LightGBM 模型在烧瓶路线中预测相同的值

Question

我是 Whosebug 社区的新用户，感谢您的帮助。这是我面临的情况：我有一个 model.py 文件负责使用 sklearn 的 RandomizedSearchCV 训练 LightGBMRegressor 模型。训练结束后，我用 pickle 保存模型。

    n_estimators = [int(x) for x in np.linspace(start = 200, stop = 4000, num = 20)]
    max_depth = [int(x) for x in np.linspace(10, 100, num = 10)]
    num_leaves = [int(x) for x in np.linspace(10, 150, num = 10)]
    learning_rate = [0.03, 0.05, 0.1, 0.2, 0.3]
    subsample_for_bin = [100000,200000, 300000, 400000]
    random_grid = {'n_estimators': n_estimators,
               'max_depth': max_depth,
               'num_leaves': num_leaves,
               'learning_rate': learning_rate,
               'subsample_for_bin': subsample_for_bin}
    gbm = lgb.LGBMRegressor()
    gbm_random = RandomizedSearchCV(estimator = gbm, param_distributions = random_grid, scoring=['neg_mean_absolute_error', 'neg_root_mean_squared_error'],refit= 'neg_root_mean_squared_error',n_iter = 100, cv = 4, verbose = 2, random_state = 42, n_jobs = -1)
    gbm_random.fit(data_base[features_x], data_base[target_y])
    pkl_filename = "../output/lightGBM[3].pkl"
    with open(pkl_filename, 'wb') as file:
       pickle.dump(gbm_random, file)

为了验证训练，我将模型加载到 predict.py 文件中并提交测试集。

data_base_test = pd.read_csv("../output/table_test3.csv")
pkl_filename = "../output/lightGBM[3].pkl"
with open(pkl_filename, 'rb') as file:
    gbm = pickle.load(file)
predict_test = gbm.predict(data_base_test[features_x])
print(predict_test)

predict_test是：

[0.66487458 0.82479892 1.89628195 ... 3.83358101 5.21799368 0.33858825]

我对机器学习的东西没问题，但在网络开发领域是个新手。当我用 flask 创建一个 web 开发，在路线上加载模型并尝试从与之前脚本相同的测试集进行预测时，模型中的所有预测都具有相同的值 = 66。我会面临什么问题？注意：get_json 以 json 格式接收整个测试集

pkl_filename = "model/lightGBM[3].pkl"
with open(pkl_filename, 'rb') as file:
    gbm = pickle.load(file)

app = flask.Flask(__name__, template_folder='templates')

@app.route('/predict', methods=['POST'])
def main():

    test_json = request.get_json()
    df_json = pd.read_json(test_json, orient='records')
    columns_name = df_json.columns.values
    columns_name = np.delete(columns_name, np.where('qtde_venda'))
    features_x = columns_name.tolist()
    #prediction
    predict = gbm.predict(df_json[features_x])
    print(predict)
    return(flask.render_template('main.html'))


if __name__ == '__main__':

    app.run()

预测向量为：

[66. 66. 66. ... 66. 66. 66.]

预期输出与预期输出

[0.66487458 0.82479892 1.89628195 ... 3.83358101 5.21799368 0.33858825]
[66. 66. 66. ... 66. 66. 66.]

Answer 1

我不知道如何解释发生了什么，但导致错误的是 anaconda 环境。为了解决这个问题，我删除了 anaconda 并开始使用 Python Venv

LightGBM 模型在烧瓶路线中预测相同的值

LightGBM Model predict the same values in a flask route

python

flask

scikit-learn

lightgbm