In this example we see how to robustly fit a linear model to faulty data using the RANSAC algorithm.
Out:
1 2 | Estimated coefficients (true, normal, RANSAC):82.1903908408 [ 54.17236387] [ 82.08533159] |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 | import numpy as npfrom matplotlib import pyplot as pltfrom sklearn import linear_model, datasetsn_samples = 1000n_outliers = 50X, y, coef = datasets.make_regression(n_samples=n_samples, n_features=1, n_informative=1, noise=10, coef=True, random_state=0)# Add outlier datanp.random.seed(0)X[:n_outliers] = 3 + 0.5 * np.random.normal(size=(n_outliers, 1))y[:n_outliers] = -3 + 10 * np.random.normal(size=n_outliers)# Fit line using all datamodel = linear_model.LinearRegression()model.fit(X, y)# Robustly fit linear model with RANSAC algorithmmodel_ransac = linear_model.RANSACRegressor(linear_model.LinearRegression())model_ransac.fit(X, y)inlier_mask = model_ransac.inlier_mask_outlier_mask = np.logical_not(inlier_mask)# Predict data of estimated modelsline_X = np.arange(-5, 5)line_y = model.predict(line_X[:, np.newaxis])line_y_ransac = model_ransac.predict(line_X[:, np.newaxis])# Compare estimated coefficientsprint("Estimated coefficients (true, normal, RANSAC):")print(coef, model.coef_, model_ransac.estimator_.coef_)lw = 2plt.scatter(X[inlier_mask], y[inlier_mask], color='yellowgreen', marker='.', label='Inliers')plt.scatter(X[outlier_mask], y[outlier_mask], color='gold', marker='.', label='Outliers')plt.plot(line_X, line_y, color='navy', linestyle='-', linewidth=lw, label='Linear regressor')plt.plot(line_X, line_y_ransac, color='cornflowerblue', linestyle='-', linewidth=lw, label='RANSAC regressor')plt.legend(loc='lower right')plt.show() |
Total running time of the script: (0 minutes 0.126 seconds)
Download Python source code:
plot_ransac.py
Download IPython notebook:
plot_ransac.ipynb
Please login to continue.