Automatic implementations of Backward Elimination in Python.

backward_elimination_p-values_adj_R_squared.py

import statsmodels.formula.api as sm
def backwardElimination(x, SL):
    numVars = len(x[0])
    temp = np.zeros((50,6)).astype(int)
    for i in range(0, numVars):
        regressor_OLS = sm.OLS(y, x).fit()
        maxVar = max(regressor_OLS.pvalues).astype(float)
        adjR_before = regressor_OLS.rsquared_adj.astype(float)
        if maxVar > SL:
            for j in range(0, numVars - i):
                if (regressor_OLS.pvalues[j].astype(float) == maxVar):
                    temp[:,j] = x[:, j]
                    x = np.delete(x, j, 1)
                    tmp_regressor = sm.OLS(y, x).fit()
                    adjR_after = tmp_regressor.rsquared_adj.astype(float)
                    if (adjR_before >= adjR_after):
                        x_rollback = np.hstack((x, temp[:,[0,j]]))
                        x_rollback = np.delete(x_rollback, j, 1)
                        print (regressor_OLS.summary())
                        return x_rollback
                    else:
                        continue
    regressor_OLS.summary()
    return x
 
SL = 0.05
X_opt = X[:, [0, 1, 2, 3, 4, 5]]
X_Modeled = backwardElimination(X_opt, SL)

Can you please help with the error: 'float' object has no attribute 'astype' on the backward elimination method

AttributeError Traceback (most recent call last)
in ()
1 SL = 0.05
2 X_opt = X[:, [0, 1, 2, 3, 4, 5]]
----> 3 X_Modeled = backwardElimination(X_opt, SL)

in backwardElimination(x, SL)
5 for i in range(0, numVars):
6 regressor_OLS = sm.OLS(y, x).fit()
----> 7 maxVar = max(regressor_OLS.pvalues).astype(float)
8 adjR_before = regressor_OLS.rsquared_adj.astype(float)
9 if maxVar > SL:

AttributeError: 'float' object has no attribute 'astype'