{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\n\ntest = pd.read_csv('../input/bms-molecular-translation/sample_submission.csv')\n\n# the chem id below has a mean levenstein distance with all the other training chem ids of 71.0892922407769\n# we will always predict this central chem id as a dummy baseline\nchem_id_center = 'InChI=1S/C15H15NO/c1-12-7-5-6-10-14(12)11-16-15(17)13-8-3-2-4-9-13/h2-10H,11H2,1H3,(H,16,17)'\n# I found this central chemical id by computing a lot of levenstein distances between many chem ids with :\n# from Levenshtein import distance\n# distance(chem_id_1, chem_id_2)\n\n# submission\ntest['InChI'] = chem_id_center  # always predict the same chem id\ntest[['image_id', 'InChI']].to_csv('submission.csv', index=False)\ntest[['image_id', 'InChI']].head()","execution_count":null,"outputs":[]}],"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"}},"nbformat":4,"nbformat_minor":4}