Project: Clustering techniques for ecological research

Alt text source: @allison_horst https://github.com/allisonhorst/penguins

You have been asked to support a team of researchers who have been collecting data about penguins in Antartica! The data is available in csv-Format as penguins.csv

Origin of this data : Data were collected and made available by Dr. Kristen Gorman and the Palmer Station, Antarctica LTER, a member of the Long Term Ecological Research Network.

The dataset consists of 5 columns.

Column	Description
culmen_length_mm	culmen length (mm)
culmen_depth_mm	culmen depth (mm)
flipper_length_mm	flipper length (mm)
body_mass_g	body mass (g)
sex	penguin sex

Unfortunately, they have not been able to record the species of penguin, but they know that there are at least three species that are native to the region: Adelie, Chinstrap, and Gentoo. Your task is to apply your data science skills to help them identify groups in the dataset!

# Import required packages
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler

# Loading and examining the dataset
penguins_df = pd.read_csv("penguins.csv")
penguins_df.head()

## Preprocess dataset
# Use get_dummies method on the categorical feature
penguins_dummies = pd.get_dummies(penguins_df['sex'], drop_first=True)
penguins = pd.concat([penguins_df, penguins_dummies], axis=1)
penguins = penguins.drop('sex', axis=1)

# Standardise and scale before clustering
scaler = StandardScaler()
penguins_scaled = scaler.fit_transform(penguins)

## Detect the optimal number of clusters for k-means clustering
# Create an empty list to store inertia values
inertia_list = []

# Loop through cluster numbers from 1 to 9
for k in range(1, 10):
    # Apply KMeans clustering
    kmeans = KMeans(n_clusters=k, random_state=42)
    kmeans.fit(penguins_scaled)
    
    # Store the inertia for each K
    inertia_list.append(kmeans.inertia_)

# Visualize the inertia values (Elbow plot)
plt.figure(figsize=(8, 5))
plt.plot(range(1, 10), inertia_list, marker='o', linestyle='-', color='b')
plt.title('Elbow method for optimal number of clusters', fontweight='bold')
plt.xlabel('Number of clusters', fontweight='bold')
plt.ylabel('Inertia', fontweight='bold')
plt.grid(True)
plt.show()

## Run the k-means clustering algorithm
# Apply KMeans with 6 clusters
kmeans = KMeans(n_clusters=6, random_state=42)
kmeans.fit(penguins_scaled)

# Get cluster labels for each data point
cluster_labels = kmeans.labels_

# Add cluster labels to the original DataFrame
penguins['cluster'] = cluster_labels

## Visualize the clusters

# Calculate variance to guide feature selection
variance = penguins[['culmen_length_mm', 'culmen_depth_mm', 'flipper_length_mm', 'body_mass_g']].var()

# Display variance
print(variance.sort_values(ascending=False))

# Plot 2 features with the highest variance: body mass vs flipper length
plt.figure(figsize=(10, 6))
plt.scatter(penguins['body_mass_g'], penguins['flipper_length_mm'], c=cluster_labels, 
            edgecolor='k', s=80) # Edge and size of markers

plt.title('K-Means clustering (k=6): body mass vs flipper length', fontweight='bold')
plt.xlabel('Body mass (mm)', fontweight='bold')
plt.ylabel('Flipper length (mm)', fontweight='bold')
plt.grid(True)
plt.colorbar(label='Cluster')  # Color bar to indicate cluster labels
plt.show()

## Create a final characteristic table for each cluster
# Identify numeric (non-binary) columns
numeric_columns = ['culmen_length_mm', 'culmen_depth_mm', 'flipper_length_mm', 'body_mass_g']

# Add cluster labels to the dataset
penguins_df['label'] = kmeans.labels_  # Assign cluster labels from KMeans

# Aggregate data using groupby and calculate the mean for each cluster
stat_penguins = penguins_df.groupby('label')[numeric_columns].mean()

# Display the final characteristic DataFrame
print(stat_penguins)