{"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"},{"sourceId":8048741,"sourceType":"datasetVersion","datasetId":4746316}],"dockerImageVersionId":30673,"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":"2024-04-10T23:06:47.511256Z","iopub.execute_input":"2024-04-10T23:06:47.511788Z","iopub.status.idle":"2024-04-10T23:06:48.940337Z","shell.execute_reply.started":"2024-04-10T23:06:47.511742Z","shell.execute_reply":"2024-04-10T23:06:48.939158Z"},"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":"2024-04-10T23:07:10.735946Z","iopub.execute_input":"2024-04-10T23:07:10.737426Z","iopub.status.idle":"2024-04-10T23:07:10.744260Z","shell.execute_reply.started":"2024-04-10T23:07:10.737377Z","shell.execute_reply":"2024-04-10T23:07:10.743045Z"},"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":"2024-04-10T23:07:11.635537Z","iopub.execute_input":"2024-04-10T23:07:11.635971Z","iopub.status.idle":"2024-04-10T23:07:11.646196Z","shell.execute_reply.started":"2024-04-10T23:07:11.635940Z","shell.execute_reply":"2024-04-10T23:07:11.644747Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_basetable = pl.read_parquet(dataPath + \"parquet_files/train/train_base.parquet\")\ntrain_static = pl.concat(\n    [\n        pl.read_parquet(dataPath + \"parquet_files/train/train_static_0_0.parquet\").pipe(set_table_dtypes),\n        pl.read_parquet(dataPath + \"parquet_files/train/train_static_0_1.parquet\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntrain_static_cb = pl.read_parquet(dataPath + \"parquet_files/train/train_static_cb_0.parquet\").pipe(set_table_dtypes)\ntrain_person_1 = pl.read_parquet(dataPath + \"parquet_files/train/train_person_1.parquet\").pipe(set_table_dtypes) \ntrain_credit_bureau_b_2 = pl.read_parquet(dataPath + \"parquet_files/train/train_credit_bureau_b_2.parquet\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-04-10T23:07:13.214228Z","iopub.execute_input":"2024-04-10T23:07:13.214670Z","iopub.status.idle":"2024-04-10T23:07:20.956789Z","shell.execute_reply.started":"2024-04-10T23:07:13.214638Z","shell.execute_reply":"2024-04-10T23:07:20.955697Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_basetable = pl.read_parquet(dataPath + \"parquet_files/test/test_base.parquet\")\ntest_static = pl.concat(\n    [\n        pl.read_parquet(dataPath + \"parquet_files/test/test_static_0_0.parquet\").pipe(set_table_dtypes),\n        pl.read_parquet(dataPath + \"parquet_files/test/test_static_0_1.parquet\").pipe(set_table_dtypes),\n        pl.read_parquet(dataPath + \"parquet_files/test/test_static_0_2.parquet\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntest_static_cb = pl.read_parquet(dataPath + \"parquet_files/test/test_static_cb_0.parquet\").pipe(set_table_dtypes)\ntest_person_1 = pl.read_parquet(dataPath + \"parquet_files/test/test_person_1.parquet\").pipe(set_table_dtypes) \ntest_credit_bureau_b_2 = pl.read_parquet(dataPath + \"parquet_files/test/test_credit_bureau_b_2.parquet\").pipe(set_table_dtypes) ","metadata":{"execution":{"iopub.status.busy":"2024-04-10T23:07:20.960962Z","iopub.execute_input":"2024-04-10T23:07:20.961877Z","iopub.status.idle":"2024-04-10T23:07:21.061169Z","shell.execute_reply.started":"2024-04-10T23:07:20.961829Z","shell.execute_reply":"2024-04-10T23:07:21.059781Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature engineering:\nIn this part, we can see a simple example of joining tables via case_id. Here the loading and joining is done with polars library. Polars library is blazingly fast and has much smaller memory footprint than pandas.","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":"2024-04-10T23:07:21.062663Z","iopub.execute_input":"2024-04-10T23:07:21.063022Z","iopub.status.idle":"2024-04-10T23:07:22.641283Z","shell.execute_reply.started":"2024-04-10T23:07:21.062993Z","shell.execute_reply":"2024-04-10T23:07:22.640235Z"},"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":"2024-04-10T23:07:22.642999Z","iopub.execute_input":"2024-04-10T23:07:22.643390Z","iopub.status.idle":"2024-04-10T23:07:22.665406Z","shell.execute_reply.started":"2024-04-10T23:07:22.643358Z","shell.execute_reply":"2024-04-10T23:07:22.663851Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}