{"cells":[{"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 matplotlib.colors as colors\nimport matplotlib.cm as cmx\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\ntrain = 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\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)","execution_count":26,"outputs":[{"output_type":"stream","text":"['potential_energy.csv', 'mulliken_charges.csv', 'train.csv', 'scalar_coupling_contributions.csv', 'sample_submission.csv', 'structures', 'test.csv', 'magnetic_shielding_tensors.csv', 'dipole_moments.csv', 'structures.csv']\n","name":"stdout"},{"output_type":"stream","text":"/opt/conda/lib/python3.6/site-packages/numpy/lib/arraysetops.py:569: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison\n mask |= (ar1 == a)\n","name":"stderr"}]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"%%time\n# This block is SPPED UP\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":27,"outputs":[{"output_type":"stream","text":"CPU times: user 352 ms, sys: 140 ms, total: 492 ms\nWall time: 486 ms\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head(5)","execution_count":28,"outputs":[{"output_type":"execute_result","execution_count":28,"data":{"text/plain":" molecule_name atom_index_0 ... z_1 dist_speedup\n0 dsgdb9nsd_000001 1 ... 0.008001 1.091953\n1 dsgdb9nsd_000001 1 ... 0.000277 1.783120\n2 dsgdb9nsd_000001 1 ... -0.876644 1.783147\n3 dsgdb9nsd_000001 1 ... 0.906397 1.783157\n4 dsgdb9nsd_000001 2 ... 0.008001 1.091952\n\n[5 rows x 14 columns]","text/html":"\n\n
\n \n \n | \n molecule_name | \n atom_index_0 | \n atom_index_1 | \n type | \n scalar_coupling_constant | \n atom_0 | \n x_0 | \n y_0 | \n z_0 | \n atom_1 | \n x_1 | \n y_1 | \n z_1 | \n dist_speedup | \n
\n \n \n \n | 0 | \n dsgdb9nsd_000001 | \n 1 | \n 0 | \n 1JHC | \n 84.8076 | \n H | \n 0.002150 | \n -0.006031 | \n 0.001976 | \n C | \n -0.012698 | \n 1.085804 | \n 0.008001 | \n 1.091953 | \n
\n \n | 1 | \n dsgdb9nsd_000001 | \n 1 | \n 2 | \n 2JHH | \n -11.2570 | \n H | \n 0.002150 | \n -0.006031 | \n 0.001976 | \n H | \n 1.011731 | \n 1.463751 | \n 0.000277 | \n 1.783120 | \n
\n \n | 2 | \n dsgdb9nsd_000001 | \n 1 | \n 3 | \n 2JHH | \n -11.2548 | \n H | \n 0.002150 | \n -0.006031 | \n 0.001976 | \n H | \n -0.540815 | \n 1.447527 | \n -0.876644 | \n 1.783147 | \n
\n \n | 3 | \n dsgdb9nsd_000001 | \n 1 | \n 4 | \n 2JHH | \n -11.2543 | \n H | \n 0.002150 | \n -0.006031 | \n 0.001976 | \n H | \n -0.523814 | \n 1.437933 | \n 0.906397 | \n 1.783157 | \n
\n \n | 4 | \n dsgdb9nsd_000001 | \n 2 | \n 0 | \n 1JHC | \n 84.8074 | \n H | \n 1.011731 | \n 1.463751 | \n 0.000277 | \n C | \n -0.012698 | \n 1.085804 | \n 0.008001 | \n 1.091952 | \n
\n \n
\n