{"task": {"agent_timeout": 1800, "task": "823", "verifier_timeout": 1800, "instruction": "# 823: DS-1000 Task\n\n## Prompt\nProblem:\n\nI would like to break down a pandas column, which is the last column, consisting of a list of elements into as many columns as there are unique elements i.e. one-hot-encode them (with value 1 representing a given element existing in a row and 0 in the case of absence).\n\nFor example, taking dataframe df\n\nCol1   Col2    Col3          Col4\n C      33      11       [Apple, Orange, Banana]\n A      2.5     4.5      [Apple, Grape]\n B      42      14       [Banana]\n D      666     1919810  [Suica, Orange]\nI would like to convert this to:\n\ndf\n\nCol1 Col2     Col3  Apple  Banana  Grape  Orange  Suica\nC   33       11      1       1      0       1      0\nA  2.5      4.5      1       0      1       0      0\nB   42       14      0       1      0       0      0\nD  666  1919810      0       0      0       1      1\nHow can I use pandas/sklearn to achieve this?\n\nA:\n\n<code>\nimport pandas as pd\nimport numpy as np\nimport sklearn\ndf = load_data()\n</code>\ndf_out = ... # put solution in this variable\nBEGIN SOLUTION\n<code>\n\n## What to do\n- Edit `solution/solution.py` so the code passes the DS-1000 tests.\n- Do not access the internet or install new packages; required libraries are preinstalled in the Docker image.\n- Run tests locally via `bash tests/test.sh`.\n\n## Notes\n- Keep the variable names/signatures implied by the prompt/code_context.\n- The evaluator uses the original DS-1000 `code_context` (`test_execution` / `test_string`).\n", "memory": "", "runnable": false, "difficulty": "", "language": "", "cpus": "", "instruction_truncated": false, "category": "", "compose": false, "has_solution": true, "oracle": null, "docker_image": "ds1000:latest", "taskset": "ds1000", "tags": []}, "runs": []}