{"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":"# 🤝 Intro ","metadata":{}},{"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":"2022-10-13T14:38:29.969615Z","iopub.execute_input":"2022-10-13T14:38:29.970360Z","iopub.status.idle":"2022-10-13T14:38:29.976520Z","shell.execute_reply.started":"2022-10-13T14:38:29.970324Z","shell.execute_reply":"2022-10-13T14:38:29.975334Z"},"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":"2022-10-13T14:38:29.978807Z","iopub.execute_input":"2022-10-13T14:38:29.979149Z","iopub.status.idle":"2022-10-13T14:38:30.061473Z","shell.execute_reply.started":"2022-10-13T14:38:29.979116Z","shell.execute_reply":"2022-10-13T14:38:30.059728Z"},"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","execution":{"iopub.status.busy":"2022-10-13T14:38:30.063948Z","iopub.execute_input":"2022-10-13T14:38:30.064913Z","iopub.status.idle":"2022-10-13T14:38:30.073756Z","shell.execute_reply.started":"2022-10-13T14:38:30.064876Z","shell.execute_reply":"2022-10-13T14:38:30.072830Z"},"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%でサンプリングする\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":"2022-10-13T14:38:30.075805Z","iopub.execute_input":"2022-10-13T14:38:30.076169Z","iopub.status.idle":"2022-10-13T14:43:01.857070Z","shell.execute_reply.started":"2022-10-13T14:38:30.076143Z","shell.execute_reply":"2022-10-13T14:43:01.854888Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:01.859774Z","iopub.execute_input":"2022-10-13T14:43:01.860476Z","iopub.status.idle":"2022-10-13T14:43:04.041005Z","shell.execute_reply.started":"2022-10-13T14:43:01.860434Z","shell.execute_reply":"2022-10-13T14:43:04.039977Z"},"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":"2022-10-13T14:43:04.042590Z","iopub.execute_input":"2022-10-13T14:43:04.042980Z","iopub.status.idle":"2022-10-13T14:43:04.049995Z","shell.execute_reply.started":"2022-10-13T14:43:04.042945Z","shell.execute_reply":"2022-10-13T14:43:04.048905Z"},"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":"2022-10-13T14:43:04.051759Z","iopub.execute_input":"2022-10-13T14:43:04.052182Z","iopub.status.idle":"2022-10-13T14:43:04.066919Z","shell.execute_reply.started":"2022-10-13T14:43:04.052142Z","shell.execute_reply":"2022-10-13T14:43:04.065862Z"},"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":"2022-10-13T14:43:04.068737Z","iopub.execute_input":"2022-10-13T14:43:04.069351Z","iopub.status.idle":"2022-10-13T14:43:04.078973Z","shell.execute_reply.started":"2022-10-13T14:43:04.069315Z","shell.execute_reply":"2022-10-13T14:43:04.075218Z"},"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\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=False\n    )\n\n    return fig","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:04.080625Z","iopub.execute_input":"2022-10-13T14:43:04.081080Z","iopub.status.idle":"2022-10-13T14:43:04.109386Z","shell.execute_reply.started":"2022-10-13T14:43:04.081046Z","shell.execute_reply":"2022-10-13T14:43:04.108050Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_distributions(df[input_cols].sample(frac=0.0005), 9, 6, \"Input Variables Distributions\", 300)","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:04.110966Z","iopub.execute_input":"2022-10-13T14:43:04.111385Z","iopub.status.idle":"2022-10-13T14:43:06.835010Z","shell.execute_reply.started":"2022-10-13T14:43:04.111311Z","shell.execute_reply":"2022-10-13T14:43:06.834015Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Output Variables\n10秒以内に得点できているのはごく一部","metadata":{}},{"cell_type":"code","source":"plot_distributions(df[output_cols].sample(frac=0.0005), 1, 2, \"Output Variables Distributions\", height=600)","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:06.839642Z","iopub.execute_input":"2022-10-13T14:43:06.840491Z","iopub.status.idle":"2022-10-13T14:43:07.124506Z","shell.execute_reply.started":"2022-10-13T14:43:06.840451Z","shell.execute_reply":"2022-10-13T14:43:07.123477Z"},"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":"2022-10-13T14:43:07.125792Z","iopub.execute_input":"2022-10-13T14:43:07.126940Z","iopub.status.idle":"2022-10-13T14:43:07.132393Z","shell.execute_reply.started":"2022-10-13T14:43:07.126903Z","shell.execute_reply":"2022-10-13T14:43:07.131085Z"},"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":"2022-10-13T14:43:07.133679Z","iopub.execute_input":"2022-10-13T14:43:07.134478Z","iopub.status.idle":"2022-10-13T14:43:07.147040Z","shell.execute_reply.started":"2022-10-13T14:43:07.134443Z","shell.execute_reply":"2022-10-13T14:43:07.146094Z"},"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":"2022-10-13T14:43:07.150657Z","iopub.execute_input":"2022-10-13T14:43:07.150917Z","iopub.status.idle":"2022-10-13T14:43:13.349915Z","shell.execute_reply.started":"2022-10-13T14:43:07.150895Z","shell.execute_reply":"2022-10-13T14:43:13.348905Z"},"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":"2022-10-13T14:43:13.351503Z","iopub.execute_input":"2022-10-13T14:43:13.352144Z","iopub.status.idle":"2022-10-13T14:43:19.837718Z","shell.execute_reply.started":"2022-10-13T14:43:13.352105Z","shell.execute_reply":"2022-10-13T14:43:19.836687Z"},"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]","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:19.839019Z","iopub.execute_input":"2022-10-13T14:43:19.839410Z","iopub.status.idle":"2022-10-13T14:43:19.844436Z","shell.execute_reply.started":"2022-10-13T14:43:19.839373Z","shell.execute_reply":"2022-10-13T14:43:19.843154Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = df.drop(columns=cols_to_drop)","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:19.846203Z","iopub.execute_input":"2022-10-13T14:43:19.846909Z","iopub.status.idle":"2022-10-13T14:43:21.266924Z","shell.execute_reply.started":"2022-10-13T14:43:19.846805Z","shell.execute_reply":"2022-10-13T14:43:21.265870Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:21.268542Z","iopub.execute_input":"2022-10-13T14:43:21.268971Z","iopub.status.idle":"2022-10-13T14:43:22.013610Z","shell.execute_reply.started":"2022-10-13T14:43:21.268897Z","shell.execute_reply":"2022-10-13T14:43:22.012445Z"},"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":"2022-10-13T14:43:22.015311Z","iopub.execute_input":"2022-10-13T14:43:22.015761Z","iopub.status.idle":"2022-10-13T14:43:22.868038Z","shell.execute_reply.started":"2022-10-13T14:43:22.015722Z","shell.execute_reply":"2022-10-13T14:43:22.866975Z"},"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":"2022-10-13T14:43:22.869400Z","iopub.execute_input":"2022-10-13T14:43:22.870150Z","iopub.status.idle":"2022-10-13T14:43:22.891094Z","shell.execute_reply.started":"2022-10-13T14:43:22.870112Z","shell.execute_reply":"2022-10-13T14:43:22.890098Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"To keep things simple, let's just drop all null values.","metadata":{}},{"cell_type":"markdown","source":"欠損値のある、\"行\"を削除","metadata":{}},{"cell_type":"code","source":"df = df.dropna(axis=0)","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:22.892378Z","iopub.execute_input":"2022-10-13T14:43:22.892806Z","iopub.status.idle":"2022-10-13T14:43:26.764751Z","shell.execute_reply.started":"2022-10-13T14:43:22.892763Z","shell.execute_reply":"2022-10-13T14:43:26.763624Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"これで、欠損値を含む列がなくなる  \n以下で確認する","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":"2022-10-13T14:43:26.766570Z","iopub.execute_input":"2022-10-13T14:43:26.767033Z","iopub.status.idle":"2022-10-13T14:43:27.595915Z","shell.execute_reply.started":"2022-10-13T14:43:26.766994Z","shell.execute_reply":"2022-10-13T14:43:27.594685Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"これが最終版のトレインデータ","metadata":{}},{"cell_type":"code","source":"df","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:27.597608Z","iopub.execute_input":"2022-10-13T14:43:27.598094Z","iopub.status.idle":"2022-10-13T14:43:28.320801Z","shell.execute_reply.started":"2022-10-13T14:43:27.598055Z","shell.execute_reply":"2022-10-13T14:43:28.319687Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🚀 Model Training","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 💌 Submission","metadata":{}},{"cell_type":"code","source":"df_test = pd.read_csv('/kaggle/input/tabular-playground-series-oct-2022/test.csv')\ndf_test","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:28.322456Z","iopub.execute_input":"2022-10-13T14:43:28.322917Z","iopub.status.idle":"2022-10-13T14:43:37.008093Z","shell.execute_reply.started":"2022-10-13T14:43:28.322879Z","shell.execute_reply":"2022-10-13T14:43:37.007052Z"},"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    \n    return df","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:37.009775Z","iopub.execute_input":"2022-10-13T14:43:37.010576Z","iopub.status.idle":"2022-10-13T14:43:37.017402Z","shell.execute_reply.started":"2022-10-13T14:43:37.010535Z","shell.execute_reply":"2022-10-13T14:43:37.016299Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = preprocess(df_test)\ndf_test","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:37.019008Z","iopub.execute_input":"2022-10-13T14:43:37.019484Z","iopub.status.idle":"2022-10-13T14:43:41.271212Z","shell.execute_reply.started":"2022-10-13T14:43:37.019446Z","shell.execute_reply":"2022-10-13T14:43:41.270243Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2022-10-13T14:43:41.275373Z","iopub.execute_input":"2022-10-13T14:43:41.278028Z","iopub.status.idle":"2022-10-13T14:43:41.283480Z","shell.execute_reply.started":"2022-10-13T14:43:41.277989Z","shell.execute_reply":"2022-10-13T14:43:41.282312Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_submission","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:41.285305Z","iopub.execute_input":"2022-10-13T14:43:41.285693Z","iopub.status.idle":"2022-10-13T14:43:41.298788Z","shell.execute_reply.started":"2022-10-13T14:43:41.285655Z","shell.execute_reply":"2022-10-13T14:43:41.297802Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_submission.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2022-10-13T14:43:41.306333Z","iopub.execute_input":"2022-10-13T14:43:41.306878Z","iopub.status.idle":"2022-10-13T14:43:41.779529Z","shell.execute_reply.started":"2022-10-13T14:43:41.306844Z","shell.execute_reply":"2022-10-13T14:43:41.777104Z"},"trusted":true},"execution_count":null,"outputs":[]}]}