{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":53666,"databundleVersionId":6589269,"sourceType":"competition"}],"dockerImageVersionId":30626,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nimport matplotlib.pyplot as plt\n\n# Replace 'your_file.parquet' with the path to your .parquet file\nfile_path = '/kaggle/input/child-mind-institute-detect-sleep-states/test_series.parquet'\n\n# Read the .parquet file into a Pandas DataFrame\ndf = pd.read_parquet(file_path)\n\n# Now you can work with the DataFrame 'df'\nprint(df.head())\n\n\n\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-12-18T21:20:14.316563Z","iopub.execute_input":"2023-12-18T21:20:14.317057Z","iopub.status.idle":"2023-12-18T21:20:14.335607Z","shell.execute_reply.started":"2023-12-18T21:20:14.317020Z","shell.execute_reply":"2023-12-18T21:20:14.334592Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(df.describe())","metadata":{"execution":{"iopub.status.busy":"2023-12-18T21:18:20.633578Z","iopub.execute_input":"2023-12-18T21:18:20.634024Z","iopub.status.idle":"2023-12-18T21:18:20.655947Z","shell.execute_reply.started":"2023-12-18T21:18:20.633988Z","shell.execute_reply":"2023-12-18T21:18:20.654338Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(df.dtypes)\n","metadata":{"execution":{"iopub.status.busy":"2023-12-18T21:18:39.042069Z","iopub.execute_input":"2023-12-18T21:18:39.042461Z","iopub.status.idle":"2023-12-18T21:18:39.049755Z","shell.execute_reply.started":"2023-12-18T21:18:39.042431Z","shell.execute_reply":"2023-12-18T21:18:39.048215Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(df.isnull().sum())\n","metadata":{"execution":{"iopub.status.busy":"2023-12-18T21:18:49.150006Z","iopub.execute_input":"2023-12-18T21:18:49.150557Z","iopub.status.idle":"2023-12-18T21:18:49.158400Z","shell.execute_reply.started":"2023-12-18T21:18:49.150515Z","shell.execute_reply":"2023-12-18T21:18:49.157533Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df['enmo'].hist()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-12-18T21:20:21.503952Z","iopub.execute_input":"2023-12-18T21:20:21.504820Z","iopub.status.idle":"2023-12-18T21:20:21.778939Z","shell.execute_reply.started":"2023-12-18T21:20:21.504778Z","shell.execute_reply":"2023-12-18T21:20:21.777610Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\n# Assuming df is your DataFrame with the specified columns\n# Example: df = pd.read_csv('your_dataset.csv')\n\n# Select relevant columns for correlation\nselected_columns = ['step', 'anglez', 'enmo']\n\n# Create a correlation matrix\ncorrelation_matrix = df[selected_columns].corr()\n\n# Create a heatmap\nsns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', linewidths=0.5)\nplt.title('Heatmap of Numerical Variables')\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2023-12-18T21:23:51.034425Z","iopub.execute_input":"2023-12-18T21:23:51.034935Z","iopub.status.idle":"2023-12-18T21:23:52.230192Z","shell.execute_reply.started":"2023-12-18T21:23:51.034883Z","shell.execute_reply":"2023-12-18T21:23:52.228897Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Assuming df is your DataFrame\n# Example: df = pd.read_csv('your_dataset.csv')\n\n# Get the number of rows\nnum_rows = df.shape[0]\n\nprint(f'The DataFrame has {num_rows} rows.')\n","metadata":{},"execution_count":null,"outputs":[]}]}