努力制作带有统计模型的ARIMA预测图

Question

I'm hoping to read data from a file (Date and Quantity columns) and plot them onto a graph with an ARIMA forecast.

Unfortunately, I've had no luck with the online guides that I've used, and each has lead me to different issues.

Here is my basic code (which just plots the data without a forecast):

from pandas import Series
from matplotlib import pyplot
from statsmodels.tsa.arima_model import ARIMA

series = Series.from_csv('Quantity.csv',header=0)

model = ARIMA(series, order=(2,0,1))
series.plot()
pyplot.show()

Here is the data I'm practicing with:

Date    Quantity
2010/01/01  1358
2010/07/02  0
2010/08/03  0
2011/02/04  0
2011/11/05  0
2011/12/06  274
2012/06/07  1074
2012/08/30  2223
2013/04/16  0
2013/03/18  1753
2014/02/22  345
2014/01/27  24
2015/12/15  652
2015/09/28  275
2016/05/04  124
2017/11/07  75
2017/09/22  32
2017/04/04  12

So how can I create an ARIMA forecast and put it onto my excising plot?

Also, I'm not entirely sure how an ARIMA forecast in Python is meant to look once plotted (I've only seen them in R but from what I've seen its not the same case for Python), so perhaps an example would be nice.

Answer 1

First, I'd advise to use read_csv method and parse your dates here:

series = pd.read_csv('Quantity.csv', header=0, parse_dates=[0])
series.columns = ['Date', 'Quantity']

You need to use the fit method from the library, convert the Quantity column to float64 in order to avoid the error you mentionned:

model = ARIMA(series['Quantity'].astype(float), order=(2,0,1), dates=series['Date'])

(disp=0 if you don't want to print all the details of the computation)

Then you get your predicted value from the fitted model using:

fittedModel.forecast(steps=1)