{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":7391,"databundleVersionId":44328,"sourceType":"competition"}],"dockerImageVersionId":30822,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.dummy import DummyRegressor\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import StandardScaler, OneHotEncoder\nfrom sklearn.impute import SimpleImputer\nimport lightgbm as lgb\nimport optuna","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-12T11:45:09.522336Z","iopub.execute_input":"2025-01-12T11:45:09.522722Z","iopub.status.idle":"2025-01-12T11:45:13.639203Z","shell.execute_reply.started":"2025-01-12T11:45:09.522693Z","shell.execute_reply":"2025-01-12T11:45:13.638199Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\n\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\npaths = []\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n        paths.append(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-01-12T11:45:13.640755Z","iopub.execute_input":"2025-01-12T11:45:13.641572Z","iopub.status.idle":"2025-01-12T11:45:13.649930Z","shell.execute_reply.started":"2025-01-12T11:45:13.641530Z","shell.execute_reply":"2025-01-12T11:45:13.648444Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip install py7zr","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-12T11:45:13.651981Z","iopub.execute_input":"2025-01-12T11:45:13.652266Z","iopub.status.idle":"2025-01-12T11:45:22.504061Z","shell.execute_reply.started":"2025-01-12T11:45:13.652242Z","shell.execute_reply":"2025-01-12T11:45:22.502681Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import py7zr\nfor filenames in paths:\n    with py7zr.SevenZipFile(filenames, mode='r') as z_ref:\n        z_ref.extractall(path='/kaggle/working')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-12T11:45:22.506196Z","iopub.execute_input":"2025-01-12T11:45:22.506673Z","iopub.status.idle":"2025-01-12T11:47:02.286831Z","shell.execute_reply.started":"2025-01-12T11:45:22.506635Z","shell.execute_reply":"2025-01-12T11:47:02.285236Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Corporación Favorita Grocery Sales Forecasting\n\nPlease read data description: https://www.kaggle.com/c/favorita-grocery-sales-forecasting","metadata":{}},{"cell_type":"markdown","source":"## Splitting Data into Training and Test Sets\nThe data you are working with splited into **training** and **test** sets and stored in the following files:\n\n- **`/kaggle/working/train_data.csv`** – the training dataset used for model training.\n- **`/kaggle/working/test_data.csv`** – the test dataset used to evaluate the model's performance.","metadata":{}},{"cell_type":"code","source":"%%time\ndata = pd.read_csv(\"/kaggle/working/train.csv\", low_memory = False)\ndata[\"date\"] =  pd.to_datetime(data[\"date\"])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-12T11:47:02.288390Z","iopub.execute_input":"2025-01-12T11:47:02.288738Z","execution_failed":"2025-01-12T11:48:47.551Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"monthly_counts_data = data['date'].dt.to_period('M').value_counts().sort_index()\n\nplt.figure(figsize=(12, 6))\nmonthly_counts_data.plot(kind='bar', color='skyblue')\nplt.title('Count of Data for Each Month for All data', fontsize=14)\nplt.xlabel('Month', fontsize=12)\nplt.ylabel('Count', fontsize=12)\nplt.xticks(rotation=45)\nplt.grid(axis='y', linestyle='--', alpha=0.7)\nplt.show()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.551Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\nTHRESHOLD_TRAIN_DATE = pd.to_datetime(\"2017-07-01\")\nTHRESHOLD_TEST_DATE = pd.to_datetime(\"2017-08-01\")\n\ndata[data[\"date\"] < THRESHOLD_TRAIN_DATE].to_csv(\"/kaggle/working/train_data.csv\")\ndata[(data[\"date\"] >= THRESHOLD_TRAIN_DATE)&(data[\"date\"] < THRESHOLD_TEST_DATE)].to_csv(\"/kaggle/working/test_data.csv\")\n\n%xdel data","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.552Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\ndf = pd.read_csv(\"/kaggle/working/train_data.csv\")\ntest_df = pd.read_csv(\"/kaggle/working/test_data.csv\")","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.552Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df[\"date\"] = pd.to_datetime(df[\"date\"])\ntest_df[\"date\"] = pd.to_datetime(test_df[\"date\"])","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.552Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"monthly_counts = df['date'].dt.to_period('M').value_counts().sort_index().reset_index()\nmonthly_counts_test = test_df['date'].dt.to_period('M').value_counts().sort_index().reset_index()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.552Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"monthly_counts['type'] = 'Train'\nmonthly_counts_test['type'] = 'Test'\ncombined = pd.concat([monthly_counts, monthly_counts_test])\n\nplt.figure(figsize=(12, 6))\nsns.barplot(data=combined, x='date', y='count', hue='type', palette=['blue', 'red'])\nplt.title('Count of Data for Each Month (Train vs Test)', fontsize=14)\nplt.xlabel('Month', fontsize=12)\nplt.ylabel('Count', fontsize=12)\nplt.xticks(rotation=45)\nplt.legend(title='Dataset')\nplt.grid(axis='y', linestyle='--', alpha=0.7)\nplt.show()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.553Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.553Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Will use last year, because dataset is large","metadata":{}},{"cell_type":"code","source":"THRESHOLD_TRAIN_DATE_LOWER = pd.to_datetime(\"2017-01-01\")\ndf = df[df[\"date\"] >= THRESHOLD_TRAIN_DATE_LOWER]\ndf = df.reset_index(drop=True)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.553Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.554Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Additional Data\n\n\nTo make more effective use of the data, you also have access to several auxiliary datasets containing contextual information:\n\n#### 1. **`holidays_events.csv`**\n   - **Description**:\n     Contains information about holidays and events that may influence sales.\n   - **Useful Columns**:\n     - `date`: The date of the holiday or event.\n     - `type`: The type of event (national, regional, local).\n     - `locale`: The level of impact (national, regional, local).\n     - `description`: A description of the event.\n   - **How to Use**:\n     - Add a flag indicating whether a date is a holiday to the training and test sets.\n     - Categorize holidays by their `type` and consider their impact on sales.\n     - Use the `locale` column to analyze regional effects.","metadata":{"execution":{"iopub.status.busy":"2024-12-22T19:12:02.31896Z","iopub.execute_input":"2024-12-22T19:12:02.319553Z","iopub.status.idle":"2024-12-22T19:12:02.32548Z","shell.execute_reply.started":"2024-12-22T19:12:02.319516Z","shell.execute_reply":"2024-12-22T19:12:02.323891Z"}}},{"cell_type":"code","source":"holiday_events = pd.read_csv(\"/kaggle/working/holidays_events.csv\")\nprint(holiday_events.shape)\nholiday_events.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.554Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"holiday_events.groupby([\"type\", \"locale\"]).size()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.554Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Transferred holidays are almost normal days, we should propably skip those. Work Day type means work days to payback Bridge holidays, also should skip those.","metadata":{}},{"cell_type":"code","source":"holiday_events = holiday_events[holiday_events.transferred == False]\nholiday_events = holiday_events[holiday_events.type != \"Work Day\"]","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.554Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"holiday_events['date'] = pd.to_datetime(holiday_events['date'])\nholiday_events = holiday_events.rename(columns={\"type\": \"holiday_type\"})","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.554Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = df.merge(holiday_events[['date', 'holiday_type', 'locale']], on='date', how='left')\ntest_df = test_df.merge(holiday_events[['date', 'holiday_type', 'locale']], on='date', how='left')","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.554Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_df['is_holiday'] = test_df['holiday_type'].notna().astype(int)\ndf['is_holiday'] = df['holiday_type'].notna().astype(int)\n\ndf.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.555Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"#### 2. **`items.csv`**\n   - **Description**:\n     Contains information about the items being sold.\n   - **Useful Columns**:\n     - `item_nbr`: Unique identifier for each item.\n     - `family`: The category or family the item belongs to (e.g., \"Beverages\").\n     - `class`: A finer categorization of items.\n     - `perishable`: A binary indicator for whether the item is perishable (1 for perishable, 0 otherwise).\n   - **How to Use**:\n     - Use `family` and `class` to group items and analyze trends across categories.\n     - Include the `perishable` indicator to weight predictions for perishable items.","metadata":{}},{"cell_type":"code","source":"items = pd.read_csv(\"/kaggle/working/items.csv\")\nprint(items.shape)\nitems.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.555Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"family_counts = items[\"family\"].value_counts()\n\nplt.figure(figsize=(16, 8))\nsns.barplot(x=family_counts.index, y=family_counts.values)\nplt.xlabel('Family', fontsize=12)\nplt.ylabel('Quantity', fontsize=12)\nplt.xticks(rotation=45, ha = 'right')\nplt.show()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.555Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = df.merge(items[[\"item_nbr\", \"family\", \"class\", \"perishable\"]], how=\"left\", on=\"item_nbr\")\ntest_df = test_df.merge(items[[\"item_nbr\", \"family\", \"class\", \"perishable\"]], how=\"left\", on=\"item_nbr\")","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.555Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"#### 3. **`oil.csv`**\n   - **Description**:\n     Contains daily oil price data, which can serve as an external economic indicator.\n   - **Useful Columns**:\n     - `date`: The date corresponding to the oil price.\n     - `dcoilwtico`: The daily oil price.\n   - **How to Use**:\n     - Join this dataset with the training and test sets on the `date` column to include oil price as a feature.\n     - Analyze the correlation between oil price fluctuations and sales trends.","metadata":{}},{"cell_type":"code","source":"oil = pd.read_csv(\"/kaggle/working/oil.csv\")\nprint(oil.shape)\noil.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.555Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"oil['date'] = pd.to_datetime(oil['date'])","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = df.merge(oil, how=\"left\", on=\"date\")\ntest_df = test_df.merge(oil, how=\"left\", on=\"date\")","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df[\"dcoilwtico\"].ffill(inplace=True)\ntest_df[\"dcoilwtico\"].ffill(inplace=True)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df[\"dcoilwtico\"].bfill(inplace=True)\ntest_df[\"dcoilwtico\"].bfill(inplace=True)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df[\"unit_sales\"].corr(df[\"dcoilwtico\"])","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"plt.figure(figsize=(10, 6))\nsns.lineplot(data=df, x=\"date\", y=\"unit_sales\", label=\"Unit Sales\")\nsns.lineplot(data=df, x=\"date\", y=\"dcoilwtico\", label=\"Oil Price\")\nplt.title(\"Sales Trends vs. Oil Price\")\nplt.xlabel(\"Date\")\nplt.ylabel(\"Value\")\nplt.legend()\nplt.grid()\nplt.show()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.556Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"#### 4. **`stores.csv`**\n   - **Description**:\n     Contains information about the stores where items are sold.\n   - **Useful Columns**:\n     - `store_nbr`: Unique identifier for each store.\n     - `city`: The city where the store is located.\n     - `state`: The state where the store is located.\n     - `type`: The store type.\n     - `cluster`: A grouping of similar stores based on sales patterns.\n   - **How to Use**:\n     - Use `city` and `state` for regional analysis of sales trends.\n     - Incorporate `type` and `cluster` to identify patterns and group stores with similar behavior.\n","metadata":{}},{"cell_type":"code","source":"stores = pd.read_csv(\"/kaggle/working/stores.csv\")\nprint(stores.shape)\nstores.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"stores = stores.rename(columns={\"type\": \"store_type\"}) # type is already holiday type in df","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = df.merge(stores, on='store_nbr', how='left')\ntest_df = test_df.merge(stores, on='store_nbr', how='left')","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.556Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**[READ DATA DESCRIPTION CAREFULY](https://www.kaggle.com/competitions/favorita-grocery-sales-forecasting) !!!!** \n\n## Exploratory Data Analysis and Model Training\n\n### 1. Baseline Model\n- Consider which model would be suitable as `DummyModel` for this task, then create, train, and use its predictions as a baseline.\n\n### 2. Feature Engineering\n- Generate new features by incorporating data from additional datasets to enhance the model's predictive capabilities.\n\n### 3. Model Training and Optimization\n- Utilize advanced regression models, such as **LGBM Regression** or **CatBoost Regression**, to achieve the best results. Focus on hyperparameter tuning and evaluation metrics to optimize performance. **Use foremention Normalized Weighted Root Mean Squared Logarithmic Error**.  \n\n### Thats All :-)\n","metadata":{}},{"cell_type":"code","source":"weights = test_df.perishable.astype(float).values * 0.25 + 1\nweights","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.557Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def compute_log(arr):\n    x = np.ma.log(arr)\n    return x.filled(0)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.557Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def nwrmsle(y_pred, y_true, weights):\n    return np.sqrt(np.sum(weights * (compute_log(y_pred + 1) - compute_log(y_true + 1)) ** 2) / np.sum(weights))","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.557Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Baseline model will be dummy regressor as it is a regression task","metadata":{}},{"cell_type":"code","source":"dummy_regr = DummyRegressor(strategy=\"mean\")\ndummy_regr.fit(df, df['unit_sales'].values)\n\ndummy_prediction = dummy_regr.predict(test_df)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.557Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"nwrmsle(dummy_prediction, test_df['unit_sales'].values, weights)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.557Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Let's do feature engineering","metadata":{}},{"cell_type":"code","source":"df.isna().sum()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.557Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['locale'] = df.locale.fillna('None')\ntest_df['locale'] = test_df.locale.fillna('None')","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.557Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['holiday_type'] = df.locale.fillna('Not holiday')\ntest_df['holiday_type'] = test_df.locale.fillna('Not holiday')","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.558Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['dcoilwtico'] = df.dcoilwtico.bfill()\ntest_df['dcoilwtico'] = test_df.dcoilwtico.bfill()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.558Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Encoding","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.558Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"holiday_type_mapping = {\"Transfer\": 2, \"Holiday\": 2, \"Additional\": 2, \"Event\": 1, \"Not holiday\": 0}\n\ndf['holiday_type_ec'] = df['holiday_type'].map(holiday_type_mapping)\ntest_df['holiday_type_ec'] = test_df['holiday_type'].map(holiday_type_mapping)\n\ndf.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.558Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.locale.unique()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.558Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"holiday_locale_mapping = {\"National\": 3, \"Regional\": 2, \"Local\": 1, \"None\": 0}\n\ndf['holiday_locale_ec'] = df['locale'].map(holiday_locale_mapping)\ntest_df['holiday_locale_ec'] = test_df['locale'].map(holiday_locale_mapping)\n\ndf.head()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.558Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['onpromotion'] = df['onpromotion'].map({\"False\": 0, \"True\": 1})\ntest_df['onpromotion'] = test_df['onpromotion'].map({\"False\": 0, \"True\": 1})","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.559Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns.tolist()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.559Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preprocessor = ColumnTransformer(\n    [\n        ('scaler', StandardScaler(), ['dcoilwtico']),\n        ('one_hot', OneHotEncoder(handle_unknown='ignore'), ['family', 'city', 'state', 'store_type', 'cluster']),\n        ('imputer', SimpleImputer(strategy=\"median\"), \n         ['onpromotion', 'is_holiday', 'perishable', 'holiday_type_ec', 'holiday_locale_ec']\n        )\n    ]\n)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.559Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X_train = df[[\n    'onpromotion', 'is_holiday', 'perishable', \n    'dcoilwtico', 'holiday_type_ec', 'holiday_locale_ec',\n    'family', 'city', 'state', 'store_type', 'cluster'\n]]\nX_test = test_df[[\n    'onpromotion', 'is_holiday', 'perishable', \n    'dcoilwtico', 'holiday_type_ec', 'holiday_locale_ec',\n    'family', 'city', 'state', 'store_type', 'cluster'\n]]","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.559Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X_train_preprocessed = preprocessor.fit_transform(X_train)\nX_test_preprocessed = preprocessor.transform(X_test)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.559Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_train = df['unit_sales'].values\ny_test = test_df['unit_sales'].values","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.559Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Model training","metadata":{}},{"cell_type":"code","source":"train_data = lgb.Dataset(X_train_preprocessed, label=y_train)\nval_data = lgb.Dataset(X_test_preprocessed, label=y_test, reference=train_data)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.559Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"params = {\n    'num_leaves': 80,\n    'objective': 'regression',\n    'min_data_in_leaf': 200,\n    'learning_rate': 0.02,\n    'feature_fraction': 0.8,\n    'bagging_fraction': 0.7,\n    'bagging_freq': 1,\n    'metric': 'l2',\n    'num_threads': 16\n}","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.559Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"result = lgb.train(\n    params, \n    train_data, \n    num_boost_round=500,\n    valid_sets=[train_data, val_data]\n)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T11:48:47.560Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"lgbm_prediction = result.predict(X_test_preprocessed)\nlgbm_score = nwrmsle(y_pred=lgbm_prediction, y_true=y_test, weights=weights)\nlgbm_score","metadata":{"trusted":true,"execution":{"execution_failed":"2025-01-12T10:30:30.681Z"}},"outputs":[],"execution_count":null}]}