Data Lakehouse

import bauplan


client = bauplan.Client()

import_branch = 'your_import_branch'   
new_table = 'your_table'               
s3_uri = 's3://<bucket-name>/<object-key>'

# 1). Create a new data branch off "main" to isolate the import
client.create_branch(branch=import_branch, from_ref="main")

try:
    # 2). Create a new Iceberg table in the import branch from the S3 source
    client.create_table(table=new_table, search_uri=s3_uri, branch=import_branch)

    # 3). Import the data into the newly created table
    client.import_data(table=new_table, search_uri=s3_uri, branch=import_branch)
    print(f"✅ Data imported in '{new_table}'.")

except bauplan.exceptions.BauplanError as e:
    # 4). Catch and re-raise Bauplan-specific errors with a clear message
    raise Exception(f"🔴 The import did not work correctly: {e}")

@bauplan.model()
@bauplan.python('3.11', pip={'polars': '1.33.1'})
def silver_table(data=bauplan.Model('bronze_table')):
    import polars as pl
    
    # Convert input data into Polars and clean it
    df = data.to_polars()
    time_filter_utc = pl.Series(
        [pl.datetime(2022, 1, 1, 0, 0, 0, "UTC")]
    )[0]
    df = df.filter(pl.col("timestamp") >= time_filter_utc)
   
    return df.to_arrow()

import bauplan
import pandas as pd


client = bauplan.Client()

# query the table and return result set as an arrow Table
my_table = client.query(
    query="SELECT avg(age) AS average_age FROM titanic_dataset", 
    ref="main"
)
# efficiently cast the table to a other formats
df = my_table.to_pandas()