{"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":"gpu","dataSources":[{"sourceType":"competition","sourceId":121150,"databundleVersionId":15833391},{"sourceType":"kernelVersion","sourceId":303127857},{"sourceType":"kernelVersion","sourceId":304302040},{"sourceType":"kernelVersion","sourceId":304532015},{"sourceType":"kernelVersion","sourceId":305695459},{"sourceType":"kernelVersion","sourceId":305914191}],"dockerImageVersionId":31329,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Deep Past Initiative – Machine Translation (Inference Notebook)\n\nThis notebook is a **starter / baseline** for this Kaggle competition.","metadata":{}},{"cell_type":"code","source":"import os\nimport pandas as pd\nimport torch\nfrom torch.utils.data import DataLoader, Dataset\nfrom transformers import AutoTokenizer, AutoModelForSeq2SeqLM\nfrom tqdm.auto import tqdm","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-03-25T13:29:29.342346Z","iopub.execute_input":"2026-03-25T13:29:29.343143Z","iopub.status.idle":"2026-03-25T13:29:29.348113Z","shell.execute_reply.started":"2026-03-25T13:29:29.343104Z","shell.execute_reply":"2026-03-25T13:29:29.347068Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"MODEL_PATH = \"/kaggle/input/notebooks/sebastiaanwortelboer/training-baseline-byt5-base-refining/byt5-akkadian-model/\"\n\n\nfiles = os.listdir(MODEL_PATH)\nprint(\"Files in model path:\", files)\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-25T13:29:29.350104Z","iopub.execute_input":"2026-03-25T13:29:29.350508Z","iopub.status.idle":"2026-03-25T13:29:29.394483Z","shell.execute_reply.started":"2026-03-25T13:29:29.350478Z","shell.execute_reply":"2026-03-25T13:29:29.393674Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"TEST_DATA_PATH = \"/kaggle/input/competitions/deep-past-initiative-machine-translation/test.csv\"\nBATCH_SIZE = 16\nMAX_LENGTH = 512\nDEVICE = \"cpu\"\n\n# --- Model Loading ---\nprint(f\"Loading model from {MODEL_PATH}...\")\ntokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)\nmodel = AutoModelForSeq2SeqLM.from_pretrained(MODEL_PATH).to(DEVICE)\nmodel.eval()\n\n# --- Data Preparation ---\ntest_df = pd.read_csv(TEST_DATA_PATH)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-25T13:29:29.396235Z","iopub.execute_input":"2026-03-25T13:29:29.396520Z","iopub.status.idle":"2026-03-25T13:29:31.665814Z","shell.execute_reply.started":"2026-03-25T13:29:29.396492Z","shell.execute_reply":"2026-03-25T13:29:31.664617Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"PREFIX = \"translate Akkadian to English: \"\n\nclass InferenceDataset(Dataset):\n    def __init__(self, df, tokenizer):\n        self.texts = df['transliteration'].astype(str).tolist()\n        self.texts = [PREFIX + i for i in self.texts]\n        self.tokenizer = tokenizer\n        \n    def __len__(self):\n        return len(self.texts)\n    \n    def __getitem__(self, idx):\n        text = self.texts[idx]\n        inputs = self.tokenizer(\n            text, \n            max_length=MAX_LENGTH, \n            padding=\"max_length\", \n            truncation=True, \n            return_tensors=\"pt\"\n        )\n        return {\n            \"input_ids\": inputs[\"input_ids\"].squeeze(0),\n            \"attention_mask\": inputs[\"attention_mask\"].squeeze(0)\n        }\n\ntest_dataset = InferenceDataset(test_df, tokenizer)\ntest_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=False)\n\n# --- Inference Loop ---\nprint(\"Starting Inference...\")\nall_predictions = []","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-25T13:29:31.667284Z","iopub.execute_input":"2026-03-25T13:29:31.667661Z","iopub.status.idle":"2026-03-25T13:29:31.678667Z","shell.execute_reply.started":"2026-03-25T13:29:31.667627Z","shell.execute_reply":"2026-03-25T13:29:31.677526Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"with torch.no_grad():\n    for batch in tqdm(test_loader):\n        input_ids = batch[\"input_ids\"].to(DEVICE)\n        attention_mask = batch[\"attention_mask\"].to(DEVICE)\n  \n        outputs = model.generate(\n            input_ids=input_ids,\n            attention_mask=attention_mask,\n            max_length=MAX_LENGTH,\n            num_beams=4,\n            early_stopping=True\n        )\n        \n        decoded = tokenizer.batch_decode(outputs, skip_special_tokens=True)\n        all_predictions.extend([d.strip() for d in decoded])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-25T13:29:31.680105Z","iopub.execute_input":"2026-03-25T13:29:31.680635Z","iopub.status.idle":"2026-03-25T13:32:07.577941Z","shell.execute_reply.started":"2026-03-25T13:29:31.680581Z","shell.execute_reply":"2026-03-25T13:32:07.576924Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# --- Submission ---\nsubmission = pd.DataFrame({\n    \"id\": test_df[\"id\"],\n    \"translation\": all_predictions\n})\n\nsubmission[\"translation\"] = submission[\"translation\"].apply(lambda x: x if len(x) > 0 else \"broken text\")\n\nsubmission.to_csv(\"submission.csv\", index=False)\nprint(\"Submission file saved successfully!\")\nsubmission.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-25T13:32:07.579971Z","iopub.execute_input":"2026-03-25T13:32:07.580368Z","iopub.status.idle":"2026-03-25T13:32:07.593903Z","shell.execute_reply.started":"2026-03-25T13:32:07.580339Z","shell.execute_reply":"2026-03-25T13:32:07.592930Z"}},"outputs":[],"execution_count":null}]}