{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceType":"competition","sourceId":118765,"databundleVersionId":15231210,"isSourceIdPinned":false}],"dockerImageVersionId":31328,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\n\nDATA_DIR = \"/kaggle/input/competitions/stanford-rna-3d-folding-2\"\n\ntest_df = pd.read_csv(os.path.join(DATA_DIR, \"test_sequences.csv\"))\nsample_sub = pd.read_csv(os.path.join(DATA_DIR, \"sample_submission.csv\"))\n\ndef build_naive_coords(sequence, n_models=5):\n    n = len(sequence)\n    coords = np.zeros((n, n_models, 3))\n    \n    for m in range(n_models):\n        for i in range(n):\n            coords[i, m, 0] = i * 5 + np.random.randn() * 0.2\n            coords[i, m, 1] = np.random.randn() * 0.2\n            coords[i, m, 2] = np.random.randn() * 0.2\n    \n    return coords\n\nrows = []\n\nfor _, row in test_df.iterrows():\n    target_id = row[\"target_id\"]\n    sequence = row[\"sequence\"]\n    \n    coords = build_naive_coords(sequence)\n    \n    for i, base in enumerate(sequence, start=1):\n        out = {\n            \"ID\": f\"{target_id}_{i}\",\n            \"resname\": base,\n            \"resid\": i\n        }\n        \n        for m in range(5):\n            out[f\"x_{m+1}\"] = coords[i-1, m, 0]\n            out[f\"y_{m+1}\"] = coords[i-1, m, 1]\n            out[f\"z_{m+1}\"] = coords[i-1, m, 2]\n        \n        rows.append(out)\n\nsubmission = pd.DataFrame(rows)\n\n# clip\ncoord_cols = [c for c in submission.columns if c.startswith((\"x_\", \"y_\", \"z_\"))]\nsubmission[coord_cols] = submission[coord_cols].clip(-999.999, 9999.999)\n\nsubmission = submission[sample_sub.columns]\n\nsubmission.to_csv(\"submission.csv\", index=False)\n\nprint(\"Done! submission.csv created\")\nsubmission.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-24T21:09:31.625828Z","iopub.execute_input":"2026-03-24T21:09:31.626074Z","iopub.status.idle":"2026-03-24T21:09:33.689764Z","shell.execute_reply.started":"2026-03-24T21:09:31.626046Z","shell.execute_reply":"2026-03-24T21:09:33.688514Z"}},"outputs":[],"execution_count":null}]}