cuDF dataframe merge

dataframe_merge.py

import cudf


def merge():
    left = cudf.DataFrame(
        {
            "string_id": [
                3,
                3,
                6,
                3,
                6,
                5,
                5,
                4,
                6,
                4,
                7,
                5,
                5,
                6,
                5,
                7,
                7,
                3,
                5,
                5,
                3,
                7,
                3,
                6,
                3,
                6,
                4,
                6,
                6,
                7,
            ]
        }
    )
    right = cudf.DataFrame(
        {
            "string_id": [3, 4, 5, 6, 7],
            "embeddings": [
                [0.43440665, 0.71459431],
                [0.16957864, 0.4211413],
                [0.6488939, 0.69370209],
                [0.17119426, 0.54116936],
                [0.55397995, 0.07149349],
            ],
        }
    )
    merged = left.merge(right, on="string_id", how="left")
    print("left:")
    print(left)
    print("right:")
    print(right)
    print("merged:")
    print(merged)


if __name__ == "__main__":
    merge()