{"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_minor":4,"nbformat":4,"cells":[{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings('ignore')\nimport scipy as sp\nimport numpy as np\nimport pandas as pd\nimport os\nimport random\nimport joblib\nimport itertools\npd.set_option('display.max_rows', 500)\npd.set_option('display.max_columns', 500)\npd.set_option('display.width', 1000)\nfrom tqdm.auto import tqdm\nfrom sklearn.model_selection import StratifiedKFold, train_test_split\nfrom sklearn.preprocessing import LabelEncoder\nimport lightgbm as lgb\nfrom itertools import combinations\nfrom sklearn.impute import SimpleImputer","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_parquet(\"../input/amex-data-integer-dtypes-parquet-format/train.parquet\")\ntest = pd.read_parquet(\"../input/amex-data-integer-dtypes-parquet-format/test.parquet\")\ntrain_labels = pd.read_csv(\"../input/amex-default-prediction/train_labels.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# define some type of features\ncat_features = [\"B_30\",\"B_38\",\"D_114\",\"D_116\",\"D_117\",\"D_120\",\"D_126\",\"D_63\",\"D_64\",\"D_66\",\"D_68\"]\nnum_features = [i for i in train.columns.to_list() if i not in cat_features]\n\nprint('Starting training feature engineer...')\ntrain_num_agg = train.groupby(\"customer_ID\")[num_features].agg(['mean', 'std', 'min', 'max', 'last'])\ntrain_num_agg.columns = ['_'.join(x) for x in train_num_agg.columns]\ntrain_num_agg.reset_index(inplace = True)\ntrain_cat_agg = train.groupby(\"customer_ID\")[cat_features].agg(['count', 'last', 'nunique'])\ntrain_cat_agg.columns = ['_'.join(x) for x in train_cat_agg.columns]\ntrain_cat_agg.reset_index(inplace = True)\ntrain = train_num_agg.merge(train_cat_agg, how = 'inner', on = 'customer_ID').merge(train_labels, how = 'inner', on = 'customer_ID')\ndel train_num_agg, train_cat_agg\n\nprint('Starting test feature engineer...')\ntest_num_agg = test.groupby(\"customer_ID\")[num_features].agg(['mean', 'std', 'min', 'max', 'last'])\ntest_num_agg.columns = ['_'.join(x) for x in test_num_agg.columns]\ntest_num_agg.reset_index(inplace = True)\ntest_cat_agg = test.groupby(\"customer_ID\")[cat_features].agg(['count', 'last', 'nunique'])\ntest_cat_agg.columns = ['_'.join(x) for x in test_cat_agg.columns]\ntest_cat_agg.reset_index(inplace = True)\ntest = test_num_agg.merge(test_cat_agg, how = 'inner', on = 'customer_ID')\ndel test_num_agg, test_cat_agg","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ====================================================\n# Configurations\n# ====================================================\nclass CFG:\n    seed = 42\n    n_folds = 5\n    target = 'target'\n\n# ====================================================\n# Seed everything\n# ====================================================\ndef seed_everything(seed):\n    random.seed(seed)\n    np.random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n\n# ====================================================\n# Amex metric\n# ====================================================\ndef amex_metric(y_true, y_pred):\n    labels = np.transpose(np.array([y_true, y_pred]))\n    labels = labels[labels[:, 1].argsort()[::-1]]\n    weights = np.where(labels[:,0]==0, 20, 1)\n    cut_vals = labels[np.cumsum(weights) <= int(0.04 * np.sum(weights))]\n    top_four = np.sum(cut_vals[:,0]) / np.sum(labels[:,0])\n    gini = [0,0]\n    for i in [1,0]:\n        labels = np.transpose(np.array([y_true, y_pred]))\n        labels = labels[labels[:, i].argsort()[::-1]]\n        weight = np.where(labels[:,0]==0, 20, 1)\n        weight_random = np.cumsum(weight / np.sum(weight))\n        total_pos = np.sum(labels[:, 0] *  weight)\n        cum_pos_found = np.cumsum(labels[:, 0] * weight)\n        lorentz = cum_pos_found / total_pos\n        gini[i] = np.sum((lorentz - weight_random) * weight)\n    return 0.5 * (gini[1]/gini[0] + top_four)\n\n# ====================================================\n# LGBM amex metric\n# ====================================================\ndef lgb_amex_metric(y_pred, y_true):\n    y_true = y_true.get_label()\n    return 'amex_metric', amex_metric(y_true, y_pred), True\n\n# ====================================================\n# Train & Evaluate\n# ====================================================\ndef train_and_evaluate(train, test):\n    # Label encode categorical features\n    cat_features = [\n        \"B_30\",\n        \"B_38\",\n        \"D_114\",\n        \"D_116\",\n        \"D_117\",\n        \"D_120\",\n        \"D_126\",\n        \"D_63\",\n        \"D_64\",\n        \"D_66\",\n        \"D_68\"\n    ]\n    cat_features = [f\"{cf}_last\" for cf in cat_features]\n    for cat_col in cat_features:\n        encoder = LabelEncoder()\n        train[cat_col] = encoder.fit_transform(train[cat_col])\n        test[cat_col] = encoder.fit_transform(test[cat_col])\n        \n    # Round last float features to 2 decimal place\n    num_cols = list(train.dtypes[(train.dtypes == 'float32') | (train.dtypes == 'float64')].index)\n    num_cols = [col for col in num_cols if 'last' in col]\n    for col in num_cols:\n        train[col + '_round2'] = train[col].round(2)\n        test[col + '_round2'] = test[col].round(2)\n        \n    # Get feature list\n    \n    features = [col for col in train.columns.to_list() if col not in ['customer_ID', 'target']]\n    params = {\n        'objective': 'binary',\n        'metric': \"binary_logloss\",\n        'boosting': 'dart',\n        'seed': CFG.seed,\n        'num_leaves': 100,\n        'learning_rate': 0.01,\n        'feature_fraction': 0.20,\n        'bagging_freq': 10, \n        'bagging_fraction': 0.50,\n        'n_jobs': -1,\n        'lambda_l2': 2,\n        'min_data_in_leaf': 40,\n        'verbose':-1\n        }\n    \n    # Create a numpy array to store test predictions\n    test_predictions = np.zeros(len(test))\n    # Create a numpy array to store out of folds predictions\n    oof_predictions = np.zeros(len(train))\n    kfold = StratifiedKFold(n_splits = CFG.n_folds, shuffle = True, random_state = CFG.seed)\n    for fold, (trn_ind, val_ind) in enumerate(kfold.split(train, train[CFG.target])):\n        print(' ')\n        print('-'*50)\n        print(f'Training fold {fold} with {len(features)} features...')\n        x_train, x_val = train[features].iloc[trn_ind], train[features].iloc[val_ind]\n        y_train, y_val = train[CFG.target].iloc[trn_ind], train[CFG.target].iloc[val_ind]\n        lgb_train = lgb.Dataset(x_train, y_train, categorical_feature = cat_features)\n        lgb_valid = lgb.Dataset(x_val, y_val, categorical_feature = cat_features)\n        model = lgb.train(\n            params = params,\n            train_set = lgb_train,\n            num_boost_round = 10500,\n            valid_sets = [lgb_train, lgb_valid],\n            early_stopping_rounds = 100,\n            verbose_eval = 500,\n            feval = lgb_amex_metric\n            )\n        # Save best model\n        joblib.dump(model, f'/lgbm_fold{fold}_seed{CFG.seed}.pkl')\n        # Predict validation\n        val_pred = model.predict(x_val)\n        # Add to out of folds array\n        oof_predictions[val_ind] = val_pred\n        # Predict the test set\n        test_pred = model.predict(test[features])\n        test_predictions += test_pred / CFG.n_folds\n        # Compute fold metric\n        score = amex_metric(y_val, val_pred)\n        print(f'Our fold {fold} CV score is {score}')\n        del x_train, x_val, y_train, y_val, lgb_train, lgb_valid\n\n        \n    # Compute out of folds metric\n    score = amex_metric(train[CFG.target], oof_predictions)\n    print(f'Our out of folds CV score is {score}')\n    # Create a dataframe to store out of folds predictions\n    oof_df = pd.DataFrame({'customer_ID': train['customer_ID'], 'target': train[CFG.target], 'prediction': oof_predictions})\n    oof_df.to_csv(f'oof_lgbm_baseline_{CFG.n_folds}fold_seed{CFG.seed}.csv', index = False)\n    # Create a dataframe to store test prediction\n    test_df = pd.DataFrame({'customer_ID': test['customer_ID'], 'prediction': test_predictions})\n    test_df.to_csv(f'test_lgbm_baseline_{CFG.n_folds}fold_seed{CFG.seed}.csv', index = False)\n\n    \nseed_everything(CFG.seed)\ntrain_and_evaluate(train, test)","metadata":{},"execution_count":null,"outputs":[]}]}