{"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":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30665,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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":"2024-03-18T21:30:39.863118Z","iopub.execute_input":"2024-03-18T21:30:39.863494Z","iopub.status.idle":"2024-03-18T21:30:41.020433Z","shell.execute_reply.started":"2024-03-18T21:30:39.863461Z","shell.execute_reply":"2024-03-18T21:30:41.019351Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-03-18T21:31:30.426407Z","iopub.execute_input":"2024-03-18T21:31:30.426811Z","iopub.status.idle":"2024-03-18T21:31:30.432225Z","shell.execute_reply.started":"2024-03-18T21:31:30.426779Z","shell.execute_reply":"2024-03-18T21:31:30.431082Z"},"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":"2024-03-18T21:31:32.311752Z","iopub.execute_input":"2024-03-18T21:31:32.312143Z","iopub.status.idle":"2024-03-18T21:31:32.320900Z","shell.execute_reply.started":"2024-03-18T21:31:32.312114Z","shell.execute_reply":"2024-03-18T21:31:32.319959Z"},"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":"2024-03-18T21:31:34.935713Z","iopub.execute_input":"2024-03-18T21:31:34.936490Z","iopub.status.idle":"2024-03-18T21:31:49.594837Z","shell.execute_reply.started":"2024-03-18T21:31:34.936453Z","shell.execute_reply":"2024-03-18T21:31:49.593929Z"},"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":"2024-03-18T21:31:49.596495Z","iopub.execute_input":"2024-03-18T21:31:49.596862Z","iopub.status.idle":"2024-03-18T21:31:49.652114Z","shell.execute_reply.started":"2024-03-18T21:31:49.596833Z","shell.execute_reply":"2024-03-18T21:31:49.651132Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-03-18T21:31:54.126711Z","iopub.execute_input":"2024-03-18T21:31:54.127358Z","iopub.status.idle":"2024-03-18T21:31:56.088619Z","shell.execute_reply.started":"2024-03-18T21:31:54.127326Z","shell.execute_reply":"2024-03-18T21:31:56.087773Z"},"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":"2024-03-18T21:31:59.658628Z","iopub.execute_input":"2024-03-18T21:31:59.658983Z","iopub.status.idle":"2024-03-18T21:31:59.670970Z","shell.execute_reply.started":"2024-03-18T21:31:59.658956Z","shell.execute_reply":"2024-03-18T21:31:59.670046Z"},"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":"2024-03-18T21:32:02.133263Z","iopub.execute_input":"2024-03-18T21:32:02.133858Z","iopub.status.idle":"2024-03-18T21:32:09.832267Z","shell.execute_reply.started":"2024-03-18T21:32:02.133826Z","shell.execute_reply":"2024-03-18T21:32:09.831379Z"},"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":"2024-03-17T19:24:08.787700Z","iopub.execute_input":"2024-03-17T19:24:08.787982Z","iopub.status.idle":"2024-03-17T19:24:08.793024Z","shell.execute_reply.started":"2024-03-17T19:24:08.787957Z","shell.execute_reply":"2024-03-17T19:24:08.791972Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.describe()","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:24:08.794135Z","iopub.execute_input":"2024-03-17T19:24:08.794407Z","iopub.status.idle":"2024-03-17T19:24:10.120261Z","shell.execute_reply.started":"2024-03-17T19:24:08.794385Z","shell.execute_reply":"2024-03-17T19:24:10.119275Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.info()","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:24:10.122044Z","iopub.execute_input":"2024-03-17T19:24:10.122345Z","iopub.status.idle":"2024-03-17T19:24:10.215020Z","shell.execute_reply.started":"2024-03-17T19:24:10.122320Z","shell.execute_reply":"2024-03-17T19:24:10.214061Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Defining a function to create new features\ndef generate_features(dataframe):\n    # Transforming annuity sum into logarithmic scale\n    dataframe['log_annuity_780A'] = np.log1p(dataframe['annuity_780A'])\n    \n    # Calculating the ratio of average views to average payments\n    dataframe['avgviews_to_avgpayments_ratio'] = dataframe['avgpmtlast12m_4525200A'] / dataframe['avginstallast24m_3658937A']\n    \n    # Computing the ratio of average payments to total debt\n    dataframe['avgpayments_to_totaldebt_ratio'] = dataframe['avgpmtlast12m_4525200A'] / dataframe['totaldebt_9A']\n\n    # Calculating standard deviation for specific payment columns\n    dataframe['payments_standard_deviation'] = dataframe[['avgpmtlast12m_4525200A', 'maxpmtlast3m_4525190A']].std(axis=1)\n    \n    # Counting the number of credits with amounts higher than the mean credit amount\n    mean_credit_amount = dataframe['credamount_770A'].mean()\n    dataframe['count_credamount_above_mean'] = (dataframe['credamount_770A'] > mean_credit_amount).astype(int)\n    \n    return dataframe\n\n# Applying the function to each DataFrame\nX_train = generate_features(X_train)\nX_valid = generate_features(X_valid)\nX_test = generate_features(X_test)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:24:13.846489Z","iopub.execute_input":"2024-03-17T19:24:13.846877Z","iopub.status.idle":"2024-03-17T19:24:14.383762Z","shell.execute_reply.started":"2024-03-17T19:24:13.846849Z","shell.execute_reply":"2024-03-17T19:24:14.382985Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import RandomizedSearchCV\nimport lightgbm as lgb\n\n# Updated hyperparameter values with variations for max_depth and learning_rate\nparam_dist = {\n    'boosting_type': ['gbdt'],  # unchanged\n    'objective': ['binary'],    # unchanged\n    'metric': ['auc'],          # unchanged\n    'max_depth': [3, 6],       \n    'num_leaves': [31, 60],     \n    'learning_rate': [0.05, 0.01],  \n    'feature_fraction': [0.9],  # unchanged\n    'bagging_fraction': [0.8],  # unchanged\n    'bagging_freq': [5],        # unchanged\n    'n_estimators': [1000],     # unchanged\n    'verbose': [-1],            # unchanged\n}\n\n# Create and train LightGBM model with hyperparameter tuning\nlgb_estimator = lgb.LGBMClassifier(random_state=42, device='gpu')\n\nrandom_search = RandomizedSearchCV(\n    estimator=lgb_estimator,\n    param_distributions=param_dist,\n    n_iter=10,  # Increased number of iterations to explore different combinations\n    scoring='roc_auc',\n    cv=3,\n    verbose=1,\n    random_state=42\n)\n\n# Train with hyperparameter tuning\nrandom_search.fit(X_train, y_train)\n\n# Output the best parameters and their scores\nprint(\"Best parameters found:\", random_search.best_params_)\nprint(\"Best AUC score:\", random_search.best_score_)\n\n# Best model with optimal parameters\nbest_model = random_search.best_estimator_","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:33:37.471865Z","iopub.execute_input":"2024-03-17T19:33:37.472223Z","iopub.status.idle":"2024-03-17T20:05:00.641155Z","shell.execute_reply.started":"2024-03-17T19:33:37.472194Z","shell.execute_reply":"2024-03-17T20:05:00.640264Z"},"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]  # Используем predict_proba для получения вероятностей\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\"])}') ","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:21:47.150610Z","iopub.execute_input":"2024-03-17T20:21:47.151269Z","iopub.status.idle":"2024-03-17T20:23:53.874365Z","shell.execute_reply.started":"2024-03-17T20:21:47.151237Z","shell.execute_reply":"2024-03-17T20:23:53.873243Z"},"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":"2024-03-17T20:26:39.273488Z","iopub.execute_input":"2024-03-17T20:26:39.273986Z","iopub.status.idle":"2024-03-17T20:26:40.296832Z","shell.execute_reply.started":"2024-03-17T20:26:39.273956Z","shell.execute_reply":"2024-03-17T20:26:40.295908Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\n# Применяем те же преобразования категориальных признаков\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 = generate_features(X_submission)\n# Применяем лучшую модель для получения предсказаний\ny_submission_pred = best_model.predict_proba(X_submission)[:, 1]","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:27:28.229659Z","iopub.execute_input":"2024-03-17T20:27:28.230403Z","iopub.status.idle":"2024-03-17T20:27:28.296037Z","shell.execute_reply.started":"2024-03-17T20:27:28.230373Z","shell.execute_reply":"2024-03-17T20:27:28.295079Z"},"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":"2024-03-17T20:27:39.387100Z","iopub.execute_input":"2024-03-17T20:27:39.387710Z","iopub.status.idle":"2024-03-17T20:27:39.396309Z","shell.execute_reply.started":"2024-03-17T20:27:39.387676Z","shell.execute_reply":"2024-03-17T20:27:39.395595Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:27:44.351535Z","iopub.execute_input":"2024-03-17T20:27:44.352164Z","iopub.status.idle":"2024-03-17T20:27:44.361353Z","shell.execute_reply.started":"2024-03-17T20:27:44.352136Z","shell.execute_reply":"2024-03-17T20:27:44.360333Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}