{"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":"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":"2022-08-13T15:46:25.107941Z","iopub.execute_input":"2022-08-13T15:46:25.108292Z","iopub.status.idle":"2022-08-13T15:46:25.124567Z","shell.execute_reply.started":"2022-08-13T15:46:25.108262Z","shell.execute_reply":"2022-08-13T15:46:25.123681Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train=pd.read_csv(\"/kaggle/input/adversarial-validation-train-and-test-data-differ/train_p.csv\")\nval=pd.read_csv(\"/kaggle/input/adversarial-validation-train-and-test-data-differ/train_p.csv\")\ntest=pd.read_csv(\"/kaggle/input/tabular-playground-series-aug-2022/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2022-08-13T15:54:54.924992Z","iopub.execute_input":"2022-08-13T15:54:54.925345Z","iopub.status.idle":"2022-08-13T15:54:55.107023Z","shell.execute_reply.started":"2022-08-13T15:54:54.925314Z","shell.execute_reply":"2022-08-13T15:54:55.106047Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#train=train.fillna(0)","metadata":{"execution":{"iopub.status.busy":"2022-08-13T14:28:24.819048Z","iopub.execute_input":"2022-08-13T14:28:24.819482Z","iopub.status.idle":"2022-08-13T14:28:24.829564Z","shell.execute_reply.started":"2022-08-13T14:28:24.819446Z","shell.execute_reply":"2022-08-13T14:28:24.827641Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#train.dropna(inplace=True)\nx_train=train[test.columns].to_numpy()\nnan=np.asarray(train.isna().any(axis=1))\nlabel=np.asarray(train['failure'])","metadata":{"execution":{"iopub.status.busy":"2022-08-13T15:54:56.254836Z","iopub.execute_input":"2022-08-13T15:54:56.255186Z","iopub.status.idle":"2022-08-13T15:54:56.267990Z","shell.execute_reply.started":"2022-08-13T15:54:56.255156Z","shell.execute_reply":"2022-08-13T15:54:56.266916Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from cuml.manifold import TSNE, UMAP\numap = UMAP(n_components=2, n_neighbors=50)\nx_trans = umap.fit_transform(x_train)","metadata":{"execution":{"iopub.status.busy":"2022-08-13T15:54:58.065435Z","iopub.execute_input":"2022-08-13T15:54:58.066019Z","iopub.status.idle":"2022-08-13T15:55:01.151543Z","shell.execute_reply.started":"2022-08-13T15:54:58.065983Z","shell.execute_reply":"2022-08-13T15:55:01.150514Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"f1=x_trans[:,0]\nf2=x_trans[:,1]\n","metadata":{"execution":{"iopub.status.busy":"2022-08-13T15:54:14.669267Z","iopub.execute_input":"2022-08-13T15:54:14.669644Z","iopub.status.idle":"2022-08-13T15:54:14.675023Z","shell.execute_reply.started":"2022-08-13T15:54:14.669611Z","shell.execute_reply":"2022-08-13T15:54:14.673770Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nplt.scatter(f1[(label==0) & (nan==False)],f2[(label==0) & (nan==False)])\nplt.scatter(f1[(label==0) & (nan==True)],f2[(label==0) & (nan==True)])\n\n","metadata":{"execution":{"iopub.status.busy":"2022-08-13T15:55:01.926154Z","iopub.execute_input":"2022-08-13T15:55:01.926497Z","iopub.status.idle":"2022-08-13T15:55:02.149748Z","shell.execute_reply.started":"2022-08-13T15:55:01.926447Z","shell.execute_reply":"2022-08-13T15:55:02.148846Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.scatter(f1[(label==1) & (nan==False)],f2[(label==1) & (nan==False)])\nplt.scatter(f1[(label==1) & (nan==True)],f2[(label==1) & (nan==True)])","metadata":{"execution":{"iopub.status.busy":"2022-08-13T15:55:04.506969Z","iopub.execute_input":"2022-08-13T15:55:04.507868Z","iopub.status.idle":"2022-08-13T15:55:04.710271Z","shell.execute_reply.started":"2022-08-13T15:55:04.507834Z","shell.execute_reply":"2022-08-13T15:55:04.709397Z"},"trusted":true},"execution_count":null,"outputs":[]}]}