{"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":"# 🚚 Import","metadata":{}},{"cell_type":"markdown","source":"## Packages","metadata":{}},{"cell_type":"code","source":"import numpy as np  # linear algebra\nimport pandas as pd  # data manipulation\nimport os  # file navigation\nimport gc  # garbage collection\n\n# visualization\nimport plotly.express as px\nimport plotly.graph_objects as go\nfrom plotly import subplots\n\nfrom sklearn.model_selection import cross_validate  # k-fold Cross Validation\nfrom sklearn.preprocessing import LabelEncoder  # output binary encoding\n\nfrom xgboost import XGBClassifier  # Gradient Boosted Tree (XGBoost)\n\nfrom tensorflow.config import list_physical_devices  # check if GPU is available","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-10-17T21:18:24.643251Z","iopub.execute_input":"2022-10-17T21:18:24.643713Z","iopub.status.idle":"2022-10-17T21:18:31.736583Z","shell.execute_reply.started":"2022-10-17T21:18:24.643618Z","shell.execute_reply":"2022-10-17T21:18:31.735413Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Config","metadata":{}},{"cell_type":"code","source":"# training and cross validation\nGPU = list_physical_devices('GPU') != []\nN_ESTIMATORS = 2000\nMAX_DEPTH = 8\nLEARNING_RATE = 0.01\nFOLDS = 5\n\n# data loading\nDEBUG = False\nSAMPLE = 0.2\nSEED = 42","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:18:31.738880Z","iopub.execute_input":"2022-10-17T21:18:31.740375Z","iopub.status.idle":"2022-10-17T21:18:31.752395Z","shell.execute_reply.started":"2022-10-17T21:18:31.740325Z","shell.execute_reply":"2022-10-17T21:18:31.751266Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Dataset","metadata":{}},{"cell_type":"markdown","source":"Because of memory limitations, we can't use all of the data from the 10 train .csv files.  \nInstead, we'll get a random sample of each file (for now I'm experimenting with 20-33% sample size), and combine these samples into a unique training dataset.","metadata":{}},{"cell_type":"code","source":"for dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ncol_dtypes = {\n    'game_num': 'int8', 'event_id': 'int8', 'event_time': 'float16',\n    'ball_pos_x': 'float16', 'ball_pos_y': 'float16', 'ball_pos_z': 'float16',\n    'ball_vel_x': 'float16', 'ball_vel_y': 'float16', 'ball_vel_z': 'float16',\n    'p0_pos_x': 'float16', 'p0_pos_y': 'float16', 'p0_pos_z': 'float16',\n    'p0_vel_x': 'float16', 'p0_vel_y': 'float16', 'p0_vel_z': 'float16',\n    'p0_boost': 'float16', 'p1_pos_x': 'float16', 'p1_pos_y': 'float16',\n    'p1_pos_z': 'float16', 'p1_vel_x': 'float16', 'p1_vel_y': 'float16',\n    'p1_vel_z': 'float16', 'p1_boost': 'float16', 'p2_pos_x': 'float16',\n    'p2_pos_y': 'float16', 'p2_pos_z': 'float16', 'p2_vel_x': 'float16',\n    'p2_vel_y': 'float16', 'p2_vel_z': 'float16', 'p2_boost': 'float16',\n    'p3_pos_x': 'float16', 'p3_pos_y': 'float16', 'p3_pos_z': 'float16',\n    'p3_vel_x': 'float16', 'p3_vel_y': 'float16', 'p3_vel_z': 'float16',\n    'p3_boost': 'float16', 'p4_pos_x': 'float16', 'p4_pos_y': 'float16',\n    'p4_pos_z': 'float16', 'p4_vel_x': 'float16', 'p4_vel_y': 'float16',\n    'p4_vel_z': 'float16', 'p4_boost': 'float16', 'p5_pos_x': 'float16',\n    'p5_pos_y': 'float16', 'p5_pos_z': 'float16', 'p5_vel_x': 'float16',\n    'p5_vel_y': 'float16', 'p5_vel_z': 'float16', 'p5_boost': 'float16',\n    'boost0_timer': 'float16', 'boost1_timer': 'float16', 'boost2_timer': 'float16',\n    'boost3_timer': 'float16', 'boost4_timer': 'float16', 'boost5_timer': 'float16',\n    'player_scoring_next': 'O', 'team_scoring_next': 'O', 'team_A_scoring_within_10sec': 'O',\n    'team_B_scoring_within_10sec': 'O'\n}\ncols = list(col_dtypes.keys())\n\n# 20%\npath_to_data = '../input/tabular-playground-series-oct-2022'\ndf = pd.DataFrame({}, columns=cols)\nfor i in range(10):\n    df_tmp = pd.read_csv(f'{path_to_data}/train_{i}.csv', dtype=col_dtypes)\n    if SAMPLE < 1:\n        df_tmp = df_tmp.sample(frac=SAMPLE, random_state=SEED)\n        \n    df = pd.concat([df, df_tmp])\n    del df_tmp\n    gc.collect()\n    if DEBUG:\n        break","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:18:31.767312Z","iopub.execute_input":"2022-10-17T21:18:31.767632Z","iopub.status.idle":"2022-10-17T21:23:23.191965Z","shell.execute_reply.started":"2022-10-17T21:18:31.767603Z","shell.execute_reply":"2022-10-17T21:23:23.190786Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:23.193159Z","iopub.execute_input":"2022-10-17T21:23:23.193443Z","iopub.status.idle":"2022-10-17T21:23:25.353298Z","shell.execute_reply.started":"2022-10-17T21:23:23.193415Z","shell.execute_reply":"2022-10-17T21:23:25.352516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 👀 Quick EDA","metadata":{}},{"cell_type":"code","source":"input_cols = [\n    'ball_pos_x', 'ball_pos_y', 'ball_pos_z', 'ball_vel_x', 'ball_vel_y', 'ball_vel_z', \n    'p0_pos_x', 'p0_pos_y', 'p0_pos_z', 'p0_vel_x', 'p0_vel_y', 'p0_vel_z', \n    'p1_pos_x', 'p1_pos_y', 'p1_pos_z', 'p1_vel_x', 'p1_vel_y', 'p1_vel_z',\n    'p2_pos_x', 'p2_pos_y', 'p2_pos_z', 'p2_vel_x', 'p2_vel_y', 'p2_vel_z',\n    'p3_pos_x', 'p3_pos_y', 'p3_pos_z', 'p3_vel_x', 'p3_vel_y', 'p3_vel_z',\n    'p4_pos_x', 'p4_pos_y', 'p4_pos_z', 'p4_vel_x', 'p4_vel_y', 'p4_vel_z',\n    'p5_pos_x', 'p5_pos_y', 'p5_pos_z', 'p5_vel_x', 'p5_vel_y', 'p5_vel_z',\n    'p0_boost', 'p1_boost',  'p2_boost', 'p3_boost', 'p4_boost', 'p5_boost',\n    'boost0_timer', 'boost1_timer', 'boost2_timer', 'boost3_timer', 'boost4_timer', 'boost5_timer'\n]","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:25.354297Z","iopub.execute_input":"2022-10-17T21:23:25.355045Z","iopub.status.idle":"2022-10-17T21:23:25.360904Z","shell.execute_reply.started":"2022-10-17T21:23:25.355015Z","shell.execute_reply":"2022-10-17T21:23:25.360166Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"output_cols = ['team_A_scoring_within_10sec', 'team_B_scoring_within_10sec']","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:25.362267Z","iopub.execute_input":"2022-10-17T21:23:25.363014Z","iopub.status.idle":"2022-10-17T21:23:25.370785Z","shell.execute_reply.started":"2022-10-17T21:23:25.362947Z","shell.execute_reply":"2022-10-17T21:23:25.369945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Input Variables","metadata":{}},{"cell_type":"code","source":"def int_to_grid_coord(k, n):\n    return (k // n) + 1, (k % n) + 1","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:33:37.472084Z","iopub.execute_input":"2022-10-17T21:33:37.472806Z","iopub.status.idle":"2022-10-17T21:33:37.478406Z","shell.execute_reply.started":"2022-10-17T21:33:37.472768Z","shell.execute_reply":"2022-10-17T21:33:37.477265Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def plot_distributions(df, row_count, col_count, title, height):\n    features = df.columns\n    fig = subplots.make_subplots(\n        rows=row_count, cols=col_count,\n        subplot_titles=features\n    )\n    # placement of graph in subplot\n    for k, col in enumerate(features):\n        i, j = int_to_grid_coord(k, col_count)\n\n        fig.add_trace(\n            go.Histogram(\n                x=df[col].astype('float32'),\n                name=col\n            ),\n            row=i, col=j\n        )\n\n    fig.update_layout(\n        title=title,\n        height=row_count * height,\n        showlegend=True\n    )\n\n    return fig","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:49:17.084337Z","iopub.execute_input":"2022-10-17T21:49:17.084804Z","iopub.status.idle":"2022-10-17T21:49:17.093274Z","shell.execute_reply.started":"2022-10-17T21:49:17.084764Z","shell.execute_reply":"2022-10-17T21:49:17.092347Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_distributions(df[input_cols].sample(frac=0.0005), 9, 6, \"Input Variables Distributions\", 200)\n#print(df[input_cols].sample(frac=0.0001))\n#plt.xlabel=\"\"","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:52:05.908372Z","iopub.execute_input":"2022-10-17T21:52:05.909411Z","iopub.status.idle":"2022-10-17T21:52:07.916101Z","shell.execute_reply.started":"2022-10-17T21:52:05.909365Z","shell.execute_reply":"2022-10-17T21:52:07.914377Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_distributions(df[output_cols].sample(frac=0.0005), 2, 2, \"Output Variables Distributions\", height=600)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:54:03.815872Z","iopub.execute_input":"2022-10-17T21:54:03.816843Z","iopub.status.idle":"2022-10-17T21:54:04.147795Z","shell.execute_reply.started":"2022-10-17T21:54:03.816802Z","shell.execute_reply":"2022-10-17T21:54:04.146698Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ⚙️ Feature Engineering","metadata":{}},{"cell_type":"markdown","source":"Shoutout [this post by samuelcortinhas](https://www.kaggle.com/competitions/tabular-playground-series-oct-2022/discussion/356852) for the idea.","metadata":{}},{"cell_type":"markdown","source":"Let's derive 2 new features:\n* For each player (and the ball) let's get their velocity's magnitude.\n* For each player, let's get their distance from the ball.","metadata":{}},{"cell_type":"markdown","source":"## Euclidian Norm","metadata":{}},{"cell_type":"markdown","source":"For these 2 new features, we'll need to get the 3D euclidian norm of a vector:\n$$ \\| \\overrightarrow{v} \\| = \\sqrt{x^2 + y^2 + z^2} $$\nWe'll use numpy's linalg.norm() method for that.","metadata":{}},{"cell_type":"code","source":"def euclidian_norm(x):\n    return np.linalg.norm(x, axis=1)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:53:39.414761Z","iopub.execute_input":"2022-10-17T21:53:39.415257Z","iopub.status.idle":"2022-10-17T21:53:39.420926Z","shell.execute_reply.started":"2022-10-17T21:53:39.415217Z","shell.execute_reply":"2022-10-17T21:53:39.419713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# let's group the x, y and z variables by player and ball categories\n# this simplifies the code for the euclidian norm calculation\nvel_groups = {\n    f\"{el}_vel\": [f'{el}_vel_x', f'{el}_vel_y', f'{el}_vel_z']\n    for el in ['ball'] + [f'p{i}' for i in range(6)]\n}\npos_groups = {\n    f\"{el}_pos\": [f'{el}_pos_x', f'{el}_pos_y', f'{el}_pos_z']\n    for el in ['ball'] + [f'p{i}' for i in range(6)]\n}\npos_groups","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:53:39.922170Z","iopub.execute_input":"2022-10-17T21:53:39.922893Z","iopub.status.idle":"2022-10-17T21:53:39.933388Z","shell.execute_reply.started":"2022-10-17T21:53:39.922844Z","shell.execute_reply":"2022-10-17T21:53:39.932357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# velocity magnitude\nfor col, vec in vel_groups.items():\n    df[col] = euclidian_norm(df[vec])","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:28.850191Z","iopub.execute_input":"2022-10-17T21:23:28.850994Z","iopub.status.idle":"2022-10-17T21:23:35.257516Z","shell.execute_reply.started":"2022-10-17T21:23:28.850939Z","shell.execute_reply":"2022-10-17T21:23:35.256583Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# distance from ball\nfor col, vec in pos_groups.items():\n    df[col + \"_ball_dist\"] = euclidian_norm(df[vec].values - df[pos_groups[\"ball_pos\"]].values)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:35.258796Z","iopub.execute_input":"2022-10-17T21:23:35.259339Z","iopub.status.idle":"2022-10-17T21:23:42.444667Z","shell.execute_reply.started":"2022-10-17T21:23:35.259306Z","shell.execute_reply":"2022-10-17T21:23:42.443447Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🧹 Cleaning","metadata":{}},{"cell_type":"markdown","source":"We drop the columns below because they should not influence the results.  \ngame_num, event_id and event_time are irrelevant.  \nplayer_scoring_next and team_scoring next are a form of data leakage, as in they're synonymous with the output variable.  \nball_pos_ball_dist is always 0, the distance between the ball and itself.","metadata":{}},{"cell_type":"markdown","source":"## Dropping columns","metadata":{}},{"cell_type":"code","source":"cols_to_drop = [\n    'game_num', 'event_id', 'event_time', 'player_scoring_next', 'team_scoring_next', 'ball_pos_ball_dist'\n]\n\ndf = df.drop(columns=cols_to_drop)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:42.446375Z","iopub.execute_input":"2022-10-17T21:23:42.447142Z","iopub.status.idle":"2022-10-17T21:23:42.452687Z","shell.execute_reply.started":"2022-10-17T21:23:42.447096Z","shell.execute_reply":"2022-10-17T21:23:42.451449Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Dropping rows containing NaN","metadata":{}},{"cell_type":"code","source":"has_na = {}\nfor col in df.columns:\n    has_na[col] = df[col].isnull().values.any()\n\nprint(\"Columns that contain null values:\")\nfor col in has_na:\n    if has_na[col]:\n        print(col)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:44.788971Z","iopub.execute_input":"2022-10-17T21:23:44.789269Z","iopub.status.idle":"2022-10-17T21:23:46.150180Z","shell.execute_reply.started":"2022-10-17T21:23:44.789242Z","shell.execute_reply":"2022-10-17T21:23:46.149059Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"例えば、p0_pos_xでの欠損値について","metadata":{}},{"cell_type":"code","source":"null_p0_pos_x_count = df['p0_pos_x'].isna().sum()\nnull_p0_pos_x_perc = null_p0_pos_x_count / df.shape[0]\nprint(f\"Missing {null_p0_pos_x_count} values ({null_p0_pos_x_perc:.2%})\")","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:46.151224Z","iopub.execute_input":"2022-10-17T21:23:46.151510Z","iopub.status.idle":"2022-10-17T21:23:46.177223Z","shell.execute_reply.started":"2022-10-17T21:23:46.151483Z","shell.execute_reply":"2022-10-17T21:23:46.176161Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = df.dropna(axis=0)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:46.178541Z","iopub.execute_input":"2022-10-17T21:23:46.178843Z","iopub.status.idle":"2022-10-17T21:23:50.851524Z","shell.execute_reply.started":"2022-10-17T21:23:46.178814Z","shell.execute_reply":"2022-10-17T21:23:50.850656Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"To keep things simple, let's just drop all null values.\n\n欠損値のある、\"行\"を削除\n\nこれで、欠損値を含む列がなくなる  \n以下で確認する\n\nこれが最終版のトレインデータ","metadata":{}},{"cell_type":"code","source":"has_na = {}\nfor col in df.columns:\n    has_na[col] = df[col].isnull().values.any()\n\nprint(\"Columns that contain null values:\")\nfor col in has_na:\n    if has_na[col]:\n        print(col)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:57:20.917327Z","iopub.execute_input":"2022-10-17T21:57:20.918211Z","iopub.status.idle":"2022-10-17T21:57:22.247662Z","shell.execute_reply.started":"2022-10-17T21:57:20.918158Z","shell.execute_reply":"2022-10-17T21:57:22.246447Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Final training data\ndf\n\ndf.columns","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:52.151410Z","iopub.execute_input":"2022-10-17T21:23:52.151820Z","iopub.status.idle":"2022-10-17T21:23:52.925085Z","shell.execute_reply.started":"2022-10-17T21:23:52.151778Z","shell.execute_reply":"2022-10-17T21:23:52.924135Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🚀 Model Training","metadata":{}},{"cell_type":"code","source":"X = df.drop([\"team_A_scoring_within_10sec\",\"team_B_scoring_within_10sec\"], axis=1)\nX","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:52.935688Z","iopub.execute_input":"2022-10-17T21:23:52.935972Z","iopub.status.idle":"2022-10-17T21:23:54.105376Z","shell.execute_reply.started":"2022-10-17T21:23:52.935930Z","shell.execute_reply":"2022-10-17T21:23:54.104312Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y = df[[\"team_A_scoring_within_10sec\",\"team_B_scoring_within_10sec\"]]\ny = y.astype(int)\ny","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:54.106852Z","iopub.execute_input":"2022-10-17T21:23:54.107193Z","iopub.status.idle":"2022-10-17T21:23:54.983036Z","shell.execute_reply.started":"2022-10-17T21:23:54.107162Z","shell.execute_reply":"2022-10-17T21:23:54.981846Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import lightgbm as lgb\nfrom sklearn.model_selection import train_test_split, KFold\nfrom sklearn.metrics import log_loss, accuracy_score","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:54.984799Z","iopub.execute_input":"2022-10-17T21:23:54.985690Z","iopub.status.idle":"2022-10-17T21:23:55.234409Z","shell.execute_reply.started":"2022-10-17T21:23:54.985643Z","shell.execute_reply":"2022-10-17T21:23:55.233334Z"},"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_A = lgb.LGBMClassifier(**params)   \nmodel_B = lgb.LGBMClassifier(**params)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:55.239873Z","iopub.execute_input":"2022-10-17T21:23:55.240254Z","iopub.status.idle":"2022-10-17T21:23:55.246256Z","shell.execute_reply.started":"2022-10-17T21:23:55.240210Z","shell.execute_reply":"2022-10-17T21:23:55.245151Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train_A, X_val_A = train_test_split(X,test_size = 0.2,random_state = seed)\ny_train_A, y_val_A = train_test_split(y[\"team_A_scoring_within_10sec\"],test_size = 0.2,random_state = seed)\nX_train_B, X_val_B = train_test_split(X,test_size = 0.2,random_state = seed)\ny_train_B, y_val_B = train_test_split(y[\"team_B_scoring_within_10sec\"],test_size = 0.2,random_state = seed)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:23:55.247739Z","iopub.execute_input":"2022-10-17T21:23:55.248289Z","iopub.status.idle":"2022-10-17T21:24:05.940849Z","shell.execute_reply.started":"2022-10-17T21:23:55.248246Z","shell.execute_reply":"2022-10-17T21:24:05.939924Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"model A","metadata":{}},{"cell_type":"code","source":"model_A.fit(X_train_A,y_train_A)\npred_ = model_A.predict_proba(X_val_A)[:,1]\nloss_A = log_loss(y_val_A ,pred_)\nloss_A","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:24:05.942087Z","iopub.execute_input":"2022-10-17T21:24:05.942383Z","iopub.status.idle":"2022-10-17T21:28:37.668937Z","shell.execute_reply.started":"2022-10-17T21:24:05.942354Z","shell.execute_reply":"2022-10-17T21:28:37.667159Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"model B","metadata":{}},{"cell_type":"code","source":"model_B.fit(X_train_B,y_train_B)\npred_ = model_B.predict_proba(X_val_B)[:,1]\nloss_B = log_loss(y_val_B ,pred_)\nloss_B","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:28:37.671031Z","iopub.execute_input":"2022-10-17T21:28:37.671390Z","iopub.status.idle":"2022-10-17T21:33:09.178912Z","shell.execute_reply.started":"2022-10-17T21:28:37.671355Z","shell.execute_reply":"2022-10-17T21:33:09.177725Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = pd.read_csv('/kaggle/input/tabular-playground-series-oct-2022/test.csv')\ndf_test_ = df_test.copy()\ndf_test","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:33:09.180748Z","iopub.execute_input":"2022-10-17T21:33:09.181126Z","iopub.status.idle":"2022-10-17T21:33:18.708968Z","shell.execute_reply.started":"2022-10-17T21:33:09.181093Z","shell.execute_reply":"2022-10-17T21:33:18.707729Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def preprocess(df):\n    # velocity magnitude\n    for col, vec in vel_groups.items():\n        df[col] = euclidian_norm(df[vec])\n    \n    # ball distance\n    for col, vec in pos_groups.items():\n        df[col + \"_ball_dist\"] = euclidian_norm(df[vec].values - df[pos_groups[\"ball_pos\"]].values)\n    \n    df = df.drop(columns=['ball_pos_ball_dist'])\n    df = df.drop([\"id\"], axis=1)\n    return df","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:33:18.710609Z","iopub.execute_input":"2022-10-17T21:33:18.710924Z","iopub.status.idle":"2022-10-17T21:33:18.718300Z","shell.execute_reply.started":"2022-10-17T21:33:18.710895Z","shell.execute_reply":"2022-10-17T21:33:18.716946Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = preprocess(df_test)\ndf_test","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:33:18.720098Z","iopub.execute_input":"2022-10-17T21:33:18.720997Z","iopub.status.idle":"2022-10-17T21:33:22.650212Z","shell.execute_reply.started":"2022-10-17T21:33:18.720931Z","shell.execute_reply":"2022-10-17T21:33:22.649021Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"prediction","metadata":{}},{"cell_type":"code","source":"pred_A = model_A.predict_proba(df_test)[:,1]\npred_B = model_B.predict_proba(df_test)[:,1]","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:33:22.651462Z","iopub.execute_input":"2022-10-17T21:33:22.651778Z","iopub.status.idle":"2022-10-17T21:33:34.769914Z","shell.execute_reply.started":"2022-10-17T21:33:22.651749Z","shell.execute_reply":"2022-10-17T21:33:34.768890Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 💌 Submission","metadata":{}},{"cell_type":"code","source":"df_submission = pd.DataFrame(\n    {\n        \"id\": df_test_['id'],\n        \"team_A_scoring_within_10sec\": pred_A,\n        \"team_B_scoring_within_10sec\": pred_B\n    }\n)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:33:34.774670Z","iopub.execute_input":"2022-10-17T21:33:34.775433Z","iopub.status.idle":"2022-10-17T21:33:34.787462Z","shell.execute_reply.started":"2022-10-17T21:33:34.775393Z","shell.execute_reply":"2022-10-17T21:33:34.786352Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_submission","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:33:34.788902Z","iopub.execute_input":"2022-10-17T21:33:34.789298Z","iopub.status.idle":"2022-10-17T21:33:34.803111Z","shell.execute_reply.started":"2022-10-17T21:33:34.789264Z","shell.execute_reply":"2022-10-17T21:33:34.802246Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_submission.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2022-10-17T21:33:34.804657Z","iopub.execute_input":"2022-10-17T21:33:34.805062Z","iopub.status.idle":"2022-10-17T21:33:37.468231Z","shell.execute_reply.started":"2022-10-17T21:33:34.804950Z","shell.execute_reply":"2022-10-17T21:33:37.467183Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}