{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":53998,"databundleVersionId":5880353,"sourceType":"competition"}],"dockerImageVersionId":30684,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"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\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\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\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(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_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import mean_squared_log_error","metadata":{"execution":{"iopub.status.busy":"2024-04-10T03:38:02.510207Z","iopub.execute_input":"2024-04-10T03:38:02.511038Z","iopub.status.idle":"2024-04-10T03:38:03.904387Z","shell.execute_reply.started":"2024-04-10T03:38:02.510998Z","shell.execute_reply":"2024-04-10T03:38:03.903331Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load the data\ntrain_data = pd.read_csv('/kaggle/input/Store-Sales-Forecasting/train.csv')\ntest_data = pd.read_csv('/kaggle/input/Store-Sales-Forecasting/test.csv')\nstores_data = pd.read_csv('/kaggle/input/Store-Sales-Forecasting/stores.csv')\nholidays_data = pd.read_csv('/kaggle/input/Store-Sales-Forecasting/holidays_events.csv')","metadata":{"execution":{"iopub.status.busy":"2024-04-10T03:38:07.762503Z","iopub.execute_input":"2024-04-10T03:38:07.763165Z","iopub.status.idle":"2024-04-10T03:38:10.912141Z","shell.execute_reply.started":"2024-04-10T03:38:07.763128Z","shell.execute_reply":"2024-04-10T03:38:10.910915Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Convert 'date' column to datetime\ntrain_data['date'] = pd.to_datetime(train_data['date'])\n\n# Extract year, month, day, and day of the week from the 'date' column\ntrain_data['year'] = train_data['date'].dt.year\ntrain_data['month'] = train_data['date'].dt.month\ntrain_data['day'] = train_data['date'].dt.day\ntrain_data['day_of_week'] = train_data['date'].dt.dayofweek\n\n# Drop the original 'date' column\ntrain_data.drop('date', axis=1, inplace=True)","metadata":{"execution":{"iopub.status.busy":"2024-04-10T03:38:15.343343Z","iopub.execute_input":"2024-04-10T03:38:15.344556Z","iopub.status.idle":"2024-04-10T03:38:16.325068Z","shell.execute_reply.started":"2024-04-10T03:38:15.344507Z","shell.execute_reply":"2024-04-10T03:38:16.323874Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Perform one-hot encoding for categorical variables\ntrain_data = pd.get_dummies(train_data, columns=['store_nbr', 'family', 'onpromotion'], drop_first=True)\n\n# Drop unnecessary columns\ntrain_data.drop(['id'], axis=1, inplace=True)","metadata":{"execution":{"iopub.status.busy":"2024-04-10T03:38:33.783427Z","iopub.execute_input":"2024-04-10T03:38:33.783874Z","iopub.status.idle":"2024-04-10T03:38:36.589951Z","shell.execute_reply.started":"2024-04-10T03:38:33.783841Z","shell.execute_reply":"2024-04-10T03:38:36.588805Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n# Merge holiday events\ntrain_data = pd.merge(train_data, holidays_data, how='left', on='date')\n\n# Convert date column to datetime type\ntrain_data['date'] = pd.to_datetime(train_data['date'])\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Convert date columns to datetime type\ntrain_data['date'] = pd.to_datetime(train_data['date'])\ntest_data['date'] = pd.to_datetime(test_data['date'])\nholidays_data['date'] = pd.to_datetime(holidays_data['date'])\n\n# Merge holiday events\ntrain_data = pd.merge(train_data, holidays_data, how='left', on='date')\ntest_data = pd.merge(test_data, holidays_data, how='left', on='date')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Drop unnecessary columns\ntrain_data.drop(['id'], axis=1, inplace=True)\ntest_data.drop(['id'], axis=1, inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Perform one-hot encoding for categorical variables\ncategorical_columns = ['store_nbr', 'family']\ntrain_data = pd.get_dummies(train_data, columns=categorical_columns, drop_first=True)\ntest_data = pd.get_dummies(test_data, columns=categorical_columns, drop_first=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Separate features and target variable\nX = train_data.drop('sales', axis=1)\ny = train_data['sales']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Split the data into training and validation sets\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Assuming 'date' is a datetime feature\n# Extract relevant information\ntrain_data['year'] = train_data['date'].dt.year\ntrain_data['month'] = train_data['date'].dt.month\ntrain_data['day'] = train_data['date'].dt.day\ntrain_data['day_of_week'] = train_data['date'].dt.dayofweek\n\n# Drop or encode datetime features\ntrain_data.drop(['date'], axis=1, inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Initialize and train the model\nmodel = RandomForestRegressor(random_state=42)\nmodel.fit(X_train, y_train)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Make predictions on the validation set\ny_pred = model.predict(X_val)\n\n# Calculate RMSLE\nrmsle = mean_squared_log_error(y_val, y_pred) ** 0.5\nprint(\"RMSLE:\", rmsle)\n\n# Make predictions on the test set\ntest_predictions = model.predict(test_data)\n\n# Create submission file\nsubmission = pd.DataFrame({'id': test_data.index, 'sales': test_predictions})\nsubmission.to_csv('submission.csv', index=False)","metadata":{},"execution_count":null,"outputs":[]}]}