多元季节性时间序列模型SARIMAX的应用——预测与异常诊断

import pandas as pd
import numpy as np
import matplotlib.pylab as plt
from matplotlib.pylab import rcParams
rcParams["figure.figsize"] = 15,6
#读取数据
f = open(r"D:\miss_predict.txt")
data = pd.read_table(f)
#时间序列索引
data_bs.index = pd.date_range(start='2018-08-01 00:00:00',periods=744,freq='h',normalize=True)
data = data_bs["指标值"]

#判断数据的平稳性
%pylab inline
plt.figure(figsize(20,8))
plt.plot(data)

#使用均值填充

#判断数据的稳定性
from statsmodels.tsa.stattools import adfuller
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf

# 移动平均图
def draw_trend(timeSeries, size):
    f = plt.figure(facecolor='white')
    # 对size个数据进行移动平均
    rol_mean = timeSeries.rolling(window=size).mean()
    # 对size个数据进行加权移动平均
    rol_weighted_mean = pd.ewma(timeSeries, span=size)

    timeSeries.plot(color='blue', label='Original')
    rol_mean.plot(color='red', label='Rolling Mean')
    rol_weighted_mean.plot(color='black', label='Weighted Rolling Mean')
    plt.legend(loc='best')
    plt.title('Rolling Mean')
    plt.show()

def draw_ts(timeSeries):
    f = plt.figure(facecolor='white')
    timeSeries.plot(color='blue')
    plt.show()

'''
　　Unit Root Test
   The null hypothesis of the Augmented Dickey-Fuller is that there is a unit
   root, with the alternative that there is no unit root. That is to say the
   bigger the p-value the more reason we assert that there is a unit root
'''
def testStationarity(ts):
    dftest = adfuller(ts)
    # 对上述函数求得的值进行语义描述
    dfoutput = pd.Series(dftest[0:4], index=['Test Statistic','p-value','#Lags Used','Number of Observations Used'])
    for key,value in dftest[4].items():
        dfoutput['Critical Value (%s)'%key] = value
    return dfoutput

# 自相关和偏相关图，默认阶数为31阶
def draw_acf_pacf(ts, lags=50):
    f = plt.figure(facecolor='white')
    ax1 = f.add_subplot(211)
    plot_acf(ts, lags=50, ax=ax1)
    ax2 = f.add_subplot(212)
    plot_pacf(ts, lags=50, ax=ax2)
    plt.show()

p值没有小于0.05，且ACF/PACF图不平稳