{"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":"# What is about ?\n\nLoad data file and make simple visualization of data.","metadata":{}},{"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":"2022-11-07T03:23:37.925041Z","iopub.execute_input":"2022-11-07T03:23:37.925456Z","iopub.status.idle":"2022-11-07T03:23:37.985096Z","shell.execute_reply.started":"2022-11-07T03:23:37.925424Z","shell.execute_reply":"2022-11-07T03:23:37.983907Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load already calculated UMAP for CITE-seq part of data (both train and test concatenated)","metadata":{}},{"cell_type":"code","source":"fn = '/kaggle/input/feature-shop-for-multimodal-singlecell-competition/citeseq_UMAPfromTSVD200_n_components3_n_neighbors5_min_dist0d1_rs42.csv'\ndf = pd.read_csv(fn, index_col = 0)\nprint('Number of reduced dimensions is:', df.shape[1])\ndf\n","metadata":{"execution":{"iopub.status.busy":"2022-11-07T03:23:44.198717Z","iopub.execute_input":"2022-11-07T03:23:44.199135Z","iopub.status.idle":"2022-11-07T03:23:44.481478Z","shell.execute_reply.started":"2022-11-07T03:23:44.199096Z","shell.execute_reply":"2022-11-07T03:23:44.480335Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df['0']","metadata":{"execution":{"iopub.status.busy":"2022-11-07T03:23:47.526575Z","iopub.execute_input":"2022-11-07T03:23:47.526985Z","iopub.status.idle":"2022-11-07T03:23:47.555081Z","shell.execute_reply.started":"2022-11-07T03:23:47.526954Z","shell.execute_reply":"2022-11-07T03:23:47.553763Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Simple visualization","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns","metadata":{"execution":{"iopub.status.busy":"2022-11-08T08:38:20.881420Z","iopub.execute_input":"2022-11-08T08:38:20.881815Z","iopub.status.idle":"2022-11-08T08:38:21.520348Z","shell.execute_reply.started":"2022-11-08T08:38:20.881786Z","shell.execute_reply":"2022-11-08T08:38:21.519139Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize = (20,5))\nsns.scatterplot(x = df['0'].values, y=df['1'].values , hue = df['2'].values, palette='rainbow')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-11-08T08:38:23.495255Z","iopub.execute_input":"2022-11-08T08:38:23.495707Z","iopub.status.idle":"2022-11-08T08:38:23.547056Z","shell.execute_reply.started":"2022-11-08T08:38:23.495672Z","shell.execute_reply":"2022-11-08T08:38:23.545758Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load Meta information (donor, cell type, Gender, train/test )","metadata":{}},{"cell_type":"code","source":"fn2 = '/kaggle/input/otto-recommender-system/sample_submission.csv'\ndf2 = pd.read_csv(fn2, index_col = 0)\ndf2","metadata":{"execution":{"iopub.status.busy":"2022-11-08T08:38:12.429845Z","iopub.execute_input":"2022-11-08T08:38:12.430282Z","iopub.status.idle":"2022-11-08T08:38:12.506727Z","shell.execute_reply.started":"2022-11-08T08:38:12.430184Z","shell.execute_reply":"2022-11-08T08:38:12.505534Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df2.columns","metadata":{"execution":{"iopub.status.busy":"2022-10-24T09:55:40.549009Z","iopub.execute_input":"2022-10-24T09:55:40.549642Z","iopub.status.idle":"2022-10-24T09:55:40.557236Z","shell.execute_reply.started":"2022-10-24T09:55:40.549605Z","shell.execute_reply":"2022-10-24T09:55:40.556165Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Visualization colored by MetaData","metadata":{}},{"cell_type":"code","source":"\nfor col in ['Train0OrTest1', 'day', 'donor', 'cell_type', 'technology', 'Gender',\n       'HSC cell_type', 'EryP cell_type', 'NeuP cell_type', 'MasP cell_type',\n       'MkP cell_type', 'BP cell_type', 'MoP cell_type']:\n    print(col)\n    plt.figure(figsize = (20,10))\n    sns.scatterplot(x = df['0'].values, y=df['1'].values , hue = df2[col], palette='rainbow')\n    plt.title(col, fontsize = 20 )\n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2022-11-07T03:23:13.133259Z","iopub.execute_input":"2022-11-07T03:23:13.133826Z","iopub.status.idle":"2022-11-07T03:23:13.230352Z","shell.execute_reply.started":"2022-11-07T03:23:13.133719Z","shell.execute_reply":"2022-11-07T03:23:13.228613Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}