Created
January 8, 2025 15:13
-
-
Save thomasahle/87eb97cc1e25d6a8f21eac69cf6b8fed to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
from sklearn.linear_model import LinearRegression | |
# Generate some example data | |
np.random.seed(42) | |
n_samples = 100 | |
# Create synthetic features (x1: thickness, x2: stiffness, x3: scent, x4: another property) | |
X = np.random.rand(n_samples, 4) * 10 # Random values between 0 and 10 | |
# Create synthetic target with known coefficients: y = x1^1 * x2^0 * x3^-1 * x4^0.5 | |
true_coefficients = np.array([1.0, 0.0, -1.0, 0.5]) | |
y = np.prod(X ** true_coefficients.reshape(1, -1), axis=1) | |
# Add some noise | |
y *= np.random.lognormal(0, 0.1, n_samples) | |
# Take log of all values (add small epsilon to avoid log(0)) | |
epsilon = 1e-10 | |
log_X = np.log(X + epsilon) | |
log_y = np.log(y + epsilon) | |
# Fit linear regression | |
reg = LinearRegression() | |
reg.fit(log_X, log_y) | |
# Get the coefficients and R-squared score | |
coefficients = reg.coef_ | |
r2_score = reg.score(log_X, log_y) | |
print("True coefficients:", true_coefficients) | |
print("Fitted coefficients:", coefficients) | |
print("R-squared score:", r2_score) | |
# Test the model with a specific example | |
test_point = np.array([[2.0, 3.0, 1.5, 4.0]]) | |
log_prediction = np.sum(coefficients * np.log(test_point)) | |
prediction = np.exp(log_prediction) | |
print("\nTest prediction:") | |
print(f"Input values (x1, x2, x3, x4):", test_point[0]) | |
print(f"Predicted y:", prediction) | |
# Calculate true value for comparison | |
true_value = np.prod(test_point ** true_coefficients) | |
print(f"True y:", true_value) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment