ConvergenceWarning:最大似然优化未能收敛。

时间:2018-10-18 11:14:23

标签: python machine-learning time-series regression arima

我正在尝试使用statsmodels库中的ARIMA算法对时间序列数据集进行预测。这是一个股价数据集,当我将标准化数据输入模型时,会出现以下错误。

注意:这是单变量预测,我正尝试预测收盘价。

  

ConvergenceWarning:最大似然优化失败   汇合。检查mle_retvals“检查mle_retvals”,ConvergenceWarning)

问题:这样做的原因是什么?馈入ARIMA模型时对数据进行标准化不是一个好习惯吗?

下面显示的是我的代码:

from statsmodels.tsa.arima_model import ARIMA
import pandas as pd
from pandas.plotting import autocorrelation_plot
import matplotlib as mplt
mplt.use('agg')  # Must be before importing matplotlib.pyplot or pylab!
from matplotlib import pyplot
import numpy as np
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
from sklearn.metrics import mean_absolute_error
from math import sqrt


class RNNConfig():
    lag_order = 2
    degree_differencing = 1
    order_moving_avg = 0
    scaler = MinMaxScaler(feature_range=(0,1))
    test_ratio = 0.2
    fileName = 'AIG.csv'
    min = 10
    max = 2000
    column = 'Close'

config = RNNConfig()

def mean_absolute_percentage_error(y_true, y_pred):
    y_true, y_pred = np.array(y_true), np.array(y_pred)
    return np.mean(np.abs((y_true - y_pred) / y_true)) * 100

def scale(data):

    data[config.column] = (data[config.column] - config.min) / (config.max - config.min)

    return data

def ARIMA_model():

    stock_data = pd.read_csv(config.fileName)
    stock_data = stock_data.reindex(index=stock_data.index[::-1])

    scaled_data = scale(stock_data)

    price = scaled_data[config.column]

    size = int(len(price) * 0.66)
    train, test = price[0:size], price[size:len(price)]
    history = [x for x in train]
    predictions = list()
    for t in range(len(test)):
        model = ARIMA(history, order=(config.lag_order, config.degree_differencing, config.order_moving_avg))
        model_fit = model.fit(disp=0)
        output = model_fit.forecast()
        yhat = output[0]
        predictions.append(yhat)
        obs = test[t]
        history.append(obs)
        print('predicted=%f, expected=%f' % (yhat, obs))

    meanSquaredError = mean_squared_error(test, predictions)
    rootMeanSquaredError = sqrt(meanSquaredError)
    print("RMSE:", rootMeanSquaredError)
    mae = mean_absolute_error(test, predictions)
    print("MAE:", mae)
    mape = mean_absolute_percentage_error(test, predictions)
    print("MAPE:", mape)

    # plot
    pyplot.plot(test, color='blue', label='truth close')
    pyplot.plot(predictions, color='red',label='pred close')
    pyplot.legend(loc='upper left', frameon=False)
    pyplot.xlabel("day")
    pyplot.ylabel("closing price")
    pyplot.grid(ls='--')
    pyplot.savefig("ARIMA results.png", format='png', bbox_inches='tight', transparent=False)



if __name__ == '__main__':
    ARIMA_model()

1 个答案:

答案 0 :(得分:-5)

import warnings
from statsmodels.tools.sm_exceptions import ConvergenceWarning
warnings.simplefilter('ignore', ConvergenceWarning)