From 759c25e0ed5323a1c45d1b274605160e14899a28 Mon Sep 17 00:00:00 2001 From: Vishal Khandelwal Date: Sun, 7 Oct 2018 20:04:41 +0530 Subject: [PATCH] added linear regression example --- code/linear_regression.py | 53 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) create mode 100644 code/linear_regression.py diff --git a/code/linear_regression.py b/code/linear_regression.py new file mode 100644 index 0000000..7bf2b06 --- /dev/null +++ b/code/linear_regression.py @@ -0,0 +1,53 @@ + +import numpy as np +import matplotlib.pyplot as plt + +def estimate_coef(x, y): + # number of observations/points + n = np.size(x) + + # mean of x and y vector + m_x, m_y = np.mean(x), np.mean(y) + + # calculating cross-deviation and deviation about x + SS_xy = np.sum(y*x - n*m_y*m_x) + SS_xx = np.sum(x*x - n*m_x*m_x) + + # calculating regression coefficients + b_1 = SS_xy / SS_xx + b_0 = m_y - b_1*m_x + + return(b_0, b_1) + +def plot_regression_line(x, y, b): + # plotting the actual points as scatter plot + plt.scatter(x, y, color = "m", + marker = "o", s = 30) + + # predicted response vector + y_pred = b[0] + b[1]*x + + # plotting the regression line + plt.plot(x, y_pred, color = "g") + + # putting labels + plt.xlabel('x') + plt.ylabel('y') + + # function to show plot + plt.show() + +def main(): + # observations + x = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]) + y = np.array([1, 3, 2, 5, 7, 8, 8, 9, 10, 12]) + + # estimating coefficients + b = estimate_coef(x, y) + print("Estimated coefficients:\nb_0 = {} \\nb_1 = {}".format(b[0], b[1])) + + # plotting regression line + plot_regression_line(x, y, b) + +if __name__ == "__main__": + main()