arima 預(yù)測模型

XTS對象 (XTS Objects)

If you’re not using XTS objects to perform your forecasting in R, then you are likely missing out! The major benefits that we’ll explore throughout are that these objects are a lot easier to work with when it comes to modeling, forecasting, & visualization.

如果您沒有使用XTS對象在R中執(zhí)行預(yù)測，那么您很可能會錯過！ 我們將始終探索的主要好處是，在建模，預(yù)測和可視化方面，這些對象更易于使用。

讓我們進(jìn)入細(xì)節(jié) (Let’s Get to The Details)

XTS objects are composed of two components. The first is a date index and the second of which is a traditional data matrix.

XTS對象由兩個組件組成。 第一個是日期索引，第二個是傳統(tǒng)數(shù)據(jù)矩陣。

Whether you want to predict churn, sales, demand, or whatever else, let’s get to it!

無論您是要預(yù)測客戶流失，銷售，需求還是其他，我們都可以開始吧！

The first thing you’ll need to do is create your date index. We do so using the seq function. Very simply this function takes what is your start date, the number of records you have or length, and then the time interval or by parameter. For us, the dataset starts with the following.

您需要做的第一件事是創(chuàng)建日期索引。 我們使用seq函數(shù)。 很簡單，此功能需要的只是你的開始日期，你有記錄的數(shù)目或長度，然后將時間間隔或by參數(shù)。 對于我們來說，數(shù)據(jù)集從以下開始。

days <- seq(as.Date("2014-01-01"), length = 668, by = "day")

Now that we have our index, we can use it to create our XTS object. For this, we will use the xts function.

現(xiàn)在我們有了索引，可以使用它來創(chuàng)建XTS對象。 為此，我們將使用xts函數(shù)。

Don’t forget to install.packages('xts') and then load the library! library(xts)

不要忘了先安裝install.packages('xts') ，然后加載庫！ library(xts)

Once we’ve done this we’ll make our xts call and pass along our data matrix, and then for the date index we will pass the index to the order.by option.

完成此操作后，我們將進(jìn)行xts調(diào)用并傳遞數(shù)據(jù)矩陣，然后對于日期索引，我們會將索引傳遞給order.by選項(xiàng)。

sales_xts <- xts(sales, order.by = days)

讓我們與Arima建立預(yù)測 (Let’s Create a Forecast with Arima)

Arima stands for auto regressive integrated moving average. A very popular technique when it comes to time series forecasting. We could spend hours talking about ARIMA alone, but for this post, we’re going to give a high-level explanation and then jump directly into the application.

有馬代表自動回歸綜合移動平均線。 關(guān)于時間序列預(yù)測的一種非常流行的技術(shù)。 我們可能只花幾個小時來談?wù)揂RIMA，但是在這篇文章中，我們將給出一個高級的解釋，然后直接進(jìn)入該應(yīng)用程序。

AR：自回歸 (AR: Auto Regressive)

This is where we predict outcomes using lags or values from previous months. It may be that the outcomes of a given month have some dependency on previous values.

在這里，我們使用前幾個月的滯后或值來預(yù)測結(jié)果。 給定月份的結(jié)果可能與以前的值有一定的依賴性。

一：集成 (I: Integrated)

When it comes to time series forecasting, an implicit assumption is that our model depends on time in some capacity. This seems pretty obvious as we probably wouldn’t make our model time based otherwise ;). With that assumption out of the way, we need to understand where on the spectrum of dependence time falls in relation to our model. Yes, our model depends on time, but how much? Core to this is the idea of Stationarity; which means that the effect of time diminishes as time goes on.

在進(jìn)行時間序列預(yù)測時，一個隱含的假設(shè)是我們的模型在某種程度上取決于時間。 這似乎很明顯，因?yàn)槲覀兛赡懿粫⒛Ｐ蜁r間設(shè)為其他時間；)。 有了這個假設(shè)，我們需要了解與我們的模型有關(guān)的依賴時間范圍。 是的，我們的模型取決于時間，但是多少？ 核心思想是平穩(wěn)性 ； 這意味著隨著時間的流逝，時間的影響減弱。

Going deeper, the historical average of a dataset tends to be the best predictor of future outcomes… but there are certainly times when that’s not true.. can you think of any situations when the historical mean would not be the best predictor?

更深入地講，數(shù)據(jù)集的歷史平均值往往是未來結(jié)果的最佳預(yù)測因子……但是，在某些情況下，這是不正確的……您能想到歷史均值不是最佳預(yù)測因子的任何情況嗎？

• How about predicting sales for December? Seasonal Trends
  預(yù)測12月的銷售情況如何？ 季節(jié)性趨勢
• How about sales for a hyper-growth saas company? Consistent upward trends
  一家高速增長的saas公司的銷售情況如何？ 一致的上升趨勢

This is where the process of Differencing is introduced! Differencing is used to eliminate the effects of trends & seasonality.

這就是引入差分過程的地方！ 差異用于消除趨勢和季節(jié)性的影響。

MA：移動平均線 (MA: Moving Average)

the moving average model exists to deal with the error of your model.

存在移動平均模型以處理模型誤差。

讓我們開始建模吧！ (Let’s Get Modeling!)

火車/驗(yàn)證拆分 (Train/Validation Split)

First things first, let’s break out our data into a training dataset and then what we’ll call our validation dataset.

首先，讓我們將數(shù)據(jù)分為訓(xùn)練數(shù)據(jù)集，然后將其稱為驗(yàn)證數(shù)據(jù)集。

What makes this different than other validation testing, like cross-validation testing is that here we break it out by time, breaking train up to a given point in time and breaking out validation for everything thereafter.

與其他驗(yàn)證測試(例如交叉驗(yàn)證測試)不同的是，這里我們按時間細(xì)分，將訓(xùn)練分解到給定的時間點(diǎn)，然后對所有內(nèi)容進(jìn)行驗(yàn)證。

train <- sales_xts[index(sales_xts) <= "2015-07-01"]
validation <- sales_xts[index(sales_xts) > "2015-07-01"]

是時候建立模型了 (Time to Build a Model)

The auto.arima function incorporates the ideas we just spoke about to approximate the best arima model. I will detail the more hands-on approach in another post, but below I’ll explore the generation of an auto.arima model and how to use it to forecast.

auto.arima函數(shù)結(jié)合了我們剛才談到的想法，可以近似最佳a(bǔ)rima模型。 我將在另一篇文章中詳細(xì)介紹更多的動手方法，但是下面我將探討auto.arima模型的生成以及如何使用它進(jìn)行預(yù)測。

model <- auto.arima(train)

Now let’s generate a forecast. The same way we did before, we’ll create a date index and then create an xts object with the data matrix.

現(xiàn)在讓我們生成一個預(yù)測。 與之前相同，我們將創(chuàng)建一個日期索引，然后使用數(shù)據(jù)矩陣創(chuàng)建一個xts對象。

From here you will plot the validation data and then throw the forecast on top of the plot.

在這里，您將繪制驗(yàn)證數(shù)據(jù)，然后將預(yù)測放在該圖的頂部。

forecast <- forecast(model, h = 121)
forecast_dates <- seq(as.Date("2015-09-01"), length = 121, by = "day")forecast_xts <- xts(forecast$mean, order.by = forecast_dates)plot(validation, main = 'Forecast Comparison')lines(forecast_xts, col = "blue")

結(jié)論 (Conclusion)

I hope this was a helpful introduction to ARIMA forecasting. Be sure to let me know what’s helpful and any additional detail you’d like to learn about.

我希望這對ARIMA預(yù)測很有幫助。 請務(wù)必讓我知道有什么幫助以及您想了解的任何其他詳細(xì)信息。

If you found this helpful be sure to check out some of my other posts on datasciencelessons.com. Happy Data Science-ing!

如果您認(rèn)為這有幫助，請務(wù)必在datasciencelessons.com上查看我的其他一些帖子。 快樂數(shù)據(jù)科學(xué)！

翻譯自: https://towardsdatascience.com/predicting-the-future-learn-to-forecast-with-arima-models-879853c46a4d

arima 預(yù)測模型

總結(jié)

以上是生活随笔為你收集整理的arima 预测模型_预测未来：学习使用Arima模型进行预测的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。