def main(unused_argv):
# Setup Beam
# Here, we use a local Beam runner.
# For a truly distributed calculation, connect to a Beam cluster (e.g.
# running on some cloud provider).
runner = fn_api_runner.FnApiRunner() # Local Beam runner
with beam.Pipeline(runner=runner) as pipeline:
# Define the privacy budget available for our computation.
budget_accountant = pipeline_dp.NaiveBudgetAccountant(total_epsilon=1,
total_delta=1e-6)
# Load and parse input data
df = pd.read_csv(FLAGS.input_file)
df.rename(inplace=True,
columns={
'VisitorId': 'user_id',
'Time entered': 'enter_time',
'Time spent (minutes)': 'spent_minutes',
'Money spent (euros)': 'spent_money',
'Day': 'day'
})
restaraunt_visits_rows = [index_row[1] for index_row in df.iterrows()]
beam_data = pipeline | beam.Create(restaraunt_visits_rows)
# Wrap Beam's PCollection into it's private version
private_restaraunt_visits = beam_data | private_beam.MakePrivate(
budget_accountant=budget_accountant,
privacy_id_extractor=lambda row: row.user_id)
# Calculate the private sum
dp_result = private_restaraunt_visits | private_beam.Sum(
SumParams(noise_kind=pipeline_dp.NoiseKind.GAUSSIAN,
max_partitions_contributed=7,
max_contributions_per_partition=2,
min_value=1,
max_value=100,
budget_weight=1,
public_partitions=None,
partition_extractor=lambda row: row.day,
value_extractor=lambda row: row.spent_money))
budget_accountant.compute_budgets()
# Save the results
dp_result | beam.io.WriteToText(FLAGS.output_file)
return 0
def main(unused_argv):
# Setup Beam
# Here, we use a local Beam runner.
# For a truly distributed calculation, connect to a Beam cluster (e.g.
# running on some cloud provider).
runner = fn_api_runner.FnApiRunner() # Local Beam runner
with beam.Pipeline(runner=runner) as pipeline:
# Define the privacy budget available for our computation.
budget_accountant = pipeline_dp.NaiveBudgetAccountant(total_epsilon=1,
total_delta=1e-6)
# Load and parse input data
movie_views_pcol = pipeline | \
beam.io.ReadFromText(FLAGS.input_file) | \
beam.ParDo(ParseFile())
# Wrap Beam's PCollection into it's private version
private_movie_views = (movie_views_pcol
| 'Create private collection' >> MakePrivate(
budget_accountant=budget_accountant,
privacy_id_extractor=lambda mv: mv.user_id))
# Calculate the private sum
dp_result = private_movie_views | "Private Sum" >> private_beam.Sum(
SumParams(
# Limits to how much one user can contribute:
# .. at most two movies rated per user
max_partitions_contributed=2,
# .. at most one rating for each movie
max_contributions_per_partition=1,
# .. with minimal rating of "1"
min_value=1,
# .. and maximum rating of "5"
max_value=5,
# The aggregation key: we're grouping data by movies
partition_extractor=lambda mv: mv.movie_id,
# The value we're aggregating: we're summing up ratings
value_extractor=lambda mv: mv.rating))
budget_accountant.compute_budgets()
# Save the results
dp_result | beam.io.WriteToText(FLAGS.output_file)
return 0
def test_sum_calls_aggregate_with_params(self, mock_aggregate):
runner = fn_api_runner.FnApiRunner()
with beam.Pipeline(runner=runner) as pipeline:
# Arrange
pcol = pipeline | 'Create produce' >> beam.Create(
float(i) for i in range(1, 7))
budget_accountant = budget_accounting.NaiveBudgetAccountant(
total_epsilon=1, total_delta=0.01)
private_collection = (
pcol | 'Create private collection' >> private_beam.MakePrivate(
budget_accountant=budget_accountant,
privacy_id_extractor=PrivateBeamTest.privacy_id_extractor))
sum_params = aggregate_params.SumParams(
noise_kind=pipeline_dp.NoiseKind.GAUSSIAN,
max_partitions_contributed=2,
max_contributions_per_partition=3,
min_value=1,
max_value=5,
budget_weight=1,
public_partitions=[],
partition_extractor=lambda x: f"pk:{x // 10}",
value_extractor=lambda x: x)
# Act
transformer = private_beam.Sum(sum_params=sum_params)
private_collection | transformer
# Assert
self.assertEqual(transformer._budget_accountant, budget_accountant)
mock_aggregate.assert_called_once()
args = mock_aggregate.call_args[0]
params = pipeline_dp.AggregateParams(
noise_kind=pipeline_dp.NoiseKind.GAUSSIAN,
metrics=[pipeline_dp.Metrics.SUM],
max_partitions_contributed=sum_params.
max_partitions_contributed,
max_contributions_per_partition=sum_params.
max_contributions_per_partition,
min_value=sum_params.min_value,
max_value=sum_params.max_value,
public_partitions=sum_params.public_partitions)
self.assertEqual(params, args[1])
def test_sum_with_public_partitions_returns_sensible_result(self):
with TestPipeline() as pipeline:
# Arrange
col = [(f"{u}", "pubK1", 100.0) for u in range(30)]
col += [(f"{u + 30}", "pubK1", -100.0) for u in range(30)]
col += [(f"{u + 60}", "privK1", 100.0) for u in range(30)]
pcol = pipeline | 'Create produce' >> beam.Create(col)
# Use very high epsilon and delta to minimize noise and test
# flakiness.
budget_accountant = budget_accounting.NaiveBudgetAccountant(
total_epsilon=800, total_delta=0.999)
private_collection = (
pcol | 'Create private collection' >> private_beam.MakePrivate(
budget_accountant=budget_accountant,
privacy_id_extractor=lambda x: x[0]))
sum_params = aggregate_params.SumParams(
noise_kind=pipeline_dp.NoiseKind.GAUSSIAN,
max_partitions_contributed=2,
max_contributions_per_partition=3,
min_value=1.55,
max_value=2.7889,
budget_weight=1,
partition_extractor=lambda x: x[1],
value_extractor=lambda x: x[2],
public_partitions=["pubK1", "pubK2"])
# Act
result = private_collection | private_beam.Sum(
sum_params=sum_params)
budget_accountant.compute_budgets()
# Assert
# This is a health check to validate that the result is sensible.
# Hence, we use a very large tolerance to reduce test flakiness.
beam_util.assert_that(
result,
beam_util.equal_to([("pubK1", 130.167), ("pubK2", 0.0)],
equals_fn=lambda e, a: PrivateBeamTest.
value_per_key_within_tolerance(e, a, 10.0)))