predict_2017_06_19_5.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
    scores = list()
    num_seeds = 1
    num_splits = 3
    base_seed = 13
    ss = model_selection.ShuffleSplit(n_splits=num_splits)
    for seed in range(base_seed, base_seed + num_seeds):
        ss = model_selection.ShuffleSplit(n_splits=num_splits, random_state=seed)
        for n, (itrain, ival) in enumerate(ss.split(train2, y)):
            reg = ensemble.RandomForestClassifier(max_depth=9,
                                               random_state=seed,
                                               n_estimators=500,
                                               n_jobs=-2)
            reg.fit(train2[itrain], y[itrain])
            p = reg.predict_proba(train2[ival])[:,1]
            v.loc[ival, cname] += pconvert(p)
            score = metrics.log_loss(y[ival], p)
            print(cname, 'seed %d step %d: '%(seed, n+1), score, now())
            scores.append(score)
            z[cname] += pconvert(reg.predict_proba(test2)[:,1])

    cv=np.array(scores)
    print(cv, cv.mean(), cv.std())
    z[cname] /= num_splits * num_seeds
    v[cname] /= num_seeds