script_resnet.py 文件源码

def train_xgboost():
    df = pd.read_csv('data/stage1_labels.csv')
    print(df.head())

    x = np.array([np.mean(np.load('npy_result/%s.npy' % str(id)), axis=0) for id in df['id'].tolist()])
    y = df['cancer'].as_matrix()

    trn_x, val_x, trn_y, val_y = cross_validation.train_test_split(x, y, random_state=42, stratify=y,
                                                                   test_size=0.20)

    clf = xgb.XGBRegressor(max_depth=10,
                           n_estimators=1500,
                           min_child_weight=9,
                           learning_rate=0.05,
                           nthread=8,
                           subsample=0.80,
                           colsample_bytree=0.80,
                           seed=4242)

    clf.fit(trn_x, trn_y, eval_set=[(val_x, val_y)], verbose=True, eval_metric='logloss', early_stopping_rounds=50)
    return clf