{"cells":[{"metadata":{},"cell_type":"markdown","source":"### My manual realisation of One_hot_vector for \"primary_usage\""},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nimport time\n\n\nbld_df = pd.read_csv('/kaggle/input/ashrae-energy-prediction/building_metadata.csv', index_col = 'building_id')\nbld_df.head()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"t_point_1 = time.time()\n\nusage_columns = {i:(s[:3], s) for i,s in enumerate(set(bld_df['primary_use']))}\n# {0: ('Off', 'Office'), 1: ('War', 'Warehouse/storage')...\n\nusage_columns_dict = {v[1]:i for i, v in usage_columns.items()}\n# {'Office': 0, 'Warehouse/storage': 1, 'Religious worship':2,...\n\nshape_usage = (bld_df.shape[0],len(set(bld_df['primary_use'])))\n# = (length of bld_df, num of categories) = (1449, 16)\n\nusage_matrix = np.zeros(shape_usage, dtype = np.int8)\n\nj = range(bld_df.shape[0])\ni = list(bld_df['primary_use'].map(usage_columns_dict))\nusage_matrix[j, i] = 1\n\nprimari_use_df = pd.DataFrame(usage_matrix, index = bld_df.index, columns = [v[0] for k,v in usage_columns.items()])\n\n\nprint(f'     -----> done: {time.time()-t_point_1:0.3f} s')\n\nbld_df.merge(primari_use_df, left_index = True, right_index = True)","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":1}