{"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":"2025-06-30T14:47:44.196832Z","iopub.execute_input":"2025-06-30T14:47:44.197971Z","iopub.status.idle":"2025-06-30T14:47:44.203509Z","shell.execute_reply.started":"2025-06-30T14:47:44.197926Z","shell.execute_reply":"2025-06-30T14:47:44.202619Z"}},"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\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":"2025-06-30T14:47:44.204997Z","iopub.execute_input":"2025-06-30T14:47:44.205334Z","iopub.status.idle":"2025-06-30T14:47:44.544395Z","shell.execute_reply.started":"2025-06-30T14:47:44.205315Z","shell.execute_reply":"2025-06-30T14:47:44.543387Z"}},"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":"2025-06-30T14:47:44.545430Z","iopub.execute_input":"2025-06-30T14:47:44.545773Z","iopub.status.idle":"2025-06-30T14:47:44.671465Z","shell.execute_reply.started":"2025-06-30T14:47:44.545745Z","shell.execute_reply":"2025-06-30T14:47:44.670569Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # ----------------------------------------------\n# # 追加テーブルの特徴量作成\n# # ----------------------------------------------\n\n# # 追加テーブルの読み込み\nnew_trans = pd.read_csv(f\"{DATA_DIR}/new_merchant_transactions.csv\")\nprint(new_trans.describe())\n\n# ① purchase_amount をクリッピング（異常値対策）\nnew_trans[\"purchase_amount\"] = new_trans[\"purchase_amount\"].clip(lower=-0.1, upper=0.2)\n\n# カテゴリ変数を数値に変換（全て明示的に）\nnew_trans[\"authorized_flag\"] = new_trans[\"authorized_flag\"].map({'Y': 1, 'N': 0}).astype(int)\nnew_trans[\"category_1\"] = new_trans[\"category_1\"].map({'Y': 1, 'N': 0}).astype(int)\nnew_trans[\"category_2\"] = LabelEncoder().fit_transform(new_trans[\"category_2\"].astype(str))\nnew_trans[\"category_3\"] = LabelEncoder().fit_transform(new_trans[\"category_3\"].astype(str))\n\n\n# # 集約特徴の作成パターンを辞書化\n#agg_funcs = {\n#    \"purchase_amount\": [\"min\", \"max\"], # 正規化済みの購入金額（負値 = 顧客の支出）\n#    \"installments\":    [\"min\", \"max\"], # 分割払いの分割回数\n#    \"month_lag\":       [\"min\", \"max\"], # 基準日からの経過月数\n#    \"purchase_date\":   [\"count\"],      # 購入日時（countで空でない行を数える ⇔ 購入回数）\n#}\n\nagg_funcs = {\n    \"purchase_amount\": [\"min\", \"max\", \"mean\", \"std\", \"var\", \"skew\", \"sem\", \"prod\", \"first\", \"last\"],\n    \"installments\":    [\"min\", \"max\", \"mean\", \"std\", \"nunique\", \"first\", \"last\"],\n    \"month_lag\":       [\"min\", \"max\", \"mean\", \"median\", \"std\",  \"first\", \"last\"],\n    \"purchase_date\":   [\"count\"],  # 時系列情報の前処理が必要なら datetime に変換して後続で扱う\n    \"authorized_flag\": [\"mean\", \"sum\"],\n    \"category_1\":      [\"mean\"],\n    \"category_2\":      [\"mean\", \"nunique\"],\n    \"category_3\":      [\"mean\", \"nunique\"]\n}\n\n\n# # 例）\"month_lag\": [\"min\", \"mean\", \"max\"],\n# # 　　⇔　変数 \"month_lag\" について，同一IDの中で\n# # 　　　　最小値，平均値，最大値を取って集約特徴に追加する\n\n# # 全ての行を card_id の値でグループ化\n# # ⇒　上の集約パターンに従って実際に特徴を集約\nagg_new = new_trans.groupby(\"card_id\").agg(agg_funcs)\n\n# # 備考）上の集約特徴のテーブルは，列が MultiIndex の状態になっている\n# # 　　　⇒　列名のリストを表示して確認してみよう\nprint(agg_new.columns.to_list())\n# # 1列を指定するために「変数名と集約関数」をペアで指定する必要があることがわかる\n\n# # 新特徴の名前（列名）を機械的に生成してリスト化\n# # 　　命名規則：元変数名_集約方法（「purchase_amount_mean」など）\nflat_cols = []\nfor col_name, func in agg_new.columns.to_flat_index():\n    if isinstance(func, str):\n        new_name = f\"new_{col_name}_{func}\"\n    else:\n        # 関数名が lambda などの場合は手動で命名（例：range, q25, q75 など）\n        func_name = getattr(func, '__name__', 'custom')\n        if 'lambda' in func_name:\n            if col_name == 'purchase_amount':\n                func_name = 'range'\n            elif col_name == 'month_lag':\n                func_name = 'q25'\n            else:\n                func_name = 'custom'\n        new_name = f\"new_{col_name}_{func_name}\"\n    flat_cols.append(new_name)\n\n# # MultiIndex状態の列を通常の状態に変換（列方向に平坦化）\nagg_new.columns = flat_cols\nprint(agg_new.columns.to_list())\n\n# # groupby によるグループ化を解除（card_idを通常の列に戻す）\nagg_new = agg_new.reset_index()\n\n# # メインテーブルの特徴と結合\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# # Fill missing values created by the left join\ntrain_x = train_x.fillna(-1)\ntest_x  = test_x.fillna(-1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-30T14:47:44.673380Z","iopub.execute_input":"2025-06-30T14:47:44.673682Z","iopub.status.idle":"2025-06-30T14:47:55.345047Z","shell.execute_reply.started":"2025-06-30T14:47:44.673661Z","shell.execute_reply":"2025-06-30T14:47:55.344059Z"}},"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,"execution":{"iopub.status.busy":"2025-06-30T14:47:55.345921Z","iopub.execute_input":"2025-06-30T14:47:55.346241Z","iopub.status.idle":"2025-06-30T14:47:55.374214Z","shell.execute_reply.started":"2025-06-30T14:47:55.346213Z","shell.execute_reply":"2025-06-30T14:47:55.373375Z"}},"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,"execution":{"iopub.status.busy":"2025-06-30T14:47:55.375091Z","iopub.execute_input":"2025-06-30T14:47:55.375395Z","iopub.status.idle":"2025-06-30T14:48:03.677808Z","shell.execute_reply.started":"2025-06-30T14:47:55.375359Z","shell.execute_reply":"2025-06-30T14:48:03.676744Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ------------------------------\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})\n\nsubmission.to_csv(\"submission.csv\", index=False)","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","trusted":true,"execution":{"iopub.status.busy":"2025-06-30T14:48:03.678812Z","iopub.execute_input":"2025-06-30T14:48:03.679198Z","iopub.status.idle":"2025-06-30T14:48:05.665424Z","shell.execute_reply.started":"2025-06-30T14:48:03.679172Z","shell.execute_reply":"2025-06-30T14:48:05.664511Z"}},"outputs":[],"execution_count":null}]}