{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30664,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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","execution":{"iopub.status.busy":"2024-03-17T19:41:11.924835Z","iopub.execute_input":"2024-03-17T19:41:11.925367Z","iopub.status.idle":"2024-03-17T19:41:11.949599Z","shell.execute_reply.started":"2024-03-17T19:41:11.925329Z","shell.execute_reply":"2024-03-17T19:41:11.947672Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"I have made some feature engeneering and played around with model parameters.","metadata":{"execution":{"iopub.status.busy":"2024-03-17T16:31:38.495615Z","iopub.execute_input":"2024-03-17T16:31:38.496305Z","iopub.status.idle":"2024-03-17T16:31:38.505236Z","shell.execute_reply.started":"2024-03-17T16:31:38.496256Z","shell.execute_reply":"2024-03-17T16:31:38.503282Z"}}},{"cell_type":"code","source":"import polars as pl\nimport numpy as np\nimport pandas as pd\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_auc_score\n\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:41:12.296926Z","iopub.execute_input":"2024-03-17T19:41:12.297330Z","iopub.status.idle":"2024-03-17T19:41:12.303369Z","shell.execute_reply.started":"2024-03-17T19:41:12.297301Z","shell.execute_reply":"2024-03-17T19:41:12.302057Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def set_table_dtypes(df: pl.DataFrame) -> pl.DataFrame:\n    # implement here all desired dtypes for tables\n    # the following is just an example\n    for col in df.columns:\n        # last letter of column name will help you determine the type\n        if col[-1] in (\"P\", \"A\"):\n            df = df.with_columns(pl.col(col).cast(pl.Float64).alias(col))\n\n    return df\n\ndef convert_strings(df: pd.DataFrame) -> pd.DataFrame:\n    for col in df.columns:\n        if df[col].dtype.name in ['object', 'string']:\n            df[col] = df[col].astype(\"string\").astype('category')\n            current_categories = df[col].cat.categories\n            new_categories = current_categories.to_list() + [\"Unknown\"]\n            new_dtype = pd.CategoricalDtype(categories=new_categories, ordered=True)\n            df[col] = df[col].astype(new_dtype)\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:41:12.469942Z","iopub.execute_input":"2024-03-17T19:41:12.470683Z","iopub.status.idle":"2024-03-17T19:41:12.480127Z","shell.execute_reply.started":"2024-03-17T19:41:12.470634Z","shell.execute_reply":"2024-03-17T19:41:12.479273Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_basetable = pl.read_csv(dataPath + \"csv_files/train/train_base.csv\")\ntrain_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_1.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntrain_static_cb = pl.read_csv(dataPath + \"csv_files/train/train_static_cb_0.csv\").pipe(set_table_dtypes)\ntrain_person_1 = pl.read_csv(dataPath + \"csv_files/train/train_person_1.csv\").pipe(set_table_dtypes)\ntrain_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/train/train_credit_bureau_b_2.csv\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:41:12.630811Z","iopub.execute_input":"2024-03-17T19:41:12.631615Z","iopub.status.idle":"2024-03-17T19:41:34.780184Z","shell.execute_reply.started":"2024-03-17T19:41:12.631535Z","shell.execute_reply":"2024-03-17T19:41:34.779154Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_basetable = pl.read_csv(dataPath + \"csv_files/test/test_base.csv\")\ntest_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_1.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_2.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntest_static_cb = pl.read_csv(dataPath + \"csv_files/test/test_static_cb_0.csv\").pipe(set_table_dtypes)\ntest_person_1 = pl.read_csv(dataPath + \"csv_files/test/test_person_1.csv\").pipe(set_table_dtypes)\ntest_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/test/test_credit_bureau_b_2.csv\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:41:34.785866Z","iopub.execute_input":"2024-03-17T19:41:34.788892Z","iopub.status.idle":"2024-03-17T19:41:34.855284Z","shell.execute_reply.started":"2024-03-17T19:41:34.788844Z","shell.execute_reply":"2024-03-17T19:41:34.854349Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Let's do some data preprocessing","metadata":{}},{"cell_type":"code","source":"# We need to use aggregation functions in tables with depth > 1, so tables that contain num_group1 column or \n# also num_group2 column.\ntrain_person_1_feats_1 = train_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\n# Here num_group1=0 has special meaning, it is the person who applied for the loan.\ntrain_person_1_feats_2 = train_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\n# Here we have num_goup1 and num_group2, so we need to aggregate again.\ntrain_credit_bureau_b_2_feats = train_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)\n\n# We will process in this examples only A-type and M-type columns, so we need to select them.\nselected_static_cols = []\nfor col in train_static.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cols.append(col)\nprint(selected_static_cols)\n\nselected_static_cb_cols = []\nfor col in train_static_cb.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cb_cols.append(col)\nprint(selected_static_cb_cols)\n\n# Join all tables together.\ndata = train_basetable.join(\n    train_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n    train_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:41:34.856673Z","iopub.execute_input":"2024-03-17T19:41:34.857279Z","iopub.status.idle":"2024-03-17T19:41:42.902841Z","shell.execute_reply.started":"2024-03-17T19:41:34.857244Z","shell.execute_reply":"2024-03-17T19:41:42.901133Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_person_1_feats_1 = test_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\ntest_person_1_feats_2 = test_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\ntest_credit_bureau_b_2_feats = test_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)\n\ndata_submission = test_basetable.join(\n    test_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n    test_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:41:42.917953Z","iopub.execute_input":"2024-03-17T19:41:42.924880Z","iopub.status.idle":"2024-03-17T19:41:42.954044Z","shell.execute_reply.started":"2024-03-17T19:41:42.924798Z","shell.execute_reply":"2024-03-17T19:41:42.951047Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_ids = data[\"case_id\"].unique().shuffle(seed=1)\ncase_ids_train, case_ids_test = train_test_split(case_ids, train_size=0.6, random_state=1)\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=1)\n\ncols_pred = []\nfor col in data.columns:\n    if col[-1].isupper() and col[:-1].islower():\n        cols_pred.append(col)\n\nprint(cols_pred)\n\ndef from_polars_to_pandas(case_ids: pl.DataFrame) -> pl.DataFrame:\n    return (\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[[\"case_id\", \"WEEK_NUM\", \"target\"]].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[cols_pred].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[\"target\"].to_pandas()\n    )\n\nbase_train, X_train, y_train = from_polars_to_pandas(case_ids_train)\nbase_valid, X_valid, y_valid = from_polars_to_pandas(case_ids_valid)\nbase_test, X_test, y_test = from_polars_to_pandas(case_ids_test)\n\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:41:42.957236Z","iopub.execute_input":"2024-03-17T19:41:42.959228Z","iopub.status.idle":"2024-03-17T19:41:58.235644Z","shell.execute_reply.started":"2024-03-17T19:41:42.959132Z","shell.execute_reply":"2024-03-17T19:41:58.233738Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"Train: {X_train.shape}\")\nprint(f\"Valid: {X_valid.shape}\")\nprint(f\"Test: {X_test.shape}\")","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:41:58.237956Z","iopub.execute_input":"2024-03-17T19:41:58.238899Z","iopub.status.idle":"2024-03-17T19:41:58.250522Z","shell.execute_reply.started":"2024-03-17T19:41:58.238844Z","shell.execute_reply":"2024-03-17T19:41:58.248107Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Feature engineering\nfrom datetime import datetime\ndef feature_generator(df):\n    # Payment Ratio Feature\n    df['payment_ratio'] = df['annuity_780A'].fillna(0) / df['amtinstpaidbefduel24m_4187115A'].fillna(0)\n\n    #Debt Ratio Feature\n    df['debt_ratio'] = df['currdebt_22A'].fillna(0) / df['credamount_770A'].fillna(0)\n\n    #Historical Payment Behavior\n    df['total_payment_activity'] = df['pmtssum_45A'].fillna(0) + df['maxpmtlast3m_4525190A'].fillna(0) + df['avgpmtlast12m_4525200A'].fillna(0)\n\n    #Сlient's Credit Behavior\n    df['credit_utilization_ratio'] = df['totaldebt_9A'].fillna(0) / df['credamount_770A'].fillna(0)\n    \n    \n    return df","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:41:58.253307Z","iopub.execute_input":"2024-03-17T19:41:58.254529Z","iopub.status.idle":"2024-03-17T19:41:58.265428Z","shell.execute_reply.started":"2024-03-17T19:41:58.254484Z","shell.execute_reply":"2024-03-17T19:41:58.264160Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train = feature_generator(X_train)\nX_valid = feature_generator(X_valid)\nX_test = feature_generator(X_test)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:42:09.477521Z","iopub.execute_input":"2024-03-17T19:42:09.477973Z","iopub.status.idle":"2024-03-17T19:42:09.590882Z","shell.execute_reply.started":"2024-03-17T19:42:09.477937Z","shell.execute_reply":"2024-03-17T19:42:09.589533Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training the model","metadata":{}},{"cell_type":"code","source":"from sklearn.model_selection import RandomizedSearchCV\nimport lightgbm as lgb\n\n#Lets make our param space\nparam_space = {\n    'boosting_type': ['gbdt'],  #default\n    'objective': ['binary'],    #because binary\n    'metric': ['auc'],          #metric from comp\n    'max_depth': [4, 6],        #lets add two options: 4,6\n    'num_leaves': [30, 45],     #30 or 50\n    'learning_rate': [0.01, 0.1],#low and high lr\n    'feature_fraction': [0.9],  #the rest is same\n    'bagging_fraction': [0.8],  \n    'bagging_freq': [5],    \n    'n_estimators': [1000],     \n    'verbose': [-1],           \n}\n\n\nlgb_model = lgb.LGBMClassifier(random_state=38)\n\ngrid_search = RandomizedSearchCV(\n    estimator=lgb_model,\n    param_distributions=param_space,\n    n_iter=4,  # just 4 to make sure so that the compute will not take too long\n    scoring='roc_auc',\n    cv=3,\n    verbose=1,\n    random_state=42\n)\n\n# Lets. grid search\ngrid_search.fit(X_train, y_train)\nprint(grid_search.best_params_)\nprint(grid_search.best_score_)\nbest_model = grid_search.best_estimator_","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:42:10.516274Z","iopub.execute_input":"2024-03-17T19:42:10.516740Z","iopub.status.idle":"2024-03-17T19:42:27.099388Z","shell.execute_reply.started":"2024-03-17T19:42:10.516703Z","shell.execute_reply":"2024-03-17T19:42:27.097274Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = best_model.predict_proba(X)[:, 1]\n    base[\"score\"] = y_pred\n\nprint(f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], base_train[\"score\"])}')\nprint(f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])}')\nprint(f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], base_test[\"score\"])}')\n","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:23:02.625345Z","iopub.execute_input":"2024-03-17T19:23:02.625887Z","iopub.status.idle":"2024-03-17T19:24:50.956592Z","shell.execute_reply.started":"2024-03-17T19:23:02.625851Z","shell.execute_reply":"2024-03-17T19:24:50.954271Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def gini_stability(base, w_fallingrate=88.0, w_resstd=-0.5):\n    gini_in_time = base.loc[:, [\"WEEK_NUM\", \"target\", \"score\"]]\\\n        .sort_values(\"WEEK_NUM\")\\\n        .groupby(\"WEEK_NUM\")[[\"target\", \"score\"]]\\\n        .apply(lambda x: 2*roc_auc_score(x[\"target\"], x[\"score\"])-1).tolist()\n\n    x = np.arange(len(gini_in_time))\n    y = gini_in_time\n    a, b = np.polyfit(x, y, 1)\n    y_hat = a*x + b\n    residuals = y - y_hat\n    res_std = np.std(residuals)\n    avg_gini = np.mean(gini_in_time)\n    return avg_gini + w_fallingrate * min(0, a) + w_resstd * res_std\n\nstability_score_train = gini_stability(base_train)\nstability_score_valid = gini_stability(base_valid)\nstability_score_test = gini_stability(base_test)\n\nprint(f'The stability score on the train set is: {stability_score_train}')\nprint(f'The stability score on the valid set is: {stability_score_valid}')\nprint(f'The stability score on the test set is: {stability_score_test}')","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:25:45.087828Z","iopub.execute_input":"2024-03-17T19:25:45.088423Z","iopub.status.idle":"2024-03-17T19:25:46.271351Z","shell.execute_reply.started":"2024-03-17T19:25:45.088372Z","shell.execute_reply":"2024-03-17T19:25:46.270357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Submit","metadata":{}},{"cell_type":"code","source":"X_submission = data_submission[cols_pred].to_pandas()\nX_submission = convert_strings(X_submission)\ncategorical_cols = X_train.select_dtypes(include=['category']).columns\n\nfor col in categorical_cols:\n    train_categories = set(X_train[col].cat.categories)\n    submission_categories = set(X_submission[col].cat.categories)\n    new_categories = submission_categories - train_categories\n    X_submission.loc[X_submission[col].isin(new_categories), col] = \"Unknown\"\n    new_dtype = pd.CategoricalDtype(categories=train_categories, ordered=True)\n    X_submission[col] = X_submission[col].astype(new_dtype)\n\n\nX_submission = feature_generator(X_submission)\ny_submission_pred = best_model.predict_proba(X_submission)[:, 1]","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:32:14.236289Z","iopub.execute_input":"2024-03-17T19:32:14.236765Z","iopub.status.idle":"2024-03-17T19:32:14.312615Z","shell.execute_reply.started":"2024-03-17T19:32:14.236733Z","shell.execute_reply":"2024-03-17T19:32:14.311679Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"case_id\": data_submission[\"case_id\"].to_numpy(),\n    \"score\": y_submission_pred\n}).set_index('case_id')\nsubmission.to_csv(\"./submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:32:17.177077Z","iopub.execute_input":"2024-03-17T19:32:17.178371Z","iopub.status.idle":"2024-03-17T19:32:17.194924Z","shell.execute_reply.started":"2024-03-17T19:32:17.178316Z","shell.execute_reply":"2024-03-17T19:32:17.193744Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}