predict_2017_06_16_3.py 文件源码

def rf1(train2, y, test2, v, z):
    cname = sys._getframe().f_code.co_name
    v[cname], z[cname] = 0, 0
    N_splits = 300
    scores = []
    skf = model_selection.StratifiedKFold(n_splits=N_splits, shuffle=True)
    for n, (itrain, ival) in enumerate(skf.split(train2, y)):
        print('step %d of %d'%(n+1, skf.n_splits), now())
        clf = ensemble.RandomForestRegressor(n_estimators=1000,
                                             max_depth=3,
                                             random_state=13)
        clf.fit(train2[itrain], y[itrain])

        p = clf.predict(train2[ival])
        v.loc[ival, cname] += p
        score = metrics.log_loss(y[ival], p)
        z[cname]  += np.log1p(clf.predict(test2))
        print(cname, 'step %d: score'%(n+1), score, now())
        scores.append(score)

    print('validation loss: ', metrics.log_loss(y, v[cname]))
    cv=np.array(scores)
    print(cv, cv.mean(), cv.std())
    z[cname] /= N_splits