{"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 in \n\nimport os\nimport random\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom scipy import stats\nfrom scipy.stats import norm\n\n# Input data files are available in the \"../input/\" directory.\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Config"},{"metadata":{"trusted":true},"cell_type":"code","source":"SEED = 31","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    \nseed_everything(SEED)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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                c_prec = df[col].apply(lambda x: np.finfo(x).precision).max()\n                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max and c_prec == np.finfo(np.float16).precision:\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 and c_prec == np.finfo(np.float32).precision:\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.set_option('display.max_columns', 500)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"file_folder = '../input/champs-scalar-coupling/'\ntrain = pd.read_csv(f'{file_folder}/train.csv')\ntest = pd.read_csv(f'{file_folder}/test.csv')\nsub = pd.read_csv(f'{file_folder}/sample_submission.csv')\nstructures = pd.read_csv(f'{file_folder}/structures.csv')","execution_count":null,"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 {structures['atom'].nunique()} unique atoms.\")\nprint(f\"There are {train['type'].nunique()} unique types.\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Check missing data"},{"metadata":{"trusted":true},"cell_type":"code","source":"#missing data\ntotal = train.isnull().sum().sort_values(ascending=False)\npercent = (train.isnull().sum()/train.isnull().count()).sort_values(ascending=False)\nmissing_data = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])\nmissing_data.head(20)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Feature engineering"},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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\n\ndef make_features(df):\n    df = map_atom_info(df, 0)\n    df = map_atom_info(df, 1)\n    df_p_0 = df[['x_0', 'y_0', 'z_0']].values\n    df_p_1 = df[['x_1', 'y_1', 'z_1']].values\n    df['dist'] = np.linalg.norm(df_p_0 - df_p_1, axis=1)\n    df['dist_x'] = (df['x_0'] - df['x_1']) ** 2\n    df['dist_y'] = (df['y_0'] - df['y_1']) ** 2\n    df['dist_z'] = (df['z_0'] - df['z_1']) ** 2\n    df['type_0'] = df['type'].apply(lambda x: x[0])\n    df['type_1'] = df['type'].apply(lambda x: x[1:])\n    df['dist_to_type_mean'] = df['dist'] / df.groupby('type')['dist'].transform('mean')\n    df['dist_to_type_0_mean'] = df['dist'] / df.groupby('type_0')['dist'].transform('mean')\n    df['dist_to_type_1_mean'] = df['dist'] / df.groupby('type_1')['dist'].transform('mean')\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    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_type_0_dist_std'] = df.groupby(['molecule_name', 'type_0'])['dist'].transform('std')\n    df[f'molecule_type_0_dist_std_diff'] = df[f'molecule_type_0_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    df = df.fillna(0)\n    return df\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\ntrain = make_features(train)\ntest = make_features(test)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\ndef encode(df, col, encoder):\n    df[col] = df[col].map(encoder).fillna(0)\n    assert df[col].isnull().sum() == 0\n\ndef freq_encode(col):\n    encoder = dict(train[col].value_counts(normalize=True))\n    encode(train, col, encoder)\n    encode(test, col, encoder)\n\n\nfreq_encode('type')\nfreq_encode('type_0')\nfreq_encode('type_1')\nfreq_encode('atom_0')\nfreq_encode('atom_1')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def log_transform(df, col, offset=1):\n    df[col] = np.log(df[col] + offset)\n\ndef hist_npp_charts(df, col):\n    \"\"\"histogram and normal probability plot\"\"\"\n    sns.distplot(df[col], fit=norm);\n    fig = plt.figure()\n    res = stats.probplot(df[col], plot=plt)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"hist_npp_charts(train, 'scalar_coupling_constant')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Log transform did not change the prob plot of the target `scalar_coupling_constant`"},{"metadata":{"trusted":true},"cell_type":"code","source":"#log_transform(train, 'scalar_coupling_constant', offset=1000)\n#hist_npp_charts(train, 'scalar_coupling_constant')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Correlation matrix"},{"metadata":{"trusted":true},"cell_type":"code","source":"#correlation matrix\ncorrmat = train.corr()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"k = 80 #number of variables for heatmap\ncols = corrmat.nlargest(k, 'scalar_coupling_constant')['scalar_coupling_constant'].index\ncm = np.corrcoef(train[cols].values.T)\nsns.set(font_scale=1.25)\nplt.subplots(figsize=(40, 40))\nsns.heatmap(cm, cbar=False, annot=True, square=True, fmt='.2f', annot_kws={'size': 10}, yticklabels=cols.values, xticklabels=cols.values)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Reduce disk size of output files"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Unused because I wasn't sure of its exact behaviour.\ndef corr_columns(df, threshold=0.97):\n    print(\"Starting Preprocessing..\")\n    # Absolute value correlation matrix\n    corr_matrix = df.corr().abs()\n    # Getting the upper triangle of correlations\n    upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(np.bool))\n    # Select columns with correlations above threshold\n    to_drop = [column for column in upper.columns if any(upper[column] > threshold)]\n    return to_drop\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"keep_columns = [\n    'scalar_coupling_constant',\n    'id',\n    'molecule_atom_index_0_dist_mean_div',\n    'molecule_atom_index_0_dist_max_div',\n    'molecule_atom_index_1_dist_max_div',\n    'molecule_atom_index_0_dist_std_div',\n    'molecule_atom_index_0_dist_min_div',\n    'molecule_atom_index_1_dist_mean_div',\n    'molecule_atom_index_1_dist_std_div',\n    'molecule_atom_1_dist_std_diff',\n    'molecule_atom_index_0_dist_std_diff',\n    'molecule_atom_index_0_dist_mean_diff',\n    'molecule_atom_index_1_dist_max_diff',\n    'molecule_atom_index_0_dist_max_diff',\n    'molecule_type_0_dist_std_diff',\n    'molecule_atom_index_1_dist_mean_diff',\n    'molecule_atom_index_1_dist_std_diff',\n    'molecule_atom_1_dist_min_div',\n    'molecule_atom_1_dist_min_diff',\n    'type',\n    'type_0',\n    'type_1',\n    'molecule_type_dist_min',\n    'molecule_type_dist_mean',\n    'molecule_type_0_dist_std',\n    'dist_to_type_1_mean',\n    'dist',\n    'molecule_type_dist_max',\n    'dist_x',\n    'dist_y',\n    'dist_z'\n]\ntrain = train[keep_columns]\ntest = test[keep_columns[1:]]\nprint(f'len(keep_columns)={len(keep_columns)}, train={train.shape}, test={test.shape}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\nprint(f'train={train.shape}, test={test.shape}')\ntrain.to_csv('train.csv', index=False)\ntest.to_csv('test.csv', index=False)\nprint(os.listdir(\".\"))","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}