Feature Platform for Machine Learning

				
					# Specify inputs, entities and compute configuration
@batch_feature_view(
  description="Whether the user has a good credit score, updated daily",
  sources=[credit_scores],
  entities=[user],
  feature_start_time=datetime(2020, 10, 1),
  batch_schedule=timedelta(days=1),
)
# Define transformation logic
def user_credit_quality(credit_scores):
  return f'''
      SELECT
          USER_ID,
          IF (CREDIT_SCORE > 700, 1, 0) AS USER_HAS_GOOD_CREDIT,
          TIMESTAMP
      FROM
          {credit_scores}
      '''
    
    
    
    
    
    ‎
				
			

				
					# Specify inputs, entities, and compute configuration
@stream_feature_view(
  description="Mean transaction amount of last hour, 24h and 72h, updated every 10 min",
  source=transactions,
  entities=[user],
  feature_start_time=datetime(2020, 10, 1),
  # Define logic for time-window aggregations
  aggregation_interval=timedelta(minutes=10),
  aggregations=[
        Aggregation(column='AMOUNT', function='mean', time_window=timedelta(hours=1)), 
        Aggregation(column='AMOUNT', function='mean', time_window=timedelta(hours=24)),
        Aggregation(column='AMOUNT', function='mean', time_window=timedelta(hours=72)),     
  ],
)
# Define query to use in the transformation
def mean_transaction_amount(transactions):
  return f'''
      SELECT
          USER_ID,
          AMOUNT,
          TIMESTAMP
      FROM
          {transactions}
      '''
				
			

				
					# Indicate schema of incoming request-time data (e.g. live transaction data)
transaction_request = RequestSource([Field('amount', Float64)])

# Specify inputs and schema of the output
@on_demand_feature_view(
  description="Whether the current transaction amount is higher than the user's weekly average.",
  sources=[transaction_request, historical_metrics],
  schema=[Field('transaction_amount_is_higher_than_average', Bool)],
)
# Define transformation logic
def transaction_amount_is_higher_than_average(transaction_request, historical_metrics):
  result = {}
  result['transaction_amount_is_higher_than_average'] = (
    transaction_request['amount'] >= historical_metrics['amount_7d_mean'])
  return result
    
    
    
    
    
    
    
    
    ‎