{"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":"2022-07-08T19:32:37.012237Z","iopub.execute_input":"2022-07-08T19:32:37.013284Z","iopub.status.idle":"2022-07-08T19:32:37.023612Z","shell.execute_reply.started":"2022-07-08T19:32:37.013247Z","shell.execute_reply":"2022-07-08T19:32:37.022596Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# KMeans with CUDA ML - Rapids💯","metadata":{}},{"cell_type":"markdown","source":"### Install CUDA ML","metadata":{}},{"cell_type":"code","source":"!pip install cuml","metadata":{"execution":{"iopub.status.busy":"2022-07-08T19:32:37.026961Z","iopub.execute_input":"2022-07-08T19:32:37.027945Z","iopub.status.idle":"2022-07-08T19:32:46.663097Z","shell.execute_reply.started":"2022-07-08T19:32:37.027844Z","shell.execute_reply":"2022-07-08T19:32:46.661616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Import CUML KMeans and RobustScaler","metadata":{}},{"cell_type":"code","source":"from cuml.cluster import KMeans\nfrom cuml.preprocessing import RobustScaler\nimport cuml","metadata":{"execution":{"iopub.status.busy":"2022-07-08T19:32:46.666851Z","iopub.execute_input":"2022-07-08T19:32:46.667171Z","iopub.status.idle":"2022-07-08T19:32:46.67381Z","shell.execute_reply.started":"2022-07-08T19:32:46.667141Z","shell.execute_reply":"2022-07-08T19:32:46.6726Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Read the CSV","metadata":{}},{"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/tabular-playground-series-jul-2022/data.csv')","metadata":{"execution":{"iopub.status.busy":"2022-07-08T19:32:46.675217Z","iopub.execute_input":"2022-07-08T19:32:46.675831Z","iopub.status.idle":"2022-07-08T19:32:47.197996Z","shell.execute_reply.started":"2022-07-08T19:32:46.675794Z","shell.execute_reply":"2022-07-08T19:32:47.196717Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Transform the Data with Robust Scaler","metadata":{}},{"cell_type":"code","source":"X_scaled = RobustScaler().fit(df).transform(df)\nX_scaled = pd.DataFrame(X_scaled)","metadata":{"execution":{"iopub.status.busy":"2022-07-08T19:32:47.201331Z","iopub.execute_input":"2022-07-08T19:32:47.202161Z","iopub.status.idle":"2022-07-08T19:32:47.333086Z","shell.execute_reply.started":"2022-07-08T19:32:47.202116Z","shell.execute_reply":"2022-07-08T19:32:47.332065Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### The Model KMeans with CUML","metadata":{}},{"cell_type":"code","source":"kmeans = KMeans(n_clusters=7,random_state=0)","metadata":{"execution":{"iopub.status.busy":"2022-07-08T19:32:47.334988Z","iopub.execute_input":"2022-07-08T19:32:47.335637Z","iopub.status.idle":"2022-07-08T19:32:47.340155Z","shell.execute_reply.started":"2022-07-08T19:32:47.335601Z","shell.execute_reply":"2022-07-08T19:32:47.339206Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"kmeans = kmeans.fit(X_scaled)","metadata":{"execution":{"iopub.status.busy":"2022-07-08T19:32:47.341736Z","iopub.execute_input":"2022-07-08T19:32:47.34249Z","iopub.status.idle":"2022-07-08T19:32:47.459602Z","shell.execute_reply.started":"2022-07-08T19:32:47.342453Z","shell.execute_reply":"2022-07-08T19:32:47.458653Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"kmeans.labels_","metadata":{"execution":{"iopub.status.busy":"2022-07-08T19:32:47.461109Z","iopub.execute_input":"2022-07-08T19:32:47.461521Z","iopub.status.idle":"2022-07-08T19:32:47.469042Z","shell.execute_reply.started":"2022-07-08T19:32:47.461481Z","shell.execute_reply":"2022-07-08T19:32:47.467986Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Submission","metadata":{}},{"cell_type":"code","source":"sub = pd.DataFrame()\nsub['id'] = df['id']\nsub['Predicted'] = kmeans.labels_","metadata":{"execution":{"iopub.status.busy":"2022-07-08T19:32:47.470589Z","iopub.execute_input":"2022-07-08T19:32:47.471299Z","iopub.status.idle":"2022-07-08T19:32:47.493944Z","shell.execute_reply.started":"2022-07-08T19:32:47.47126Z","shell.execute_reply":"2022-07-08T19:32:47.493073Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2022-07-08T19:32:47.495839Z","iopub.execute_input":"2022-07-08T19:32:47.497221Z","iopub.status.idle":"2022-07-08T19:32:47.645146Z","shell.execute_reply.started":"2022-07-08T19:32:47.497186Z","shell.execute_reply":"2022-07-08T19:32:47.644114Z"},"trusted":true},"execution_count":null,"outputs":[]}]}