def backstepwise(data, out, k):
feature_num = len(data[0])
index_array = [i for i in range(feature_num)]
droper = feature_num - k
for i in range(droper):
beta = leastsquare.ls(data[:,np.array(index_array)], out)
yhat = leastsquare.predict(data[:,np.array(index_array)], beta)
theg2 = leastsquare.thegama2(yhat, out, len(index_array))
z = leastsquare.z_score(beta, np.sqrt(theg2), data[:,np.array(index_array)])
min_z = 999999999.
min_idx = None
for j in range(len(z)):
if z[j] < min_z:
min_z = z[j]
min_idx = j
index_array.remove(index_array[min_idx])
beta = leastsquare.ls(data[:,np.array(index_array)], out)
return beta, index_array
def stepwise(data, out, k):
feature_num = len(data[0])
index_array = [0]
indexs = [i for i in range(1,feature_num)]
#beta = leastsquare.ls(data[:,np.array(index_array)], out)
min_beta = None
min_idx =None
for i in range(1,k):
min_rss = 999999999
for idx in indexs:
ia = index_array + [idx]
beta = leastsquare.ls(data[:,ia], out)
rss = RSS(data[:,ia], out, beta)
if rss < min_rss:
min_rss = rss
min_beta = beta
min_idx = idx
index_array.append(min_idx)
indexs.remove(min_idx)
return min_beta, index_array
