{"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 some lib\nimport pandas as pd\nimport lightgbm as lgb\nfrom tqdm import tqdm\nfrom sklearn.model_selection import train_test_split\n\ntrain_0 = pd.read_parquet(f\"../input/compress-files-parquet-7x-loading-speedup/train_0.parquet.gzip\")\n\ndisplay(train_0)","metadata":{"execution":{"iopub.status.busy":"2022-10-01T09:27:12.540686Z","iopub.execute_input":"2022-10-01T09:27:12.541554Z","iopub.status.idle":"2022-10-01T09:27:23.114222Z","shell.execute_reply.started":"2022-10-01T09:27:12.541445Z","shell.execute_reply":"2022-10-01T09:27:23.112666Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# confirm train data size and columns\nprint(\"train_0\",train_0.shape)\n    \nprint(train_0.columns)\nprint(train_0.dtypes)\n'''\ntarget columns=\"team_A_scoring_within10sec\" & \"team_B_scoring_within_10sec\"\nwe use target columns as train_y, others as train_X\n'''","metadata":{"execution":{"iopub.status.busy":"2022-10-01T09:27:23.116489Z","iopub.execute_input":"2022-10-01T09:27:23.116863Z","iopub.status.idle":"2022-10-01T09:27:23.135815Z","shell.execute_reply.started":"2022-10-01T09:27:23.116830Z","shell.execute_reply":"2022-10-01T09:27:23.131040Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''make training and valid data'''\ntry:\n    train_0 = train_0.drop([\"game_num\",\"event_id\",\"event_time\",\"player_scoring_next\",\"team_scoring_next\"],axis=1)\nexcept:\n    pass\n\nX = train_0.drop([\"team_A_scoring_within_10sec\",\"team_B_scoring_within_10sec\"],axis=1)\nyA = train_0[[\"team_A_scoring_within_10sec\"]]\nyB = train_0[[\"team_B_scoring_within_10sec\"]]\n\n\nprint(\"X label:\",X.columns)\nprint(\"X shape:\",X.shape)\nprint(\"y_label:\",yA.columns)\nprint(\"y shape:\",yA.shape)\n\ntrain_XA,valid_XA,train_yA,valid_yA = train_test_split(X,yA,test_size=0.3,random_state=42)\ntrain_XB,valid_XB,train_yB,valid_yB = train_test_split(X,yB,test_size=0.3,random_state=42)","metadata":{"execution":{"iopub.status.busy":"2022-10-01T09:27:23.138783Z","iopub.execute_input":"2022-10-01T09:27:23.139673Z","iopub.status.idle":"2022-10-01T09:27:28.750884Z","shell.execute_reply.started":"2022-10-01T09:27:23.139586Z","shell.execute_reply":"2022-10-01T09:27:28.748892Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_A = lgb.LGBMClassifier()\nmodel_B = lgb.LGBMClassifier()\nmodel_A.fit(train_XA,train_yA,eval_set = [(valid_XA,valid_yA),(train_XA,train_yA)])\nmodel_B.fit(train_XB,train_yB,eval_set = [(valid_XB,valid_yB),(train_XB,train_yB)])\n\ndel train_0,train_XA,train_yA,train_XB,train_yB,valid_XA,valid_yA,valid_XB,valid_yB","metadata":{"execution":{"iopub.status.busy":"2022-10-01T09:30:06.548572Z","iopub.execute_input":"2022-10-01T09:30:06.549091Z","iopub.status.idle":"2022-10-01T09:31:39.107488Z","shell.execute_reply.started":"2022-10-01T09:30:06.549043Z","shell.execute_reply":"2022-10-01T09:31:39.104717Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = pd.read_parquet(\"../input/compress-files-parquet-7x-loading-speedup/test.parquet.gzip\")\ndisplay(test)","metadata":{"execution":{"iopub.status.busy":"2022-10-01T09:32:13.988666Z","iopub.execute_input":"2022-10-01T09:32:13.989158Z","iopub.status.idle":"2022-10-01T09:32:16.369862Z","shell.execute_reply.started":"2022-10-01T09:32:13.989121Z","shell.execute_reply":"2022-10-01T09:32:16.367763Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_X = test.drop([\"id\"],axis=1)\npredict_A = model_A.predict_proba(test_X)[:,1]\npredict_B = model_B.predict_proba(test_X)[:,1]\n\nprint(predict_A)\nprint(predict_B)","metadata":{"execution":{"iopub.status.busy":"2022-10-01T09:34:36.746317Z","iopub.execute_input":"2022-10-01T09:34:36.746815Z","iopub.status.idle":"2022-10-01T09:34:40.741013Z","shell.execute_reply.started":"2022-10-01T09:34:36.746772Z","shell.execute_reply":"2022-10-01T09:34:40.739730Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.read_csv(\"../input/tabular-playground-series-oct-2022/sample_submission.csv\")\nsubmission[\"team_A_scoring_within_10sec\"] = predict_A\nsubmission[\"team_B_scoring_within_10sec\"] = predict_B\n\ndisplay(submission)\n\nsubmission.to_csv(\"submission.csv\",index=False)","metadata":{"execution":{"iopub.status.busy":"2022-10-01T09:35:01.333392Z","iopub.execute_input":"2022-10-01T09:35:01.334083Z","iopub.status.idle":"2022-10-01T09:35:04.569588Z","shell.execute_reply.started":"2022-10-01T09:35:01.334001Z","shell.execute_reply":"2022-10-01T09:35:04.568315Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}