{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.11.11"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":10445,"databundleVersionId":200747,"sourceType":"competition"}],"dockerImageVersionId":31040,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport pandas as pd\nfrom sklearn.preprocessing import LabelEncoder\nfrom xgboost import XGBRegressor\nimport matplotlib.pyplot as plt\n\nrseed = 71","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-29T14:10:15.642100Z","iopub.execute_input":"2025-06-29T14:10:15.642523Z","iopub.status.idle":"2025-06-29T14:10:15.648910Z","shell.execute_reply.started":"2025-06-29T14:10:15.642461Z","shell.execute_reply":"2025-06-29T14:10:15.647500Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ----------------------------------------------\n# データ読み込み\n# ----------------------------------------------\nDATA_DIR = \"/kaggle/input/elo-merchant-category-recommendation\"\ntrain = pd.read_csv(f\"{DATA_DIR}/train.csv\")\ntest  = pd.read_csv(f\"{DATA_DIR}/test.csv\")\n\n# 元テーブルからID列と目的変数をコピー\ntrain_card_id = train['card_id'].copy()\ntest_card_id  = test['card_id'].copy()\ntrain_y       = train['target'].copy()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-29T14:10:15.650885Z","iopub.execute_input":"2025-06-29T14:10:15.651351Z","iopub.status.idle":"2025-06-29T14:10:16.003634Z","shell.execute_reply.started":"2025-06-29T14:10:15.651324Z","shell.execute_reply":"2025-06-29T14:10:16.002802Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ----------------------------------------------\n# メインテーブルの特徴量作成\n# ・年月文字列は欠損補完・Label Encoding\n# ・他はそのまま\n# ----------------------------------------------\n\n# 元テーブルから特徴量をコピー（目的変数は削除）\ntrain_x = train.copy().drop(columns=[\"target\"])\ntest_x  = test.copy()\n\n# 年月文字列に欠損があるので補完\ntrain_x[\"first_active_month\"] = train_x[\"first_active_month\"].fillna(\"Unknown\")\ntest_x[\"first_active_month\"]  = test_x[\"first_active_month\"].fillna(\"Unknown\")\n\n# 年月文字列をLabel Encoding\nle = LabelEncoder()\nall_months = pd.concat([train_x[\"first_active_month\"], test_x[\"first_active_month\"]])\nle.fit(all_months)\ntrain_x[\"fam_label\"] = le.transform(train_x[\"first_active_month\"])\ntest_x[\"fam_label\"]  = le.transform(test_x[\"first_active_month\"])\n\n# 変換前の年月文字列を削除\ntrain_x = train_x.drop(columns=[\"first_active_month\"])\ntest_x  = test_x.drop(columns=[\"first_active_month\"])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-29T14:10:16.004569Z","iopub.execute_input":"2025-06-29T14:10:16.004923Z","iopub.status.idle":"2025-06-29T14:10:16.128914Z","shell.execute_reply.started":"2025-06-29T14:10:16.004902Z","shell.execute_reply":"2025-06-29T14:10:16.127976Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"new_trans = pd.read_csv(f\"{DATA_DIR}/new_merchant_transactions.csv\")\n\n\nnew_trans[\"category_1\"] = new_trans[\"category_1\"].map({\"Y\": 1, \"N\": 0})\n\nagg_funcs_new = {\n    \"purchase_amount\": [\"min\", \"max\", \"mean\", \"std\", \"sum\",\n                        (\"range\", lambda x: x.max() - x.min())],\n    \"installments\":    [\"min\", \"max\", \"mean\", \"std\",\n                        (\"range\", lambda x: x.max() - x.min())],\n    \"month_lag\":       [\"min\", \"max\", \"mean\", \"std\",\n                        (\"range\", lambda x: x.max() - x.min())],\n    \"purchase_date\":   [\"count\"],\n    \"merchant_id\":     [\"nunique\"],\n    \"category_1\":      [\"mean\"]\n}\n\nagg_new = new_trans.groupby(\"card_id\").agg(agg_funcs_new)\nagg_new.columns = [\n    f\"new_{c}_{f if isinstance(f,str) else f.__name__}\"\n    for c, f in agg_new.columns.to_flat_index()\n]\nagg_new = agg_new.reset_index()\n\ntrain_x = train_x.merge(agg_new, on=\"card_id\", how=\"left\")\ntest_x  = test_x.merge(agg_new, on=\"card_id\", how=\"left\")\n\n\n\n\nhist_trans = pd.read_csv(f\"{DATA_DIR}/historical_transactions.csv\")\nhist_trans[\"authorized_flag\"] = hist_trans[\"authorized_flag\"].map({\"Y\": 1, \"N\": 0})\nhist_trans[\"category_1\"] = hist_trans[\"category_1\"].map({\"Y\": 1, \"N\": 0})\n\nagg_funcs_hist = {\n    \"purchase_amount\": [\"min\", \"max\", \"mean\", \"std\", \"sum\",\n                        (\"range\", lambda x: x.max() - x.min())],\n    \"installments\":    [\"min\", \"max\", \"mean\", \"std\"],\n    \"month_lag\":       [\"min\", \"max\", \"mean\"],\n    \"authorized_flag\": [\"mean\", \"sum\"],\n    \"category_1\":      [\"mean\"],\n    \"purchase_date\":   [\"count\"],\n    \"merchant_id\":     [\"nunique\"]\n}\n\nagg_hist = hist_trans.groupby(\"card_id\").agg(agg_funcs_hist)\nagg_hist.columns = [\n    f\"hist_{c}_{f if isinstance(f,str) else f.__name__}\"\n    for c, f in agg_hist.columns.to_flat_index()\n]\nagg_hist = agg_hist.reset_index()\n\ntrain_x = train_x.merge(agg_hist, on=\"card_id\", how=\"left\")\ntest_x  = test_x.merge(agg_hist, on=\"card_id\", how=\"left\")\n# Fill missing values created by the left join\ntrain_x = train_x.fillna(-1)\ntest_x  = test_x.fillna(-1)\n\nillegal = r\"[\\[\\]<>]\"\ntrain_x.columns = train_x.columns.str.replace(illegal, \"\", regex=True)\ntest_x.columns  = test_x.columns.str.replace(illegal, \"\", regex=True)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-29T14:10:16.131206Z","iopub.execute_input":"2025-06-29T14:10:16.131938Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ID列を削除\ntrain_x = train_x.drop(columns=[\"card_id\"])\ntest_x  = test_x.drop(columns=[\"card_id\"])","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ----------------------------------------------\n# 使用する特徴量の可視化\n# ----------------------------------------------\n\n# 各特徴の統計量\nprint(pd.concat([train_x, train_y], axis=1).describe())\n\n# 各特徴のヒストグラム\ntrain_x.hist(bins=100, color=\"blue\", grid=True, label='pandas')\nplt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # ------------------------------\n# # XGBoostの学習・推論・submit\n# # ------------------------------\n# model = XGBRegressor(random_state=rseed)\n# model.fit(train_x, train_y)\n# preds = model.predict(test_x)\n\n# submission = pd.DataFrame({\n#     \"card_id\": test_card_id,\n#     \"target\":  preds\n# })\n\n# submission.to_csv(\"submission.csv\", index=False)\n\n\n# ------------------------------\n# XGBoost の学習・推論・submit\n# ------------------------------\nmodel = XGBRegressor(random_state=rseed)\nmodel.fit(train_x, train_y)\npreds = model.predict(test_x)\n\nsubmission = pd.DataFrame({\n    \"card_id\": test_card_id,\n    \"target\": preds\n})\nsubmission.to_csv(\"submission.csv\", index=False)","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","trusted":true},"outputs":[],"execution_count":null}]}