def apply_beta(beta, X):
'''
Apply beta, the function generated by linear_regression, to the
specified values
Inputs:
beta: beta as returned by linear_regression
X: (2D Numpy array of floats) predictor/independent variables
Returns:
result of applying beta to the data, as an array.
Given:
beta = array([B0, B1, B2,...BK])
X = array([[x11, x12, ..., x0K],
[x21, x22, ..., x1K],
...
[xN1, xN2, ..., xNK]])
result will be:
array([B0+B1*x11+B2*x12+...+BK*x1K,
B0+B1*x21+B2*x22+...+BK*x2K,
...
B0+B1*xN1+B2*xN2+...+BK*xNK])
'''
assert_Xbeta(X, beta, fname='apply_beta')
# Add a column of ones
X_incl_ones = prepend_ones_column(X)
# Calculate X*beta
yhat = np.dot(X_incl_ones, beta)
return yhat
def apply_beta(beta, X):
'''
Apply beta, the function generated by linear_regression, to the
specified values
Inputs:
model: beta as returned by linear_regression
Xs: 2D array of floats
Returns:
result of applying beta to the data, as an array.
Given:
beta = array([B0, B1, B2,...BK])
Xs = array([[x11, x12, ..., x0K],
[x21, x22, ..., x1K],
...
[xN1, xN2, ..., xNK]])
result will be:
array([B0+B1*x11+B2*x12+...+BK*x1K,
B0+B1*x21+B2*x22+...+BK*x2K,
...
B0+B1*xN1+B2*xN2+...+BK*xNK])
'''
assert_Xbeta(X, beta, fname='apply_beta')
# Add a column of ones
X_incl_ones = prepend_ones_column(X)
# Calculate X*beta
yhat = np.dot(X_incl_ones, beta)
return yhat