predict_2017_06_22_3.py 文件源码

def xgb2(train2, y, test2, v, z):
    cname = sys._getframe().f_code.co_name
    v[cname], z[cname] = 0, 0
    N_splits = 7
    N_seeds = 2
    scores = []
    skf = model_selection.StratifiedKFold(n_splits=N_splits, shuffle=True)
    xgb_params = dict(
            max_depth = 4,
            learning_rate = 0.03,
            subsample = 0.7,
            #colsample_bytree = 0.8,
            objective = 'binary:logistic',
            eval_metric = 'logloss',
            seed = 1,
            silent = 1
        )
    dtest = xgb.DMatrix(test2)
    for s in range(N_seeds):
        xgb_params['seed'] = s + 4242
        for n, (itrain, ival) in enumerate(skf.split(train2, y)):
            print('step %d of %d'%(n+1, skf.n_splits), now())
            dtrain = xgb.DMatrix(train2.ix[itrain], y[itrain])
            dvalid = xgb.DMatrix(train2.ix[ival], y[ival])
            watch = [(dtrain, 'train'), (dvalid, 'valid')]
            clf = xgb.train(xgb_params, dtrain, 10000, watch, early_stopping_rounds=100, verbose_eval=1000)

            p = clf.predict(dvalid)
            v.loc[ival, cname] += pconvert(p)
            score = metrics.log_loss(y[ival], p)
            z[cname]  += pconvert(clf.predict(dtest))
            print(cname, 'seed %d step %d: '%(xgb_params['seed'], 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 * N_seeds
    v[cname] /= N_seeds