{"task": {"agent_timeout": 1800, "task": "978", "verifier_timeout": 1800, "instruction": "# 978: DS-1000 Task\n\n## Prompt\nProblem:\n\nI have a logistic regression model using Pytorch, where my input is high-dimensional and my output must be a scalar - 0, 1 or 2.\n\nI'm using a linear layer combined with a softmax layer to return a n x 3 tensor, where each column represents the probability of the input falling in one of the three classes (0, 1 or 2).\n\nHowever, I must return a 1 x n tensor, and I want to somehow pick the lowest probability for each input and create a tensor indicating which class had the lowest probability. How can I achieve this using Pytorch?\n\nTo illustrate, my Softmax outputs this:\n\n[[0.2, 0.1, 0.7],\n [0.6, 0.3, 0.1],\n [0.15, 0.8, 0.05]]\nAnd I must return this:\n\n[1, 2, 2], which has the type torch.LongTensor\n\n\nA:\n\n<code>\nimport numpy as np\nimport pandas as pd\nimport torch\nsoftmax_output = load_data()\ndef solve(softmax_output):\n</code>\ny = ... # 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": []}