{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"dockerImageVersionId":30775,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport os","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-10-29T08:10:01.195375Z","iopub.execute_input":"2024-10-29T08:10:01.196430Z","iopub.status.idle":"2024-10-29T08:10:02.636337Z","shell.execute_reply.started":"2024-10-29T08:10:01.196376Z","shell.execute_reply":"2024-10-29T08:10:02.635148Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef Training_data_generator():\n    # Path to the parquet training directory\n    \n    series_train=\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\"\n    \n    df_train=pd.read_csv(\"/kaggle/input/child-mind-institute-problematic-internet-use/train.csv\")\n    print(df_train.shape)\n    X=[]\n    Y=[]\n    Z=[]\n    enmo=[]\n    light=[]\n    anglez=[]\n    steps=[]\n    \n    for id1 in df_train['id']:\n        folder =\"id=\"+ id1\n        parquet_directory= os.path.join(series_train,folder)\n        file= os.path.join(parquet_directory,\"part-0.parquet\")\n        try:\n            \n            parq = pd.read_parquet(file)\n            parq=parq.drop_duplicates()\n            X.append(parq['X'].mean())\n            Y.append(parq['Y'].mean())\n            Z.append(parq['Z'].mean())\n            enmo.append(parq['enmo'].mean())\n            anglez.append(parq['anglez'].mean())\n            steps.append(max(parq['step']))\n            \n            \n        except:\n            X.append(np.nan)\n            Y.append(np.nan)\n            Z.append(np.nan)\n            enmo.append(np.nan)\n            anglez.append(np.nan)\n            steps.append(np.nan)\n            \n            \n    \n    df_train['avg_x'] = X\n    df_train['avg_y'] = Y\n    df_train['avg_z'] = Z\n    df_train['avg_enmo']= enmo\n    df_train['anglez']= anglez\n    df_train['steps']=steps\n    df_train['avg_x']=df_train['avg_x'].fillna(df_train['avg_x'].mean())\n    df_train['avg_y']=df_train['avg_y'].fillna(df_train['avg_y'].mean())\n    df_train['avg_z']=df_train['avg_z'].fillna(df_train['avg_z'].mean())\n    df_train['avg_enmo']= df_train['avg_enmo'].fillna(df_train['avg_enmo'].mean())\n    df_train['anglez']= df_train['anglez'].fillna(df_train['anglez'].mean())\n    df_train['steps']=df_train['steps'].fillna(df_train['steps'].mean())\n    \n    return df_train\n","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:10:02.638788Z","iopub.execute_input":"2024-10-29T08:10:02.639304Z","iopub.status.idle":"2024-10-29T08:10:02.652292Z","shell.execute_reply.started":"2024-10-29T08:10:02.639262Z","shell.execute_reply":"2024-10-29T08:10:02.650868Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pd.read_parquet(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet/id=001f3379/part-0.parquet\")\n","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:10:02.654023Z","iopub.execute_input":"2024-10-29T08:10:02.654456Z","iopub.status.idle":"2024-10-29T08:10:02.987366Z","shell.execute_reply.started":"2024-10-29T08:10:02.654415Z","shell.execute_reply":"2024-10-29T08:10:02.986223Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\n\ndf = Training_data_generator()\nthreshold= int(0.3 * df.shape[1])\ndf=df.dropna(thresh=threshold)\n\n\n","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:10:02.990120Z","iopub.execute_input":"2024-10-29T08:10:02.990522Z","iopub.status.idle":"2024-10-29T08:14:42.502030Z","shell.execute_reply.started":"2024-10-29T08:10:02.990481Z","shell.execute_reply":"2024-10-29T08:14:42.500818Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"columns=[  'Basic_Demos-Age', 'Basic_Demos-Sex',\n                 'CGAS-CGAS_Score' , 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                 'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec'\n              , 'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-PAQ_A_Total',\n                'PAQ_C-PAQ_C_Total', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T',\n                'PreInt_EduHx-computerinternet_hoursday', 'sii'\n]\ndf=df[columns]\ndf.columns\ndf.shape","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:14:42.503788Z","iopub.execute_input":"2024-10-29T08:14:42.504254Z","iopub.status.idle":"2024-10-29T08:14:42.519541Z","shell.execute_reply.started":"2024-10-29T08:14:42.504200Z","shell.execute_reply":"2024-10-29T08:14:42.518302Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def Testing_generator():\n    series_test=\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\"\n    \n    df_test=pd.read_csv(\"/kaggle/input/child-mind-institute-problematic-internet-use/test.csv\")\n    print(df_test.shape)\n    X=[]\n    Y=[]\n    Z=[]\n    enmo=[]\n    light=[]\n    anglez=[]\n    steps=[]\n    for id1 in df_test['id']:\n        folder =\"id=\"+ id1\n        parquet_directory= os.path.join(series_test,folder)\n        file= os.path.join(parquet_directory,\"part-0.parquet\")\n        try:\n            \n            parq = pd.read_parquet(file)\n            X.append(parq['X'].mean())\n            Y.append(parq['Y'].mean())\n            Z.append(parq['Z'].mean())\n            enmo.append(parq['enmo'].mean())\n            anglez.append(parq['anglez'].mean())\n            steps.append(max(parq['step']))\n            \n            \n        except:\n            X.append(np.nan)\n            Y.append(np.nan)\n            Z.append(np.nan)\n            enmo.append(np.nan)\n            anglez.append(np.nan)\n            steps.append(np.nan)\n            \n    \n    df_test['avg_x'] = X\n    df_test['avg_y'] = Y\n    df_test['avg_z'] = Z\n    df_test['avg_enmo']= enmo\n    df_test['anglez']= anglez\n    df_test['steps']=steps\n    df_test['avg_x'] = df_test['avg_x'].fillna(df_test['avg_x'].mean())\n    df_test['avg_y'] = df_test['avg_y'].fillna(df_test['avg_y'].mean())\n    df_test['avg_z'] = df_test['avg_z'].fillna(df_test['avg_z'].mean())\n    df_test['avg_enmo']=df_test['avg_enmo'].fillna(df_test['avg_enmo'].mean())\n\n    df_test['anglez']= df_test['anglez'].fillna(df_test['anglez'].mean())\n    df_test['steps']=df_test['steps'].fillna(df_test['steps'].mean())\n    return df_test","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:14:42.521104Z","iopub.execute_input":"2024-10-29T08:14:42.521637Z","iopub.status.idle":"2024-10-29T08:14:42.535979Z","shell.execute_reply.started":"2024-10-29T08:14:42.521590Z","shell.execute_reply":"2024-10-29T08:14:42.534957Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndf_test = Testing_generator()\ncolumns=[\n         'Basic_Demos-Age', 'Basic_Demos-Sex',\n                 'CGAS-CGAS_Score' , 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                 'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec'\n              , 'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-PAQ_A_Total',\n                'PAQ_C-PAQ_C_Total', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T',\n                'PreInt_EduHx-computerinternet_hoursday'\n\n        ]\ndf_test=df_test[columns]\ndf_test.columns\n","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:14:42.537883Z","iopub.execute_input":"2024-10-29T08:14:42.538343Z","iopub.status.idle":"2024-10-29T08:14:42.751496Z","shell.execute_reply.started":"2024-10-29T08:14:42.538293Z","shell.execute_reply":"2024-10-29T08:14:42.750230Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for feature in df.columns:\n    if(df[feature].isnull().sum() > 0):\n        df[feature] = df[feature].fillna(df[feature].mode()[0])\nfor  feature in df_test.columns:\n    if(df_test[feature].isnull().sum() > 0):\n        df_test[feature] = df_test[feature].fillna(df[feature].mode()[0])\n\n\ndf['sii']\n","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:14:42.752802Z","iopub.execute_input":"2024-10-29T08:14:42.753123Z","iopub.status.idle":"2024-10-29T08:14:42.836422Z","shell.execute_reply.started":"2024-10-29T08:14:42.753090Z","shell.execute_reply":"2024-10-29T08:14:42.835082Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n\nfrom sklearn.preprocessing import OneHotEncoder\ncolumns=df.select_dtypes(exclude=[\"number\",\"bool_\"]).columns\n\n\nencoder = OneHotEncoder(sparse_output=False)\n\n# Apply one-hot encoding to the categorical columns\none_hot_encoded = encoder.fit_transform(df[columns])\n\n#Create a DataFrame with the one-hot encoded columns\n#We use get_feature_names_out() to get the column names for the encoded data\none_hot_df = pd.DataFrame(one_hot_encoded, columns=encoder.get_feature_names_out(columns))\n\n# Concatenate the one-hot encoded dataframe with the original dataframe\ndf = pd.concat([df, one_hot_df], axis=1)\n\n# Drop the original categorical columns\ndf= df.drop(columns, axis=1)\n\ny= df['sii']\ndf=df.drop('sii',axis=1)\none_hot_encoded = encoder.fit_transform(df_test[columns])\n\n#Create a DataFrame with the one-hot encoded columns\n#We use get_feature_names_out() to get the column names for the encoded data\none_hot_df = pd.DataFrame(one_hot_encoded, columns=encoder.get_feature_names_out(columns))\n\n\n# Concatenate the one-hot encoded dataframe with the original dataframe\ndf_test = pd.concat([df_test, one_hot_df], axis=1)\n\n# Drop the original categorical columns\ndf_test= df_test.drop(columns, axis=1)\n\ndf_test\n","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:14:42.838024Z","iopub.execute_input":"2024-10-29T08:14:42.838480Z","iopub.status.idle":"2024-10-29T08:14:42.986134Z","shell.execute_reply.started":"2024-10-29T08:14:42.838430Z","shell.execute_reply":"2024-10-29T08:14:42.984665Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\ncorrelation=df[[\n                'Basic_Demos-Age', 'Basic_Demos-Sex',\n                 'CGAS-CGAS_Score' , 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                 'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec'\n              , 'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-PAQ_A_Total',\n                'PAQ_C-PAQ_C_Total', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T',\n                'PreInt_EduHx-computerinternet_hoursday'\n]].corr()\n\naxis_corr = sns.heatmap(\ncorrelation,\nvmin=-1, vmax=1, center=0,\ncmap=sns.diverging_palette(500, 500, n=2000),\nsquare=True,\n)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:14:42.990351Z","iopub.execute_input":"2024-10-29T08:14:42.990789Z","iopub.status.idle":"2024-10-29T08:14:43.661157Z","shell.execute_reply.started":"2024-10-29T08:14:42.990750Z","shell.execute_reply":"2024-10-29T08:14:43.659871Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"From here we realize that we don't need columns like sex,'Fitness_Endurance-Time_Mins','Fitness_Endurance-Time_Sec','Fitness_Endurance-Max_Stage'","metadata":{}},{"cell_type":"code","source":"correlation=df[[\n       'Basic_Demos-Age', 'Physical-BMI','Physical-Height', 'Physical-Weight',\n       'Physical-Waist_Circumference',\n       'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n        'FGC-FGC_CU', 'FGC-FGC_CU_Zone',\n       'FGC-FGC_GSND', 'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone',\n       'FGC-FGC_PU', 'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone',\n       'FGC-FGC_SRR', 'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone',\n       'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n       'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n       'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n       'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n       'BIA-BIA_TBW', \n       \n]].corr()\n\ncolumns=['Basic_Demos-Age', 'Physical-BMI','Physical-Height', 'Physical-Weight',\n       'Physical-Waist_Circumference',\n       'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n        'FGC-FGC_CU', 'FGC-FGC_CU_Zone',\n       'FGC-FGC_GSND', 'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone',\n       'FGC-FGC_PU', 'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone',\n       'FGC-FGC_SRR', 'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone',\n       'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n       'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n       'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n       'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n       'BIA-BIA_TBW']\naxis_corr = sns.heatmap(\ncorrelation,\nvmin=-1, vmax=1, center=0,\ncmap=sns.diverging_palette(500, 500, n=10),\nsquare=True,\n)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:14:43.662425Z","iopub.execute_input":"2024-10-29T08:14:43.662789Z","iopub.status.idle":"2024-10-29T08:14:44.218200Z","shell.execute_reply.started":"2024-10-29T08:14:43.662746Z","shell.execute_reply":"2024-10-29T08:14:44.216872Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ny=y.fillna(y.mean())\ny=np.round(y)\n\n","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:14:44.219755Z","iopub.execute_input":"2024-10-29T08:14:44.220156Z","iopub.status.idle":"2024-10-29T08:14:44.228091Z","shell.execute_reply.started":"2024-10-29T08:14:44.220117Z","shell.execute_reply":"2024-10-29T08:14:44.226608Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.tree import DecisionTreeRegressor\nfrom sklearn.model_selection import GridSearchCV \nimport xgboost as xgb\nimport math\nimport lightgbm as lgb\nfrom sklearn.preprocessing import StandardScaler\n \nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\nfrom sklearn.metrics import accuracy_score\n\n\n\nmy_model = xgb.XGBClassifier(objective=\"multi:softprob\", random_state=42)\nskf = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)\nparam_grid = { \n    'alpha': [0.01, 0.1, 1.0, 10.0], \n    \n} \naccuracy=[]\nX = df\nscaler = StandardScaler()\nmodel = scaler.fit(X)\nX = model.transform(X)\ngrid_search = GridSearchCV(my_model, param_grid) \ngrid_search.fit(X, y) \n    \ny_pred = grid_search.predict(X)","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:14:44.229835Z","iopub.execute_input":"2024-10-29T08:14:44.230266Z","iopub.status.idle":"2024-10-29T08:15:04.966941Z","shell.execute_reply.started":"2024-10-29T08:14:44.230226Z","shell.execute_reply":"2024-10-29T08:15:04.965912Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cm=confusion_matrix(y_pred,y)\ncm_display = ConfusionMatrixDisplay(confusion_matrix = cm, display_labels = [0, 1,2,3])\ncm_display.plot()","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:15:04.968321Z","iopub.execute_input":"2024-10-29T08:15:04.969584Z","iopub.status.idle":"2024-10-29T08:15:05.319871Z","shell.execute_reply.started":"2024-10-29T08:15:04.969518Z","shell.execute_reply":"2024-10-29T08:15:05.318579Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def quadratic_weighted_kappa(y_true, y_pred):\n    return cohen_kappa_score(y_true, y_pred, weights='quadratic')\n","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:15:05.321603Z","iopub.execute_input":"2024-10-29T08:15:05.322101Z","iopub.status.idle":"2024-10-29T08:15:05.328178Z","shell.execute_reply.started":"2024-10-29T08:15:05.322051Z","shell.execute_reply":"2024-10-29T08:15:05.327003Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.read_csv(\"/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv\")\n\n\ndf_test = model.transform(df_test)\n\nnew1=grid_search.predict(df_test)\n\nsubmission['sii']= new1.astype(int)\nsubmission.to_csv(\"submission.csv\",index= False)\n","metadata":{"execution":{"iopub.status.busy":"2024-10-29T08:20:10.343836Z","iopub.execute_input":"2024-10-29T08:20:10.344402Z","iopub.status.idle":"2024-10-29T08:20:10.381109Z","shell.execute_reply.started":"2024-10-29T08:20:10.344346Z","shell.execute_reply":"2024-10-29T08:20:10.379106Z"},"trusted":true},"execution_count":null,"outputs":[]}]}