ransac.py

import numpy as np
import matplotlib.pyplot as plt

from sklearn.linear_model import LinearRegression, RANSACRegressor


# For reproducibility
np.random.seed(1000)

nb_samples = 200
nb_noise_samples = 150


def show_dataset(X, Y):
    fig, ax = plt.subplots(1, 1, figsize=(30, 25))
    ax.scatter(X, Y)
    ax.set_xlabel('X')
    ax.set_ylabel('Y')
    ax.grid()
    plt.show()

# Create dataset
X = np.arange(-5, 5, 0.05)

Y = X + 2
Y += np.random.uniform(-0.5, 0.5, size=nb_samples)

for i in range(nb_noise_samples, nb_samples):
    Y[i] += np.random.uniform(12, 15)

# Show the dataset
show_dataset(X, Y)

from sklearn.linear_model import LinearRegression
lr = LinearRegression(normalize=True)
lr.fit(X.reshape((-1, 1)), Y.reshape((-1, 1)))
lr.intercept_
lr.coef_

from sklearn.linear_model import RANSACRegressor
rs = RANSACRegressor(lr)
rs.fit(X.reshape((-1, 1)), Y.reshape((-1, 1)))
rs.estimator_.intercept_
rs.estimator_.coef_