{"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":30684,"isInternetEnabled":false,"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":"2024-04-10T22:28:47.601050Z","iopub.execute_input":"2024-04-10T22:28:47.601501Z","iopub.status.idle":"2024-04-10T22:28:47.627917Z","shell.execute_reply.started":"2024-04-10T22:28:47.601461Z","shell.execute_reply":"2024-04-10T22:28:47.627102Z"},"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":"2024-04-10T22:28:47.629404Z","iopub.execute_input":"2024-04-10T22:28:47.630125Z","iopub.status.idle":"2024-04-10T22:28:47.635436Z","shell.execute_reply.started":"2024-04-10T22:28:47.630093Z","shell.execute_reply":"2024-04-10T22:28:47.634063Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# utility functions\ndef 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\n\n# this converts all string columns to category columns\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":"2024-04-10T22:28:47.636840Z","iopub.execute_input":"2024-04-10T22:28:47.637718Z","iopub.status.idle":"2024-04-10T22:28:47.650110Z","shell.execute_reply.started":"2024-04-10T22:28:47.637687Z","shell.execute_reply":"2024-04-10T22:28:47.648331Z"},"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":"2024-04-10T22:28:47.652214Z","iopub.execute_input":"2024-04-10T22:28:47.652626Z","iopub.status.idle":"2024-04-10T22:29:03.864544Z","shell.execute_reply.started":"2024-04-10T22:28:47.652590Z","shell.execute_reply":"2024-04-10T22:29:03.863441Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_applprev = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/train/train_applprev_1_0.csv\").pipe(\n            set_table_dtypes\n        ),\n        pl.read_csv(dataPath + \"csv_files/train/train_applprev_1_1.csv\").pipe(\n            set_table_dtypes\n        ),\n    ],\n    how=\"vertical_relaxed\",\n)\ntrain_applprev = train_applprev.filter(pl.col(\"num_group1\") == 0)\ntrain_applprev.head()\n# total_rows = len(filtered_df)\n# unique_case_id = len(filtered_df[\"case_id\"].unique())\n\n# print(f\"Total number of rows: {total_rows}\")\n# print(f\"Number of unique case_id: {unique_case_id}\")\n# The dataset is unique at this level","metadata":{"execution":{"iopub.status.busy":"2024-04-10T22:29:03.866782Z","iopub.execute_input":"2024-04-10T22:29:03.867529Z","iopub.status.idle":"2024-04-10T22:29:13.079361Z","shell.execute_reply.started":"2024-04-10T22:29:03.867485Z","shell.execute_reply":"2024-04-10T22:29:13.078121Z"},"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":"2024-04-10T22:29:13.080698Z","iopub.execute_input":"2024-04-10T22:29:13.081022Z","iopub.status.idle":"2024-04-10T22:29:13.125732Z","shell.execute_reply.started":"2024-04-10T22:29:13.080996Z","shell.execute_reply":"2024-04-10T22:29:13.124357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_applprev = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/test/test_applprev_1_0.csv\").pipe(\n            set_table_dtypes\n        ),\n        pl.read_csv(dataPath + \"csv_files/test/test_applprev_1_1.csv\").pipe(\n            set_table_dtypes\n        ),\n    ],\n    how=\"vertical_relaxed\",\n)\ntest_applprev = test_applprev.filter(pl.col(\"num_group1\") == 0)\ntest_applprev.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-10T22:29:13.128554Z","iopub.execute_input":"2024-04-10T22:29:13.128937Z","iopub.status.idle":"2024-04-10T22:29:13.153989Z","shell.execute_reply.started":"2024-04-10T22:29:13.128905Z","shell.execute_reply":"2024-04-10T22:29:13.152601Z"},"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\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).join(train_applprev, how=\"left\", on=\"case_id\")\n","metadata":{"execution":{"iopub.status.busy":"2024-04-10T22:29:13.155828Z","iopub.execute_input":"2024-04-10T22:29:13.156186Z","iopub.status.idle":"2024-04-10T22:29:16.185956Z","shell.execute_reply.started":"2024-04-10T22:29:13.156150Z","shell.execute_reply":"2024-04-10T22:29:16.184800Z"},"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).join(test_applprev, how=\"left\", on=\"case_id\")\n","metadata":{"execution":{"iopub.status.busy":"2024-04-10T22:29:16.187345Z","iopub.execute_input":"2024-04-10T22:29:16.187747Z","iopub.status.idle":"2024-04-10T22:29:16.202804Z","shell.execute_reply.started":"2024-04-10T22:29:16.187709Z","shell.execute_reply":"2024-04-10T22:29:16.201470Z"},"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(\n    case_ids, train_size=0.6, random_state=1\n)\ncase_ids_valid, case_ids_test = train_test_split(\n    case_ids_test, train_size=0.5, random_state=1\n)\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\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))[\n            [\"case_id\", \"WEEK_NUM\", \"target\"]\n        ].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\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)\n\n# Convert the \"credacc_transactions_402L\" column in X_train to float\nX_train[\"credacc_transactions_402L\"] = X_train[\"credacc_transactions_402L\"].astype(\n    float\n).fillna(0.0)\nX_valid[\"credacc_transactions_402L\"] = X_valid[\"credacc_transactions_402L\"].astype(\n    float\n).fillna(0.0)\n\nX_submission = data_submission[cols_pred].to_pandas()\n# Convert the \"credacc_transactions_402L\" column in X_submission to float and fill NaN values with 0.0\nX_submission[\"credacc_transactions_402L\"] = (\n    X_submission[\"credacc_transactions_402L\"].fillna(0.0).astype(float)\n)\nX_submission = convert_strings(X_submission)\n\ncategorical_cols_train = X_train.select_dtypes(include=[\"category\"]).columns\ncategorical_cols_valid = X_valid.select_dtypes(include=[\"category\"]).columns\ncategorical_cols_submission = X_submission.select_dtypes(include=[\"category\"]).columns\n\n# Merge the two lists of columns\ncategorical_cols = list(set(categorical_cols_train).union(categorical_cols_submission))\n\nfor col in categorical_cols:\n    X_train[col] = X_train[col].cat.add_categories(\"Missing\").fillna(\"Missing\")\n    X_valid[col] = X_valid[col].cat.add_categories(\"Missing\").fillna(\"Missing\")\n    X_test[col] = X_test[col].cat.add_categories(\"Missing\").fillna(\"Missing\")\n    X_submission[col] = X_submission[col].cat.add_categories(\"Missing\").fillna(\"Missing\")\n\nnumerical_cols = X_train.select_dtypes(include=[np.number]).columns\nX_train[numerical_cols] = X_train[numerical_cols].fillna(0)\nnumerical_cols = X_valid.select_dtypes(include=[np.number]).columns\nX_valid[numerical_cols] = X_valid[numerical_cols].fillna(0)\nnumerical_cols = X_submission.select_dtypes(include=[np.number]).columns\nX_submission[numerical_cols] = X_submission[numerical_cols].fillna(0)\nnumerical_cols = X_test.select_dtypes(include=[np.number]).columns\nX_test[numerical_cols] = X_test[numerical_cols].fillna(0)","metadata":{"execution":{"iopub.status.busy":"2024-04-10T22:29:16.204826Z","iopub.execute_input":"2024-04-10T22:29:16.205285Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"nan_count = X_test.isna().sum().sum()\nprint(nan_count)","metadata":{"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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from catboost import CatBoostClassifier, Pool\n\n\ncat_features_index = [X_train.columns.get_loc(col) for col in categorical_cols]\n# Initialize data\ntrain_data = Pool(data=X_train, label=y_train, cat_features=cat_features_index)\nvalid_data = Pool(data=X_valid, label=y_valid, cat_features=cat_features_index)\n\n# Initialize CatBoostClassifier\ncat_model = CatBoostClassifier(\n    iterations=1000,\n    learning_rate=0.05,\n    depth=3,\n    loss_function=\"Logloss\",\n    eval_metric=\"AUC\",\n    random_seed=42,\n    bagging_temperature=0.2,\n    od_type=\"Iter\",\n    od_wait=10,\n    verbose=50,\n)\n\n# Fit model\ncat_model.fit(train_data, eval_set=valid_data)\n\n# Get predicted classes\nfor base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = cat_model.predict(X, prediction_type=\"Probability\")[:, 1]\n    base[\"score\"] = y_pred\n\nprint(\n    f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], base_train[\"score\"])}'\n)\nprint(\n    f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])}'\n)\nprint(\n    f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], base_test[\"score\"])}'\n)\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}\")\n\n\n# Ensure that all categorical columns are included in cat_features\n# cat_features = [i for i, col in enumerate(X_train.columns) if col in categorical_cols]\n\n\n# Pass cat_features to the model\n# model = CatBoostClassifier(cat_features=cat_features)\n# model.fit(X_train, y_train)\n\ny_submission_pred = cat_model.predict(X_submission)","metadata":{"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":{"trusted":true},"execution_count":null,"outputs":[]}]}