4, cluster_std=1.5, random_state=19)
Xs = StandardScaler().fit_transform(X)
mean_humidity = Xs[:, 0]
sunshine_duration = Xs[:, 1]

km = KMeans(n_clusters=4, n_init=10, random_state=19).fit(Xs)
region = km.labels_

pca = PCA(n_components=2).fit(Xs)
Z = pca.transform(Xs)
C = pca.transform(km.cluster_centers_)
print("Explained variance ratio:", pca.explained_variance_ratio_.round(3))
print("Total (2 PCs):", round(pca.explained_variance_ratio_.sum(), 3))
print("Cluster sizes:", np.bincount(region))
print("Cluster means (first 3 features):\n", km.cluster_centers_[:, :3].round(2))

plt.scatter(Z[:, 0], Z[:, 1], c=region, s=15)
plt.scatter(C[:, 0], C[:, 1], c="r", marker="x", s=100)
plt.xlabel("PC1"); plt.ylabel("PC2")
plt.show()

Packages and prices

Choose how much help you need. Each higher package includes everything in the lower ones. Prices exclude 11% VAT.

• Payment: 50% down payment before work starts, balance after the deliverables are handed over
• Tax: Prices exclude 11% VAT
• Data and academic integrity: Results are computed from your own research data; you write and stand behind your manuscript, we help with the analysis and your understanding of it
• Revisions: Up to 2 revisions are included in the price (Package 3: 3 rounds)

Frequently asked questions