{"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":"

Hello there!

\n\n

This notebook introduces a super simple way to create a submission file for the competition of \"Parkinson's Freezing of Gait Prediction\".

\n\n

In this notebook, you will create features by combining 3-dimensional accelerometer data values with metadata about subjects in order to detect FoG (Freezing of Gait) events.

\n\n

To predict FoG events ('StartHesitation', 'Turn', 'Walking') at a given time point t, you will use the accelerometer data values and subject information at the same time point t.

\n\n

However, since this procedure does not handle temporal information well, it must be necessary to conduct innovative feature engineering to achieve better performance.

\n\n

The purpose of publishing this notebook is to demonstrate the rough procedure up to submitting results for the competition using simple code as much as possible.

\n\n

I hope that the release of this notebook will contribute even a little to the excitement of the competition.

\n\n

Let's enjoy Kaggle together!

\n\n

Import Modules

","metadata":{}},{"cell_type":"code","source":"import os\nimport tqdm\nimport glob\nimport numpy as np\nimport pandas as pd\nfrom sklearn.ensemble import RandomForestClassifier","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-04-20T03:15:05.766077Z","iopub.execute_input":"2023-04-20T03:15:05.766473Z","iopub.status.idle":"2023-04-20T03:15:07.514213Z","shell.execute_reply.started":"2023-04-20T03:15:05.766437Z","shell.execute_reply":"2023-04-20T03:15:07.512381Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# parent directory\npdir = '/kaggle/input/tlvmc-parkinsons-freezing-gait-prediction'","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:07.517604Z","iopub.execute_input":"2023-04-20T03:15:07.518217Z","iopub.status.idle":"2023-04-20T03:15:07.525605Z","shell.execute_reply.started":"2023-04-20T03:15:07.518154Z","shell.execute_reply":"2023-04-20T03:15:07.523962Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# load meta data","metadata":{}},{"cell_type":"code","source":"df_tdcs_meta = pd.read_csv(os.path.join(pdir, 'tdcsfog_metadata.csv'))\ndf_tdcs_meta.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:07.529844Z","iopub.execute_input":"2023-04-20T03:15:07.530428Z","iopub.status.idle":"2023-04-20T03:15:07.602251Z","shell.execute_reply.started":"2023-04-20T03:15:07.530366Z","shell.execute_reply":"2023-04-20T03:15:07.601233Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_defog_meta = pd.read_csv(os.path.join(pdir, 'defog_metadata.csv'))\ndf_defog_meta.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:07.604277Z","iopub.execute_input":"2023-04-20T03:15:07.604822Z","iopub.status.idle":"2023-04-20T03:15:07.624322Z","shell.execute_reply.started":"2023-04-20T03:15:07.604788Z","shell.execute_reply":"2023-04-20T03:15:07.623084Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subjects = pd.read_csv(os.path.join(pdir, 'subjects.csv'))\ndf_subjects.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:07.625769Z","iopub.execute_input":"2023-04-20T03:15:07.626794Z","iopub.status.idle":"2023-04-20T03:15:07.651947Z","shell.execute_reply.started":"2023-04-20T03:15:07.626758Z","shell.execute_reply":"2023-04-20T03:15:07.650754Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load tdcsfog data","metadata":{}},{"cell_type":"code","source":"# list of all tdcsfog csv file path\ntdcs_file_path = glob.glob(os.path.join(pdir, 'train', 'tdcsfog', '*.csv'), recursive=True)\n\n# In this notebook, we limit the number of files to be read in order to reduce the time required for model training.\ntdcs_file_path = tdcs_file_path[::100]\n\nprint(f'the number of files to be read: {len(tdcs_file_path)}')","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:16.114026Z","iopub.execute_input":"2023-04-20T03:15:16.114548Z","iopub.status.idle":"2023-04-20T03:15:16.126800Z","shell.execute_reply.started":"2023-04-20T03:15:16.114506Z","shell.execute_reply":"2023-04-20T03:15:16.125187Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Initialize a DataFrame to combine data from multiple CSV files.\ndf_tdcs = pd.DataFrame()\n\n# load tdcsfog time series in combination with metadata.\nfor fp in tqdm.tqdm(tdcs_file_path): \n \n # load data into a variable 'tmp'.\n tmp = pd.read_csv(fp)\n \n # get file Id from csv file name.\n file_id = os.path.basename(fp).replace(\".csv\", \"\")\n \n # get subject Id.\n subject = df_tdcs_meta.loc[df_tdcs_meta['Id'] == file_id, 'Subject'].iloc[0]\n \n # add metadata.\n tmp['Medication'] = df_tdcs_meta.loc[df_tdcs_meta['Id'] == file_id, 'Medication'].iloc[0]\n tmp['Age'] = df_subjects.loc[df_subjects['Subject'] == subject, 'Age'].iloc[0]\n tmp['Sex'] = df_subjects.loc[df_subjects['Subject'] == subject, 'Sex'].iloc[0]\n tmp['YearsSinceDx'] = df_subjects.loc[df_subjects['Subject'] == subject, 'YearsSinceDx'].iloc[0]\n tmp['NFOGQ'] =df_subjects.loc[df_subjects['Subject'] == subject, 'NFOGQ'].iloc[0]\n \n # concat the data\n df_tdcs = pd.concat([df_tdcs, tmp]).reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:17.231566Z","iopub.execute_input":"2023-04-20T03:15:17.232095Z","iopub.status.idle":"2023-04-20T03:15:17.586593Z","shell.execute_reply.started":"2023-04-20T03:15:17.232049Z","shell.execute_reply":"2023-04-20T03:15:17.585013Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# check the contents of the df_tdcs\ndf_tdcs.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:18.354260Z","iopub.execute_input":"2023-04-20T03:15:18.354834Z","iopub.status.idle":"2023-04-20T03:15:18.375299Z","shell.execute_reply.started":"2023-04-20T03:15:18.354784Z","shell.execute_reply":"2023-04-20T03:15:18.373697Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load defog data","metadata":{}},{"cell_type":"code","source":"# list of all tdcsfog csv file path\ndefog_file_path = glob.glob(os.path.join(pdir, 'train', 'defog', '*.csv'), recursive=True)\n\n# In this notebook, we limit the number of files to be read in order to reduce the time required for model training.\ndefog_file_path = defog_file_path[::50]\n\nprint(f'the number of files to be read: {len(defog_file_path)}')","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:19.704624Z","iopub.execute_input":"2023-04-20T03:15:19.705071Z","iopub.status.idle":"2023-04-20T03:15:19.722578Z","shell.execute_reply.started":"2023-04-20T03:15:19.705032Z","shell.execute_reply":"2023-04-20T03:15:19.721175Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Initialize a DataFrame to combine data from multiple CSV files.\ndf_defog = pd.DataFrame()\n\nfor fp in tqdm.tqdm(defog_file_path):\n # load data into a variable 'tmp'.\n tmp = pd.read_csv(fp)\n \n # get file Id from csv file name.\n file_id = os.path.basename(fp).replace(\".csv\", \"\")\n \n # get subject Id.\n subject = df_defog_meta.loc[df_defog_meta['Id'] == file_id, 'Subject'].iloc[0]\n \n # add metadata.\n tmp['Medication'] = df_defog_meta.loc[df_defog_meta['Id'] == file_id, 'Medication'].iloc[0]\n tmp['Age'] = df_subjects.loc[df_subjects['Subject'] == subject, 'Age'].iloc[0]\n tmp['Sex'] = df_subjects.loc[df_subjects['Subject'] == subject, 'Sex'].iloc[0]\n tmp['YearsSinceDx'] = df_subjects.loc[df_subjects['Subject'] == subject, 'YearsSinceDx'].iloc[0]\n tmp['NFOGQ'] =df_subjects.loc[df_subjects['Subject'] == subject, 'NFOGQ'].iloc[0]\n \n # extract data from the time period where Valid and Task are both True.\n tmp = tmp[(tmp['Valid'] == True) & (tmp['Task']==True)]\n tmp = tmp.drop(['Valid', 'Task'], axis=1)\n \n # concat the data\n df_defog = pd.concat([df_defog, tmp]).reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:20.717643Z","iopub.execute_input":"2023-04-20T03:15:20.718075Z","iopub.status.idle":"2023-04-20T03:15:21.279638Z","shell.execute_reply.started":"2023-04-20T03:15:20.718037Z","shell.execute_reply":"2023-04-20T03:15:21.278230Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# check the contents of the df_defog\ndf_defog.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:21.702330Z","iopub.execute_input":"2023-04-20T03:15:21.703287Z","iopub.status.idle":"2023-04-20T03:15:21.723138Z","shell.execute_reply.started":"2023-04-20T03:15:21.703234Z","shell.execute_reply":"2023-04-20T03:15:21.721284Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prepare train data","metadata":{}},{"cell_type":"code","source":"# concat tdcs and defog data.\ndf_train = pd.concat([df_tdcs, df_defog]).reset_index(drop=True)\ndf_train.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:23.830178Z","iopub.execute_input":"2023-04-20T03:15:23.830699Z","iopub.status.idle":"2023-04-20T03:15:23.891263Z","shell.execute_reply.started":"2023-04-20T03:15:23.830654Z","shell.execute_reply":"2023-04-20T03:15:23.889891Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# encode string columns into 0/1 format\ndf_train['Medication'] = np.where(df_train['Medication']=='on', 1, 0)\ndf_train['Sex'] = np.where(df_train['Sex']=='M', 1, 0)\ndf_train.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:26.781334Z","iopub.execute_input":"2023-04-20T03:15:26.781875Z","iopub.status.idle":"2023-04-20T03:15:26.822640Z","shell.execute_reply.started":"2023-04-20T03:15:26.781826Z","shell.execute_reply":"2023-04-20T03:15:26.821123Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# split data into features and target.\ny = df_train[['StartHesitation', 'Turn', 'Walking']] # target\nX = df_train.drop(['StartHesitation', 'Turn', 'Walking', 'Time'], axis=1) # feature","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:27.802597Z","iopub.execute_input":"2023-04-20T03:15:27.803091Z","iopub.status.idle":"2023-04-20T03:15:27.820691Z","shell.execute_reply.started":"2023-04-20T03:15:27.803052Z","shell.execute_reply":"2023-04-20T03:15:27.819572Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# check the contents of the target\ny.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:32.673371Z","iopub.execute_input":"2023-04-20T03:15:32.674038Z","iopub.status.idle":"2023-04-20T03:15:32.685784Z","shell.execute_reply.started":"2023-04-20T03:15:32.673997Z","shell.execute_reply":"2023-04-20T03:15:32.684493Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# check the contents of the feature\nX.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:33.517312Z","iopub.execute_input":"2023-04-20T03:15:33.518129Z","iopub.status.idle":"2023-04-20T03:15:33.534507Z","shell.execute_reply.started":"2023-04-20T03:15:33.518086Z","shell.execute_reply":"2023-04-20T03:15:33.533026Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train RandomForestClassifier","metadata":{}},{"cell_type":"code","source":"# train the model with default parameter\nrf = RandomForestClassifier(random_state=0)\nrf.fit(X, y)","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:15:35.072636Z","iopub.execute_input":"2023-04-20T03:15:35.073142Z","iopub.status.idle":"2023-04-20T03:16:01.294639Z","shell.execute_reply.started":"2023-04-20T03:15:35.073103Z","shell.execute_reply":"2023-04-20T03:16:01.293147Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prepare test data\n\n## Process the test data in the same way as the training data","metadata":{}},{"cell_type":"code","source":"# list of all tdcsfog csv file path\ntdcs_test_file_path = glob.glob(os.path.join(pdir, 'test', 'tdcsfog', '*.csv'), recursive=True)\nprint(f'the number of files to be read: {len(tdcs_test_file_path)}')","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:01.298124Z","iopub.execute_input":"2023-04-20T03:16:01.299059Z","iopub.status.idle":"2023-04-20T03:16:01.312395Z","shell.execute_reply.started":"2023-04-20T03:16:01.299010Z","shell.execute_reply":"2023-04-20T03:16:01.310793Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Initialize a DataFrame to combine data from multiple CSV files.\ndf_tdcs_test = pd.DataFrame()\n\nfor fp in tqdm.tqdm(tdcs_test_file_path):\n \n # load data into a variable 'tmp'.\n tmp = pd.read_csv(fp)\n \n # get file Id from csv file name.\n file_id = os.path.basename(fp).replace(\".csv\", \"\")\n \n # get subject Id.\n subject = df_tdcs_meta.loc[df_tdcs_meta['Id'] == file_id, 'Subject'].iloc[0]\n \n # add metadata.\n tmp['Medication'] = df_tdcs_meta.loc[df_tdcs_meta['Id'] == file_id, 'Medication'].iloc[0]\n tmp['Age'] = df_subjects.loc[df_subjects['Subject'] == subject, 'Age'].iloc[0]\n tmp['Sex'] = df_subjects.loc[df_subjects['Subject'] == subject, 'Sex'].iloc[0]\n tmp['YearsSinceDx'] = df_subjects.loc[df_subjects['Subject'] == subject, 'YearsSinceDx'].iloc[0]\n tmp['NFOGQ'] =df_subjects.loc[df_subjects['Subject'] == subject, 'NFOGQ'].iloc[0]\n \n # add Id data to submit.\n tmp['Id'] = file_id + '_' + tmp['Time'].astype(str)\n \n # concat the data\n df_tdcs_test = pd.concat([df_tdcs_test, tmp]).reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:01.314298Z","iopub.execute_input":"2023-04-20T03:16:01.314717Z","iopub.status.idle":"2023-04-20T03:16:01.362969Z","shell.execute_reply.started":"2023-04-20T03:16:01.314651Z","shell.execute_reply":"2023-04-20T03:16:01.361465Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# check the contents of the df_tdcs_test\ndf_tdcs_test.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:01.365575Z","iopub.execute_input":"2023-04-20T03:16:01.366078Z","iopub.status.idle":"2023-04-20T03:16:01.386036Z","shell.execute_reply.started":"2023-04-20T03:16:01.366034Z","shell.execute_reply":"2023-04-20T03:16:01.384786Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# list of all tdcsfog csv file path\ndefog_test_file_path = glob.glob(os.path.join(pdir, 'test', 'defog', '*.csv'), recursive=True)\nprint(f'the number of files to be read: {len(defog_test_file_path)}')","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:01.388496Z","iopub.execute_input":"2023-04-20T03:16:01.388915Z","iopub.status.idle":"2023-04-20T03:16:01.399630Z","shell.execute_reply.started":"2023-04-20T03:16:01.388819Z","shell.execute_reply":"2023-04-20T03:16:01.397924Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Initialize a DataFrame to combine data from multiple CSV files.\ndf_defog_test = pd.DataFrame()\n\nfor fp in tqdm.tqdm(defog_test_file_path):\n # load data into a variable 'tmp'.\n tmp = pd.read_csv(fp)\n \n # get file Id from csv file name.\n file_id = os.path.basename(fp).replace(\".csv\", \"\")\n \n # get subject Id.\n subject = df_defog_meta.loc[df_defog_meta['Id'] == file_id, 'Subject'].iloc[0]\n \n # add metadata.\n tmp['Medication'] = df_defog_meta.loc[df_defog_meta['Id'] == file_id, 'Medication'].iloc[0]\n tmp['Age'] = df_subjects.loc[df_subjects['Subject'] == subject, 'Age'].iloc[0]\n tmp['Sex'] = df_subjects.loc[df_subjects['Subject'] == subject, 'Sex'].iloc[0]\n tmp['YearsSinceDx'] = df_subjects.loc[df_subjects['Subject'] == subject, 'YearsSinceDx'].iloc[0]\n tmp['NFOGQ'] =df_subjects.loc[df_subjects['Subject'] == subject, 'NFOGQ'].iloc[0]\n \n # add Id data to submit.\n tmp['Id'] = file_id + '_' + tmp['Time'].astype(str)\n \n # concat the data\n df_defog_test = pd.concat([df_defog_test, tmp]).reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:01.401336Z","iopub.execute_input":"2023-04-20T03:16:01.401671Z","iopub.status.idle":"2023-04-20T03:16:02.400989Z","shell.execute_reply.started":"2023-04-20T03:16:01.401639Z","shell.execute_reply":"2023-04-20T03:16:02.399275Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# check the contents of the df_defog_test\ndf_defog_test.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:02.403227Z","iopub.execute_input":"2023-04-20T03:16:02.403606Z","iopub.status.idle":"2023-04-20T03:16:02.422224Z","shell.execute_reply.started":"2023-04-20T03:16:02.403572Z","shell.execute_reply":"2023-04-20T03:16:02.420543Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# concat tdcs and defog data.\ndf_test = pd.concat([df_tdcs_test, df_defog_test]).reset_index(drop=True)\n\n# encode string columns into 0/1 format\ndf_test['Medication'] = np.where(df_test['Medication']=='on', 1, 0)\ndf_test['Sex'] = np.where(df_test['Sex']=='M', 1, 0)\ndisplay(df_test)","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:02.424481Z","iopub.execute_input":"2023-04-20T03:16:02.426380Z","iopub.status.idle":"2023-04-20T03:16:02.609835Z","shell.execute_reply.started":"2023-04-20T03:16:02.426318Z","shell.execute_reply":"2023-04-20T03:16:02.608195Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# split data into submission Id and feature.\nId = df_test['Id'] # Id for submission data\nX_test = df_test.drop(['Time', 'Id'], axis=1) # feature of test data\nX_test.head()","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:02.611913Z","iopub.execute_input":"2023-04-20T03:16:02.612326Z","iopub.status.idle":"2023-04-20T03:16:02.645268Z","shell.execute_reply.started":"2023-04-20T03:16:02.612289Z","shell.execute_reply":"2023-04-20T03:16:02.643825Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Predict and submit","metadata":{}},{"cell_type":"code","source":"# calculate prediction using trained RandomForestClassifier model.\nprediction = rf.predict(X_test)","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:02.648782Z","iopub.execute_input":"2023-04-20T03:16:02.649244Z","iopub.status.idle":"2023-04-20T03:16:08.207550Z","shell.execute_reply.started":"2023-04-20T03:16:02.649203Z","shell.execute_reply":"2023-04-20T03:16:08.206009Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Prepare submit data\nsubmit = pd.DataFrame(Id, columns=['Id'])\nsubmit['StartHesitation'] = prediction[:, 0]\nsubmit['Turn'] = prediction[:, 1]\nsubmit['Walking'] = prediction[:, 2]","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:08.209864Z","iopub.execute_input":"2023-04-20T03:16:08.210478Z","iopub.status.idle":"2023-04-20T03:16:08.225650Z","shell.execute_reply.started":"2023-04-20T03:16:08.210424Z","shell.execute_reply":"2023-04-20T03:16:08.224285Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(submit)","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:13.733126Z","iopub.execute_input":"2023-04-20T03:16:13.733591Z","iopub.status.idle":"2023-04-20T03:16:13.749350Z","shell.execute_reply.started":"2023-04-20T03:16:13.733553Z","shell.execute_reply":"2023-04-20T03:16:13.748198Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Save the created submission data.\nsubmit.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2023-04-20T03:16:14.741205Z","iopub.execute_input":"2023-04-20T03:16:14.742737Z","iopub.status.idle":"2023-04-20T03:16:15.174122Z","shell.execute_reply.started":"2023-04-20T03:16:14.742678Z","shell.execute_reply":"2023-04-20T03:16:15.172557Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Congratulations!

\n\n

You're now ready to submit your work on Kaggle!

\n\n

Enjoy your experience on Kaggle!

","metadata":{}}]}