{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"},"kaggle":{"accelerator":"none","dataSources":[{"sourceType":"competition","sourceId":121150,"databundleVersionId":15833391}],"isInternetEnabled":true,"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":"#Just run normally\nname_path = \"/kaggle/input/deep-past-initiative-machine-translation/OA_Lexicon_eBL.csv\"\nlex_df = pd.read_csv(name_path)\npn_set = set(\n    lex_df.loc[lex_df[\"type\"] == \"PN\", \"form\"]\n    .dropna()\n)\n\ngn_set = set(\n    lex_df.loc[lex_df[\"type\"] == \"GN\", \"form\"]\n    .dropna()\n\ndef tag_person_names(text: str) -> str:\n    tokens = text.split()\n    out = []\n    for t in tokens:\n        nt = normalize(t)\n        if nt in pn_set:\n            out.append(f\"<PN>{t}</PN>\")\n        elif nt in gn_set:\n            out.append(f\"<GN>{t}</GN>\")\n        else:\n            out.append(t)\n    return \" \".join(out)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#Add in preprocessing\ntext = tag_person_names(text)\n\n\n#Add in postproocessing\ntext = text.replace(\"<PN>\", \"\").replace(\"</PN>\", \"\")\ntext = text.replace(\"<GN>\", \"\").replace(\"</GN>\", \"\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}