{"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":"nvidiaTeslaT4","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"},{"sourceId":8366526,"sourceType":"datasetVersion","datasetId":4973267}],"dockerImageVersionId":30665,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"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'\n\nfrom 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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-05-11T02:17:08.453822Z","iopub.execute_input":"2024-05-11T02:17:08.454416Z","iopub.status.idle":"2024-05-11T02:17:13.626880Z","shell.execute_reply.started":"2024-05-11T02:17:08.454382Z","shell.execute_reply":"2024-05-11T02:17:13.626025Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"raw","source":"","metadata":{}},{"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\n\n\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 return expr_max +expr_last+expr_mean\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\n\ndef 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\n\ndef 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\n\ndef 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\n\ndef 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":"2024-05-11T02:17:13.628469Z","iopub.execute_input":"2024-05-11T02:17:13.629068Z","iopub.status.idle":"2024-05-11T02:17:13.667188Z","shell.execute_reply.started":"2024-05-11T02:17:13.629040Z","shell.execute_reply":"2024-05-11T02:17:13.665987Z"},"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":"2024-05-11T02:17:13.668530Z","iopub.execute_input":"2024-05-11T02:17:13.668926Z","iopub.status.idle":"2024-05-11T02:17:13.681051Z","shell.execute_reply.started":"2024-05-11T02:17:13.668894Z","shell.execute_reply":"2024-05-11T02:17:13.680198Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndata_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":"2024-05-11T02:17:13.683388Z","iopub.execute_input":"2024-05-11T02:17:13.684002Z","iopub.status.idle":"2024-05-11T02:19:27.998494Z","shell.execute_reply.started":"2024-05-11T02:17:13.683971Z","shell.execute_reply":"2024-05-11T02:19:27.997390Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndf_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\ngc.collect()\ndf_train = df_train.pipe(Pipeline.filter_cols)\ndf_train, cat_cols = to_pandas(df_train)\ndf_train = reduce_mem_usage(df_train)\nprint(\"train data shape:\\t\", df_train.shape)\nnums=df_train.select_dtypes(exclude='category').columns\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 # 计算列之间的相关性\n correlation_matrix = matrix.corr()\n\n # 分组列\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]","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:19:27.999909Z","iopub.execute_input":"2024-05-11T02:19:28.000203Z","iopub.status.idle":"2024-05-11T02:21:05.436929Z","shell.execute_reply.started":"2024-05-11T02:19:28.000177Z","shell.execute_reply":"2024-05-11T02:21:05.436002Z"},"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\nn_est=6000\nDRY_RUN = True if sample.shape[0] == 10 else False \nif DRY_RUN:\n device='cpu'\n df_train = df_train.iloc[:50000]\n #n_samples=10000\n n_est=600\nprint(device)","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:21:05.438222Z","iopub.execute_input":"2024-05-11T02:21:05.438586Z","iopub.status.idle":"2024-05-11T02:21:05.452337Z","shell.execute_reply.started":"2024-05-11T02:21:05.438553Z","shell.execute_reply":"2024-05-11T02:21:05.451547Z"},"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":"2024-05-11T02:21:05.453436Z","iopub.execute_input":"2024-05-11T02:21:05.453777Z","iopub.status.idle":"2024-05-11T02:21:05.782858Z","shell.execute_reply.started":"2024-05-11T02:21:05.453752Z","shell.execute_reply":"2024-05-11T02:21:05.781971Z"},"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()\ndf_test = df_test.select([col for col in df_train.columns if col != \"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":"2024-05-11T02:21:05.785224Z","iopub.execute_input":"2024-05-11T02:21:05.785511Z","iopub.status.idle":"2024-05-11T02:21:06.283565Z","shell.execute_reply.started":"2024-05-11T02:21:05.785487Z","shell.execute_reply":"2024-05-11T02:21:06.282700Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Selection","metadata":{}},{"cell_type":"code","source":"y = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\ntarget = df_train[\"target\"]\ndf_train= df_train.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"])\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)\n","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:21:06.284770Z","iopub.execute_input":"2024-05-11T02:21:06.285114Z","iopub.status.idle":"2024-05-11T02:21:06.414912Z","shell.execute_reply.started":"2024-05-11T02:21:06.285082Z","shell.execute_reply":"2024-05-11T02:21:06.414149Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train[cat_cols] = df_train[cat_cols].astype(str)\ndf_test[cat_cols] = df_test[cat_cols].astype(str)","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:21:06.416005Z","iopub.execute_input":"2024-05-11T02:21:06.416341Z","iopub.status.idle":"2024-05-11T02:21:06.694222Z","shell.execute_reply.started":"2024-05-11T02:21:06.416312Z","shell.execute_reply":"2024-05-11T02:21:06.693464Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"params = {'boosting_type': 'gbdt',\n 'objective': 'binary',\n 'metric': 'auc',\n 'n_estimators': 3000,\n 'random_state': 42,\n 'extra_trees': True,\n 'device': 'gpu',\n 'verbose': -1,\n 'sample_weight': 'balanced',\n 'zero_as_missing': True,\n 'max_depth': 4,\n 'colsample_bytree': 0.7154,\n 'colsample_bynode': 0.6163,\n 'num_leaves': 26,\n 'min_data_in_leaf': 82,\n 'bagging_fraction': 0.9272,\n 'bagging_freq': 2,\n 'feature_fraction': 0.8439,\n 'max_bin': 198,\n 'min_gain_to_split': 0.0510,\n 'learning_rate': 0.0651,\n 'reg_alpha': 0.2050,\n 'reg_lambda': 2.3108,\n 'min_sum_hessian_in_leaf': 3.07e-06,\n 'lambda_l1': 0.06476,\n 'lambda_l2': 0.35793} ","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:21:06.695290Z","iopub.execute_input":"2024-05-11T02:21:06.695591Z","iopub.status.idle":"2024-05-11T02:21:06.702131Z","shell.execute_reply.started":"2024-05-11T02:21:06.695567Z","shell.execute_reply":"2024-05-11T02:21:06.701120Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nfrom catboost import CatBoostClassifier, Pool\n\nfitted_models_cat = []\nfitted_models_lgb = []\n\ncv_scores_cat = []\ncv_scores_lgb = []\n\n\nfor idx_train, idx_valid in cv.split(df_train, y, groups=weeks):#\n X_train, y_train = df_train.iloc[idx_train], y.iloc[idx_train]# \n X_valid, y_valid = df_train.iloc[idx_valid], y.iloc[idx_valid]\n train_pool = Pool(X_train, y_train,cat_features=cat_cols)\n val_pool = Pool(X_valid, y_valid,cat_features=cat_cols)\n '''\n clf = CatBoostClassifier(\n eval_metric='AUC',\n task_type='GPU',\n learning_rate=0.03,\n iterations=n_est)\n random_seed=42\n clf.fit(train_pool, eval_set=val_pool,verbose=300,early_stopping_rounds = 200)\n fitted_models_cat.append(clf)\n y_pred_valid = clf.predict_proba(X_valid)[:,1]\n auc_score = roc_auc_score(y_valid, y_pred_valid)\n cv_scores_cat.append(auc_score)\n '''\n \n \n X_train[cat_cols] = X_train[cat_cols].astype(\"category\")\n X_valid[cat_cols] = X_valid[cat_cols].astype(\"category\")\n \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 \n fitted_models_lgb.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_lgb.append(auc_score)\n \n \n#print(\"CV AUC scores: \", cv_scores_cat)\n#print(\"Maximum CV AUC score: \", max(cv_scores_cat))\n\n\nprint(\"CV AUC scores: \", cv_scores_lgb)\nprint(\"Maximum CV AUC score: \", max(cv_scores_lgb))","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:21:06.703229Z","iopub.execute_input":"2024-05-11T02:21:06.703523Z","iopub.status.idle":"2024-05-11T02:22:05.678219Z","shell.execute_reply.started":"2024-05-11T02:21:06.703487Z","shell.execute_reply":"2024-05-11T02:22:05.677241Z"},"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 \n y_preds = [estimator.predict_proba(X) for estimator in self.estimators[:5]]\n \n X[cat_cols] = X[cat_cols].astype(\"category\")\n y_preds += [estimator.predict_proba(X) for estimator in self.estimators[5:]]\n \n return np.mean(y_preds, axis=0)\n \n def predict_proba_lgb(self, X):\n\n X[cat_cols] = X[cat_cols].astype(\"category\")\n y_preds = [estimator.predict_proba(X) for estimator in self.estimators]\n \n return np.mean(y_preds, axis=0)\n\nmodel = VotingModel(fitted_models_lgb)","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:22:05.679350Z","iopub.execute_input":"2024-05-11T02:22:05.679668Z","iopub.status.idle":"2024-05-11T02:22:05.688981Z","shell.execute_reply.started":"2024-05-11T02:22:05.679641Z","shell.execute_reply":"2024-05-11T02:22:05.688069Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install --no-index --find-links /kaggle/input/faiss-whl/faiss_gpu-1.7.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl faiss-gpu","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:22:05.690312Z","iopub.execute_input":"2024-05-11T02:22:05.691098Z","iopub.status.idle":"2024-05-11T02:22:20.627385Z","shell.execute_reply.started":"2024-05-11T02:22:05.691061Z","shell.execute_reply":"2024-05-11T02:22:20.626238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import faiss\nfrom scipy.spatial.distance import cdist\nfrom sklearn.preprocessing import MinMaxScaler,StandardScaler\n\n#数据处理\nX_train = df_train.drop(columns=['month_decision'])\nX_test = df_test.drop(columns=['month_decision'])\n\nX_test = X_test.loc[:,X_test.select_dtypes(include=[np.number]).columns]\n\nX_train = X_train.loc[:,X_train.select_dtypes(include=[np.number]).columns]\n\nX_test.fillna(0,inplace=True)\nX_train.fillna(0,inplace=True)\n\nX_train = X_train.iloc[:,:50].values\nX_test = X_test.iloc[:,:50].values\n\nscaler = MinMaxScaler()\nscaler.fit(np.concatenate([X_train,X_test]))\nX_train = scaler.transform(X_train)\nX_test = scaler.transform(X_test)\n\nX_test = X_test.astype(X_train.dtype)\n\nX_train = np.ascontiguousarray(X_train)\nX_test = np.ascontiguousarray(X_test)\n\n#计算相似度\nd = X_train.shape[1]\n\nindex = faiss.IndexFlatL2(d)\nindex.add(X_train)\n\nk = 1\ndistances, labels = index.search(X_test, k)","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:22:20.628965Z","iopub.execute_input":"2024-05-11T02:22:20.629288Z","iopub.status.idle":"2024-05-11T02:22:21.344271Z","shell.execute_reply.started":"2024-05-11T02:22:20.629261Z","shell.execute_reply":"2024-05-11T02:22:21.343412Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = df_test.drop(columns=[\"WEEK_NUM\"])\ndf_test = df_test.set_index(\"case_id\")\n\ny_pred = pd.Series(model.predict_proba_lgb(df_test)[:, 1], index=df_test.index)\ndf_test['similar_row'] = labels\ndf_test['similar_distances'] = distances","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:33:36.319938Z","iopub.execute_input":"2024-05-11T02:33:36.320314Z","iopub.status.idle":"2024-05-11T02:33:38.071998Z","shell.execute_reply.started":"2024-05-11T02:33:36.320283Z","shell.execute_reply":"2024-05-11T02:33:38.070524Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test['simliar_target'] = target.iloc[df_test['similar_row']].values\ndf_test['pred'] = y_pred","metadata":{"execution":{"iopub.status.busy":"2024-05-11T02:35:35.378054Z","iopub.execute_input":"2024-05-11T02:35:35.378997Z","iopub.status.idle":"2024-05-11T02:35:35.385944Z","shell.execute_reply.started":"2024-05-11T02:35:35.378954Z","shell.execute_reply":"2024-05-11T02:35:35.384732Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"thro = np.percentile(distances, 5)\ndf_test.loc[df_test['similar_distances']