如何使用Pyspark实现ARIMA模型以用于预测？

from pyspark.sql import SparkSession
from pyspark.ml.feature import VectorAssembler
from pyspark.ml.regression import LinearRegression
from pyspark.ml.tuning import ParamGridBuilder, CrossValidator
from pyspark.ml.evaluation import RegressionEvaluator
from statsmodels.tsa.arima_model import ARIMA

spark = SparkSession.builder.appName("ARIMA").getOrCreate()

data = spark.read.csv("data.csv", header=True, inferSchema=True)
data = data.select("date", "value")  # 根据实际数据集的列名进行选择
data = data.withColumn("date", data["date"].cast("date"))

data = data.withColumn("value", data["value"].cast("double"))
data = data.orderBy("date")
data = data.select("value").rdd.flatMap(lambda x: x).collect()

model = ARIMA(data, order=(p, d, q)).fit()
forecast = model.predict(start=len(data), end=len(data)+n-1)  # 预测未来n个时间点的值