{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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)\nimport seaborn as sns\nimport matplotlib.pyplot as plt\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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"data_train= pd.read_csv('/kaggle/input/cat-in-the-dat-ii/train.csv')\ndata_test = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/test.csv')\ndata_test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\ndata_train.loc[:,'ord_2']=data_train.ord_2.fillna(\"NONE\")\nlbl=LabelEncoder()\ndata_train.loc[:,'ord_2']= lbl.fit_transform(data_train.ord_2.values)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_train.ord_2.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"exam=np.array([[0,0,1],[1,0,0],[1,0,1]])\nexam.nbytes\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from scipy import sparse\nsparse_mat = sparse.csr_matrix(exam)\nsparse_mat.data.nbytes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sparse_mat.indptr.nbytes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"exam= np.random.randint(1000,size=100000)\nfrom sklearn.preprocessing import OneHotEncoder\nohe= OneHotEncoder()\nohe_exam = ohe.fit_transform(exam.reshape(-1,1))\nprint(f\"Size of array:{exam.data.nbytes}\")\nprint(f\"Size of Sparse array:{ohe_exam.data.nbytes}\")\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}