jorgecarleitao / datafusion-python Goto Github PK

import datafusion
import pyarrow

# an alias
f = datafusion.functions

# create a context
ctx = datafusion.ExecutionContext()

# create a RecordBatch and a new DataFrame from it
batch = pyarrow.RecordBatch.from_arrays(
    [pyarrow.array([1, 2, 3]), pyarrow.array([4, 5, 6])],
    names=["a", "b"],
)
df = ctx.create_dataframe([[batch]])

# create a new statement
df = df.select(
    f.col("a") + f.col("b"),
    f.col("a") - f.col("b"),
)

# execute and collect the first (and only) batch
result = df.collect()[0]

assert result.column(0) == pyarrow.array([5, 7, 9])
assert result.column(1) == pyarrow.array([-3, -3, -3])

def is_null(array: pyarrow.Array) -> pyarrow.Array:
    return array.is_null()

udf = f.udf(is_null, [pyarrow.int64()], pyarrow.bool_())

df = df.select(udf(f.col("a")))

import pyarrow
import pyarrow.compute


class Accumulator:
    """
    Interface of a user-defined accumulation.
    """
    def __init__(self):
        self._sum = pyarrow.scalar(0.0)

    def to_scalars(self) -> [pyarrow.Scalar]:
        return [self._sum]

    def update(self, values: pyarrow.Array) -> None:
        # not nice since pyarrow scalars can't be summed yet. This breaks on `None`
        self._sum = pyarrow.scalar(self._sum.as_py() + pyarrow.compute.sum(values).as_py())

    def merge(self, states: pyarrow.Array) -> None:
        # not nice since pyarrow scalars can't be summed yet. This breaks on `None`
        self._sum = pyarrow.scalar(self._sum.as_py() + pyarrow.compute.sum(states).as_py())

    def evaluate(self) -> pyarrow.Scalar:
        return self._sum


df = ...

udaf = f.udaf(Accumulator, pyarrow.float64(), pyarrow.float64(), [pyarrow.float64()])

df = df.aggregate(
    [],
    [udaf(f.col("a"))]
)