{"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":"# https://blog.csdn.net/s09094031/article/details/92428209?app_version=6.3.1&csdn_share_tail=%7B%22type%22%3A%22blog%22%2C%22rType%22%3A%22article%22%2C%22rId%22%3A%2292428209%22%2C%22source%22%3A%22unlogin%22%7D&utm_source=app","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:44.075421Z","iopub.execute_input":"2024-05-07T01:42:44.076175Z","iopub.status.idle":"2024-05-07T01:42:44.102666Z","shell.execute_reply.started":"2024-05-07T01:42:44.076128Z","shell.execute_reply":"2024-05-07T01:42:44.101845Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Adding Count Encoding features for String, Boolean, Categorical features\n \n
\n 📌   My idea here was to add Count Encoding of data(pl.String, pl.Boolean, pl.Categorical)\n
\n\n
\n 📌   Next Idea : Treating Imbalanced Data (like SMOTE...?)\n
\n","metadata":{}},{"cell_type":"code","source":"import sys\nfrom pathlib import Path\nimport subprocess\nimport os\nimport gc\nfrom glob import glob\n\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nfrom datetime import datetime\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nimport warnings\nwarnings.filterwarnings('ignore')\n\nROOT = '/kaggle/input/home-credit-credit-risk-model-stability'","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-05-07T01:42:44.104342Z","iopub.execute_input":"2024-05-07T01:42:44.104641Z","iopub.status.idle":"2024-05-07T01:42:46.387697Z","shell.execute_reply.started":"2024-05-07T01:42:44.104616Z","shell.execute_reply":"2024-05-07T01:42:46.386723Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import TimeSeriesSplit, GroupKFold, StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, RegressorMixin\nfrom sklearn.metrics import roc_auc_score\nimport lightgbm as lgb\n\nfrom imblearn.over_sampling import SMOTE\nfrom sklearn.preprocessing import OrdinalEncoder\nfrom sklearn.impute import KNNImputer","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:46.389506Z","iopub.execute_input":"2024-05-07T01:42:46.390031Z","iopub.status.idle":"2024-05-07T01:42:50.844630Z","shell.execute_reply.started":"2024-05-07T01:42:46.389995Z","shell.execute_reply":"2024-05-07T01:42:50.843768Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Pipeline:\n\n def set_table_dtypes(df):\n for col in df.columns:\n if col in [\"case_id\", \"WEEK_NUM\", \"num_group1\", \"num_group2\"]:\n df = df.with_columns(pl.col(col).cast(pl.Int64))\n elif col in [\"date_decision\"]:\n df = df.with_columns(pl.col(col).cast(pl.Date))\n elif col[-1] in (\"P\", \"A\"):\n df = df.with_columns(pl.col(col).cast(pl.Float64))\n elif col[-1] in (\"M\",):\n df = df.with_columns(pl.col(col).cast(pl.String))\n elif col[-1] in (\"D\",):\n df = df.with_columns(pl.col(col).cast(pl.Date))\n return df\n\n def handle_dates(df):\n for col in df.columns:\n if col[-1] in (\"D\",):\n df = df.with_columns(pl.col(col) - pl.col(\"date_decision\")) #!!?\n df = df.with_columns(pl.col(col).dt.total_days()) # t - t-1\n df = df.drop(\"date_decision\", \"MONTH\")\n return df\n\n def filter_cols(df):\n for col in df.columns:\n if col not in [\"target\", \"case_id\", \"WEEK_NUM\"]:\n isnull = df[col].is_null().mean()\n if isnull > 0.7:\n df = df.drop(col)\n \n for col in df.columns:\n if (col not in [\"target\", \"case_id\", \"WEEK_NUM\"]) & (df[col].dtype == pl.String):\n freq = df[col].n_unique()\n if (freq == 1) | (freq > 200):\n df = df.drop(col)\n \n return df","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:50.845976Z","iopub.execute_input":"2024-05-07T01:42:50.846858Z","iopub.status.idle":"2024-05-07T01:42:50.859854Z","shell.execute_reply.started":"2024-05-07T01:42:50.846819Z","shell.execute_reply":"2024-05-07T01:42:50.858888Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nclass Aggregator:\n #Please add or subtract features yourself, be aware that too many features will take up too much space.\n def num_expr(df):\n cols = [col for col in df.columns if col[-1] in (\"P\", \"A\")]\n expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n \n expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n expr_var = [pl.var(col).alias(f\"var_{col}\") for col in cols]\n\n return expr_max +expr_last+expr_mean+expr_var\n \n def date_expr(df):\n cols = [col for col in df.columns if col[-1] in (\"D\")]\n expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n return expr_max +expr_last+expr_mean\n \n def str_expr(df):\n cols = [col for col in df.columns if col[-1] in (\"M\",)]\n expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n #expr_count = [pl.count(col).alias(f\"count_{col}\") for col in cols]\n return expr_max +expr_last#+expr_count\n \n def other_expr(df):\n cols = [col for col in df.columns if col[-1] in (\"T\", \"L\")]\n expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n return expr_max +expr_last\n \n def count_expr(df):\n cols = [col for col in df.columns if \"num_group\" in col]\n expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols] \n #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n return expr_max +expr_last\n \n def get_exprs(df):\n exprs = Aggregator.num_expr(df) + \\\n Aggregator.date_expr(df) + \\\n Aggregator.str_expr(df) + \\\n Aggregator.other_expr(df) + \\\n Aggregator.count_expr(df)\n\n return exprs","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:50.862499Z","iopub.execute_input":"2024-05-07T01:42:50.862798Z","iopub.status.idle":"2024-05-07T01:42:50.878727Z","shell.execute_reply.started":"2024-05-07T01:42:50.862772Z","shell.execute_reply":"2024-05-07T01:42:50.877901Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def read_file(path, depth=None):\n df = pl.read_parquet(path)\n df = df.pipe(Pipeline.set_table_dtypes)\n if depth in [1,2]:\n df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df)) \n return df\n\ndef read_files(regex_path, depth=None):\n chunks = []\n \n for path in glob(str(regex_path)):\n df = pl.read_parquet(path)\n df = df.pipe(Pipeline.set_table_dtypes)\n if depth in [1, 2]:\n df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n chunks.append(df)\n \n df = pl.concat(chunks, how=\"vertical_relaxed\")\n df = df.unique(subset=[\"case_id\"])\n return df","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:50.879759Z","iopub.execute_input":"2024-05-07T01:42:50.880129Z","iopub.status.idle":"2024-05-07T01:42:50.892524Z","shell.execute_reply.started":"2024-05-07T01:42:50.880104Z","shell.execute_reply":"2024-05-07T01:42:50.891655Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def feature_eng(df_base, depth_0, depth_1, depth_2):\n df_base = (\n df_base\n .with_columns(\n month_decision = pl.col(\"date_decision\").dt.month(),\n weekday_decision = pl.col(\"date_decision\").dt.weekday(),\n )\n )\n for i, df in enumerate(depth_0 + depth_1 + depth_2):\n df_base = df_base.join(df, how=\"left\", on=\"case_id\", suffix=f\"_{i}\")\n df_base = df_base.pipe(Pipeline.handle_dates)\n return df_base","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:50.893715Z","iopub.execute_input":"2024-05-07T01:42:50.894310Z","iopub.status.idle":"2024-05-07T01:42:50.902707Z","shell.execute_reply.started":"2024-05-07T01:42:50.894280Z","shell.execute_reply":"2024-05-07T01:42:50.901914Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def to_pandas(df_data, cat_cols=None):\n df_data = df_data.to_pandas()\n if cat_cols is None:\n cat_cols = list(df_data.select_dtypes(\"object\").columns)\n df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n return df_data, cat_cols","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:50.903736Z","iopub.execute_input":"2024-05-07T01:42:50.904001Z","iopub.status.idle":"2024-05-07T01:42:50.912339Z","shell.execute_reply.started":"2024-05-07T01:42:50.903978Z","shell.execute_reply":"2024-05-07T01:42:50.911386Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def reduce_mem_usage(df):\n \"\"\" iterate through all the columns of a dataframe and modify the data type\n to reduce memory usage. \n \"\"\"\n start_mem = df.memory_usage().sum() / 1024**2\n print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n \n for col in df.columns:\n col_type = df[col].dtype\n if str(col_type)==\"category\":\n continue\n \n if col_type != object:\n c_min = df[col].min()\n c_max = df[col].max()\n if str(col_type)[:3] == 'int':\n if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n df[col] = df[col].astype(np.int8)\n elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n df[col] = df[col].astype(np.int16)\n elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n df[col] = df[col].astype(np.int32)\n elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n df[col] = df[col].astype(np.int64) \n else:\n if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n df[col] = df[col].astype(np.float16)\n elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n df[col] = df[col].astype(np.float32)\n else:\n df[col] = df[col].astype(np.float64)\n else:\n continue\n end_mem = df.memory_usage().sum() / 1024**2\n print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))\n print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))\n \n return df","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:50.913471Z","iopub.execute_input":"2024-05-07T01:42:50.913735Z","iopub.status.idle":"2024-05-07T01:42:50.928090Z","shell.execute_reply.started":"2024-05-07T01:42:50.913712Z","shell.execute_reply":"2024-05-07T01:42:50.927204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\n\nTRAIN_DIR = ROOT / \"parquet_files\" / \"train\"\nTEST_DIR = ROOT / \"parquet_files\" / \"test\"","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:50.929426Z","iopub.execute_input":"2024-05-07T01:42:50.930389Z","iopub.status.idle":"2024-05-07T01:42:50.938787Z","shell.execute_reply.started":"2024-05-07T01:42:50.930354Z","shell.execute_reply":"2024-05-07T01:42:50.937842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_store = {\n \"df_base\": read_file(TRAIN_DIR / \"train_base.parquet\"),\n \"depth_0\": [\n read_file(TRAIN_DIR / \"train_static_cb_0.parquet\"),\n read_files(TRAIN_DIR / \"train_static_0_*.parquet\"),\n ],\n \"depth_1\": [\n read_files(TRAIN_DIR / \"train_applprev_1_*.parquet\", 1),\n read_file(TRAIN_DIR / \"train_tax_registry_a_1.parquet\", 1),\n read_file(TRAIN_DIR / \"train_tax_registry_b_1.parquet\", 1),\n read_file(TRAIN_DIR / \"train_tax_registry_c_1.parquet\", 1),\n read_files(TRAIN_DIR / \"train_credit_bureau_a_1_*.parquet\", 1),\n read_file(TRAIN_DIR / \"train_credit_bureau_b_1.parquet\", 1),\n read_file(TRAIN_DIR / \"train_other_1.parquet\", 1),\n read_file(TRAIN_DIR / \"train_person_1.parquet\", 1),\n read_file(TRAIN_DIR / \"train_deposit_1.parquet\", 1),\n read_file(TRAIN_DIR / \"train_debitcard_1.parquet\", 1),\n ],\n \"depth_2\": [\n read_file(TRAIN_DIR / \"train_credit_bureau_b_2.parquet\", 2),\n read_files(TRAIN_DIR / \"train_credit_bureau_a_2_*.parquet\", 2),\n read_file(TRAIN_DIR / \"train_applprev_2.parquet\", 2),\n read_file(TRAIN_DIR / \"train_person_2.parquet\", 2)\n ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:42:50.940091Z","iopub.execute_input":"2024-05-07T01:42:50.940392Z","iopub.status.idle":"2024-05-07T01:45:17.792250Z","shell.execute_reply.started":"2024-05-07T01:42:50.940367Z","shell.execute_reply":"2024-05-07T01:45:17.791124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\ndf_train = df_train.pipe(Pipeline.filter_cols)\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:45:17.793479Z","iopub.execute_input":"2024-05-07T01:45:17.793798Z","iopub.status.idle":"2024-05-07T01:45:43.036780Z","shell.execute_reply.started":"2024-05-07T01:45:17.793771Z","shell.execute_reply":"2024-05-07T01:45:43.035770Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cnt_encoding_cols = df_train.select(pl.selectors.by_dtype([pl.String, pl.Boolean, pl.Categorical])).columns\n\nmappings = {}\nfor col in cnt_encoding_cols:\n mappings[col] = df_train.group_by(col).len()\n\ndf_train_lazy = df_train.select(mappings.keys()).lazy()\n# df_train_lazy = pl.LazyFrame(df_train.select('case_id'))\n\nfor col, mapping in mappings.items():\n remapping = {category: count for category, count in mapping.rows()}\n remapping[None] = -2\n expr = pl.col(col).replace(\n remapping,\n default=-1,\n )\n df_train_lazy = df_train_lazy.with_columns(expr.alias(col + '_cnt'))\n del col, mapping, remapping\n gc.collect()\n\ndel mappings\ntransformed_train = df_train_lazy.collect()\n\ndf_train = pl.concat([df_train, transformed_train.select(\"^*cnt$\")], how='horizontal')\ndel transformed_train, cnt_encoding_cols\n\ngc.collect()\n","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:45:43.038002Z","iopub.execute_input":"2024-05-07T01:45:43.038297Z","iopub.status.idle":"2024-05-07T01:46:09.532148Z","shell.execute_reply.started":"2024-05-07T01:45:43.038272Z","shell.execute_reply":"2024-05-07T01:46:09.531170Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndf_train, cat_cols = to_pandas(df_train)\ndf_train = reduce_mem_usage(df_train)\n\n# Drop date columns\ndate_cols = df_train.columns[df_train.columns.str.endswith('D')]\ndf_train = df_train.drop(date_cols, axis=1)\n\nprint(\"train data shape:\\t\", df_train.shape)\nnums=df_train.select_dtypes(exclude='category').columns\n\nfrom itertools import combinations, permutations\n#df_train=df_train[nums]\nnans_df = df_train[nums].isna()\nnans_groups={}\nfor col in nums:\n cur_group = nans_df[col].sum()\n try:\n nans_groups[cur_group].append(col)\n except:\n nans_groups[cur_group]=[col]\ndel nans_df; x=gc.collect()\n\ndef reduce_group(grps):\n use = []\n for g in grps:\n mx = 0; vx = g[0]\n for gg in g:\n n = df_train[gg].nunique()\n if n>mx:\n mx = n\n vx = gg\n #print(str(gg)+'-'+str(n),', ',end='')\n use.append(vx)\n #print()\n print('Use these',use)\n return use\n\ndef group_columns_by_correlation(matrix, threshold=0.8):\n # 莥įŽ—列䚋间įš„į›¸å…ŗ性\n correlation_matrix = matrix.corr()\n\n # 分įģ„列\n groups = []\n remaining_cols = list(matrix.columns)\n while remaining_cols:\n col = remaining_cols.pop(0)\n group = [col]\n correlated_cols = [col]\n for c in remaining_cols:\n if correlation_matrix.loc[col, c] >= threshold:\n group.append(c)\n correlated_cols.append(c)\n groups.append(group)\n remaining_cols = [c for c in remaining_cols if c not in correlated_cols]\n \n return groups\n\nuses=[]\nfor k,v in nans_groups.items():\n if len(v)>1:\n Vs = nans_groups[k]\n #cross_features=list(combinations(Vs, 2))\n #make_corr(Vs)\n grps= group_columns_by_correlation(df_train[Vs], threshold=0.8)\n use=reduce_group(grps)\n uses=uses+use\n #make_corr(use)\n else:\n uses=uses+v\n print('####### NAN count =',k)\nprint(uses)\nprint(len(uses))\nuses=uses+list(df_train.select_dtypes(include='category').columns)\nprint(len(uses))\ndf_train=df_train[uses]\ndf_train.drop(['requesttype_4525192L_cnt','max_empl_employedtotal_800L_cnt', 'max_empl_industry_691L_cnt'], axis=1, inplace=True)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:46:09.536830Z","iopub.execute_input":"2024-05-07T01:46:09.537147Z","iopub.status.idle":"2024-05-07T01:47:04.528317Z","shell.execute_reply.started":"2024-05-07T01:46:09.537122Z","shell.execute_reply":"2024-05-07T01:47:04.526903Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = pd.read_csv(\"/kaggle/input/home-credit-credit-risk-model-stability/sample_submission.csv\")\ndevice='gpu'\n#n_samples=200000\nDRY_RUN = True if sample.shape[0] == 10 else False \nif DRY_RUN:\n device='cpu'\n df_train = df_train.iloc[:1000000]\nprint(device)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.529348Z","iopub.status.idle":"2024-05-07T01:47:04.529710Z","shell.execute_reply.started":"2024-05-07T01:47:04.529540Z","shell.execute_reply":"2024-05-07T01:47:04.529554Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_store = {\n \"df_base\": read_file(TEST_DIR / \"test_base.parquet\"),\n \"depth_0\": [\n read_file(TEST_DIR / \"test_static_cb_0.parquet\"),\n read_files(TEST_DIR / \"test_static_0_*.parquet\"),\n ],\n \"depth_1\": [\n read_files(TEST_DIR / \"test_applprev_1_*.parquet\", 1),\n read_file(TEST_DIR / \"test_tax_registry_a_1.parquet\", 1),\n read_file(TEST_DIR / \"test_tax_registry_b_1.parquet\", 1),\n read_file(TEST_DIR / \"test_tax_registry_c_1.parquet\", 1),\n read_files(TEST_DIR / \"test_credit_bureau_a_1_*.parquet\", 1),\n read_file(TEST_DIR / \"test_credit_bureau_b_1.parquet\", 1),\n read_file(TEST_DIR / \"test_other_1.parquet\", 1),\n read_file(TEST_DIR / \"test_person_1.parquet\", 1),\n read_file(TEST_DIR / \"test_deposit_1.parquet\", 1),\n read_file(TEST_DIR / \"test_debitcard_1.parquet\", 1),\n ],\n \"depth_2\": [\n read_file(TEST_DIR / \"test_credit_bureau_b_2.parquet\", 2),\n read_files(TEST_DIR / \"test_credit_bureau_a_2_*.parquet\", 2),\n read_file(TEST_DIR / \"test_applprev_2.parquet\", 2),\n read_file(TEST_DIR / \"test_person_2.parquet\", 2)\n ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.530980Z","iopub.status.idle":"2024-05-07T01:47:04.531324Z","shell.execute_reply.started":"2024-05-07T01:47:04.531157Z","shell.execute_reply":"2024-05-07T01:47:04.531171Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = feature_eng(**data_store)\nprint(\"test data shape:\\t\", df_test.shape)\ndel data_store\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.532582Z","iopub.status.idle":"2024-05-07T01:47:04.532948Z","shell.execute_reply.started":"2024-05-07T01:47:04.532756Z","shell.execute_reply":"2024-05-07T01:47:04.532770Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cnt_encoding_cols = df_test.select(pl.selectors.by_dtype([pl.String, pl.Boolean, pl.Categorical])).columns\n\nmappings = {}\nfor col in cnt_encoding_cols:\n mappings[col] = df_test.group_by(col).len()\n\ndf_test_lazy = df_test.select(mappings.keys()).lazy()\n# df_test_lazy = pl.LazyFrame(df_test.select('case_id'))\n\nfor col, mapping in mappings.items():\n remapping = {category: count for category, count in mapping.rows()}\n remapping[None] = -2\n expr = pl.col(col).replace(\n remapping,\n default=-1,\n )\n df_test_lazy = df_test_lazy.with_columns(expr.alias(col + '_cnt'))\n del col, mapping, remapping\ndel mappings\ntransformed_test = df_test_lazy.collect()\n\ndf_test = pl.concat([df_test, transformed_test.select(\"^*cnt$\")], how='horizontal')\ndel transformed_test, cnt_encoding_cols","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.534160Z","iopub.status.idle":"2024-05-07T01:47:04.534673Z","shell.execute_reply.started":"2024-05-07T01:47:04.534416Z","shell.execute_reply":"2024-05-07T01:47:04.534436Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndf_test = df_test.select([col for col in df_train.columns if col not in ['requesttype_4525192L_cnt',\n 'max_empl_employedtotal_800L_cnt',\n 'max_empl_industry_691L_cnt',\n \"target\"]])\nprint(\"train data shape:\\t\", df_train.shape)\nprint(\"test data shape:\\t\", df_test.shape)\n\ndf_test, cat_cols = to_pandas(df_test, cat_cols)\ndf_test = reduce_mem_usage(df_test)\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.536370Z","iopub.status.idle":"2024-05-07T01:47:04.536864Z","shell.execute_reply.started":"2024-05-07T01:47:04.536610Z","shell.execute_reply":"2024-05-07T01:47:04.536631Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Selection","metadata":{}},{"cell_type":"code","source":"# drop_list = ['max_empl_employedtotal_800L', 'monthsannuity_845L', 'lastactivateddate_801D', \n# 'max_numberofoverdueinstls_725L', 'requesttype_4525192L', 'max_pmts_year_507T', \n# 'lastrejectcommodtypec_5251769M', 'numinstpaidlate1d_3546852L', 'numinstmatpaidtearly2d_4499204L', \n# 'max_overdueamountmaxdateyear_2T', 'max_overdueamountmaxdateyear_994T', 'twobodfilling_608L', \n# 'maxdpdlast12m_727P', 'numinsttopaygrest_4493213L', 'currdebtcredtyperange_828A', 'maxdpdlast9m_1059P', \n# 'numinstpaid_4499208L', 'applicationscnt_867L', 'numinstlswithoutdpd_562L', 'fourthquarter_440L', \n# 'max_num_group1_6', 'max_safeguarantyflag_411L', 'max_dpdmaxdateyear_896T', 'numinstregularpaid_973L', \n# 'avgdbdtollast24m_4525197P', 'numinstpaidearly5dest_4493211L', 'numinstpaidearly5dobd_4499205L', \n# 'homephncnt_628L', 'max_role_1084L', 'max_remitter_829L', 'numrejects9m_859L', \n# 'numinstlallpaidearly3d_817L', 'numinstpaidearly3dest_4493216L', 'annuitynextmonth_57A', \n# 'numinstregularpaidest_4493210L', 'firstquarter_103L', 'clientscnt_533L', 'maxdpdlast3m_392P', \n# 'sellerplacescnt_216L', 'secondquarter_766L', 'max_periodicityofpmts_1102L', 'numinstlsallpaid_934L', \n# 'opencred_647L', 'numinstls_657L', 'numactivecredschannel_414L', 'numinstpaidearly3d_3546850L', \n# 'numinstpaidearlyest_4493214L', 'max_totaldebtoverduevalue_718A', 'paytype1st_925L', \n# 'max_inittransactioncode_279L', 'max_contractst_545M', 'max_cancelreason_3545846M', \n# 'max_rejectreason_755M', 'max_personindex_1023L', 'max_subjectroles_name_838M', 'maxdpdlast6m_474P', \n# 'max_subjectrole_182M', 'actualdpdtolerance_344P', 'max_num_group1_9', 'max_collaterals_typeofguarante_669M', \n# 'numinstpaidearly_338L', 'clientscnt_887L', 'maritalst_893M', 'max_subjectrole_93M', 'max_type_25L', \n# 'max_refreshdate_3813885D', 'numinstpaidearly5d_1087L', 'max_actualdpd_943P', 'max_description_351M', \n# 'education_88M', 'clientscnt_946L', 'clientscnt12m_3712952L', 'numactiverelcontr_750L', \n# 'max_education_927M', 'applicationscnt_1086L', 'sellerplacecnt_915L', 'max_purposeofcred_426M', \n# 'max_subjectroles_name_541M', 'clientscnt_1022L', 'clientscnt_360L', 'max_totaloutstanddebtvalue_668A', \n# 'applicationscnt_629L', 'max_outstandingamount_354A', 'clientscnt_1071L', 'numactivecreds_622L', \n# 'clientscnt_493L', 'paytype_783L', 'clientscnt6m_3712949L', 'clientscnt_304L', 'max_classificationofcontr_13M', \n# 'numnotactivated_1143L', 'commnoinclast6m_3546845L', 'max_numberofoutstandinstls_520L', \n# 'applicationscnt_464L', 'clientscnt_1130L', 'max_numberofoverdueinstls_834L', 'clientscnt3m_3712950L', \n# 'max_rejectreasonclient_4145042M', 'max_contaddr_smempladdr_334L', 'numpmtchanneldd_318L', \n# 'numcontrs3months_479L', 'max_overdueamount_31A', 'max_collaterals_typeofguarante_359M', \n# 'clientscnt_257L', 'clientscnt_157L', 'applications30d_658L', 'clientscnt_100L', \n# 'max_collater_typofvalofguarant_298M', 'max_pmts_month_706T', 'max_pmts_month_158T', \n# 'mastercontrexist_109L', 'max_collater_typofvalofguarant_407M', 'mastercontrelectronic_519L', \n# 'applicationcnt_361L', 'max_persontype_1072L', 'max_empladdr_district_926M', 'deferredmnthsnum_166L', \n# 'max_empladdr_zipcode_114M', 'max_persontype_792L', 'max_contaddr_matchlist_1032L']","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.538506Z","iopub.status.idle":"2024-05-07T01:47:04.539003Z","shell.execute_reply.started":"2024-05-07T01:47:04.538738Z","shell.execute_reply":"2024-05-07T01:47:04.538757Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_train = df_train.drop(drop_list)\n# df_test = df_test.drop(drop_list)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.540176Z","iopub.status.idle":"2024-05-07T01:47:04.540675Z","shell.execute_reply.started":"2024-05-07T01:47:04.540407Z","shell.execute_reply":"2024-05-07T01:47:04.540427Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Handle categorical features (Ordinal encoding)","metadata":{}},{"cell_type":"code","source":"# cat_list = [col for col in df_train.columns if df_train[col].dtype.name == 'category']\n\n# catfreq_dict = {}\n# catcatfreq_dict = {}\n\n# for col in cat_list:\n# catfreq_dict[col] = len(list(df_train[col].value_counts()))\n# catcatfreq_dict[col] = {}\n# for d in dict(df_train[col].value_counts()).items():\n# catcatfreq_dict[col][d[0]] = d[1]\n\n# catfreq_df = pd.DataFrame.from_dict(catfreq_dict, orient='index', columns=['Categories'])\n# display(catfreq_df.sort_values(by=\"Categories\", ascending=False).head())\n# display(catfreq_df.sort_values(by=\"Categories\", ascending=True).head())","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.541936Z","iopub.status.idle":"2024-05-07T01:47:04.542385Z","shell.execute_reply.started":"2024-05-07T01:47:04.542153Z","shell.execute_reply":"2024-05-07T01:47:04.542172Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ordinal_enc = OrdinalEncoder(handle_unknown='use_encoded_value', unknown_value=np.nan)\n# df_train[cat_list] = ordinal_enc.fit_transform(df_train[cat_list])\n# df_test[cat_list] = ordinal_enc.transform(df_test[cat_list])\n# df_train[cat_list].head()","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.543843Z","iopub.status.idle":"2024-05-07T01:47:04.544328Z","shell.execute_reply.started":"2024-05-07T01:47:04.544085Z","shell.execute_reply":"2024-05-07T01:47:04.544107Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Handle NaN","metadata":{}},{"cell_type":"code","source":"# nan_list = []\n# for col, boo in df_train.isnull().any().items():\n# if boo == True:\n# nan_list.append(col)\n\n# print(f\"Number of col contains Nan value: {len(nan_list)}\")\n# for i, v in df_train.isna().sum().items():\n# if v/len(df_train)>0.6:\n# print(f\"{i} : \\t {round((v/len(df_train))*100)}% Nan \")","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.546356Z","iopub.status.idle":"2024-05-07T01:47:04.546840Z","shell.execute_reply.started":"2024-05-07T01:47:04.546592Z","shell.execute_reply":"2024-05-07T01:47:04.546614Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ### trial\n# from sklearn.impute import SimpleImputer\n# imp = SimpleImputer(missing_values=np.nan, strategy='mean')\n# df_train[nan_list] = imp.fit_transform(df_train[nan_list])\n# df_test[nan_list] = imp.transform(df_test[nan_list])","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.548230Z","iopub.status.idle":"2024-05-07T01:47:04.548755Z","shell.execute_reply.started":"2024-05-07T01:47:04.548467Z","shell.execute_reply":"2024-05-07T01:47:04.548488Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ## no work (too slow..) \n# ## require dimensionality reduction first & features with high feature impor. \n# imputer = KNNImputer()\n# df_train = imputer.fit_transform(df_train)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.550208Z","iopub.status.idle":"2024-05-07T01:47:04.550700Z","shell.execute_reply.started":"2024-05-07T01:47:04.550438Z","shell.execute_reply":"2024-05-07T01:47:04.550469Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\ndf_train= df_train.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"])\n# df_train, y = SMOTE().fit_resample(df_train, y)\ncv = StratifiedGroupKFold(n_splits=10, shuffle=False)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.551819Z","iopub.status.idle":"2024-05-07T01:47:04.552299Z","shell.execute_reply.started":"2024-05-07T01:47:04.552114Z","shell.execute_reply":"2024-05-07T01:47:04.552132Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nparams = {\n \"boosting_type\": \"gbdt\",\n \"objective\": \"binary\",\n \"metric\": \"auc\",\n \"max_depth\": 10, \n \"learning_rate\": 0.05,\n \"n_estimators\": 2000, \n \"colsample_bytree\": 0.8,\n \"colsample_bynode\": 0.8,\n \"verbose\": -1,\n \"random_state\": 42,\n \"reg_alpha\": 0.1,\n \"reg_lambda\": 10,\n \"extra_trees\":True,\n 'num_leaves':64,\n \"sample_weight\":'balanced',\n \"device\": \"gpu\", \n \"verbose\": -1,\n}\n\nfitted_models = []\ncv_scores = []\n\n\nfor idx_train, idx_valid in cv.split(df_train, y, groups=weeks):# Because it takes a long time to divide the data set, \n X_train, y_train = df_train.iloc[idx_train], y.iloc[idx_train]# each time the data set is divided, two models are trained to each other twice, which saves time.\n X_valid, y_valid = df_train.iloc[idx_valid], y.iloc[idx_valid]\n model = lgb.LGBMClassifier(**params)\n model.fit(\n X_train, y_train,\n eval_set = [(X_valid, y_valid)],\n callbacks = [lgb.log_evaluation(200), lgb.early_stopping(100)] )\n fitted_models.append(model)\n y_pred_valid = model.predict_proba(X_valid)[:,1]\n auc_score = roc_auc_score(y_valid, y_pred_valid)\n cv_scores.append(auc_score)\n \nprint(\"CV AUC scores: \", cv_scores)\nprint(\"Maximum CV AUC score: \", max(cv_scores))","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.553843Z","iopub.status.idle":"2024-05-07T01:47:04.554199Z","shell.execute_reply.started":"2024-05-07T01:47:04.554036Z","shell.execute_reply":"2024-05-07T01:47:04.554051Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class VotingModel(BaseEstimator, RegressorMixin):\n def __init__(self, estimators):\n super().__init__()\n self.estimators = estimators\n \n def fit(self, X, y=None):\n return self\n \n def predict(self, X):\n y_preds = [estimator.predict(X) for estimator in self.estimators]\n return np.mean(y_preds, axis=0)\n \n def predict_proba(self, X):\n y_preds = [estimator.predict_proba(X) for estimator in self.estimators]\n return np.mean(y_preds, axis=0)\n\nmodel = VotingModel(fitted_models)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.555310Z","iopub.status.idle":"2024-05-07T01:47:04.555655Z","shell.execute_reply.started":"2024-05-07T01:47:04.555471Z","shell.execute_reply":"2024-05-07T01:47:04.555484Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lgb.plot_importance(fitted_models[2], importance_type=\"split\", figsize=(10,50))\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.557065Z","iopub.status.idle":"2024-05-07T01:47:04.557379Z","shell.execute_reply.started":"2024-05-07T01:47:04.557224Z","shell.execute_reply":"2024-05-07T01:47:04.557237Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"features = X_train.columns\nimportances = fitted_models[2].feature_importances_\nfeature_importance = pd.DataFrame({'importance':importances,'features':features}).sort_values('importance', ascending=False).reset_index(drop=True)\nfeature_importance\n\ndrop_list = []\nfor i, f in feature_importance.iterrows():\n if f['importance']<80:\n drop_list.append(f['features'])\nprint(f\"Number of features which are not important: {len(drop_list)} \")\n\nprint(drop_list)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.559298Z","iopub.status.idle":"2024-05-07T01:47:04.560227Z","shell.execute_reply.started":"2024-05-07T01:47:04.559541Z","shell.execute_reply":"2024-05-07T01:47:04.559562Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Submission","metadata":{}},{"cell_type":"code","source":"df_test = df_test.drop(columns=[\"WEEK_NUM\"])\ndf_test = df_test.set_index(\"case_id\")\n","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.562028Z","iopub.status.idle":"2024-05-07T01:47:04.562501Z","shell.execute_reply.started":"2024-05-07T01:47:04.562256Z","shell.execute_reply":"2024-05-07T01:47:04.562276Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = pd.Series(model.predict_proba(df_test)[:, 1], index=df_test.index)\ndf_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\ndf_subm = df_subm.set_index(\"case_id\")\n\ndf_subm[\"score\"] = y_pred\ndf_subm.to_csv(\"submission.csv\")\ndf_subm","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.564010Z","iopub.status.idle":"2024-05-07T01:47:04.564489Z","shell.execute_reply.started":"2024-05-07T01:47:04.564239Z","shell.execute_reply":"2024-05-07T01:47:04.564259Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#X_test = df_test.drop(columns=[\"WEEK_NUM\"])\n#X_test = X_test.set_index(\"case_id\")\n\n#lgb_pred = pd.Series(model.predict_proba(X_test)[:, 1], index=X_test.index)\n\n#df_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\n#df_subm = df_subm.set_index(\"case_id\")\n\n#df_subm[\"score\"] = lgb_pred\n\n#df_subm.head()\n\n#df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.566282Z","iopub.status.idle":"2024-05-07T01:47:04.566774Z","shell.execute_reply.started":"2024-05-07T01:47:04.566516Z","shell.execute_reply":"2024-05-07T01:47:04.566536Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"* handle nan value (both numeric & categorical)\n* preprocess the minority categorical value (drop / keep)\n* float to int after ordinal encode\n* oversampling (smote? (considering date feature)\n* high dimension (pca) \n* create new features based on high fea_imp features\n...\n...","metadata":{}},{"cell_type":"code","source":"# X_resampled, y_resampled = SMOTE().fit_resample(X, y)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T01:47:04.568181Z","iopub.status.idle":"2024-05-07T01:47:04.568544Z","shell.execute_reply.started":"2024-05-07T01:47:04.568348Z","shell.execute_reply":"2024-05-07T01:47:04.568362Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}