onlinerake: Streaming Survey Raking

Contents:

Raking adjusts weights so that weighted shares of groups match known population shares. The standard algorithm, iterative proportional fitting (IPF), needs every row seen so far. StreamingRaker rakes a stream without storing it: its state is p + 5 running totals for p margins, each arriving row gets its weight in closed form, and the cost per row does not grow with the stream.

Which Tool

  • Rows can be stored and the stream is survey-sized: refit BatchIPF periodically. It is exact at each refit.

  • Rows cannot or should not be stored, memory is fixed, or the stream is long: StreamingRaker.

  • fit_penalized_raking minimizes the streaming objective over all stored rows at once.

  • OnlineRakingSGD and OnlineRakingMWU store every row and re-optimize all weights at each arrival.

Quick Start

from onlinerake import StreamingRaker, Targets

raker = StreamingRaker(Targets(female=0.5), outcomes=["spend"])
for female, spend in [(1, 10.0), (1, 12.0), (1, 11.0), (0, 20.0)] * 50:
    raker.partial_fit({"female": female}, outcomes={"spend": spend})

print(round(raker.margins["female"], 2))  # 0.52
print(round(raker.estimate("spend"), 1))  # 15.3

The manuscript in ms/onlinerake.pdf derives the update and evaluates it against full-data and periodic IPF.

Indices and tables