basic-linear-regression.py

import numpy as np
import matplotlib.pyplot as plt

# load the data
X = []
Y = []
for line in open('data_1d.csv'):
    x, y = line.split(',')
    X.append(float(x))
    Y.append(float(y))

# let's turn X and Y into numpy arrays since that will be useful later
X = np.array(X)
Y = np.array(Y)


# let's plot the data to see what it looks like
plt.scatter(X, Y)
plt.show()


# apply the equations we learned to calculate a and b

# denominator is common
# note: this could be more efficient if
#       we only computed the sums and means once

denominator = X.dot(X) - X.mean() * X.sum()
a = ( X.dot(Y) - Y.mean()*X.sum() ) / denominator
b = ( Y.mean() * X.dot(X) - X.mean() * X.dot(Y) ) / denominator

# let's calculate the predicted Y
Yhat = a*X + b

# let's plot everything together to make sure it worked
plt.scatter(X, Y)
plt.plot(X, Yhat)
plt.show()

# determine how good the model is by computing the r-squared
d1 = Y - Yhat
d2 = Y - Y.mean()
r2 = 1 - d1.dot(d1) / d2.dot(d2)
print("the r-squared is:", r2)