在Pyspark中如何在时间序列数据上使用滑动窗口进行数据转换

Question

import org.apache.spark.mllib.rdd.RDDFunctions._

sc.parallelize(1 to 100, 10)
  .sliding(3)
  .map(curSlice => (curSlice.sum / curSlice.size))
  .collect()

Answer 1

据我所知，slike函数在Python中不可用，slidingGrdd是一个私有类，不能在mllib之外访问。

如果要在现有的RDD上使用slike，可以像下面这样创建穷人的slike:

def sliding(rdd, n):
    assert n > 0
    def gen_window(xi, n):
        x, i = xi
        return [(i - offset, (i, x)) for offset in xrange(n)]

    return (
        rdd.
        zipWithIndex(). # Add index
        flatMap(lambda xi: gen_window(xi, n)). # Generate pairs with offset
        groupByKey(). # Group to create windows
        # Sort values to ensure order inside window and drop indices
        mapValues(lambda vals: [x for (i, x) in sorted(vals)]).
        sortByKey(). # Sort to makes sure we keep original order
        values(). # Get values
        filter(lambda x: len(x) == n)) # Drop beginning and end

或者，您可以尝试类似的方法（使用toolz)

from toolz.itertoolz import sliding_window, concat

def sliding2(rdd, n):
    assert n > 1

    def get_last_el(i, iter):
        """Return last n - 1 elements from the partition"""
        return  [(i, [x for x in iter][(-n + 1):])]

    def slide(i, iter):
        """Prepend previous items and return sliding window"""
        return sliding_window(n, concat([last_items.value[i - 1], iter]))

    def clean_last_items(last_items):
        """Adjust for empty or to small partitions"""
        clean = {-1: [None] * (n - 1)}
        for i in range(rdd.getNumPartitions()):
            clean[i] = (clean[i - 1] + list(last_items[i]))[(-n + 1):]
        return {k: tuple(v) for k, v in clean.items()}

    last_items = sc.broadcast(clean_last_items(
        rdd.mapPartitionsWithIndex(get_last_el).collectAsMap()))

    return rdd.mapPartitionsWithIndex(slide)