Jason_Liu_stack_res.py 文件源码

def get_additional_features(train,test,magic=False,ID=False):
    col = list(test.columns)
    if ID!=True:
        col.remove('ID')
    n_comp = 12
    # tSVD
    tsvd = TruncatedSVD(n_components=n_comp, random_state=420)
    tsvd_results_train = tsvd.fit_transform(train[col])
    tsvd_results_test = tsvd.transform(test[col])
    # PCA
    pca = PCA(n_components=n_comp, random_state=420)
    pca2_results_train = pca.fit_transform(train[col])
    pca2_results_test = pca.transform(test[col])
    # ICA
    ica = FastICA(n_components=n_comp, random_state=420)
    ica2_results_train = ica.fit_transform(train[col])
    ica2_results_test = ica.transform(test[col])
    # GRP
    grp = GaussianRandomProjection(n_components=n_comp, eps=0.1, random_state=420)
    grp_results_train = grp.fit_transform(train[col])
    grp_results_test = grp.transform(test[col])
    # SRP
    srp = SparseRandomProjection(n_components=n_comp, dense_output=True, random_state=420)
    srp_results_train = srp.fit_transform(train[col])
    srp_results_test = srp.transform(test[col])
    for i in range(1, n_comp + 1):
        train['tsvd_' + str(i)] = tsvd_results_train[:, i - 1]
        test['tsvd_' + str(i)] = tsvd_results_test[:, i - 1]
        train['pca_' + str(i)] = pca2_results_train[:, i - 1]
        test['pca_' + str(i)] = pca2_results_test[:, i - 1]
        train['ica_' + str(i)] = ica2_results_train[:, i - 1]
        test['ica_' + str(i)] = ica2_results_test[:, i - 1]
        train['grp_' + str(i)] = grp_results_train[:, i - 1]
        test['grp_' + str(i)] = grp_results_test[:, i - 1]
        train['srp_' + str(i)] = srp_results_train[:, i - 1]
        test['srp_' + str(i)] = srp_results_test[:, i - 1]
    if magic==True:
        magic_mat = train[['ID','X0','y']]
        magic_mat = magic_mat.groupby(['X0'])['y'].mean()
        magic_mat = pd.DataFrame({'X0':magic_mat.index,'magic':list(magic_mat)})
        mean_magic = magic_mat['magic'].mean()
        train = train.merge(magic_mat,on='X0',how='left')
        test = test.merge(magic_mat,on='X0',how = 'left')
        test['magic'] = test['magic'].fillna(mean_magic)
    return train,test

## Preparing stacking functions. Each one takes the out of bag values as the Input

## xgb will not be used in this case, but still post it here.