Run AI on your production data, safely.

import bauplan

client = bauplan.Client()

dev_branch = client.create_branch(
    branch="fritz.dev",
    from_ref="main",
)

tables = client.get_tables(ref=dev_branch)
print(tables)

preview = client.query("SELECT * FROM my_table LIMIT 5", ref=dev_branch)
print(preview)

assert client.merge_branch(
    source_ref=dev_branch, 
    into_branch="main"
)

import bauplan
from bauplan.standard_expectations import expect_column_no_nulls

@bauplan.model()
@bauplan.python("3.11", pip={"pandas": "2.2.0"})
def clean_data(data=bauplan.Model("source_data")):
    df = data.to_pandas()
    return df.dropna()

@bauplan.expectation()
@bauplan.python("3.11")
def test_clean_data(data=bauplan.Model("clean_data")):
    return expect_column_no_nulls(data, "id")

import bauplan

client = bauplan.Client()

dev_branch = client.create_branch(
    branch="fritz.dev",
    from_ref="main",
)

job_state = client.run("./my_project", ref=dev_branch)

if not job_state.success:
    raise Exception(f"{job_state.job_id} failed")

assert client.merge_branch(
    source_ref=dev_branch, 
    into_branch="main"
)