| { | |
| "statement": "SELECT * FROM MYTABLE", | |
| "resultSetMetaData": { | |
| "format": "arrowv1" | |
| }, | |
| "timeout": 60, | |
| "database": "MYDATABASE", | |
| "schema": "MYSCHEMA", | |
| "warehouse": "MYWAREHOUSE", | |
| "role": "MYROLE" |
This is a simple example demonstrating why you might want to use IbisML instead of just plain Ibis in an ML preprocessing pipeline.
You are training an ML model that gets better accuracy when the floating point number columns in the training data are normalized (by subtracting the mean and dividing by the standard deviation). Your data contains multiple floating point columns.
To demonstrate this, we can use the iris flower dataset.
| import ibis | |
| import random | |
| con = ibis.connect("duckdb://penguins.ddb") | |
| con.create_table( | |
| "penguins", ibis.examples.penguins.fetch().to_pyarrow(), overwrite = True | |
| ) | |
| ibis.options.interactive = True |
This is a set of examples demonstrating whether various Python and R dataframe libraries and OLAP query engines preserve (or do not preserve) the original order of the records in the data.
The examples all use this dataset describing the 28 times when a person walked on the moon:
| year | mission | name | minutes |
|---|---|---|---|
| 1969 | Apollo 11 | Neil Armstrong | 151 |
| 1969 | Apollo 11 | Buzz Aldrin | 151 |
| import pyarrow as pa | |
| import numpy as np | |
| import pandas as pd | |
| # Create an array of some fixed-width type containing nulls | |
| a = pa.array(obj=pd.Series([1, 2, 3]), type=pa.int64(), mask=np.array([1, 0, 1], dtype=bool)) | |
| # Get the values buffer as a bytearray | |
| b = a.buffers() | |
| v = bytearray(b[1].to_pybytes()) |
| /* | |
| * Licensed to the Apache Software Foundation (ASF) under one or more | |
| * contributor license agreements. See the NOTICE file distributed with | |
| * this work for additional information regarding copyright ownership. | |
| * The ASF licenses this file to You under the Apache License, Version 2.0 | |
| * (the "License"); you may not use this file except in compliance with | |
| * the License. You may obtain a copy of the License at | |
| * | |
| * http://www.apache.org/licenses/LICENSE-2.0 | |
| * |
| /* | |
| * Licensed to the Apache Software Foundation (ASF) under one or more | |
| * contributor license agreements. See the NOTICE file distributed with | |
| * this work for additional information regarding copyright ownership. | |
| * The ASF licenses this file to You under the Apache License, Version 2.0 | |
| * (the "License"); you may not use this file except in compliance with | |
| * the License. You may obtain a copy of the License at | |
| * | |
| * http://www.apache.org/licenses/LICENSE-2.0 | |
| * |
| /* | |
| * Licensed to the Apache Software Foundation (ASF) under one | |
| * or more contributor license agreements. See the NOTICE file | |
| * distributed with this work for additional information | |
| * regarding copyright ownership. The ASF licenses this file | |
| * to you under the Apache License, Version 2.0 (the | |
| * "License"); you may not use this file except in compliance | |
| * with the License. You may obtain a copy of the License at | |
| * | |
| * http://www.apache.org/licenses/LICENSE-2.0 |
| import pandas as pd | |
| import ibis | |
| # Different ways to create a DuckDB table from Ibis | |
| # ibis.memtable(...): ephemeral, all in-memory, stored as a view inside duckdb, removed when the session ends | |
| # ibis.memtable(...).cache(): ephemeral, stored as temporary table in the duckdb database, removed when the session ends, expression is cached for the lifetime of the session | |
| # con.create_table(..., temp=True): ephemeral, stored as temporary table in the duckdb database, removed when the session ends, expression is NOT cached for the lifetime of the session | |
| # con.create_table(...): persistent, across sessions (assuming you're not using an in-memory connection) |
| import pandas as pd | |
| import pyarrow as pa | |
| import ibis | |
| from pyspark.sql import SparkSession | |
| # create example data in a pandas DataFrame | |
| df = pd.DataFrame(data={'fruit': ['apple', 'apple', 'apple', 'orange', 'orange', 'orange'], | |
| 'variety': ['gala', 'honeycrisp', 'fuji', 'navel', 'valencia', 'cara cara'], | |
| 'weight': [134.2 , 158.6, None, 142.1, 96.7, None]}) |