{"cells":[{"metadata":{},"cell_type":"markdown","source":"In [Just speed up calculate distance from Benchmark](https://www.kaggle.com/seriousran/just-speed-up-calculate-distance-from-benchmark) kernel by [Chanran Kim](https://www.kaggle.com/seriousran), <br/> a faster way to calculate distance is provided. <br/>\n\nHowever, the computation requires data preprocessing.  If we include data preprocessing then there is a way to gain about 2x speedup again.\n\nFrom\n> CPU times: user 10 s, sys: 8.75 s, total: 18.8 s\n> Wall time: 18.8 s\n\nTo\n\n> CPU times: user 6.43 s, sys: 2.82 s, total: 9.25 s\n> Wall time: 9.14 s"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nsns.set()\n\nimport os\nprint(os.listdir(\"../input\"))\n\nfrom sklearn.model_selection import GroupKFold\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.ensemble import RandomForestRegressor\n\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Calculate distance Chanran Kim way\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv', index_col='id')\ntest = pd.read_csv('../input/test.csv', index_col='id')\n\nstructures = pd.read_csv('../input/structures.csv')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n# This block is SPPED UP\n\ndef map_atom_info(df, atom_idx):\n    df = pd.merge(df, structures, how = 'left',\n                  left_on  = ['molecule_name', f'atom_index_{atom_idx}'],\n                  right_on = ['molecule_name',  'atom_index'])\n    \n    df = df.drop('atom_index', axis=1)\n    df = df.rename(columns={'atom': f'atom_{atom_idx}',\n                            'x': f'x_{atom_idx}',\n                            'y': f'y_{atom_idx}',\n                            'z': f'z_{atom_idx}'})\n    return df\n\ntrain = map_atom_info(train, 0)\ntrain = map_atom_info(train, 1)\n\ntest = map_atom_info(test, 0)\ntest = map_atom_info(test, 1)\n\ntrain_p_0 = train[['x_0', 'y_0', 'z_0']].values\ntrain_p_1 = train[['x_1', 'y_1', 'z_1']].values\ntest_p_0 = test[['x_0', 'y_0', 'z_0']].values\ntest_p_1 = test[['x_1', 'y_1', 'z_1']].values\n\ntrain['dist_speedup'] = np.linalg.norm(train_p_0 - train_p_1, axis=1)\ntest['dist_speedup'] = np.linalg.norm(test_p_0 - test_p_1, axis=1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Calculate distance via faster method"},{"metadata":{},"cell_type":"markdown","source":"Let's reload data to ensure fair comparison"},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv', index_col='id')\ntest = pd.read_csv('../input/test.csv', index_col='id')\n\nstructures = pd.read_csv('../input/structures.csv')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n# This block is SPPED UP\ndef add_dist(train, structures=structures):\n    dist = (train[['molecule_name', 'atom_index_0']].merge(structures, how='left', \n                    left_on=['molecule_name', 'atom_index_0'], \n                    right_on=['molecule_name', 'atom_index'])[['x', 'y', 'z'] ]\n        -\n        train[['molecule_name', 'atom_index_1']].merge(structures, how='left', \n                    left_on=['molecule_name', 'atom_index_1'], \n                    right_on=['molecule_name', 'atom_index'])[['x', 'y', 'z'] ]\n       )\n    train['dist_speed'] = np.linalg.norm(dist, axis=1)\n    \nadd_dist(train)\nadd_dist(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"markdown","source":"It is always possible to improve code efficiency ;)"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}