ARIMA初探

数据探查

import pandas as pd
import numpy as np
import matplotlib.pylab as plt
from matplotlib.pylab import rcParams
#rcParams设定好画布的大小
rcParams['figure.figsize'] = 15, 6

path = '/Users/***/workspace/Analytics_Vidhya/Articles/Time_Series_Analysis/AirPassengers.csv'
dateparse = lambda dates: pd.datetime.strptime(dates, '%Y-%m')
#---其中parse_dates 表明选择数据中的哪个column作为date-time信息，
#---index_col 告诉pandas以哪个column作为 index
#--- date_parser 使用一个function(本文用lambda表达式代替)，使一个string转换为一个datetime变量
data = pd.read_csv(path, parse_dates=['Month'], index_col='Month',date_parser=dateparse)
data.head(6)

Month	#Passengers
1949-01-01	112
1949-02-01	118
1949-03-01	132
1949-04-01	129
1949-05-01	121
1949-06-01	135

from statsmodels.tsa.stattools import adfuller

def test_stationarity(timeseries):
    # 这里以一年为一个窗口，每一个时间t的值由它前面12个月（包括自己）的均值代替，标准差同理。
    # rolmean = pd.rolling_mean(timeseries, window=12)
    #
    # rolstd = pd.rolling_std(timeseries, window=12)
    rolmean = timeseries.rolling(window=12).mean()
    rolstd = timeseries.rolling(12).std()

    # plot rolling statistics:
    fig = plt.figure()
    fig.add_subplot()
    orig = plt.plot(timeseries, color='blue', label='Original')
    mean = plt.plot(rolmean, color='red', label='rolling mean')
    std = plt.plot(rolstd, color='black', label='Rolling standard deviation')

    plt.legend(loc='best')
    plt.title('Rolling Mean & Standard Deviation')
    plt.show(block=False)

    # Dickey-Fuller test:

    print('Results of Dickey-Fuller Test:')

    dftest = adfuller(timeseries, autolag='AIC')
    # dftest的输出前一项依次为检测值，p值，滞后数，使用的观测数，各个置信度下的临界值
    dfoutput = pd.Series(dftest[0:4], index=['Test Statistic