Fitting the Model

Question: Can we use linear regression to predict Palmer Penguins body mass using the beak length?

1. Data Preparation

First, we load the dataset and remove any missing values to ensure the model can process the data.

# Load libraries
import seaborn as sns
import pandas as pd
from sklearn.linear_model import LinearRegression

# Load and clean dataset
penguins = sns.load_dataset("penguins").dropna()

# Prepare features (X) and target (y)
X = penguins[["bill_length_mm"]]
y = penguins["body_mass_g"]

2. Fitting the Model

We fit a single linear regression model to the entire population of penguins, regardless of their species.

# Select the model
model = LinearRegression(fit_intercept=True)

# Fit the model
model.fit(X, y)

# Check the model performance
print(f"Global R^2 Score: {model.score(X, y):.3f}")

Global R^2 Score: 0.347

3. Visualization

Using a regression plot, we can see how well a single line fits the diverse penguin population.

# Load plotting libraries
import seaborn as sns
import matplotlib.pyplot as plt

# Plot the regression line and data points
sns.regplot(data=penguins, x="bill_length_mm", y="body_mass_g", 
            scatter_kws={'alpha':0.5}, line_kws={'color':'red'})
plt.title("Linear Regression: All Species Combined")

Text(0.5, 1.0, 'Linear Regression: All Species Combined')