The unified reasoning engine

import outerproduct as op

# Set the OUTERPRODUCT_API_KEY environment variable
# Create an API key at console.outerproduct.com (contact us to get access)
op.init()  
ws = op.Workspace()

# 1. Register multiple data sources 
ws.register_parquet("segments", "data/segments.parquet") 
ws.register_s3("events", "s3://acme-data/events.parquet", connector="prod-aws")
ws.register_snowflake("customers", "ANALYTICS.PUBLIC.CUSTOMERS", connector="prod-snowflake")
ws.register_databricks("payments", "main.finance.payments", connector="prod-databricks")

# 2. Query tables
df = ws.sql("""
    SELECT c.customer_id, c.plan, COUNT(e.event_id) AS events_30d, c.churned FROM customers c
    LEFT JOIN events e ON e.customer_id = c.customer_id
    GROUP BY c.customer_id, c.plan, c.churned
""")

# 3. Model training
split = int(0.8 * df.count())
train_df = df.filter(op.col("id") < split)
model = op.reasoning.fit(
    train_df,
    task=op.Binclass(label_column="churned"),
    hpo_space=op.HPOSpace.add(op.ModelSpace("tabicl")).add(op.ModelSpace("tabm")),
    optimizer=op.Optimizer(kind="tpe", n_trials_per_step=5, n_steps=10),
	metrics=[op.metric('accuracy'), op.metric('logloss')]
).wait()

# 4. Reasoning 
test_df = df.filter(op.col("id") >= split).drop(op.col("churned"))
predictions, reasoning = model.predict_and_explain(test_df)
scenarios = model.scenario(test_df, target_value=0.5)