{"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":"2025-06-28T10:12:59.548676Z"}},"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},"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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"historical = pd.read_csv(\"/kaggle/input/elo-merchant-category-recommendation/historical_transactions.csv\")\nnew_merchant = pd.read_csv(\"/kaggle/input/elo-merchant-category-recommendation/new_merchant_transactions.csv\")\n\n\n# 集約特徴量を強化（historical + new_merchant、関数拡張）\ndef aggregate_transactions(df, prefix):\n    df['purchase_date'] = pd.to_datetime(df['purchase_date'])\n    df['purchase_month'] = df['purchase_date'].dt.month\n\n    aggs = {\n        'purchase_amount': ['min', 'max', 'mean', 'std', 'sum', 'count'],\n        'installments': ['min', 'max', 'mean', 'std'],\n        'month_lag': ['min', 'max', 'mean', 'std'],\n        'purchase_month': ['nunique'],\n    }\n\n    agg_df = df.groupby('card_id').agg(aggs)\n    agg_df.columns = [f\"{prefix}_{k}_{stat}\" for k, stats in aggs.items() for stat in stats]\n    agg_df.reset_index(inplace=True)\n    return agg_df\n\nagg_hist = aggregate_transactions(historical, \"hist\")\nagg_new  = aggregate_transactions(new_merchant, \"new\")\n\ntrain_x = train.merge(agg_hist, on=\"card_id\", how=\"left\")\ntrain_x = train_x.merge(agg_new, on=\"card_id\", how=\"left\")\ntest_x  = test.merge(agg_hist, on=\"card_id\", how=\"left\")\ntest_x  = test_x.merge(agg_new, on=\"card_id\", how=\"left\")\n\n# モデルに与える列を整理（object列などを除外）\ndrop_cols = [\"card_id\", \"first_active_month\", \"target\"]\ntrain_y = train_x[\"target\"]\ntrain_x = train_x.drop(columns=drop_cols, errors='ignore')\ntest_x = test_x.drop(columns=drop_cols, errors='ignore')\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ID列を削除\n# 'card_id' が存在する場合のみ削除する\nif 'card_id' in train_x.columns:\n    train_x = train_x.drop(columns=[\"card_id\"])\nif 'card_id' in test_x.columns:\n    test_x = test_x.drop(columns=[\"card_id\"])\n","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# ------------------------------\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})\nprint(submission)\n\nsubmission.to_csv(\"submission.csv\", index=False)","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","trusted":true},"outputs":[],"execution_count":null}]}