{"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":59094,"databundleVersionId":7010844,"sourceType":"competition"}],"dockerImageVersionId":30579,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-11-15T06:54:23.199064Z","iopub.execute_input":"2023-11-15T06:54:23.200407Z","iopub.status.idle":"2023-11-15T06:54:23.762057Z","shell.execute_reply.started":"2023-11-15T06:54:23.200348Z","shell.execute_reply":"2023-11-15T06:54:23.760781Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fn1 = '/kaggle/input/open-problems-single-cell-perturbations/adata_excluded_ids.csv'\nfn2 = '/kaggle/input/open-problems-single-cell-perturbations/adata_obs_meta.csv'\nfn3 = '/kaggle/input/open-problems-single-cell-perturbations/adata_train.parquet'\nfn4 = '/kaggle/input/open-problems-single-cell-perturbations/de_train.parquet'\nfn5 = '/kaggle/input/open-problems-single-cell-perturbations/id_map.csv'\nfn6 = '/kaggle/input/open-problems-single-cell-perturbations/multiome_obs_meta.csv'\nfn7 = '/kaggle/input/open-problems-single-cell-perturbations/multiome_train.parquet'\nfn8 = '/kaggle/input/open-problems-single-cell-perturbations/multiome_var_meta.csv'","metadata":{"execution":{"iopub.status.busy":"2023-11-15T06:54:27.349236Z","iopub.execute_input":"2023-11-15T06:54:27.349882Z","iopub.status.idle":"2023-11-15T06:54:27.356949Z","shell.execute_reply.started":"2023-11-15T06:54:27.349837Z","shell.execute_reply":"2023-11-15T06:54:27.355558Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_adata_excluded_ids = pd.read_csv(fn1)# , index_col = 0)\nprint(df_adata_excluded_ids.shape)\ndf_adata_excluded_ids.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_obs_meta = pd.read_csv(fn2)# , index_col = 0)\nprint(df_obs_meta.shape)\ndf_obs_meta.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_adata_train = pd.read_parquet(fn3)# , index_col = 0)\nprint(df_adata_train.shape)\ndf_adata_train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_de_train = pd.read_parquet(fn4)# , index_col = 0)\nprint(df_de_train.shape)\ndf_de_train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"id_map = pd.read_csv(fn5)# , index_col = 0)\nprint(id_map.shape)\nid_map.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nmultiome_obs_meta = pd.read_csv(fn6)# , index_col = 0)\nprint(multiome_obs_meta.shape)\nmultiome_obs_meta.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_multiome_train = pd.read_parquet(fn7)# , index_col = 0)\nprint(df_multiome_train.shape)\ndf_multiome_train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_multiome_var_meta = pd.read_csv(fn8)# , index_col = 0)\nprint(df_multiome_var_meta.shape)\ndf_multiome_var_meta.head()","metadata":{"execution":{"iopub.status.busy":"2023-11-15T06:56:28.495049Z","iopub.execute_input":"2023-11-15T06:56:28.496071Z","iopub.status.idle":"2023-11-15T06:56:29.147271Z","shell.execute_reply.started":"2023-11-15T06:56:28.496024Z","shell.execute_reply":"2023-11-15T06:56:29.146143Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}