{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":96164,"databundleVersionId":12993472,"sourceType":"competition"},{"sourceId":12462463,"sourceType":"datasetVersion","datasetId":7861436},{"sourceId":12475102,"sourceType":"datasetVersion","datasetId":7870836},{"sourceId":250087140,"sourceType":"kernelVersion"},{"sourceId":250232985,"sourceType":"kernelVersion"},{"sourceId":250368902,"sourceType":"kernelVersion"}],"dockerImageVersionId":31089,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"Gambit - giving up material for an advantage in time","metadata":{}},{"cell_type":"code","source":"import pandas as pd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T09:22:38.285460Z","iopub.execute_input":"2025-07-15T09:22:38.286002Z","iopub.status.idle":"2025-07-15T09:22:39.841079Z","shell.execute_reply.started":"2025-07-15T09:22:38.285981Z","shell.execute_reply":"2025-07-15T09:22:39.840176Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def iBlend(path_to_ds, file_short_names, sls):\n\n    def tida(sls):\n        \n        def read_subm(sls,i):\n            tnm = sls[\"subm\"][i][\"name\"]\n            FiN = sls[\"path\"] + tnm + \".csv\"\n            return pd.read_csv(FiN).rename(columns={'target':tnm, sls[\"target\"]:tnm})\n        \n        dfs_subm = [read_subm(sls,i) for i in range(len(sls[\"subm\"]))]\n        df_subms = pd.merge(dfs_subm[0],  dfs_subm[1], on=['ID'])\n        \n        for i in range(2, len(sls[\"subm\"])): \n            df_subms = pd.merge(df_subms, dfs_subm[i], on=['ID'])\n            \n        cols = [col for col in df_subms.columns if col != \"ID\"]\n        short_name_cols = [c.replace(sls[\"prefix\"], '') for c in cols]\n        corrects = [wt for wt in sls[\"subwts\"]]\n        weights = [subm['weight'] for subm in sls[\"subm\"]]\n        \n        def alls(x, cs=cols):\n            tes = {c: x[c] for c in cs}.items()\n            subms_sorted = [\n              t[0].replace(sls[\"prefix\"], '')\n              for t in sorted(tes,key=lambda k:k[1],reverse=True if sls[\"sort\"]=='desc' else False)]\n            return subms_sorted\n        \n        def correct(x, cs=cols, w=weights, cw=corrects):\n            ic = [x['alls'].index(c) for c in short_name_cols]\n            cS = [x[cols[j]] * (w[j] + cw[ic[j]]) for j in range(len(cols))]\n            return sum(cS)\n        \n        df_subms['alls']        = df_subms.apply(lambda x: alls   (x), axis=1)\n        df_subms[sls[\"target\"]] = df_subms.apply(lambda x: correct(x), axis=1)\n        \n        schema_rename = { old_nc:new_shnc for old_nc, new_shnc in zip(cols, short_name_cols) }\n        \n        df_subms = df_subms.rename(columns=schema_rename)\n        df_subms = df_subms.rename(columns={sls[\"target\"]:\"ensemble\"})\n        \n        df_subms.insert(loc=1, column=' _ ', value=['   '] * sls[\"q_rows\"])\n        \n        df_subms[' _ '] = df_subms[' _ '].astype(str)\n        pd.set_option('display.max_rows',100)\n        pd.set_option('display.float_format', '{:.7f}'.format)\n        vcols = ['ID'] + [' _ '] + short_name_cols + [' _ '] + ['alls'] + [' _ '] + ['ensemble']\n        df_subms = df_subms[vcols]\n        display(df_subms.head(7))\n        pd.set_option('display.float_format', '{:.11f}'.format)\n        df_subms = df_subms.rename(columns={\"ensemble\":sls[\"target\"]})\n        \n        return df_subms\n        \n\n    sample_subm = pd.read_csv(path_to_ds + file_short_names[1] + \".csv\")\n\n    \n    def ensemble_tida(sls,submission=sample_subm):   \n        sls['sort'] = 'desc'\n        dfs = tida(sls)\n        dfD = dfs[['ID', sls['target']]]\n        dfD.to_csv(f'tida_desc.csv', index=False)\n        sls['sort'] = 'asc'\n        dfs = tida(sls)\n        dfA = dfs[['ID', sls['target']]]\n        dfA.to_csv(f'tida_asc.csv',  index=False)\n        target,d,a = sls['target'],sls['desc'],sls['asc']\n        submission[target] = dfD[target] * d + a * dfA[target]\n        return submission\n\n    submission = ensemble_tida(sls)\n    \n    return submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T09:22:45.327838Z","iopub.execute_input":"2025-07-15T09:22:45.328610Z","iopub.status.idle":"2025-07-15T09:22:45.345890Z","shell.execute_reply.started":"2025-07-15T09:22:45.328574Z","shell.execute_reply":"2025-07-15T09:22:45.345022Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"path_to_ds ='/kaggle/input/13-juli-2025-drw/submission '\n\nfile_short_names = ['0.73799','0.72837','0.70871']\n\nparams = {\n      'path'  : path_to_ds,                                 \n      'sort'  : \"dynamic\",\n      'target': \"prediction\",\n      'q_rows': 538_150,\n      'prefix': \"subm_\",\n      'desc'  : 0.30,\n      'asc'   : 0.70,\n      'subwts': [+0.40, -0.10, -0.30],                          # LB = 0.80384,  v.8\n      'subm'  : [\n        { 'name':file_short_names[0],'weight':0.37, },\n        { 'name':file_short_names[1],'weight':0.34, },\n        { 'name':file_short_names[2],'weight':0.29, },\n      ]\n    }\n\npath_to_ds ='/kaggle/input/13-juli-2025-drw/submission '\n\nfile_short_names = ['0.73799','0.72837','0.70871']\n\nparams = {\n      'path'  : path_to_ds,                                 \n      'sort'  : \"dynamic\",\n      'target': \"prediction\",\n      'q_rows': 538_150,\n      'prefix': \"subm_\",\n      'desc'  : 0.20,\n      'asc'   : 0.80,\n      'subwts': [+0.50, -0.15, -0.35],                          # LB = 0.78384,  v.9\n      'subm'  : [\n        { 'name':file_short_names[0],'weight':0.38, },\n        { 'name':file_short_names[1],'weight':0.34, },\n        { 'name':file_short_names[2],'weight':0.28, },\n      ]\n    }\n\n\npath_to_ds ='/kaggle/input/13-juli-2025-drw/submission '\n\nfile_short_names = ['0.73799','0.72837','0.70871']\n\nparams = {\n      'path'  : path_to_ds,                                 \n      'sort'  : \"dynamic\",\n      'target': \"prediction\",\n      'q_rows': 538_150,\n      'prefix': \"subm_\",\n      'desc'  : 0.33,\n      'asc'   : 0.67,\n      'subwts': [+0.40, -0.10, -0.30],                          # LB = 0.80925,  v.10\n      'subm'  : [\n        { 'name':file_short_names[0],'weight':0.34, },\n        { 'name':file_short_names[1],'weight':0.33, },\n        { 'name':file_short_names[2],'weight':0.33, },\n      ]\n    }\n\n\npath_to_ds ='/kaggle/input/13-juli-2025-drw/submission '\n\nfile_short_names = ['0.73799','0.72837','0.70871','0.81760']\n\nparams = {\n      'path'  : path_to_ds,                                 \n      'sort'  : \"dynamic\",\n      'target': \"prediction\",\n      'q_rows': 538_150,\n      'prefix': \"subm_\",\n      'desc'  : 0.33,\n      'asc'   : 0.67,\n      'subwts': [+1.00, -0.20, -0.30, -0.50],                   # LB = 0.82968,  v.11\n      'subm'  : [\n        { 'name':file_short_names[0],'weight':0.34, },\n        { 'name':file_short_names[1],'weight':0.33, },\n        { 'name':file_short_names[2],'weight':0.33, },\n        { 'name':file_short_names[3],'weight':1.00, },\n      ]\n    }","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-14T03:46:50.535339Z","iopub.execute_input":"2025-07-14T03:46:50.535631Z","iopub.status.idle":"2025-07-14T03:46:50.541358Z","shell.execute_reply.started":"2025-07-14T03:46:50.535610Z","shell.execute_reply":"2025-07-14T03:46:50.540559Z"},"jupyter":{"source_hidden":true},"_kg_hide-input":true,"_kg_hide-output":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"path_to_ds ='/kaggle/input/15-juli-2025-drw/submission '\n\nfile_short_names = ['0.83975','0.86767','0.89178']\n\nparams = {\n      'path'  : path_to_ds,                                 \n      'sort'  : \"dynamic\",\n      'target': \"prediction\",\n      'q_rows': 538_150,\n      'prefix': \"subm_\",\n      'desc'  : 0.30,\n      'asc'   : 0.70,\n      'subwts': [+0.40, -0.10, -0.30],                          # LB = 0.93980\n      'subm'  : [\n        { 'name':file_short_names[0],'weight':0.20, },\n        { 'name':file_short_names[1],'weight':0.30, },\n        { 'name':file_short_names[2],'weight':0.50, },\n      ]\n    }\n\n\npath_to_ds ='/kaggle/input/15-juli-2025-drw/submission '\n\nfile_short_names = ['0.83975','0.86767','0.88377','0.89178','0.90038']\n\nparams = {\n      'path'  : path_to_ds,                                 \n      'sort'  : \"dynamic\",\n      'target': \"prediction\",\n      'q_rows': 538_150,\n      'prefix': \"subm_\",\n      'desc'  : 0.30,\n      'asc'   : 0.70,\n      'subwts': [+0.20, +0.10, -0.05,-0.10,-0.15],              # LB = ?\n      'subm'  : [\n         { 'name':file_short_names[0],'weight':0.21, },\n         { 'name':file_short_names[1],'weight':0.21, },\n         { 'name':file_short_names[2],'weight':0.21, },\n         { 'name':file_short_names[3],'weight':0.21, },\n         { 'name':file_short_names[4],'weight':0.21, },\n      ]\n    }","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T09:23:02.864910Z","iopub.execute_input":"2025-07-15T09:23:02.865322Z","iopub.status.idle":"2025-07-15T09:23:02.870707Z","shell.execute_reply.started":"2025-07-15T09:23:02.865296Z","shell.execute_reply":"2025-07-15T09:23:02.869798Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = iBlend ( path_to_ds, file_short_names, params )\n\ndf.to_csv('submission.csv', index=False)\n\ndisplay(df)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T09:23:11.570783Z","iopub.execute_input":"2025-07-15T09:23:11.571084Z","iopub.status.idle":"2025-07-15T09:23:47.977988Z","shell.execute_reply.started":"2025-07-15T09:23:11.571059Z","shell.execute_reply":"2025-07-15T09:23:47.977223Z"}},"outputs":[],"execution_count":null}]}