{"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":"gpu","dataSources":[{"sourceId":7391,"databundleVersionId":44328,"sourceType":"competition"}],"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T02:56:48.891990Z","iopub.execute_input":"2025-01-13T02:56:48.892305Z","iopub.status.idle":"2025-01-13T02:56:50.696173Z","shell.execute_reply.started":"2025-01-13T02:56:48.892279Z","shell.execute_reply":"2025-01-13T02:56:50.695259Z"}},"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":"2025-01-13T02:56:50.697318Z","iopub.execute_input":"2025-01-13T02:56:50.697705Z","iopub.status.idle":"2025-01-13T02:56:50.705666Z","shell.execute_reply.started":"2025-01-13T02:56:50.697682Z","shell.execute_reply":"2025-01-13T02:56:50.704860Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip install py7zr","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T02:56:50.707664Z","iopub.execute_input":"2025-01-13T02:56:50.707859Z","iopub.status.idle":"2025-01-13T02:56:55.202777Z","shell.execute_reply.started":"2025-01-13T02:56:50.707843Z","shell.execute_reply":"2025-01-13T02:56:55.201832Z"}},"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":"2025-01-13T02:56:55.204491Z","iopub.execute_input":"2025-01-13T02:56:55.204829Z","iopub.status.idle":"2025-01-13T02:58:08.064997Z","shell.execute_reply.started":"2025-01-13T02:56:55.204797Z","shell.execute_reply":"2025-01-13T02:58:08.063901Z"}},"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\")\ndata[\"date\"] =  pd.to_datetime(data[\"date\"])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T02:58:08.065978Z","iopub.execute_input":"2025-01-13T02:58:08.066233Z","iopub.status.idle":"2025-01-13T02:59:29.964835Z","shell.execute_reply.started":"2025-01-13T02:58:08.066211Z","shell.execute_reply":"2025-01-13T02:59:29.963910Z"}},"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":{"iopub.status.busy":"2025-01-13T02:59:29.965973Z","iopub.execute_input":"2025-01-13T02:59:29.966308Z","iopub.status.idle":"2025-01-13T02:59:36.510654Z","shell.execute_reply.started":"2025-01-13T02:59:29.966272Z","shell.execute_reply":"2025-01-13T02:59:36.509738Z"}},"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":{"iopub.status.busy":"2025-01-13T02:59:36.511592Z","iopub.execute_input":"2025-01-13T02:59:36.511882Z","iopub.status.idle":"2025-01-13T03:05:34.335017Z","shell.execute_reply.started":"2025-01-13T02:59:36.511854Z","shell.execute_reply":"2025-01-13T03:05:34.334109Z"}},"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":{"iopub.status.busy":"2025-01-13T03:05:34.335997Z","iopub.execute_input":"2025-01-13T03:05:34.336252Z","iopub.status.idle":"2025-01-13T03:06:55.758694Z","shell.execute_reply.started":"2025-01-13T03:05:34.336231Z","shell.execute_reply":"2025-01-13T03:06:55.757737Z"}},"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":{"iopub.status.busy":"2025-01-13T03:06:55.762276Z","iopub.execute_input":"2025-01-13T03:06:55.762552Z","iopub.status.idle":"2025-01-13T03:07:05.557479Z","shell.execute_reply.started":"2025-01-13T03:06:55.762529Z","shell.execute_reply":"2025-01-13T03:07:05.556773Z"}},"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":{"iopub.status.busy":"2025-01-13T03:07:05.558603Z","iopub.execute_input":"2025-01-13T03:07:05.558820Z","iopub.status.idle":"2025-01-13T03:07:10.906116Z","shell.execute_reply.started":"2025-01-13T03:07:05.558796Z","shell.execute_reply":"2025-01-13T03:07:10.905155Z"}},"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":{"iopub.status.busy":"2025-01-13T03:07:10.907077Z","iopub.execute_input":"2025-01-13T03:07:10.907368Z","iopub.status.idle":"2025-01-13T03:07:11.971985Z","shell.execute_reply.started":"2025-01-13T03:07:10.907346Z","shell.execute_reply":"2025-01-13T03:07:11.971095Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T03:07:11.972931Z","iopub.execute_input":"2025-01-13T03:07:11.973272Z","iopub.status.idle":"2025-01-13T03:07:11.986493Z","shell.execute_reply.started":"2025-01-13T03:07:11.973238Z","shell.execute_reply":"2025-01-13T03:07:11.985705Z"}},"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":{"iopub.status.busy":"2025-01-13T03:07:11.987212Z","iopub.execute_input":"2025-01-13T03:07:11.987464Z","iopub.status.idle":"2025-01-13T03:07:12.003803Z","shell.execute_reply.started":"2025-01-13T03:07:11.987420Z","shell.execute_reply":"2025-01-13T03:07:12.003144Z"}},"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":{"iopub.status.busy":"2025-01-13T03:07:12.004558Z","iopub.execute_input":"2025-01-13T03:07:12.004847Z","iopub.status.idle":"2025-01-13T03:07:12.022915Z","shell.execute_reply.started":"2025-01-13T03:07:12.004819Z","shell.execute_reply":"2025-01-13T03:07:12.022253Z"}},"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":{"iopub.status.busy":"2025-01-13T03:07:12.023681Z","iopub.execute_input":"2025-01-13T03:07:12.023903Z","iopub.status.idle":"2025-01-13T03:07:12.040571Z","shell.execute_reply.started":"2025-01-13T03:07:12.023873Z","shell.execute_reply":"2025-01-13T03:07:12.039942Z"}},"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":{"iopub.status.busy":"2025-01-13T03:07:12.041223Z","iopub.execute_input":"2025-01-13T03:07:12.041462Z","iopub.status.idle":"2025-01-13T03:07:12.052361Z","shell.execute_reply.started":"2025-01-13T03:07:12.041423Z","shell.execute_reply":"2025-01-13T03:07:12.051525Z"}},"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":"markdown","source":"**1. Baseline Model**","metadata":{}},{"cell_type":"code","source":"from sklearn.dummy import DummyRegressor\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import mean_squared_error","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T03:07:12.053220Z","iopub.execute_input":"2025-01-13T03:07:12.053451Z","iopub.status.idle":"2025-01-13T03:07:12.288100Z","shell.execute_reply.started":"2025-01-13T03:07:12.053414Z","shell.execute_reply":"2025-01-13T03:07:12.287421Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['onpromotion'] = df['onpromotion'].fillna(0).astype(int)\ntest_df['onpromotion'] = test_df['onpromotion'].fillna(0).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T03:07:12.288875Z","iopub.execute_input":"2025-01-13T03:07:12.289169Z","iopub.status.idle":"2025-01-13T03:07:27.858119Z","shell.execute_reply.started":"2025-01-13T03:07:12.289139Z","shell.execute_reply":"2025-01-13T03:07:27.857240Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['unit_sales'] = df['unit_sales'].apply(lambda x: max(0, x))\nX = df[['store_nbr', 'item_nbr', 'onpromotion']]\ny = df['unit_sales']\n\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)\n\ndummy_model = DummyRegressor(strategy=\"mean\")\ndummy_model.fit(X_train, y_train)\n\ny_pred_val = dummy_model.predict(X_val)\n\nrmse = np.sqrt(mean_squared_error(y_val, y_pred_val))\nprint(f\"Baseline RMSE (Dummy Regressor - Mean): {rmse}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T03:07:27.858879Z","iopub.execute_input":"2025-01-13T03:07:27.859128Z","iopub.status.idle":"2025-01-13T03:08:22.354033Z","shell.execute_reply.started":"2025-01-13T03:07:27.859105Z","shell.execute_reply":"2025-01-13T03:08:22.353218Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**2. Feature Engineering**","metadata":{}},{"cell_type":"markdown","source":"*Temporal features*","metadata":{}},{"cell_type":"code","source":"df['day_of_week'] = df['date'].dt.dayofweek\ntest_df['day_of_week'] = test_df['date'].dt.dayofweek\n\ndf['week_of_year'] = df['date'].dt.isocalendar().week\ntest_df['week_of_year'] = test_df['date'].dt.isocalendar().week\n\ndf['month'] = df['date'].dt.month\ntest_df['month'] = test_df['date'].dt.month\n\ndf['year'] = df['date'].dt.year\ntest_df['year'] = test_df['date'].dt.year\n\ndf['is_weekend'] = df['day_of_week'].isin([5, 6]).astype(int)\ntest_df['is_weekend'] = test_df['day_of_week'].isin([5, 6]).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T03:08:22.354851Z","iopub.execute_input":"2025-01-13T03:08:22.355093Z","iopub.status.idle":"2025-01-13T03:08:40.609629Z","shell.execute_reply.started":"2025-01-13T03:08:22.355064Z","shell.execute_reply":"2025-01-13T03:08:40.608887Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"*Fill missing values after merges*","metadata":{}},{"cell_type":"code","source":"df.fillna(0, inplace=True)\ntest_df.fillna(0, inplace=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T03:14:40.155178Z","iopub.execute_input":"2025-01-13T03:14:40.155623Z","iopub.status.idle":"2025-01-13T03:14:40.445717Z","shell.execute_reply.started":"2025-01-13T03:14:40.155585Z","shell.execute_reply":"2025-01-13T03:14:40.444538Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"*Save processed data*","metadata":{}},{"cell_type":"code","source":"df.to_csv('train_filtered_features.csv', index=False)\ntest_df.to_csv('test_filtered_features.csv', index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-13T03:14:41.703302Z","iopub.execute_input":"2025-01-13T03:14:41.703647Z"}},"outputs":[],"execution_count":null}]}