{"cells":[{"metadata":{},"cell_type":"markdown","source":"Fork from **Andrew Lukyanenko**\n\nThis kernel is still a draft.\n\nUses OpenBabel API. \nIdea from https://www.kaggle.com/c/champs-scalar-coupling/discussion/93928#latest-546589\n\nWith Openbabel it's easy to navigate through bonds, so I added sp, 2J angle and 3J dihedral angle.\n\nSome basic info here https://yvesrubin.files.wordpress.com/2011/03/coupling-constants-for-1h-and-13c-nmr.pdf\n\nWhat to do next?\nIf you are a python fan, you certainly can improve my code!\n\nIf you are a chemist, you may extract more useful info from openbabel.\n\nif you aren in ML, extracting *everything* from openbabel and create a data file might work. I also did a learning for each bond, but not sure it's good."},{"metadata":{},"cell_type":"markdown","source":"## General information\n\nThis kernel is created using data of `Predicting Molecular Properties` competition.\nWe have information about atom couples in molecules and need to predict `scalar_coupling_constant` between these atoms.\n\n![](http://www.et.byu.edu/~rowley/VLEfinal/methane_dimer.gif)\n\nIn this kernel I'll do EDA and will try some approaches to modelling.\n\n*Work still in progress*\n\n\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls ../input/","execution_count":1,"outputs":[{"output_type":"stream","text":"dipole_moments.csv\t\tsample_submission.csv\t\t   test.csv\r\nmagnetic_shielding_tensors.csv\tscalar_coupling_contributions.csv  train.csv\r\nmulliken_charges.csv\t\tstructures\r\npotential_energy.csv\t\tstructures.csv\r\n","name":"stdout"}]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"!conda install -y -c openbabel openbabel \nimport openbabel\n","execution_count":2,"outputs":[{"output_type":"stream","text":"Collecting package metadata: done\nSolving environment: done\n\n## Package Plan ##\n\n  environment location: /opt/conda\n\n  added / updated specs:\n    - openbabel\n\n\nThe following packages will be downloaded:\n\n    package                    |            build\n    ---------------------------|-----------------\n    ca-certificates-2019.5.15  |                0         133 KB\n    libgcc-7.2.0               |       h69d50b8_2         304 KB\n    openbabel-2.4.1            |           py36_5         5.1 MB  openbabel\n    openssl-1.0.2s             |       h7b6447c_0         3.1 MB\n    ------------------------------------------------------------\n                                           Total:         8.7 MB\n\nThe following NEW packages will be INSTALLED:\n\n  libgcc             pkgs/main/linux-64::libgcc-7.2.0-h69d50b8_2\n  openbabel          openbabel/linux-64::openbabel-2.4.1-py36_5\n\nThe following packages will be UPDATED:\n\n  ca-certificates                               2019.1.23-0 --> 2019.5.15-0\n  openssl                                 1.0.2r-h7b6447c_0 --> 1.0.2s-h7b6447c_0\n\n\n\nDownloading and Extracting Packages\nlibgcc-7.2.0         | 304 KB    | ##################################### | 100% \nopenbabel-2.4.1      | 5.1 MB    | ##################################### | 100% \nopenssl-1.0.2s       | 3.1 MB    | ##################################### | 100% \nca-certificates-2019 | 133 KB    | ##################################### | 100% \nPreparing transaction: done\nVerifying transaction: done\nExecuting transaction: done\n","name":"stdout"}]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"#!rm -r /opt/conda/lib/python3.6/site-packages/lightgbm\n#!git clone --recursive https://github.com/Microsoft/LightGBM\n#!apt-get install -y -qq libboost-all-dev    ","execution_count":3,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"#%%bash\n#cd LightGBM\n#rm -r build\n#mkdir build\n#cd build\n#cmake -DUSE_GPU=1 -DOpenCL_LIBRARY=/usr/local/cuda/lib64/libOpenCL.so -DOpenCL_INCLUDE_DIR=/usr/local/cuda/include/ ..\n#make -j$(nproc)","execution_count":4,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"#!cd LightGBM/python-package/;python3 setup.py install --precompile","execution_count":5,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"#!mkdir -p /etc/OpenCL/vendors && echo \"libnvidia-opencl.so.1\" > /etc/OpenCL/vendors/nvidia.icd\n#!rm -r LightGBM","execution_count":6,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"importing libraries"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\n\nimport matplotlib.pyplot as plt\n%matplotlib inline\nfrom tqdm import tqdm_notebook\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import NuSVR, SVR\nfrom sklearn.metrics import mean_absolute_error\npd.options.display.precision = 15\n\nimport lightgbm as lgb\nimport xgboost as xgb\nimport time\nimport datetime\nfrom catboost import CatBoostRegressor\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.model_selection import StratifiedKFold, KFold, RepeatedKFold\nfrom sklearn import metrics\nfrom sklearn import linear_model\nimport gc\nimport seaborn as sns\nimport warnings\nwarnings.filterwarnings(\"ignore\")\n\nfrom IPython.display import HTML\nimport json\nimport altair as alt\n\nimport networkx as nx\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nalt.renderers.enable('notebook')\n\nos.environ[\"TZ\"]=\"Europe/Paris\"\ntime.tzset()","execution_count":7,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# from https://www.kaggle.com/artgor/artgor-utils\ndef reduce_mem_usage(df, verbose=True):\n    numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']\n    start_mem = df.memory_usage().sum() / 1024**2    \n    for col in df.columns:\n        col_type = df[col].dtypes\n        if col_type in numerics:\n            c_min = df[col].min()\n            c_max = df[col].max()\n            if str(col_type)[:3] == 'int':\n                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n                    df[col] = df[col].astype(np.int8)\n                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n                    df[col] = df[col].astype(np.int16)\n                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n                    df[col] = df[col].astype(np.int32)\n                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n                    df[col] = df[col].astype(np.int64)  \n            else:\n                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n                    df[col] = df[col].astype(np.float16)\n                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n                    df[col] = df[col].astype(np.float32)\n                else:\n                    df[col] = df[col].astype(np.float64)    \n    end_mem = df.memory_usage().sum() / 1024**2\n    if verbose: print('Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction)'.format(end_mem, 100 * (start_mem - end_mem) / start_mem))\n    return df\n    \n","execution_count":8,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data loading and overview"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv')\ntest = pd.read_csv('../input/test.csv')\nsub = pd.read_csv('../input/sample_submission.csv')","execution_count":9,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(f'There are {train.shape[0]} rows in train data.')\nprint(f'There are {test.shape[0]} rows in test data.')\n\nprint(f\"There are {train['molecule_name'].nunique()} distinct molecules in train data.\")\nprint(f\"There are {test['molecule_name'].nunique()} distinct molecules in test data.\")\nprint(f\"There are {train['atom_index_0'].nunique()} unique atoms.\")\nprint(f\"There are {train['type'].nunique()} unique types.\")","execution_count":10,"outputs":[{"output_type":"stream","text":"There are 4658147 rows in train data.\nThere are 2505542 rows in test data.\nThere are 85003 distinct molecules in train data.\nThere are 45772 distinct molecules in test data.\nThere are 29 unique atoms.\nThere are 8 unique types.\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":11,"outputs":[{"output_type":"execute_result","execution_count":11,"data":{"text/plain":"   id           ...            scalar_coupling_constant\n0   0           ...                  84.807599999999994\n1   1           ...                 -11.257000000000000\n2   2           ...                 -11.254799999999999\n3   3           ...                 -11.254300000000001\n4   4           ...                  84.807400000000001\n\n[5 rows x 6 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>id</th>\n      <th>molecule_name</th>\n      <th>atom_index_0</th>\n      <th>atom_index_1</th>\n      <th>type</th>\n      <th>scalar_coupling_constant</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1JHC</td>\n      <td>84.807599999999994</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>2</td>\n      <td>2JHH</td>\n      <td>-11.257000000000000</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>3</td>\n      <td>2JHH</td>\n      <td>-11.254799999999999</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>4</td>\n      <td>2JHH</td>\n      <td>-11.254300000000001</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>2</td>\n      <td>0</td>\n      <td>1JHC</td>\n      <td>84.807400000000001</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"So in out main data files we have information about moleculas and pairs of atoms\n- test set in ~2 times smaller that train set;\n- we have 29 unique atoms types and 8 coupling types;"},{"metadata":{"trusted":true},"cell_type":"code","source":"train.describe()","execution_count":12,"outputs":[{"output_type":"execute_result","execution_count":12,"data":{"text/plain":"                          id            ...             scalar_coupling_constant\ncount  4.658147000000000e+06            ...                4.658147000000000e+06\nmean   2.329073000000000e+06            ...                1.592164991825936e+01\nstd    1.344691356527209e+06            ...                3.494197741570011e+01\nmin    0.000000000000000e+00            ...               -3.621860000000000e+01\n25%    1.164536500000000e+06            ...               -2.549780000000000e-01\n50%    2.329073000000000e+06            ...                2.281130000000000e+00\n75%    3.493609500000000e+06            ...                7.390655000000000e+00\nmax    4.658146000000000e+06            ...                2.048800000000000e+02\n\n[8 rows x 4 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>id</th>\n      <th>atom_index_0</th>\n      <th>atom_index_1</th>\n      <th>scalar_coupling_constant</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>4.658147000000000e+06</td>\n      <td>4.658147000000000e+06</td>\n      <td>4.658147000000000e+06</td>\n      <td>4.658147000000000e+06</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>2.329073000000000e+06</td>\n      <td>1.335688568866547e+01</td>\n      <td>5.883966306773917e+00</td>\n      <td>1.592164991825936e+01</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>1.344691356527209e+06</td>\n      <td>3.267712409449629e+00</td>\n      <td>4.993943098105586e+00</td>\n      <td>3.494197741570011e+01</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>0.000000000000000e+00</td>\n      <td>0.000000000000000e+00</td>\n      <td>0.000000000000000e+00</td>\n      <td>-3.621860000000000e+01</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>1.164536500000000e+06</td>\n      <td>1.100000000000000e+01</td>\n      <td>2.000000000000000e+00</td>\n      <td>-2.549780000000000e-01</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>2.329073000000000e+06</td>\n      <td>1.300000000000000e+01</td>\n      <td>5.000000000000000e+00</td>\n      <td>2.281130000000000e+00</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>3.493609500000000e+06</td>\n      <td>1.600000000000000e+01</td>\n      <td>8.000000000000000e+00</td>\n      <td>7.390655000000000e+00</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>4.658146000000000e+06</td>\n      <td>2.800000000000000e+01</td>\n      <td>2.800000000000000e+01</td>\n      <td>2.048800000000000e+02</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"atom_count = train['atom_index_0'].value_counts().reset_index().rename(columns={'atom_index_0': 'count', 'index': 'atom_index_0'})\nchart1 = alt.Chart(atom_count).mark_bar().encode(\n    x=alt.X(\"atom_index_0:N\", axis=alt.Axis(title='atom_index_0')),\n    y=alt.Y('count:Q', axis=alt.Axis(title='Count')),\n    tooltip=['atom_index_0', 'count']\n).properties(title=\"Counts of atom_index_0\", width=350).interactive()\n\natom_count = train['atom_index_1'].value_counts().reset_index().rename(columns={'atom_index_1': 'count', 'index': 'atom_index_1'})\nchart2 = alt.Chart(atom_count).mark_bar().encode(\n    x=alt.X(\"atom_index_1:N\", axis=alt.Axis(title='atom_index_1')),\n    y=alt.Y('count:Q', axis=alt.Axis(title='Count')),\n    tooltip=['atom_index_1', 'count']\n).properties(title=\"Counts of atom_index_1\", width=350).interactive()\n\ntype_count = train['type'].value_counts().reset_index().rename(columns={'type': 'count', 'index': 'type'})\nchart3 = alt.Chart(type_count).mark_bar().encode(\n    x=alt.X(\"type:N\", axis=alt.Axis(title='type')),\n    y=alt.Y('count:Q', axis=alt.Axis(title='Count')),\n    tooltip=['type', 'count']\n).properties(title=\"Counts of type\", width=350).interactive()\n\nhist_df = pd.cut(train['scalar_coupling_constant'], 20).value_counts().sort_index().reset_index().rename(columns={'index': 'bins'})\nhist_df['bins'] = hist_df['bins'].astype(str)\nchart4 = alt.Chart(hist_df).mark_bar().encode(\n    x=alt.X(\"bins:O\", axis=alt.Axis(title='Target bins')),\n    y=alt.Y('scalar_coupling_constant:Q', axis=alt.Axis(title='Count')),\n    tooltip=['scalar_coupling_constant', 'bins']\n).properties(title=\"scalar_coupling_constant histogram\", width=400).interactive()\n\n\n(chart1 | chart2) & (chart3 | chart4)","execution_count":13,"outputs":[{"output_type":"display_data","data":{"text/html":"<div class=\"vega-embed\" id=\"93d525d3-7454-458e-a0c8-20cf2d47fa89\"></div>\n\n<style>\n.vega-embed .vega-actions > a {\n    transition: opacity 200ms ease-in;\n    opacity: 0.3;\n    margin-right: 0.6em;\n    color: #444;\n    text-decoration: none;\n}\n\n.vega-embed .vega-actions > a:hover {\n    color: #000;\n    text-decoration: underline;\n}\n\n.vega-embed:hover .vega-actions > a {\n    opacity: 1;\n    transition: 0s;\n}\n\n.vega-embed .error p {\n    color: firebrick;\n    font-size: 1.2em;\n}\n</style>\n"},"metadata":{"jupyter-vega3":"#93d525d3-7454-458e-a0c8-20cf2d47fa89"}},{"output_type":"display_data","data":{"application/javascript":"var spec = {\"config\": {\"view\": {\"width\": 400, \"height\": 300}}, \"vconcat\": [{\"hconcat\": [{\"data\": {\"name\": \"data-bd650d94dea89e9b7debcb25ac305b73\"}, \"mark\": \"bar\", \"encoding\": {\"tooltip\": [{\"type\": \"quantitative\", \"field\": \"atom_index_0\"}, {\"type\": \"quantitative\", \"field\": \"count\"}], \"x\": {\"type\": \"nominal\", \"axis\": {\"title\": \"atom_index_0\"}, \"field\": \"atom_index_0\"}, \"y\": {\"type\": \"quantitative\", \"axis\": {\"title\": \"Count\"}, \"field\": \"count\"}}, \"selection\": {\"selector001\": {\"type\": \"interval\", \"bind\": \"scales\", \"encodings\": [\"x\", \"y\"]}}, \"title\": \"Counts of atom_index_0\", \"width\": 350}, {\"data\": {\"name\": \"data-dc52daaae98aba4f767be711bfd461c0\"}, \"mark\": \"bar\", \"encoding\": {\"tooltip\": [{\"type\": \"quantitative\", \"field\": \"atom_index_1\"}, {\"type\": \"quantitative\", \"field\": \"count\"}], \"x\": {\"type\": \"nominal\", \"axis\": {\"title\": \"atom_index_1\"}, \"field\": \"atom_index_1\"}, \"y\": {\"type\": \"quantitative\", \"axis\": {\"title\": \"Count\"}, \"field\": \"count\"}}, \"selection\": {\"selector002\": {\"type\": \"interval\", \"bind\": \"scales\", \"encodings\": [\"x\", \"y\"]}}, \"title\": \"Counts of atom_index_1\", \"width\": 350}]}, {\"hconcat\": [{\"data\": {\"name\": \"data-ebdc32f1be979a9c6ddbf0cea0b853fe\"}, \"mark\": \"bar\", \"encoding\": {\"tooltip\": [{\"type\": \"nominal\", \"field\": \"type\"}, {\"type\": \"quantitative\", \"field\": \"count\"}], \"x\": {\"type\": \"nominal\", \"axis\": {\"title\": \"type\"}, \"field\": \"type\"}, \"y\": {\"type\": \"quantitative\", \"axis\": {\"title\": \"Count\"}, \"field\": \"count\"}}, \"selection\": {\"selector003\": {\"type\": \"interval\", \"bind\": \"scales\", \"encodings\": [\"x\", \"y\"]}}, \"title\": \"Counts of type\", \"width\": 350}, {\"data\": {\"name\": \"data-49f16c2b497caf509825d63ea0302313\"}, \"mark\": \"bar\", \"encoding\": {\"tooltip\": [{\"type\": \"quantitative\", \"field\": \"scalar_coupling_constant\"}, {\"type\": \"nominal\", \"field\": \"bins\"}], \"x\": {\"type\": \"ordinal\", \"axis\": {\"title\": \"Target bins\"}, \"field\": \"bins\"}, \"y\": {\"type\": \"quantitative\", \"axis\": {\"title\": \"Count\"}, \"field\": \"scalar_coupling_constant\"}}, \"selection\": {\"selector004\": {\"type\": \"interval\", \"bind\": \"scales\", \"encodings\": [\"x\", \"y\"]}}, \"title\": \"scalar_coupling_constant histogram\", \"width\": 400}]}], \"$schema\": \"https://vega.github.io/schema/vega-lite/v2.6.0.json\", \"datasets\": {\"data-bd650d94dea89e9b7debcb25ac305b73\": [{\"atom_index_0\": 12, \"count\": 552263}, {\"atom_index_0\": 13, \"count\": 505229}, {\"atom_index_0\": 9, \"count\": 485891}, {\"atom_index_0\": 14, \"count\": 476556}, {\"atom_index_0\": 10, \"count\": 473624}, {\"atom_index_0\": 11, \"count\": 446131}, {\"atom_index_0\": 15, \"count\": 422173}, {\"atom_index_0\": 16, \"count\": 360001}, {\"atom_index_0\": 17, \"count\": 285575}, {\"atom_index_0\": 18, \"count\": 212841}, {\"atom_index_0\": 19, \"count\": 143722}, {\"atom_index_0\": 20, \"count\": 94149}, {\"atom_index_0\": 8, \"count\": 80296}, {\"atom_index_0\": 21, \"count\": 48795}, {\"atom_index_0\": 22, \"count\": 30594}, {\"atom_index_0\": 7, \"count\": 14104}, {\"atom_index_0\": 23, \"count\": 10245}, {\"atom_index_0\": 24, \"count\": 7108}, {\"atom_index_0\": 6, \"count\": 2825}, {\"atom_index_0\": 25, \"count\": 1439}, {\"atom_index_0\": 26, \"count\": 1050}, {\"atom_index_0\": 5, \"count\": 985}, {\"atom_index_0\": 3, \"count\": 829}, {\"atom_index_0\": 2, \"count\": 651}, {\"atom_index_0\": 4, \"count\": 635}, {\"atom_index_0\": 1, \"count\": 225}, {\"atom_index_0\": 27, \"count\": 116}, {\"atom_index_0\": 28, \"count\": 92}, {\"atom_index_0\": 0, \"count\": 3}], \"data-dc52daaae98aba4f767be711bfd461c0\": [{\"atom_index_1\": 2, \"count\": 537311}, {\"atom_index_1\": 1, \"count\": 517218}, {\"atom_index_1\": 3, \"count\": 458480}, {\"atom_index_1\": 4, \"count\": 439876}, {\"atom_index_1\": 5, \"count\": 415448}, {\"atom_index_1\": 6, \"count\": 392783}, {\"atom_index_1\": 7, \"count\": 359545}, {\"atom_index_1\": 0, \"count\": 322761}, {\"atom_index_1\": 8, \"count\": 248731}, {\"atom_index_1\": 11, \"count\": 136544}, {\"atom_index_1\": 12, \"count\": 117024}, {\"atom_index_1\": 13, \"count\": 108353}, {\"atom_index_1\": 14, \"count\": 95001}, {\"atom_index_1\": 15, \"count\": 89218}, {\"atom_index_1\": 10, \"count\": 85942}, {\"atom_index_1\": 16, \"count\": 81188}, {\"atom_index_1\": 17, \"count\": 70360}, {\"atom_index_1\": 18, \"count\": 57310}, {\"atom_index_1\": 19, \"count\": 41672}, {\"atom_index_1\": 20, \"count\": 30523}, {\"atom_index_1\": 21, \"count\": 16680}, {\"atom_index_1\": 9, \"count\": 14834}, {\"atom_index_1\": 22, \"count\": 12414}, {\"atom_index_1\": 23, \"count\": 4058}, {\"atom_index_1\": 24, \"count\": 3520}, {\"atom_index_1\": 26, \"count\": 629}, {\"atom_index_1\": 25, \"count\": 596}, {\"atom_index_1\": 28, \"count\": 76}, {\"atom_index_1\": 27, \"count\": 52}], \"data-ebdc32f1be979a9c6ddbf0cea0b853fe\": [{\"type\": \"3JHC\", \"count\": 1510379}, {\"type\": \"2JHC\", \"count\": 1140674}, {\"type\": \"1JHC\", \"count\": 709416}, {\"type\": \"3JHH\", \"count\": 590611}, {\"type\": \"2JHH\", \"count\": 378036}, {\"type\": \"3JHN\", \"count\": 166415}, {\"type\": \"2JHN\", \"count\": 119253}, {\"type\": \"1JHN\", \"count\": 43363}], \"data-49f16c2b497caf509825d63ea0302313\": [{\"bins\": \"(-36.46, -24.164]\", \"scalar_coupling_constant\": 92}, {\"bins\": \"(-24.164, -12.109]\", \"scalar_coupling_constant\": 88965}, {\"bins\": \"(-12.109, -0.0538]\", \"scalar_coupling_constant\": 1171006}, {\"bins\": \"(-0.0538, 12.001]\", \"scalar_coupling_constant\": 2572510}, {\"bins\": \"(12.001, 24.056]\", \"scalar_coupling_constant\": 64140}, {\"bins\": \"(24.056, 36.111]\", \"scalar_coupling_constant\": 18227}, {\"bins\": \"(36.111, 48.166]\", \"scalar_coupling_constant\": 12397}, {\"bins\": \"(48.166, 60.221]\", \"scalar_coupling_constant\": 16153}, {\"bins\": \"(60.221, 72.276]\", \"scalar_coupling_constant\": 5657}, {\"bins\": \"(72.276, 84.331]\", \"scalar_coupling_constant\": 192254}, {\"bins\": \"(84.331, 96.386]\", \"scalar_coupling_constant\": 312829}, {\"bins\": \"(96.386, 108.441]\", \"scalar_coupling_constant\": 76866}, {\"bins\": \"(108.441, 120.495]\", \"scalar_coupling_constant\": 67526}, {\"bins\": \"(120.495, 132.55]\", \"scalar_coupling_constant\": 36547}, {\"bins\": \"(132.55, 144.605]\", \"scalar_coupling_constant\": 12719}, {\"bins\": \"(144.605, 156.66]\", \"scalar_coupling_constant\": 969}, {\"bins\": \"(156.66, 168.715]\", \"scalar_coupling_constant\": 29}, {\"bins\": \"(168.715, 180.77]\", \"scalar_coupling_constant\": 1}, {\"bins\": \"(180.77, 192.825]\", \"scalar_coupling_constant\": 640}, {\"bins\": \"(192.825, 204.88]\", \"scalar_coupling_constant\": 8620}]}};\nvar opt = {};\nvar selector = \"#93d525d3-7454-458e-a0c8-20cf2d47fa89\";\nvar type = \"vega-lite\";\n\nvar output_area = this;\n\nrequire(['nbextensions/jupyter-vega3/index'], function(vega) {\n  vega.render(selector, spec, type, opt, output_area);\n}, function (err) {\n  if (err.requireType !== 'scripterror') {\n    throw(err);\n  }\n});\n"},"metadata":{"jupyter-vega3":"#93d525d3-7454-458e-a0c8-20cf2d47fa89"}},{"output_type":"execute_result","execution_count":13,"data":{"text/plain":""},"metadata":{}},{"data":{"image/png":"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"},"metadata":{"jupyter-vega3":"#93d525d3-7454-458e-a0c8-20cf2d47fa89"},"output_type":"display_data"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize = (18, 8))\nplt.subplot(1, 2, 1);\nplt.hist(train['scalar_coupling_constant'], bins=20);\nplt.title('Basic scalar_coupling_constant histogram');\nplt.subplot(1, 2, 2);\nsns.violinplot(x='type', y='scalar_coupling_constant', data=train);\nplt.title('Violinplot of scalar_coupling_constant by type');","execution_count":14,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1296x576 with 2 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"There are many interesting things here:\n- among first atoms there is a little number of atoms with index lower than 7 or higher than 24;\n- among second atoms there is a little number of atoms with index higher than 24. Also index with atom with index 9 in quite rare;\n- coupling types are unevenly distributed. There are 3 very popular, 3 quite rare and 2 with medium frequency;\n- target variable has a bimodal distribution;\n- different coupling types have really different values of target variable. Maybe it would make sense to build separate models for each of them;"},{"metadata":{},"cell_type":"markdown","source":"## Plotting network graphs by type\n\nWe have molecules, atom pairs, so this means data, which is interconnected. Network graphs should be useful to visualize such data!"},{"metadata":{},"cell_type":"markdown","source":"## Better network graphs\nBut there is a little problem: as we saw earlier, there are atoms which are very rare, as a result graphs will be skewed due to them. Now I'll drop atoms for each type which are present in less then 1% of connections"},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize = (20, 12))\nfor i, t in enumerate(train['type'].unique()):\n    train_type = train.loc[train['type'] == t]\n    bad_atoms_0 = list(train_type['atom_index_0'].value_counts(normalize=True)[train_type['atom_index_0'].value_counts(normalize=True) < 0.01].index)\n    bad_atoms_1 = list(train_type['atom_index_1'].value_counts(normalize=True)[train_type['atom_index_1'].value_counts(normalize=True) < 0.01].index)\n    bad_atoms = list(set(bad_atoms_0 + bad_atoms_1))\n    train_type = train_type.loc[(train_type['atom_index_0'].isin(bad_atoms_0) == False) & (train_type['atom_index_1'].isin(bad_atoms_0) == False)]\n    G = nx.from_pandas_edgelist(train_type, 'atom_index_0', 'atom_index_1', ['scalar_coupling_constant'])\n    plt.subplot(2, 4, i + 1);\n    nx.draw(G, with_labels=True);\n    plt.title(f'Graph for type {t}')","execution_count":15,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1440x864 with 8 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"Now the graphs are much more clear!"},{"metadata":{},"cell_type":"markdown","source":"## Feature engineering\n\nFor now I'll use a basic approach to feature engineering.\n\nI'll use this useful kernel:\nhttps://www.kaggle.com/seriousran/just-speed-up-calculate-distance-from-benchmark"},{"metadata":{"trusted":true},"cell_type":"code","source":"structures = 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)\n\natom_count=structures.groupby(['molecule_name','atom']).size().unstack(fill_value=0)\ntrain=pd.merge(train,atom_count, how = 'left', left_on  = 'molecule_name', right_on = 'molecule_name')\ntest=pd.merge(test,atom_count, how = 'left', left_on  = 'molecule_name', right_on = 'molecule_name')","execution_count":16,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":17,"outputs":[{"output_type":"execute_result","execution_count":17,"data":{"text/plain":"   id     molecule_name  atom_index_0  atom_index_1  type ...  C  F  H  N  O\n0   0  dsgdb9nsd_000001             1             0  1JHC ...  1  0  4  0  0\n1   1  dsgdb9nsd_000001             1             2  2JHH ...  1  0  4  0  0\n2   2  dsgdb9nsd_000001             1             3  2JHH ...  1  0  4  0  0\n3   3  dsgdb9nsd_000001             1             4  2JHH ...  1  0  4  0  0\n4   4  dsgdb9nsd_000001             2             0  1JHC ...  1  0  4  0  0\n\n[5 rows x 19 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>id</th>\n      <th>molecule_name</th>\n      <th>atom_index_0</th>\n      <th>atom_index_1</th>\n      <th>type</th>\n      <th>scalar_coupling_constant</th>\n      <th>atom_0</th>\n      <th>x_0</th>\n      <th>y_0</th>\n      <th>z_0</th>\n      <th>atom_1</th>\n      <th>x_1</th>\n      <th>y_1</th>\n      <th>z_1</th>\n      <th>C</th>\n      <th>F</th>\n      <th>H</th>\n      <th>N</th>\n      <th>O</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1JHC</td>\n      <td>84.807599999999994</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>C</td>\n      <td>-0.0126981359</td>\n      <td>1.085804158</td>\n      <td>0.0080009958</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>2</td>\n      <td>2JHH</td>\n      <td>-11.257000000000000</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>H</td>\n      <td>1.0117308430</td>\n      <td>1.463751162</td>\n      <td>0.0002765748</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>3</td>\n      <td>2JHH</td>\n      <td>-11.254799999999999</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>H</td>\n      <td>-0.5408150690</td>\n      <td>1.447526614</td>\n      <td>-0.8766437152</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>4</td>\n      <td>2JHH</td>\n      <td>-11.254300000000001</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>H</td>\n      <td>-0.5238136345</td>\n      <td>1.437932644</td>\n      <td>0.9063972942</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>2</td>\n      <td>0</td>\n      <td>1JHC</td>\n      <td>84.807400000000001</td>\n      <td>H</td>\n      <td>1.011730843</td>\n      <td>1.4637511620</td>\n      <td>0.0002765748</td>\n      <td>C</td>\n      <td>-0.0126981359</td>\n      <td>1.085804158</td>\n      <td>0.0080009958</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"**Creating mol reference with OpenBabel**"},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nobConversion = openbabel.OBConversion()\nobConversion.SetInFormat(\"xyz\")\n\nstructdir='../input/structures/'\nmols=[]\nmols_files=os.listdir(structdir)\nmols_index=dict(map(reversed,enumerate(mols_files)))\nfor f in mols_index.keys():\n    mol = openbabel.OBMol()\n    obConversion.ReadFile(mol, structdir+f) \n    mols.append(mol)\n    ","execution_count":18,"outputs":[{"output_type":"stream","text":"CPU times: user 57.8 s, sys: 20.4 s, total: 1min 18s\nWall time: 2min 34s\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"def Atoms(molname,AtomId1,AtomId2):\n    mol=mols[mols_index[molname+'.xyz']]\n    return mol, mol.GetAtomById(AtomId1), mol.GetAtomById(AtomId2)\n\ndef SecondAtom(bond,FirstAtom):\n    if FirstAtom.GetId()==bond.GetBeginAtom().GetId(): return bond.GetEndAtom()\n    else: return bond.GetBeginAtom()\n\ndef Angle2J(molname,AtomId1,AtomId2,debug=False):\n    mol,firstAtom,lastAtom=Atoms(molname,AtomId1,AtomId2)\n    if debug: print (mol.GetFormula())\n    if debug: print(firstAtom.GetType(),firstAtom.GetId(),':',lastAtom.GetType(),lastAtom.GetId())\n    for b in openbabel.OBAtomBondIter(firstAtom): # all bonds for first atom\n      secondAtom=SecondAtom(b,firstAtom)\n      lastBond=secondAtom.GetBond(lastAtom)\n      if lastBond: # found!\n        if debug: print('middle',secondAtom.GetId(),secondAtom.GetType())\n        return firstAtom.GetAngle(secondAtom,lastAtom)\n\nAngle2J('dsgdb9nsd_000003',1,2,debug=True) #water","execution_count":19,"outputs":[{"output_type":"stream","text":"H2O\nHO 1 : HO 2\nmiddle 0 O3\n","name":"stdout"},{"output_type":"execute_result","execution_count":19,"data":{"text/plain":"103.71576124592411"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"def Torsion3J(molname,AtomId1,AtomId2,debug=False):\n    mol,firstAtom,lastAtom=Atoms(molname,AtomId1,AtomId2)\n    if debug: print (molname, mol.GetFormula())\n    if debug: print(firstAtom.GetType(),firstAtom.GetId(),':',lastAtom.GetType(),lastAtom.GetId())\n    for b in openbabel.OBAtomBondIter(firstAtom): # all bonds for first atom\n      secondAtom=SecondAtom(b,firstAtom)\n      for b2 in openbabel.OBAtomBondIter(secondAtom): # all bonds for second atom \n        thirdAtom=SecondAtom(b2,secondAtom)\n        lastBond=thirdAtom.GetBond(lastAtom)\n        if lastBond: # found!\n          if debug: print(secondAtom.GetType(),secondAtom.GetId(),'<->',thirdAtom.GetType(),thirdAtom.GetId())\n          return mol.GetTorsion(firstAtom,secondAtom,thirdAtom,lastAtom)\n          \nTorsion3J('dsgdb9nsd_000007',2,5,debug=True) #methanol","execution_count":20,"outputs":[{"output_type":"stream","text":"dsgdb9nsd_000007 C2H6\nH 2 : H 5\nC3 0 <-> C3 1\n","name":"stdout"},{"output_type":"execute_result","execution_count":20,"data":{"text/plain":"60.00280550635594"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['bonds']=train['type'].str[0].astype(int)\ntest['bonds']=test['type'].str[0].astype(int)\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'] = np.linalg.norm(train_p_0 - train_p_1, axis=1)\ntest['dist'] = np.linalg.norm(test_p_0 - test_p_1, axis=1)\ntrain['abs_dist']=np.linalg.norm(train_p_0-train_p_1,axis=1,ord=1)\ntest['abs_dist']=np.linalg.norm(test_p_0-test_p_1,axis=1,ord=1)","execution_count":21,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def dist12(name='xy',a='x',b='y'):\n    train_p_0=train[[a+'_0',b+'_0']].values\n    train_p_1=train[[a+'_1',b+'_1']].values\n    test_p_0=test[[a+'_0',b+'_0']].values\n    test_p_1=test[[a+'_1',b+'_1']].values\n    \n    train[name] = np.linalg.norm(train_p_0 - train_p_1, axis=1)\n    test[name] = np.linalg.norm(test_p_0 - test_p_1, axis=1)\n    train['abs_'+name]= np.linalg.norm(train_p_0-train_p_1,axis=1,ord=1)\n    test['abs_'+name]= np.linalg.norm(test_p_0-test_p_1,axis=1,ord=1)","execution_count":22,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dist12('dist_xy','x','y')\ndist12('dist_xz','x','z')\ndist12('dist_yz','y','z')","execution_count":23,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head(5)","execution_count":24,"outputs":[{"output_type":"execute_result","execution_count":24,"data":{"text/plain":"   id     molecule_name      ...                 dist_yz   abs_dist_yz\n0   0  dsgdb9nsd_000001      ...       1.091852098455768  1.0978603510\n1   1  dsgdb9nsd_000001      ...       1.469783462212843  1.4714820252\n2   2  dsgdb9nsd_000001      ...       1.698470922926572  2.3321777672\n3   3  dsgdb9nsd_000001      ...       1.703822051159491  2.3483851354\n4   4  dsgdb9nsd_000001      ...       0.378025931005217  0.3856714250\n\n[5 rows x 28 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>id</th>\n      <th>molecule_name</th>\n      <th>atom_index_0</th>\n      <th>atom_index_1</th>\n      <th>type</th>\n      <th>scalar_coupling_constant</th>\n      <th>atom_0</th>\n      <th>x_0</th>\n      <th>y_0</th>\n      <th>z_0</th>\n      <th>atom_1</th>\n      <th>x_1</th>\n      <th>y_1</th>\n      <th>z_1</th>\n      <th>C</th>\n      <th>F</th>\n      <th>H</th>\n      <th>N</th>\n      <th>O</th>\n      <th>bonds</th>\n      <th>dist</th>\n      <th>abs_dist</th>\n      <th>dist_xy</th>\n      <th>abs_dist_xy</th>\n      <th>dist_xz</th>\n      <th>abs_dist_xz</th>\n      <th>dist_yz</th>\n      <th>abs_dist_yz</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1JHC</td>\n      <td>84.807599999999994</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>C</td>\n      <td>-0.0126981359</td>\n      <td>1.085804158</td>\n      <td>0.0080009958</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1.091953059611900</td>\n      <td>1.1127089029</td>\n      <td>1.091936438293093</td>\n      <td>1.1066840275</td>\n      <td>0.016024313311731</td>\n      <td>0.0208734273</td>\n      <td>1.091852098455768</td>\n      <td>1.0978603510</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>2</td>\n      <td>2JHH</td>\n      <td>-11.257000000000000</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>H</td>\n      <td>1.0117308430</td>\n      <td>1.463751162</td>\n      <td>0.0002765748</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>1.783119756038801</td>\n      <td>2.4810624522</td>\n      <td>1.783118946094350</td>\n      <td>2.4793629066</td>\n      <td>1.009581857521592</td>\n      <td>1.0112799726</td>\n      <td>1.469783462212843</td>\n      <td>1.4714820252</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>3</td>\n      <td>2JHH</td>\n      <td>-11.254799999999999</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>H</td>\n      <td>-0.5408150690</td>\n      <td>1.447526614</td>\n      <td>-0.8766437152</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>1.783147496403011</td>\n      <td>2.8751432522</td>\n      <td>1.551657880596930</td>\n      <td>1.9965234166</td>\n      <td>1.032852522585415</td>\n      <td>1.4215853206</td>\n      <td>1.698470922926572</td>\n      <td>2.3321777672</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>4</td>\n      <td>2JHH</td>\n      <td>-11.254300000000001</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>H</td>\n      <td>-0.5238136345</td>\n      <td>1.437932644</td>\n      <td>0.9063972942</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>1.783156685329616</td>\n      <td>2.8743491859</td>\n      <td>1.536772626258658</td>\n      <td>1.9699280121</td>\n      <td>1.046238902945277</td>\n      <td>1.4303852243</td>\n      <td>1.703822051159491</td>\n      <td>2.3483851354</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>2</td>\n      <td>0</td>\n      <td>1JHC</td>\n      <td>84.807400000000001</td>\n      <td>H</td>\n      <td>1.011730843</td>\n      <td>1.4637511620</td>\n      <td>0.0002765748</td>\n      <td>C</td>\n      <td>-0.0126981359</td>\n      <td>1.085804158</td>\n      <td>0.0080009958</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1.091951618581363</td>\n      <td>1.4101004039</td>\n      <td>1.091924297120763</td>\n      <td>1.4023759829</td>\n      <td>1.024458100407177</td>\n      <td>1.0321533999</td>\n      <td>0.378025931005217</td>\n      <td>0.3856714250</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"So, everyone uses this distance feature, let's have a look at it!"},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize = (18, 8))\nplt.subplot(1, 2, 1);\nplt.hist(train['dist_xz'], bins=20);\nplt.title('Basic dist histogram');\nplt.subplot(1, 2, 2);\nsns.violinplot(x='type', y='dist_xz', data=train);\nplt.title('Violinplot of dist_xz by type');","execution_count":25,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1296x576 with 2 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"It seems that the values are quite different for different types!"},{"metadata":{"trusted":true},"cell_type":"code","source":"train['dist_to_type_mean'] = train['dist'] / train.groupby('type')['dist'].transform('mean')\ntest['dist_to_type_mean'] = test['dist'] / test.groupby('type')['dist'].transform('mean')\n\ntrain['dist_to_type_std'] = train['dist'] / train.groupby('type')['dist'].transform('std')\ntest['dist_to_type_std'] = test['dist'] / test.groupby('type')['dist'].transform('std')\n\ntrain['dist_to_type_mean_xy'] = train['dist_xy'] / train.groupby('type')['dist_xy'].transform('mean')\ntest['dist_to_type_mean_xy'] = test['dist_xy'] / test.groupby('type')['dist_xy'].transform('mean')\n\ntrain['dist_to_type_mean_xz'] = train['dist_xz'] / train.groupby('type')['dist_xz'].transform('mean')\ntest['dist_to_type_mean_xz'] = test['dist_xz'] / test.groupby('type')['dist_xz'].transform('mean')\n\ntrain['dist_to_type_mean_yz'] = train['dist_yz'] / train.groupby('type')['dist_yz'].transform('mean')\ntest['dist_to_type_mean_yz'] = test['dist_yz'] / test.groupby('type')['dist_yz'].transform('mean')","execution_count":26,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":27,"outputs":[{"output_type":"execute_result","execution_count":27,"data":{"text/plain":"   id         ...          dist_to_type_mean_yz\n0   0         ...             1.298372056998296\n1   1         ...             1.119381740886271\n2   2         ...             1.293549279488992\n3   3         ...             1.297624679295201\n4   4         ...             0.449528197392408\n\n[5 rows x 33 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>id</th>\n      <th>molecule_name</th>\n      <th>atom_index_0</th>\n      <th>atom_index_1</th>\n      <th>type</th>\n      <th>scalar_coupling_constant</th>\n      <th>atom_0</th>\n      <th>x_0</th>\n      <th>y_0</th>\n      <th>z_0</th>\n      <th>atom_1</th>\n      <th>x_1</th>\n      <th>y_1</th>\n      <th>z_1</th>\n      <th>C</th>\n      <th>F</th>\n      <th>H</th>\n      <th>N</th>\n      <th>O</th>\n      <th>bonds</th>\n      <th>dist</th>\n      <th>abs_dist</th>\n      <th>dist_xy</th>\n      <th>abs_dist_xy</th>\n      <th>dist_xz</th>\n      <th>abs_dist_xz</th>\n      <th>dist_yz</th>\n      <th>abs_dist_yz</th>\n      <th>dist_to_type_mean</th>\n      <th>dist_to_type_std</th>\n      <th>dist_to_type_mean_xy</th>\n      <th>dist_to_type_mean_xz</th>\n      <th>dist_to_type_mean_yz</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1JHC</td>\n      <td>84.807599999999994</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>C</td>\n      <td>-0.0126981359</td>\n      <td>1.085804158</td>\n      <td>0.0080009958</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1.091953059611900</td>\n      <td>1.1127089029</td>\n      <td>1.091936438293093</td>\n      <td>1.1066840275</td>\n      <td>0.016024313311731</td>\n      <td>0.0208734273</td>\n      <td>1.091852098455768</td>\n      <td>1.0978603510</td>\n      <td>0.999133993514757</td>\n      <td>160.140258468183134</td>\n      <td>1.308822885399792</td>\n      <td>0.017808845798591</td>\n      <td>1.298372056998296</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>2</td>\n      <td>2JHH</td>\n      <td>-11.257000000000000</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>H</td>\n      <td>1.0117308430</td>\n      <td>1.463751162</td>\n      <td>0.0002765748</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>1.783119756038801</td>\n      <td>2.4810624522</td>\n      <td>1.783118946094350</td>\n      <td>2.4793629066</td>\n      <td>1.009581857521592</td>\n      <td>1.0112799726</td>\n      <td>1.469783462212843</td>\n      <td>1.4714820252</td>\n      <td>1.004633785679569</td>\n      <td>76.528200864254643</td>\n      <td>1.420898540772882</td>\n      <td>0.653242996633718</td>\n      <td>1.119381740886271</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>3</td>\n      <td>2JHH</td>\n      <td>-11.254799999999999</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>H</td>\n      <td>-0.5408150690</td>\n      <td>1.447526614</td>\n      <td>-0.8766437152</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>1.783147496403011</td>\n      <td>2.8751432522</td>\n      <td>1.551657880596930</td>\n      <td>1.9965234166</td>\n      <td>1.032852522585415</td>\n      <td>1.4215853206</td>\n      <td>1.698470922926572</td>\n      <td>2.3321777672</td>\n      <td>1.004649414975929</td>\n      <td>76.529391429362306</td>\n      <td>1.236456167519326</td>\n      <td>0.668300120399065</td>\n      <td>1.293549279488992</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>1</td>\n      <td>4</td>\n      <td>2JHH</td>\n      <td>-11.254300000000001</td>\n      <td>H</td>\n      <td>0.002150416</td>\n      <td>-0.0060313176</td>\n      <td>0.0019761204</td>\n      <td>H</td>\n      <td>-0.5238136345</td>\n      <td>1.437932644</td>\n      <td>0.9063972942</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>1.783156685329616</td>\n      <td>2.8743491859</td>\n      <td>1.536772626258658</td>\n      <td>1.9699280121</td>\n      <td>1.046238902945277</td>\n      <td>1.4303852243</td>\n      <td>1.703822051159491</td>\n      <td>2.3483851354</td>\n      <td>1.004654592141451</td>\n      <td>76.529785801091180</td>\n      <td>1.224594683901192</td>\n      <td>0.676961685734461</td>\n      <td>1.297624679295201</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4</td>\n      <td>dsgdb9nsd_000001</td>\n      <td>2</td>\n      <td>0</td>\n      <td>1JHC</td>\n      <td>84.807400000000001</td>\n      <td>H</td>\n      <td>1.011730843</td>\n      <td>1.4637511620</td>\n      <td>0.0002765748</td>\n      <td>C</td>\n      <td>-0.0126981359</td>\n      <td>1.085804158</td>\n      <td>0.0080009958</td>\n      <td>1</td>\n      <td>0</td>\n      <td>4</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1.091951618581363</td>\n      <td>1.4101004039</td>\n      <td>1.091924297120763</td>\n      <td>1.4023759829</td>\n      <td>1.024458100407177</td>\n      <td>1.0321533999</td>\n      <td>0.378025931005217</td>\n      <td>0.3856714250</td>\n      <td>0.999132674975848</td>\n      <td>160.140047134004675</td>\n      <td>1.308808332680748</td>\n      <td>1.138545907231645</td>\n      <td>0.449528197392408</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#%%time\n#### get atom or mol in train?\n######train['sp']=train.apply(lambda row: Atoms(row.molecule_name, row.atom_index_0, row.atom_index_1)[2],axis=1) # second atom is C or N for bond 1\n","execution_count":28,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_features(df):\n    df['molecule_couples'] = df.groupby('molecule_name')['id'].transform('count')\n    df['molecule_dist_mean'] = df.groupby('molecule_name')['dist'].transform('mean')\n    df['molecule_dist_min'] = df.groupby('molecule_name')['dist'].transform('min')\n    df['molecule_dist_max'] = df.groupby('molecule_name')['dist'].transform('max')\n    df['atom_0_couples_count'] = df.groupby(['molecule_name', 'atom_index_0'])['id'].transform('count')\n    df['atom_1_couples_count'] = df.groupby(['molecule_name', 'atom_index_1'])['id'].transform('count')\n    \n    df[f'molecule_atom_index_0_x_1_std'] = df.groupby(['molecule_name', 'atom_index_0'])['x_1'].transform('std')\n    df[f'molecule_atom_index_0_y_1_mean'] = df.groupby(['molecule_name', 'atom_index_0'])['y_1'].transform('mean')\n    df[f'molecule_atom_index_0_y_1_mean_diff'] = df[f'molecule_atom_index_0_y_1_mean'] - df['y_1']\n    df[f'molecule_atom_index_0_y_1_mean_div'] = df[f'molecule_atom_index_0_y_1_mean'] / df['y_1']\n    df[f'molecule_atom_index_0_y_1_max'] = df.groupby(['molecule_name', 'atom_index_0'])['y_1'].transform('max')\n    df[f'molecule_atom_index_0_y_1_max_diff'] = df[f'molecule_atom_index_0_y_1_max'] - df['y_1']\n    df[f'molecule_atom_index_0_y_1_std'] = df.groupby(['molecule_name', 'atom_index_0'])['y_1'].transform('std')\n    df[f'molecule_atom_index_0_z_1_std'] = df.groupby(['molecule_name', 'atom_index_0'])['z_1'].transform('std')\n    df[f'molecule_atom_index_0_dist_mean'] = df.groupby(['molecule_name', 'atom_index_0'])['dist'].transform('mean')\n    df[f'molecule_atom_index_0_dist_mean_diff'] = df[f'molecule_atom_index_0_dist_mean'] - df['dist']\n    df[f'molecule_atom_index_0_dist_mean_div'] = df[f'molecule_atom_index_0_dist_mean'] / df['dist']\n    df[f'molecule_atom_index_0_dist_max'] = df.groupby(['molecule_name', 'atom_index_0'])['dist'].transform('max')\n    df[f'molecule_atom_index_0_dist_max_diff'] = df[f'molecule_atom_index_0_dist_max'] - df['dist']\n    df[f'molecule_atom_index_0_dist_max_div'] = df[f'molecule_atom_index_0_dist_max'] / df['dist']\n    df[f'molecule_atom_index_0_dist_min'] = df.groupby(['molecule_name', 'atom_index_0'])['dist'].transform('min')\n    df[f'molecule_atom_index_0_dist_min_diff'] = df[f'molecule_atom_index_0_dist_min'] - df['dist']\n    df[f'molecule_atom_index_0_dist_min_div'] = df[f'molecule_atom_index_0_dist_min'] / df['dist']\n    df[f'molecule_atom_index_0_dist_std'] = df.groupby(['molecule_name', 'atom_index_0'])['dist'].transform('std')\n    df[f'molecule_atom_index_0_dist_std_diff'] = df[f'molecule_atom_index_0_dist_std'] - df['dist']\n    df[f'molecule_atom_index_0_dist_std_div'] = df[f'molecule_atom_index_0_dist_std'] / df['dist']\n    df[f'molecule_atom_index_1_dist_mean'] = df.groupby(['molecule_name', 'atom_index_1'])['dist'].transform('mean')\n    df[f'molecule_atom_index_1_dist_mean_diff'] = df[f'molecule_atom_index_1_dist_mean'] - df['dist']\n    df[f'molecule_atom_index_1_dist_mean_div'] = df[f'molecule_atom_index_1_dist_mean'] / df['dist']\n    df[f'molecule_atom_index_1_dist_max'] = df.groupby(['molecule_name', 'atom_index_1'])['dist'].transform('max')\n    df[f'molecule_atom_index_1_dist_max_diff'] = df[f'molecule_atom_index_1_dist_max'] - df['dist']\n    df[f'molecule_atom_index_1_dist_max_div'] = df[f'molecule_atom_index_1_dist_max'] / df['dist']\n    df[f'molecule_atom_index_1_dist_min'] = df.groupby(['molecule_name', 'atom_index_1'])['dist'].transform('min')\n    df[f'molecule_atom_index_1_dist_min_diff'] = df[f'molecule_atom_index_1_dist_min'] - df['dist']\n    df[f'molecule_atom_index_1_dist_min_div'] = df[f'molecule_atom_index_1_dist_min'] / df['dist']\n    df[f'molecule_atom_index_1_dist_std'] = df.groupby(['molecule_name', 'atom_index_1'])['dist'].transform('std')\n    df[f'molecule_atom_index_1_dist_std_diff'] = df[f'molecule_atom_index_1_dist_std'] - df['dist']\n    df[f'molecule_atom_index_1_dist_std_div'] = df[f'molecule_atom_index_1_dist_std'] / df['dist']\n    df[f'molecule_atom_1_dist_mean'] = df.groupby(['molecule_name', 'atom_1'])['dist'].transform('mean')\n    df[f'molecule_atom_1_dist_min'] = df.groupby(['molecule_name', 'atom_1'])['dist'].transform('min')\n    df[f'molecule_atom_1_dist_min_diff'] = df[f'molecule_atom_1_dist_min'] - df['dist']\n    df[f'molecule_atom_1_dist_min_div'] = df[f'molecule_atom_1_dist_min'] / df['dist']\n    df[f'molecule_atom_1_dist_std'] = df.groupby(['molecule_name', 'atom_1'])['dist'].transform('std')\n    df[f'molecule_atom_1_dist_std_diff'] = df[f'molecule_atom_1_dist_std'] - df['dist']\n    df[f'molecule_bonds_dist_std'] = df.groupby(['molecule_name', 'bonds'])['dist'].transform('std')\n    df[f'molecule_bonds_dist_std_diff'] = df[f'molecule_bonds_dist_std'] - df['dist']\n    df[f'molecule_type_dist_mean'] = df.groupby(['molecule_name', 'type'])['dist'].transform('mean')\n    df[f'molecule_type_dist_mean_diff'] = df[f'molecule_type_dist_mean'] - df['dist']\n    df[f'molecule_type_dist_mean_div'] = df[f'molecule_type_dist_mean'] / df['dist']\n    df[f'molecule_type_dist_max'] = df.groupby(['molecule_name', 'type'])['dist'].transform('max')\n    df[f'molecule_type_dist_min'] = df.groupby(['molecule_name', 'type'])['dist'].transform('min')\n    df[f'molecule_type_dist_std'] = df.groupby(['molecule_name', 'type'])['dist'].transform('std')\n    df[f'molecule_type_dist_std_diff'] = df[f'molecule_type_dist_std'] - df['dist']\n\n    return df\n","execution_count":29,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\ntrain = create_features(train)\ntest = create_features(test)\n\ntrain=reduce_mem_usage(train)\ntest=reduce_mem_usage(test)","execution_count":30,"outputs":[{"output_type":"stream","text":"Mem. usage decreased to 897.36 Mb (71.0% reduction)\nMem. usage decreased to 468.34 Mb (71.5% reduction)\nCPU times: user 1min 33s, sys: 2min 50s, total: 4min 23s\nWall time: 4min 23s\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# memory usage\nimport sys\ndef sizeof_fmt(num, suffix='B'):\n    ''' By Fred Cirera, after https://stackoverflow.com/a/1094933/1870254'''\n    for unit in ['','Ki','Mi','Gi','Ti','Pi','Ei','Zi']:\n        if abs(num) < 1024.0:\n            return \"%3.1f%s%s\" % (num, unit, suffix)\n        num /= 1024.0\n    return \"%.1f%s%s\" % (num, 'Yi', suffix)\n\nfor name, size in sorted(((name, sys.getsizeof(value)) for name,value in locals().items()),\n                         key= lambda x: -x[1])[:10]:\n    print(\"{:>30}: {:>8}\".format(name,sizeof_fmt(size)))","execution_count":31,"outputs":[{"output_type":"stream","text":"                         train:   1.9GiB\n                          test:   1.0GiB\n                    structures: 384.6MiB\n                           sub:  38.2MiB\n                    atom_count:  14.1MiB\n                    train_type:   6.1MiB\n                    mols_index:   5.0MiB\n                          mols:   1.1MiB\n                    mols_files:   1.1MiB\n                           _ii:   5.3KiB\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":""},{"metadata":{},"cell_type":"markdown","source":"## Basic model\n\nI'll use the function for metric calculation from this kernel: https://www.kaggle.com/abhishek/competition-metric"},{"metadata":{"trusted":true},"cell_type":"code","source":"def metric(df, preds):\n    df[\"prediction\"] = preds\n    maes = []\n    for t in df.type.unique():\n        y_true = df[df.type==t].scalar_coupling_constant.values\n        y_pred = df[df.type==t].prediction.values\n        mae = np.log(metrics.mean_absolute_error(y_true, y_pred))\n        maes.append(mae)\n    return np.mean(maes)","execution_count":32,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def group_mean_log_mae(y_true, y_pred, groups, floor=1e-9):\n    maes = (y_true-y_pred).abs().groupby(groups).mean()\n    return np.log(maes.map(lambda x: max(x, floor))).mean()","execution_count":33,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for f in [ 'atom_0', 'atom_1']:\n    lbl = LabelEncoder()\n    lbl.fit(list(train[f].values) )\n    train[f] = lbl.transform(list(train[f].values))\n    test[f] = lbl.transform(list(test[f].values))","execution_count":34,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def train_model(X, X_test, y, params, folds, model_type='lgb', plot_feature_importance=False, model=None):\n\n    oof = np.zeros(len(X))\n    print(X.shape,X_test.shape)\n    prediction = np.zeros(len(X_test))\n    scores = []\n    feature_importance = pd.DataFrame()\n    for fold_n, (train_index, valid_index) in enumerate(folds.split(X)):\n        print('Fold', fold_n, 'started at', time.ctime())\n      \n        X_train, X_valid = X.iloc[train_index], X.iloc[valid_index]\n        y_train, y_valid = y.iloc[train_index], y.iloc[valid_index]\n        if model_type == 'lgb':\n            model = lgb.LGBMRegressor(**params, n_estimators = 2000, n_jobs = -1)\n            model.fit(X_train, y_train, \n                    eval_set=[(X_train, y_train), (X_valid, y_valid)], eval_metric='mae',\n                    verbose=500, early_stopping_rounds=200)\n            \n            y_pred_valid = model.predict(X_valid)\n            y_pred = model.predict(X_test, num_iteration=model.best_iteration_)\n            \n        if model_type == 'xgb':\n            train_data = xgb.DMatrix(data=X_train, label=y_train, feature_names=X_tr.columns)\n            valid_data = xgb.DMatrix(data=X_valid, label=y_valid, feature_names=X_tr.columns)\n\n            watchlist = [(train_data, 'train'), (valid_data, 'valid_data')]\n            model = xgb.train(dtrain=train_data, num_boost_round=20000, evals=watchlist, early_stopping_rounds=200, verbose_eval=500, params=params)\n            y_pred_valid = model.predict(xgb.DMatrix(X_valid, feature_names=X_tr.columns), ntree_limit=model.best_ntree_limit)\n            y_pred = model.predict(xgb.DMatrix(X_test, feature_names=X_tr.columns), ntree_limit=model.best_ntree_limit)\n            \n        if model_type == 'rcv':\n            model = RidgeCV(alphas=(0.01, 0.1, 1.0, 10.0, 100.0), scoring='neg_mean_absolute_error', cv=3)\n            model.fit(X_train, y_train)\n            print(model.alpha_)\n\n            y_pred_valid = model.predict(X_valid).reshape(-1,)\n            score = mean_absolute_error(y_valid, y_pred_valid)\n            print(f'Fold {fold_n}. MAE: {score:.4f}.')\n            print('')\n            \n            y_pred = model.predict(X_test).reshape(-1,)\n        \n        if model_type == 'sklearn':\n            model = model\n            model.fit(X_train, y_train)\n            \n            y_pred_valid = model.predict(X_valid).reshape(-1,)\n            score = mean_absolute_error(y_valid, y_pred_valid)\n            print(f'Fold {fold_n}. MAE: {score:.4f}.')\n            print('')\n            \n            y_pred = model.predict(X_test).reshape(-1,)\n        \n        if model_type == 'cat':\n            model = CatBoostRegressor(iterations=20000,  eval_metric='MAE', **params)\n            model.fit(X_train, y_train, eval_set=(X_valid, y_valid), cat_features=[], use_best_model=True, verbose=False)\n\n            y_pred_valid = model.predict(X_valid)\n            y_pred = model.predict(X_test)\n        \n        oof[valid_index] = y_pred_valid.reshape(-1,)\n        scores.append(mean_absolute_error(y_valid, y_pred_valid))\n\n        prediction += y_pred    \n        \n        if model_type == 'lgb':\n            # feature importance\n            fold_importance = pd.DataFrame()\n            fold_importance[\"feature\"] = X.columns\n            fold_importance[\"importance\"] = model.feature_importances_\n            fold_importance[\"fold\"] = fold_n + 1\n            feature_importance = pd.concat([feature_importance, fold_importance], axis=0)\n\n    prediction /= n_fold\n    \n    print('CV mean score: {0:.4f}, std: {1:.4f}.'.format(np.mean(scores), np.std(scores)))\n    \n    if model_type == 'lgb':\n        feature_importance[\"importance\"] /= n_fold\n        if plot_feature_importance:\n            cols = feature_importance[[\"feature\", \"importance\"]].groupby(\"feature\").mean().sort_values(\n                by=\"importance\", ascending=False)[:50].index\n\n            best_features = feature_importance.loc[feature_importance.feature.isin(cols)]\n\n            plt.figure(figsize=(16, 12));\n            sns.barplot(x=\"importance\", y=\"feature\", data=best_features.sort_values(by=\"importance\", ascending=False));\n            plt.title('LGB Features (avg over folds)');\n        \n            return oof, prediction, feature_importance\n        return oof, prediction\n    \n    else:\n        return oof, prediction, model","execution_count":35,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"params = {\n          'num_leaves': 128,\n          'min_child_samples': 50,\n          'objective': 'regression',\n          'max_depth': 9,\n          'learning_rate': 0.2,\n          \"boosting_type\": \"gbdt\",\n          \"subsample_freq\": 1,\n          \"subsample\": 0.9,\n          \"bagging_seed\": 11,\n          \"metric\": 'mae',\n          \"verbosity\": -1,\n          'reg_alpha': 0.1302650970728192,\n          'reg_lambda': 0.3603427518866501,\n          'colsample_bytree': 1.0,\n          'device' : 'cpu',\n          'gpu_platform_id' : 0,\n          'gpu_device_id' : 0,\n          'gpu_use_dp': False\n         }","execution_count":36,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction_lgb=pd.DataFrame(test.shape[0],index=test['id'],columns=['scalar_coupling_constant'],dtype=float)\noof_lgb=pd.DataFrame(train.shape[0],index=train['id'],columns=['oof'],dtype=float)\n\nfor t in train['type'].unique():\n    print(f'Training of type {t}')\n    b=int(t[0]) # current bond for this type\n    print('Predicting J=',b)\n    X=train[train.type==t]\n    if (b==1):\n        X['sp']=X.apply(lambda row: Atoms(row.molecule_name, row.atom_index_0, row.atom_index_1)[2].GetHyb(),axis=1) # second atom is C or N for bond 1\n    if (b==2):\n        X['Angle']=X.apply(lambda row: Angle2J(row.molecule_name , row.atom_index_0, row.atom_index_1),axis=1) \n    if (b==3):\n        X['Torsion']=X.apply(lambda row: Torsion3J(row.molecule_name , row.atom_index_0, row.atom_index_1),axis=1) \n        X['cosT']=np.cos(np.deg2rad(X['Torsion']))\n        X['cos2T']=np.cos(2*np.deg2rad(X['Torsion']))\n    y = X['scalar_coupling_constant']\n    ids_train=X['id']\n    X = X.drop(['id','type', 'molecule_name', 'scalar_coupling_constant','bonds'], axis=1)\n    \n    X_test = test[test.type==t]\n    if (b==1): \n        X_test['sp']=X_test.apply(lambda row: Atoms(row.molecule_name, row.atom_index_0, row.atom_index_1)[2].GetHyb(),axis=1) # second atom is C or N for bond 1\n    if (b==2):\n        X_test['Angle']=X_test.apply(lambda row: Angle2J(row.molecule_name , row.atom_index_0, row.atom_index_1),axis=1) \n    if (b==3):\n        X_test['Torsion']=X_test.apply(lambda row: Torsion3J(row.molecule_name , row.atom_index_0, row.atom_index_1),axis=1)  \n        X_test['cosT']=np.cos(np.deg2rad(X_test['Torsion']))\n        X_test['cos2T']=np.cos(2*np.deg2rad(X_test['Torsion']))\n    ids_test=X_test['id']    \n    X_test=X_test.drop(['id', 'type', 'molecule_name','bonds'], axis=1)\n    \n    n_fold = 5\n    folds = KFold(n_splits=n_fold, shuffle=True, random_state=11)\n    \n    fold_oof_lgb, fold_prediction_lgb, feature_importance = train_model(X=X,X_test=X_test,y=y,params=params,folds=folds, model_type='lgb', plot_feature_importance=True)\n    \n    prediction_lgb.loc[ids_test,'scalar_coupling_constant']=fold_prediction_lgb\n    oof_lgb.loc[ids_train,'oof']=fold_oof_lgb\n      ","execution_count":null,"outputs":[{"output_type":"stream","text":"Training of type 1JHC\nPredicting J= 1\n(709416, 82) (380609, 82)\nFold 0 started at Sat Jun  8 14:23:27 2019\nTraining until validation scores don't improve for 200 rounds.\n[100]\ttraining's l1: 2.08753\tvalid_1's l1: 2.19636\n[200]\ttraining's l1: 1.82966\tvalid_1's l1: 2.01051\n[300]\ttraining's l1: 1.67875\tvalid_1's l1: 1.92239\n[400]\ttraining's l1: 1.56104\tvalid_1's l1: 1.86226\n[500]\ttraining's l1: 1.46918\tvalid_1's l1: 1.82178\n[600]\ttraining's l1: 1.39124\tvalid_1's l1: 1.78879\n[700]\ttraining's l1: 1.32146\tvalid_1's l1: 1.76323\n[800]\ttraining's l1: 1.2596\tvalid_1's l1: 1.74281\n[900]\ttraining's l1: 1.20342\tvalid_1's l1: 1.72501\n[1000]\ttraining's l1: 1.15259\tvalid_1's l1: 1.71022\n[1100]\ttraining's l1: 1.10547\tvalid_1's l1: 1.69861\n[1200]\ttraining's l1: 1.06226\tvalid_1's l1: 1.68863\n[1300]\ttraining's l1: 1.02093\tvalid_1's l1: 1.67906\n[1400]\ttraining's l1: 0.98345\tvalid_1's l1: 1.67035\n[1500]\ttraining's l1: 0.94799\tvalid_1's l1: 1.66332\n[1600]\ttraining's l1: 0.914166\tvalid_1's l1: 1.6559\n[1700]\ttraining's l1: 0.882667\tvalid_1's l1: 1.65017\n[1800]\ttraining's l1: 0.852592\tvalid_1's l1: 1.64449\n[1900]\ttraining's l1: 0.824106\tvalid_1's l1: 1.6388\n[2000]\ttraining's l1: 0.79723\tvalid_1's l1: 1.63454\nDid not meet early stopping. Best iteration is:\n[2000]\ttraining's l1: 0.79723\tvalid_1's l1: 1.63454\nFold 1 started at Sat Jun  8 14:29:07 2019\nTraining until validation scores don't improve for 200 rounds.\n[100]\ttraining's l1: 2.08667\tvalid_1's l1: 2.18402\n[200]\ttraining's l1: 1.83081\tvalid_1's l1: 2.00126\n[300]\ttraining's l1: 1.67671\tvalid_1's l1: 1.9098\n[400]\ttraining's l1: 1.56414\tvalid_1's l1: 1.85422\n[500]\ttraining's l1: 1.47329\tvalid_1's l1: 1.81375\n[600]\ttraining's l1: 1.39398\tvalid_1's l1: 1.78183\n[700]\ttraining's l1: 1.32354\tvalid_1's l1: 1.75588\n[800]\ttraining's l1: 1.26235\tvalid_1's l1: 1.73476\n[900]\ttraining's l1: 1.20801\tvalid_1's l1: 1.71942\n[1000]\ttraining's l1: 1.15598\tvalid_1's l1: 1.70457\n[1100]\ttraining's l1: 1.10872\tvalid_1's l1: 1.6913\n[1200]\ttraining's l1: 1.0644\tvalid_1's l1: 1.68016\n[1300]\ttraining's l1: 1.02481\tvalid_1's l1: 1.67056\n[1400]\ttraining's l1: 0.986082\tvalid_1's l1: 1.66185\n[1500]\ttraining's l1: 0.950696\tvalid_1's l1: 1.65366\n[1600]\ttraining's l1: 0.916645\tvalid_1's l1: 1.64689\n[1700]\ttraining's l1: 0.884689\tvalid_1's l1: 1.64013\n[1800]\ttraining's l1: 0.853729\tvalid_1's l1: 1.63437\n[1900]\ttraining's l1: 0.825098\tvalid_1's l1: 1.62941\n[2000]\ttraining's l1: 0.797791\tvalid_1's l1: 1.62447\nDid not meet early stopping. Best iteration is:\n[2000]\ttraining's l1: 0.797791\tvalid_1's l1: 1.62447\nFold 2 started at Sat Jun  8 14:34:47 2019\nTraining until validation scores don't improve for 200 rounds.\n[100]\ttraining's l1: 2.08299\tvalid_1's l1: 2.19752\n[200]\ttraining's l1: 1.83125\tvalid_1's l1: 2.01786\n[300]\ttraining's l1: 1.67444\tvalid_1's l1: 1.92044\n[400]\ttraining's l1: 1.56079\tvalid_1's l1: 1.86237\n[500]\ttraining's l1: 1.46869\tvalid_1's l1: 1.82099\n[600]\ttraining's l1: 1.39058\tvalid_1's l1: 1.78861\n[700]\ttraining's l1: 1.3222\tvalid_1's l1: 1.76343\n[800]\ttraining's l1: 1.26324\tvalid_1's l1: 1.74485\n[900]\ttraining's l1: 1.20804\tvalid_1's l1: 1.72766\n[1000]\ttraining's l1: 1.15643\tvalid_1's l1: 1.71236\n[1100]\ttraining's l1: 1.10805\tvalid_1's l1: 1.69988\n[1200]\ttraining's l1: 1.06316\tvalid_1's l1: 1.6865\n[1300]\ttraining's l1: 1.02293\tvalid_1's l1: 1.67623\n[1400]\ttraining's l1: 0.984664\tvalid_1's l1: 1.66654\n[1500]\ttraining's l1: 0.949757\tvalid_1's l1: 1.65929\n[1600]\ttraining's l1: 0.915845\tvalid_1's l1: 1.65273\n[1700]\ttraining's l1: 0.88409\tvalid_1's l1: 1.646\n[1800]\ttraining's l1: 0.854208\tvalid_1's l1: 1.63958\n[1900]\ttraining's l1: 0.826641\tvalid_1's l1: 1.63505\n[2000]\ttraining's l1: 0.799626\tvalid_1's l1: 1.63044\nDid not meet early stopping. Best iteration is:\n[2000]\ttraining's l1: 0.799626\tvalid_1's l1: 1.63044\nFold 3 started at Sat Jun  8 14:40:24 2019\nTraining until validation scores don't improve for 200 rounds.\n[100]\ttraining's l1: 2.08489\tvalid_1's l1: 2.19204\n[200]\ttraining's l1: 1.83018\tvalid_1's l1: 2.01011\n[300]\ttraining's l1: 1.68104\tvalid_1's l1: 1.92229\n[400]\ttraining's l1: 1.5633\tvalid_1's l1: 1.85934\n[500]\ttraining's l1: 1.47063\tvalid_1's l1: 1.81838\n[600]\ttraining's l1: 1.39043\tvalid_1's l1: 1.78398\n[700]\ttraining's l1: 1.32202\tvalid_1's l1: 1.75782\n[800]\ttraining's l1: 1.26002\tvalid_1's l1: 1.73782\n[900]\ttraining's l1: 1.20348\tvalid_1's l1: 1.72004\n[1000]\ttraining's l1: 1.15142\tvalid_1's l1: 1.70474\n[1100]\ttraining's l1: 1.10395\tvalid_1's l1: 1.69144\n[1200]\ttraining's l1: 1.06209\tvalid_1's l1: 1.68175\n[1300]\ttraining's l1: 1.02281\tvalid_1's l1: 1.67339\n[1400]\ttraining's l1: 0.98441\tvalid_1's l1: 1.66484\n[1500]\ttraining's l1: 0.949197\tvalid_1's l1: 1.65713\n[1600]\ttraining's l1: 0.91534\tvalid_1's l1: 1.65022\n[1700]\ttraining's l1: 0.883008\tvalid_1's l1: 1.64366\n[1800]\ttraining's l1: 0.853092\tvalid_1's l1: 1.63714\n[1900]\ttraining's l1: 0.823647\tvalid_1's l1: 1.63166\n[2000]\ttraining's l1: 0.796519\tvalid_1's l1: 1.62666\nDid not meet early stopping. Best iteration is:\n[2000]\ttraining's l1: 0.796519\tvalid_1's l1: 1.62666\nFold 4 started at Sat Jun  8 14:46:02 2019\nTraining until validation scores don't improve for 200 rounds.\n[100]\ttraining's l1: 2.08944\tvalid_1's l1: 2.19328\n[200]\ttraining's l1: 1.83983\tvalid_1's l1: 2.01522\n[300]\ttraining's l1: 1.6836\tvalid_1's l1: 1.92131\n[400]\ttraining's l1: 1.56763\tvalid_1's l1: 1.86153\n[500]\ttraining's l1: 1.47541\tvalid_1's l1: 1.82023\n[600]\ttraining's l1: 1.39689\tvalid_1's l1: 1.78824\n[700]\ttraining's l1: 1.32818\tvalid_1's l1: 1.76466\n[800]\ttraining's l1: 1.26754\tvalid_1's l1: 1.74405\n[900]\ttraining's l1: 1.21081\tvalid_1's l1: 1.72544\n[1000]\ttraining's l1: 1.15943\tvalid_1's l1: 1.7109\n[1100]\ttraining's l1: 1.11119\tvalid_1's l1: 1.69798\n[1200]\ttraining's l1: 1.06772\tvalid_1's l1: 1.68736\n[1300]\ttraining's l1: 1.02632\tvalid_1's l1: 1.67756\n[1400]\ttraining's l1: 0.987287\tvalid_1's l1: 1.66821\n[1500]\ttraining's l1: 0.950614\tvalid_1's l1: 1.65982\n[1600]\ttraining's l1: 0.91635\tvalid_1's l1: 1.65279\n[1700]\ttraining's l1: 0.884685\tvalid_1's l1: 1.64679\n[1800]\ttraining's l1: 0.854719\tvalid_1's l1: 1.64098\n[1900]\ttraining's l1: 0.826037\tvalid_1's l1: 1.63559\n[2000]\ttraining's l1: 0.798966\tvalid_1's l1: 1.63145\nDid not meet early stopping. Best iteration is:\n[2000]\ttraining's l1: 0.798966\tvalid_1's l1: 1.63145\nCV mean score: 1.6295, std: 0.0036.\nTraining of type 2JHH\nPredicting J= 2\n(378036, 82) (203126, 82)\nFold 0 started at Sat Jun  8 14:52:24 2019\nTraining until validation scores don't improve for 200 rounds.\n[100]\ttraining's l1: 0.41791\tvalid_1's l1: 0.455721\n[200]\ttraining's l1: 0.351186\tvalid_1's l1: 0.414825\n[300]\ttraining's l1: 0.31226\tvalid_1's l1: 0.396066\n[400]\ttraining's l1: 0.283206\tvalid_1's l1: 0.384617\n[500]\ttraining's l1: 0.260701\tvalid_1's l1: 0.377507\n[600]\ttraining's l1: 0.240264\tvalid_1's l1: 0.37105\n[700]\ttraining's l1: 0.22321\tvalid_1's l1: 0.366787\n[800]\ttraining's l1: 0.208355\tvalid_1's l1: 0.363241\n[900]\ttraining's l1: 0.194433\tvalid_1's l1: 0.359773\n[1000]\ttraining's l1: 0.182417\tvalid_1's l1: 0.35734\n[1100]\ttraining's l1: 0.17154\tvalid_1's l1: 0.355205\n[1200]\ttraining's l1: 0.162109\tvalid_1's l1: 0.353594\n[1300]\ttraining's l1: 0.153086\tvalid_1's l1: 0.35224\n[1400]\ttraining's l1: 0.144528\tvalid_1's l1: 0.351034\n[1500]\ttraining's l1: 0.136631\tvalid_1's l1: 0.349977\n[1600]\ttraining's l1: 0.129435\tvalid_1's l1: 0.349109\n[1700]\ttraining's l1: 0.122859\tvalid_1's l1: 0.348156\n[1800]\ttraining's l1: 0.116579\tvalid_1's l1: 0.347352\n[1900]\ttraining's l1: 0.110742\tvalid_1's l1: 0.346462\n[2000]\ttraining's l1: 0.105247\tvalid_1's l1: 0.345812\nDid not meet early stopping. Best iteration is:\n[2000]\ttraining's l1: 0.105247\tvalid_1's l1: 0.345812\nFold 1 started at Sat Jun  8 14:56:00 2019\nTraining until validation scores don't improve for 200 rounds.\n[100]\ttraining's l1: 0.417811\tvalid_1's l1: 0.461868\n[200]\ttraining's l1: 0.35077\tvalid_1's l1: 0.420437\n[300]\ttraining's l1: 0.31311\tvalid_1's l1: 0.402127\n[400]\ttraining's l1: 0.282842\tvalid_1's l1: 0.38932\n[500]\ttraining's l1: 0.25928\tvalid_1's l1: 0.380785\n[600]\ttraining's l1: 0.240051\tvalid_1's l1: 0.374981\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#'categorical_feature' : \"name:type, atom_0, atom_1\",","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":""},{"metadata":{"trusted":true},"cell_type":"code","source":"sub=sub.drop(['scalar_coupling_constant'],axis=1).merge(prediction_lgb,on='id')\nsub.to_csv('submission.csv', index=False)\nsub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_data = pd.DataFrame(train['scalar_coupling_constant'])\nplot_data.index.name = 'id'\nplot_data['yhat'] = oof_lgb['oof']\nplot_data['type'] = train['type']\n\ndef plot_oof_preds(ctype, llim, ulim):\n        plt.figure(figsize=(6,6))\n        sns.scatterplot(x='scalar_coupling_constant',y='yhat',\n                        data=plot_data.loc[plot_data['type']==ctype,\n                        ['scalar_coupling_constant', 'yhat']]);\n        plt.xlim((llim, ulim))\n        plt.ylim((llim, ulim))\n        plt.plot([llim, ulim], [llim, ulim])\n        plt.xlabel('scalar_coupling_constant')\n        plt.ylabel('predicted')\n        plt.title(f'{ctype}', fontsize=18)\n        plt.show()\n\nplot_oof_preds('1JHC', 0, 250)\nplot_oof_preds('1JHN', 0, 100)\nplot_oof_preds('2JHC', -50, 50)\nplot_oof_preds('2JHH', -50, 50)\nplot_oof_preds('2JHN', -25, 25)\nplot_oof_preds('3JHC', -25, 100)\nplot_oof_preds('3JHH', -20, 20)\nplot_oof_preds('3JHN', -15, 15)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"raw","source":""}],"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}