{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np\nimport pandas as pd","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-09-28T09:48:01.983533Z","iopub.execute_input":"2023-09-28T09:48:01.984049Z","iopub.status.idle":"2023-09-28T09:48:02.309674Z","shell.execute_reply.started":"2023-09-28T09:48:01.984021Z","shell.execute_reply":"2023-09-28T09:48:02.307952Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In this notebook we simply compute the median values for both experiment types and make constant predictions as these medians.","metadata":{}},{"cell_type":"markdown","source":"# Read the data","metadata":{}},{"cell_type":"code","source":"train_data = pd.read_csv(\"/kaggle/input/stanford-ribonanza-rna-folding/train_data.csv\")\nsample_submission = pd.read_csv('/kaggle/input/stanford-ribonanza-rna-folding/sample_submission.csv')","metadata":{"execution":{"iopub.status.busy":"2023-09-28T09:48:02.311453Z","iopub.execute_input":"2023-09-28T09:48:02.311856Z","iopub.status.idle":"2023-09-28T09:48:02.316251Z","shell.execute_reply.started":"2023-09-28T09:48:02.311827Z","shell.execute_reply":"2023-09-28T09:48:02.315330Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Compute the medians","metadata":{}},{"cell_type":"code","source":"reactivity_columns = train_data.columns[train_data.columns.str.startswith('reactivity_0')]\nsn_filter = (train_data.SN_filter == 1)\nexp_type = (train_data.experiment_type == '2A3_MaP')\ntwoA3 = train_data[sn_filter & exp_type][reactivity_columns].median().median()\nDMS_MaP = train_data[sn_filter & ~exp_type][reactivity_columns].median().median()","metadata":{"execution":{"iopub.status.busy":"2023-09-28T09:49:29.843276Z","iopub.execute_input":"2023-09-28T09:49:29.843761Z","iopub.status.idle":"2023-09-28T09:49:29.850332Z","shell.execute_reply.started":"2023-09-28T09:49:29.843730Z","shell.execute_reply":"2023-09-28T09:49:29.848765Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(twoA3, DMS_MaP)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Form the submission","metadata":{}},{"cell_type":"code","source":"sample_submission['reactivity_2A3_MaP'] = twoA3\nsample_submission['reactivity_DMS_MaP'] = DMS_MaP","metadata":{"execution":{"iopub.status.busy":"2023-09-28T09:49:30.565819Z","iopub.execute_input":"2023-09-28T09:49:30.566230Z","iopub.status.idle":"2023-09-28T09:49:31.173976Z","shell.execute_reply.started":"2023-09-28T09:49:30.566198Z","shell.execute_reply":"2023-09-28T09:49:31.173017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission.to_csv('submission.csv', index=None)","metadata":{"execution":{"iopub.status.busy":"2023-09-28T09:49:35.480449Z","iopub.execute_input":"2023-09-28T09:49:35.480833Z","iopub.status.idle":"2023-09-28T09:57:23.153046Z","shell.execute_reply.started":"2023-09-28T09:49:35.480807Z","shell.execute_reply":"2023-09-28T09:57:23.151586Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}