Skip to content

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.

ColumnDescription
culmen_length_mmculmen length (mm)
culmen_depth_mmculmen depth (mm)
flipper_length_mmflipper length (mm)
body_mass_gbody mass (g)
sexpenguin 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 numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import silhouette_score

# Loading and examining the dataset
penguins_df = pd.read_csv("penguins.csv")
penguins_df = pd.get_dummies(penguins_df, dtype='int')
stat_penguins = StandardScaler().fit_transform(penguins_df)
# Convert the scaled data back to a DataFrame
stat_penguins = pd.DataFrame(scaled_penguins_df, columns=penguins_df.columns)


#determing the inertia of clusters

num_clusters = [i for i in range(3, 11)]

def num_cluster(num_clusters, x_val):
    inertia = []
    for num in num_clusters:
        kmeans = KMeans(n_clusters=num, random_state=42)
        kmeans.fit(x_val)
        inertia.append(kmeans.inertia_)
    return inertia

# determining the silhoutte score 
def sil_score1(num_clusters, x_val):
    sil_scores = []
    for num in num_clusters:
        kmeans = KMeans(n_clusters=num, random_state=42)
        kmeans.fit(x_val)
        sil_scores.append(silhouette_score(x_val, kmeans.labels_))
    return sil_scores

# Compute inertia values
inertia = num_cluster(num_clusters,stat_penguins)
# Compute the silhoutte score values
sil_scores = sil_score1(num_clusters,stat_penguins)

# Plot the inertia results
plt.figure(figsize=(10, 6))
plt.plot(num_clusters, inertia, marker='o', color='blue')
plt.xlabel('Number Of Clusters')
plt.ylabel('Inertia')
plt.title('Elbow Method')
plt.show()

# Plot the silhouette score results
plt.figure(figsize=(10, 6))
plt.plot(num_clusters, sil_scores, marker='o', color='red')
plt.xlabel('Number Of Clusters')
plt.ylabel('Silhouette Score')
plt.title('Silhouette Score vs. Number of Clusters')
plt.show()

kmeans4 = KMeans(n_clusters = 4 , random_state= 42)
kmeans4.fit(stat_penguins)
print(kmeans4.labels_[:5])
print('Unique labels:', np.unique(kmeans4.labels_) )
penguins_df['label'] = kmeans4.labels_

#visulaize the cluster of data points for labels and culmen_length_mm
plt.scatter(penguins_df['label'], penguins_df['culmen_length_mm'], c= kmeans4.labels_, cmap='viridis')
plt.xlabel('Cluster')
plt.ylabel('culmen_length_mm')
plt.title(f'K-means Clustering (K={n_clusters})')
plt.show()

# create final data frame
numeric_columns = ['culmen_length_mm', 'culmen_depth_mm', 'flipper_length_mm','label']
stat_penguins= penguins_df[numeric_columns].groupby('label').mean()
stat_penguins.head()