{"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":"markdown","source":"# TPS_OCT_2022_EDA_LGBM_part2🥅\n\nThis is a continuation from TPS_OCT_2022_EDA_LGBM_part1.","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom datetime import datetime\nfrom tqdm.notebook import tqdm\n\nfrom sklearn import preprocessing\nfrom sklearn.model_selection import train_test_split, KFold\nfrom sklearn.metrics import log_loss, accuracy_score\n\nimport lightgbm as lgb\nimport optuna\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","metadata":{"execution":{"iopub.status.busy":"2022-10-14T20:17:05.923883Z","iopub.execute_input":"2022-10-14T20:17:05.924356Z","iopub.status.idle":"2022-10-14T20:17:08.046524Z","shell.execute_reply.started":"2022-10-14T20:17:05.924319Z","shell.execute_reply":"2022-10-14T20:17:08.045024Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def add_feature(data):\n    # between ball and player (Distance = sqrt((Bx - Px)^2) + ((By - Py)^2) +((Bz - Pz)^2)) e.g. Bx = ball position x, Px = player position x\n    data['p0_dist_ball'] = ((data['ball_pos_x'] - data['p0_pos_x'])**2 + (data['ball_pos_y'] - data['p0_pos_y'])**2 + (data['ball_pos_z'] - data['p0_pos_z'])**2)** 0.5\n    data['p1_dist_ball'] = ((data['ball_pos_x'] - data['p1_pos_x'])**2 + (data['ball_pos_y'] - data['p1_pos_y'])**2 + (data['ball_pos_z'] - data['p1_pos_z'])**2)** 0.5\n    data['p2_dist_ball'] = ((data['ball_pos_x'] - data['p2_pos_x'])**2 + (data['ball_pos_y'] - data['p2_pos_y'])**2 + (data['ball_pos_z'] - data['p2_pos_z'])**2)** 0.5\n    data['p3_dist_ball'] = ((data['ball_pos_x'] - data['p3_pos_x'])**2 + (data['ball_pos_y'] - data['p3_pos_y'])**2 + (data['ball_pos_z'] - data['p3_pos_z'])**2)** 0.5\n    data['p4_dist_ball'] = ((data['ball_pos_x'] - data['p4_pos_x'])**2 + (data['ball_pos_y'] - data['p2_pos_y'])**2 + (data['ball_pos_z'] - data['p4_pos_z'])**2)** 0.5\n    data['p5_dist_ball'] = ((data['ball_pos_x'] - data['p5_pos_x'])**2 + (data['ball_pos_y'] - data['p5_pos_y'])**2 + (data['ball_pos_z'] - data['p5_pos_z'])**2)** 0.5\n    \n     # distance between goal and player\n    goal_a_0 = [0, -120, 1.2]\n    goal_a_1 = [20, -120, 1.2]\n    goal_a_2 = [-20, -120, 1.2]\n    goal_b_0 = [0, -120, 1.2]\n    goal_b_1 = [20, 120, 1.2]\n    goal_b_2 = [-20, 120, 1.2]\n    \n    data['p0_dist_goal_0'] = ((goal_a_0[0] - data['p0_pos_x'])**2 + (goal_a_1[1] - data['p1_pos_y'])**2 + (goal_a_1[2] - data['p0_pos_z'])**2)** 0.5\n    data['p1_dist_goal_0'] = ((goal_a_0[0] - data['p1_pos_x'])**2 + (goal_a_1[1] - data['p1_pos_y'])**2 + (goal_a_1[2] - data['p1_pos_z'])**2)** 0.5\n    data['p2_dist_goal_0'] = ((goal_a_0[0] - data['p2_pos_x'])**2 + (goal_a_1[1] - data['p2_pos_y'])**2 + (goal_a_1[2] - data['p2_pos_z'])**2)** 0.5\n    data['p0_dist_goal_1'] = ((goal_a_1[0] - data['p0_pos_x'])**2 + (goal_a_1[1] - data['p1_pos_y'])**2 + (goal_a_1[2] - data['p0_pos_z'])**2)** 0.5\n    data['p1_dist_goal_1'] = ((goal_a_1[0] - data['p1_pos_x'])**2 + (goal_a_1[1] - data['p1_pos_y'])**2 + (goal_a_1[2] - data['p1_pos_z'])**2)** 0.5\n    data['p2_dist_goal_1'] = ((goal_a_1[0] - data['p2_pos_x'])**2 + (goal_a_1[1] - data['p2_pos_y'])**2 + (goal_a_1[2] - data['p2_pos_z'])**2)** 0.5\n    data['p0_dist_goal_2'] = ((goal_a_2[0] - data['p0_pos_x'])**2 + (goal_a_2[1] - data['p1_pos_y'])**2 + (goal_a_2[2] - data['p0_pos_z'])**2)** 0.5\n    data['p1_dist_goal_2'] = ((goal_a_2[0] - data['p1_pos_x'])**2 + (goal_a_2[1] - data['p1_pos_y'])**2 + (goal_a_2[2] - data['p1_pos_z'])**2)** 0.5\n    data['p2_dist_goal_2'] = ((goal_a_2[0] - data['p2_pos_x'])**2 + (goal_a_2[1] - data['p2_pos_y'])**2 + (goal_a_2[2] - data['p2_pos_z'])**2)** 0.5\n    \n    data['p3_dist_goal_0'] = ((goal_b_0[0] - data['p3_pos_x'])**2 + (goal_b_1[1] - data['p3_pos_y'])**2 + (goal_b_1[2] - data['p3_pos_z'])**2)** 0.5\n    data['p4_dist_goal_0'] = ((goal_b_0[0] - data['p4_pos_x'])**2 + (goal_b_1[1] - data['p4_pos_y'])**2 + (goal_b_1[2] - data['p4_pos_z'])**2)** 0.5\n    data['p5_dist_goal_0'] = ((goal_b_0[0] - data['p5_pos_x'])**2 + (goal_b_1[1] - data['p5_pos_y'])**2 + (goal_b_1[2] - data['p5_pos_z'])**2)** 0.5\n    data['p3_dist_goal_1'] = ((goal_b_1[0] - data['p3_pos_x'])**2 + (goal_b_1[1] - data['p3_pos_y'])**2 + (goal_b_1[2] - data['p3_pos_z'])**2)** 0.5\n    data['p4_dist_goal_1'] = ((goal_b_1[0] - data['p4_pos_x'])**2 + (goal_b_1[1] - data['p4_pos_y'])**2 + (goal_b_1[2] - data['p4_pos_z'])**2)** 0.5\n    data['p5_dist_goal_1'] = ((goal_b_1[0] - data['p5_pos_x'])**2 + (goal_b_1[1] - data['p5_pos_y'])**2 + (goal_b_1[2] - data['p5_pos_z'])**2)** 0.5\n    data['p3_dist_goal_2'] = ((goal_b_2[0] - data['p3_pos_x'])**2 + (goal_b_2[1] - data['p3_pos_y'])**2 + (goal_b_2[2] - data['p3_pos_z'])**2)** 0.5\n    data['p4_dist_goal_2'] = ((goal_b_2[0] - data['p4_pos_x'])**2 + (goal_b_2[1] - data['p4_pos_y'])**2 + (goal_b_2[2] - data['p4_pos_z'])**2)** 0.5\n    data['p5_dist_goal_2'] = ((goal_b_2[0] - data['p5_pos_x'])**2 + (goal_b_2[1] - data['p5_pos_y'])**2 + (goal_b_2[2] - data['p5_pos_z'])**2)** 0.5\n    \n     # between ball and goal\n    data[\"goal_a_distance\"] = ((data[\"ball_pos_x\"] - 0)**2 + (data[\"ball_pos_y\"] - 120)**2 + (data[\"ball_pos_z\"] - 1.2)**2)**0.5\n    data[\"goal_b_distance\"] = ((data[\"ball_pos_x\"] - 0)**2 + (data[\"ball_pos_y\"] + 120)**2 + (data[\"ball_pos_z\"] - 1.2)**2)**0.5\n    \n     # spped (speed = sqrt(Vx^2 + Vy^2 + Vz^2)) \n    data['ball_speed'] = ((data['ball_vel_x'])**2 + (data['ball_vel_y'])**2 +  (data['ball_vel_z'])**2)** 0.5\n    data['p0_speed'] = ((data['p0_vel_x'])**2 + (data['p0_vel_y'])**2 +  (data['p0_vel_z'])**2)** 0.5\n    data['p1_speed'] = ((data['p1_vel_x'])**2 + (data['p1_vel_y'])**2 + (data['p1_vel_z'])**2)** 0.5\n    data['p2_speed'] = ((data['p2_vel_x'])**2 + (data['p2_vel_y'])**2 + (data['p2_vel_z'])**2)** 0.5\n    data['p3_speed'] = ((data['p3_vel_x'])**2 + (data['p3_vel_y'])**2 + (data['p3_vel_z'])**2)** 0.5\n    data['p4_speed'] = ((data['p4_vel_x'])**2 + (data['p4_vel_y'])**2 + (data['p4_vel_z'])**2)** 0.5\n    data['p5_speed'] = ((data['p5_vel_x'])**2 + (data['p5_vel_y'])**2 + (data['p5_vel_z'])**2)** 0.5\n    \n     # coordinate direction angle\n    data['ball-cos_a'] = data['ball_vel_x'] / (((data['ball_vel_x'])**2 + (data['ball_vel_y'])**2 +  (data['ball_vel_z'])**2)** 0.5)\n    data['ball-cos_b'] = data['ball_vel_y'] / (((data['ball_vel_x'])**2 + (data['ball_vel_y'])**2 +  (data['ball_vel_z'])**2)** 0.5)\n    data['ball-cos_c'] = data['ball_vel_z'] / (((data['ball_vel_x'])**2 + (data['ball_vel_y'])**2 +  (data['ball_vel_z'])**2)** 0.5)\n    \n    data['p0_cos_a'] = data['p0_vel_x'] /  (((data['p0_vel_x'])**2 + (data['p0_vel_y'])**2 + (data['p0_vel_z'])**2)** 0.5)\n    data['p0_cos_b'] = data['p0_vel_y'] /  (((data['p0_vel_x'])**2 + (data['p0_vel_y'])**2 + (data['p0_vel_z'])**2)** 0.5)\n    data['p0_cos_c'] = data['p0_vel_z'] /  (((data['p0_vel_x'])**2 + (data['p0_vel_y'])**2 + (data['p0_vel_z'])**2)** 0.5)\n    data['p1_cos_a'] = data['p1_vel_x'] / (((data['p1_vel_x'])**2 + (data['p1_vel_y'])**2 + (data['p1_vel_z'])**2)** 0.5)\n    data['p1_cos_b'] = data['p1_vel_y'] / (((data['p1_vel_x'])**2 + (data['p1_vel_y'])**2 + (data['p1_vel_z'])**2)** 0.5)\n    data['p1_cos_c'] = data['p1_vel_z'] / (((data['p1_vel_x'])**2 + (data['p1_vel_y'])**2 + (data['p1_vel_z'])**2)** 0.5)\n    data['p2_cos_a'] = data['p2_vel_x'] / (((data['p2_vel_x'])**2 + (data['p2_vel_y'])**2 + (data['p2_vel_z'])**2)** 0.5)\n    data['p2_cos_b'] = data['p2_vel_y'] / (((data['p2_vel_x'])**2 + (data['p2_vel_y'])**2 + (data['p2_vel_z'])**2)** 0.5)\n    data['p2_cos_c'] = data['p2_vel_z'] / (((data['p2_vel_x'])**2 + (data['p2_vel_y'])**2 + (data['p2_vel_z'])**2)** 0.5)\n    data['p3_cos_a'] = data['p3_vel_x'] / (((data['p3_vel_x'])**2 + (data['p3_vel_y'])**2 + (data['p3_vel_z'])**2)** 0.5)\n    data['p3_cos_b'] = data['p3_vel_y'] / (((data['p3_vel_x'])**2 + (data['p3_vel_y'])**2 + (data['p3_vel_z'])**2)** 0.5)\n    data['p3_cos_c'] = data['p3_vel_z'] / (((data['p3_vel_x'])**2 + (data['p3_vel_y'])**2 + (data['p3_vel_z'])**2)** 0.5)\n    data['p4_cos_a'] = data['p4_vel_x'] / (((data['p4_vel_x'])**2 + (data['p4_vel_y'])**2 + (data['p4_vel_z'])**2)** 0.5)\n    data['p4_cos_b'] = data['p4_vel_y'] / (((data['p4_vel_x'])**2 + (data['p4_vel_y'])**2 + (data['p4_vel_z'])**2)** 0.5)\n    data['p4_cos_c'] = data['p4_vel_z'] / (((data['p4_vel_x'])**2 + (data['p4_vel_y'])**2 + (data['p4_vel_z'])**2)** 0.5)\n    data['p5_cos_a'] = data['p5_vel_x'] / (((data['p5_vel_x'])**2 + (data['p5_vel_y'])**2 + (data['p5_vel_z'])**2)** 0.5)\n    data['p5_cos_b'] = data['p5_vel_y'] / (((data['p5_vel_x'])**2 + (data['p5_vel_y'])**2 + (data['p5_vel_z'])**2)** 0.5)\n    data['p5_cos_c'] = data['p5_vel_z'] / (((data['p5_vel_x'])**2 + (data['p5_vel_y'])**2 + (data['p5_vel_z'])**2)** 0.5)\n    \n    return data","metadata":{"execution":{"iopub.status.busy":"2022-10-14T20:17:08.049464Z","iopub.execute_input":"2022-10-14T20:17:08.050165Z","iopub.status.idle":"2022-10-14T20:17:08.102277Z","shell.execute_reply.started":"2022-10-14T20:17:08.050125Z","shell.execute_reply":"2022-10-14T20:17:08.101324Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_dtypes = pd.read_csv(\"/kaggle/input/tabular-playground-series-oct-2022/train_dtypes.csv\")\ntrain_dtypes = dict(train_dtypes.to_records(index=False))\n\ntest_dtypes = pd.read_csv(\"/kaggle/input/tabular-playground-series-oct-2022/test_dtypes.csv\")\ntest_dtypes = dict(test_dtypes.to_records(index=False))\n\ntest = pd.read_csv(\"/kaggle/input/tabular-playground-series-oct-2022/test.csv\")\ntest = test.interpolate(limit_direction = 'both', axis=1)\nadd_feature(test)\ntest = test.drop(['id'], axis = 1)\ndisplay(test)\n\nsub = pd.read_csv(\"/kaggle/input/tabular-playground-series-oct-2022/sample_submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2022-10-14T20:17:08.103601Z","iopub.execute_input":"2022-10-14T20:17:08.104553Z","iopub.status.idle":"2022-10-14T20:17:38.113070Z","shell.execute_reply.started":"2022-10-14T20:17:08.104515Z","shell.execute_reply":"2022-10-14T20:17:38.112037Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"n_splits = 5\nseed = 42\n\nparams = {'objective':'binary',\n          'metric' : 'auc',\n          'seed': 42,\n          'num_leaves' : 64,\n          'min_child_samples': 20,\n          'max_depth' : 6,\n          'n_estimators': 300,\n          'learning_rate': 0.1,\n         }\n\nmodel = lgb.LGBMClassifier(**params)   ","metadata":{"execution":{"iopub.status.busy":"2022-10-14T20:17:38.115622Z","iopub.execute_input":"2022-10-14T20:17:38.116009Z","iopub.status.idle":"2022-10-14T20:17:38.122831Z","shell.execute_reply.started":"2022-10-14T20:17:38.115975Z","shell.execute_reply":"2022-10-14T20:17:38.121401Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def models(X,y, model,sub):\n    \n    for i in range(2):\n        X_train, X_val, y_train, y_val = train_test_split(X,y[i],test_size=0.2, random_state = seed)\n        model.fit(X_train,y_train)\n        pred_ = model.predict_proba(X_val)[:,1]\n        loss = log_loss(y_val ,pred_)\n        pred = model.predict_proba(test)[:,1]\n        if i == 0:\n            sub['team_A_scoring_within_10sec'] =  pred\n        else:\n            sub['team_B_scoring_within_10sec'] = pred\n        print(f\"\\n{y[i]} Logloss = {loss}\\n  prediction {pred}\\n\")\n        \n    return sub","metadata":{"execution":{"iopub.status.busy":"2022-10-14T20:17:38.124597Z","iopub.execute_input":"2022-10-14T20:17:38.125909Z","iopub.status.idle":"2022-10-14T20:17:38.135992Z","shell.execute_reply.started":"2022-10-14T20:17:38.125863Z","shell.execute_reply":"2022-10-14T20:17:38.134713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**train_0, train_1**","metadata":{}},{"cell_type":"code","source":"train_ = pd.DataFrame()\n\nfor i in tqdm(range(0,2)):\n    train_i = pd.read_csv(f\"/kaggle/input/tabular-playground-series-oct-2022/train_{i}.csv\", dtype = train_dtypes)\n    train_ = pd.concat([train_, train_i])\n    del train_i\n    \ntrain_['team_A_scoring_within_10sec']= train_['team_A_scoring_within_10sec'].astype(int)\ntrain_['team_B_scoring_within_10sec']= train_['team_B_scoring_within_10sec'].astype(int)\n\ny = [train_['team_A_scoring_within_10sec'],train_['team_B_scoring_within_10sec']]\n\ntrain_ = train_.drop(['game_num', 'event_id', 'event_time', 'player_scoring_next', 'team_scoring_next', 'team_A_scoring_within_10sec', 'team_B_scoring_within_10sec'], axis=1)\ntrain_ = train_.interpolate(limit_direction = 'both', axis=1)\nadd_feature(train_)\n\nX = train_\ndisplay(X)\n\nmodels(X,y,model, sub)\nsub.to_csv('submission_01.csv', index=False)\n\ndel train_\ndel sub","metadata":{"execution":{"iopub.status.busy":"2022-10-14T20:17:38.138155Z","iopub.execute_input":"2022-10-14T20:17:38.138696Z","iopub.status.idle":"2022-10-14T20:34:30.458207Z","shell.execute_reply.started":"2022-10-14T20:17:38.138650Z","shell.execute_reply":"2022-10-14T20:34:30.456805Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**train_2, train_3**","metadata":{}},{"cell_type":"code","source":"sub = pd.read_csv(\"/kaggle/input/tabular-playground-series-oct-2022/sample_submission.csv\")\ntrain_ = pd.DataFrame()\n\nfor i in tqdm(range(2,4)):\n    train_i = pd.read_csv(f\"/kaggle/input/tabular-playground-series-oct-2022/train_{i}.csv\", dtype = train_dtypes)\n    train_ = pd.concat([train_, train_i])\n    del train_i\n    \ntrain_['team_A_scoring_within_10sec']= train_['team_A_scoring_within_10sec'].astype(int)\ntrain_['team_B_scoring_within_10sec']= train_['team_B_scoring_within_10sec'].astype(int)\n\ny = [train_['team_A_scoring_within_10sec'],train_['team_B_scoring_within_10sec']]\n\ntrain_ = train_.drop(['game_num', 'event_id', 'event_time', 'player_scoring_next', 'team_scoring_next', 'team_A_scoring_within_10sec', 'team_B_scoring_within_10sec'], axis=1)\ntrain_ = train_.interpolate(limit_direction = 'both', axis=1)\nadd_feature(train_)\n\nX = train_\ndisplay(X)\n\nmodels(X,y,model, sub)\nsub.to_csv('submission_23.csv', index=False)\n\ndel train_\ndel sub","metadata":{"execution":{"iopub.status.busy":"2022-10-14T20:39:10.470185Z","iopub.execute_input":"2022-10-14T20:39:10.470703Z","iopub.status.idle":"2022-10-14T20:55:14.197549Z","shell.execute_reply.started":"2022-10-14T20:39:10.470667Z","shell.execute_reply":"2022-10-14T20:55:14.195802Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**train_3, train_4**","metadata":{}},{"cell_type":"code","source":"sub = pd.read_csv(\"/kaggle/input/tabular-playground-series-oct-2022/sample_submission.csv\")\ntrain_ = pd.DataFrame()\n\nfor i in tqdm(range(4,6)):\n    train_i = pd.read_csv(f\"/kaggle/input/tabular-playground-series-oct-2022/train_{i}.csv\", dtype = train_dtypes)\n    train_ = pd.concat([train_, train_i])\n    del train_i\n    \ntrain_['team_A_scoring_within_10sec']= train_['team_A_scoring_within_10sec'].astype(int)\ntrain_['team_B_scoring_within_10sec']= train_['team_B_scoring_within_10sec'].astype(int)\n\ny = [train_['team_A_scoring_within_10sec'],train_['team_B_scoring_within_10sec']]\n\ntrain_ = train_.drop(['game_num', 'event_id', 'event_time', 'player_scoring_next', 'team_scoring_next', 'team_A_scoring_within_10sec', 'team_B_scoring_within_10sec'], axis=1)\ntrain_ = train_.interpolate(limit_direction = 'both', axis=1)\nadd_feature(train_)\n\nX = train_\ndisplay(X)\n\nmodels(X,y,model, sub)\nsub.to_csv('submission_45.csv', index=False)\n\ndel train_\ndel sub","metadata":{"execution":{"iopub.status.busy":"2022-10-14T20:55:14.200259Z","iopub.execute_input":"2022-10-14T20:55:14.200882Z","iopub.status.idle":"2022-10-14T21:11:37.682034Z","shell.execute_reply.started":"2022-10-14T20:55:14.200847Z","shell.execute_reply":"2022-10-14T21:11:37.680922Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**train_6, train_7**","metadata":{}},{"cell_type":"code","source":"sub = pd.read_csv(\"/kaggle/input/tabular-playground-series-oct-2022/sample_submission.csv\")\ntrain_ = pd.DataFrame()\n\nfor i in tqdm(range(6,8)):\n    train_i = pd.read_csv(f\"/kaggle/input/tabular-playground-series-oct-2022/train_{i}.csv\", dtype = train_dtypes)\n    train_ = pd.concat([train_, train_i])\n    del train_i\n    \ntrain_['team_A_scoring_within_10sec']= train_['team_A_scoring_within_10sec'].astype(int)\ntrain_['team_B_scoring_within_10sec']= train_['team_B_scoring_within_10sec'].astype(int)\n\ny = [train_['team_A_scoring_within_10sec'],train_['team_B_scoring_within_10sec']]\n\ntrain_ = train_.drop(['game_num', 'event_id', 'event_time', 'player_scoring_next', 'team_scoring_next', 'team_A_scoring_within_10sec', 'team_B_scoring_within_10sec'], axis=1)\ntrain_ = train_.interpolate(limit_direction = 'both', axis=1)\nadd_feature(train_)\n\nX = train_\ndisplay(X)\n\nmodels(X,y,model, sub)\nsub.to_csv('submission_67.csv', index=False)\n\ndel train_\ndel sub","metadata":{"execution":{"iopub.status.busy":"2022-10-14T21:11:37.683319Z","iopub.execute_input":"2022-10-14T21:11:37.684186Z","iopub.status.idle":"2022-10-14T21:28:05.212727Z","shell.execute_reply.started":"2022-10-14T21:11:37.684152Z","shell.execute_reply":"2022-10-14T21:28:05.211339Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**train_8, train_9**","metadata":{}},{"cell_type":"code","source":"sub = pd.read_csv(\"/kaggle/input/tabular-playground-series-oct-2022/sample_submission.csv\")\ntrain_ = pd.DataFrame()\n\nfor i in tqdm(range(8,10)):\n    train_i = pd.read_csv(f\"/kaggle/input/tabular-playground-series-oct-2022/train_{i}.csv\", dtype = train_dtypes)\n    train_ = pd.concat([train_, train_i])\n    del train_i\n    \ntrain_['team_A_scoring_within_10sec']= train_['team_A_scoring_within_10sec'].astype(int)\ntrain_['team_B_scoring_within_10sec']= train_['team_B_scoring_within_10sec'].astype(int)\n\ny = [train_['team_A_scoring_within_10sec'],train_['team_B_scoring_within_10sec']]\n\ntrain_ = train_.drop(['game_num', 'event_id', 'event_time', 'player_scoring_next', 'team_scoring_next', 'team_A_scoring_within_10sec', 'team_B_scoring_within_10sec'], axis=1)\ntrain_ = train_.interpolate(limit_direction = 'both', axis=1)\nadd_feature(train_)\n\nX = train_\ndisplay(X)\n\nmodels(X,y,model, sub)\nsub.to_csv('submission_89.csv', index=False)\n\ndel train_\ndel sub","metadata":{"execution":{"iopub.status.busy":"2022-10-14T21:28:05.215663Z","iopub.execute_input":"2022-10-14T21:28:05.216072Z","iopub.status.idle":"2022-10-14T21:44:55.490789Z","shell.execute_reply.started":"2022-10-14T21:28:05.216037Z","shell.execute_reply":"2022-10-14T21:44:55.489357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_1 = pd.read_csv('submission_01.csv')\ntrain_2 = pd.read_csv('submission_23.csv')\ntrain_3 = pd.read_csv('submission_45.csv')\ntrain_4 = pd.read_csv('submission_67.csv')\ntrain_5 = pd.read_csv('submission_89.csv')\n\ntrain_1, train_2, train_3, train_4, train_5","metadata":{"execution":{"iopub.status.busy":"2022-10-14T21:44:55.492210Z","iopub.execute_input":"2022-10-14T21:44:55.492601Z","iopub.status.idle":"2022-10-14T21:44:57.199297Z","shell.execute_reply.started":"2022-10-14T21:44:55.492566Z","shell.execute_reply":"2022-10-14T21:44:57.198394Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = (train_1+ train_2 + train_3 + train_4 + train_5)/5\nsubmission['id'] = submission['id'].astype(int)\nsubmission.to_csv('submission.csv', index=False)\nsubmission\n","metadata":{"execution":{"iopub.status.busy":"2022-10-14T21:46:17.499523Z","iopub.execute_input":"2022-10-14T21:46:17.499997Z","iopub.status.idle":"2022-10-14T21:46:20.334592Z","shell.execute_reply.started":"2022-10-14T21:46:17.499963Z","shell.execute_reply":"2022-10-14T21:46:20.333250Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"It will take quite a while to get the results, but thank you for reading to the end. GOOD LUCK! 😉","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}