{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"from datetime import date, timedelta\nimport gc # garbage collector\nimport pandas as pd\nimport numpy as np\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.preprocessing import LabelEncoder\n\nimport lightgbm as lgb\n\nimport os\nprint(os.listdir(\"../input/favorita-grocery-sales-forecasting\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install patool","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install pyunpack","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pyunpack\n\ndef unzip(zip_path, data_folder):\n    print('Unzipping file: {}'.format(zip_path))\n    pyunpack.Archive(zip_path).extractall(data_folder)\n\n  # Checks if unzip was successful\n#       if not os.path.exists(output_file):\n#         raise ValueError(\n#             'Error in unzipping process! {} not found.'.format(output_file))\n\n\n\nlist_dir =  os.listdir(\"../input/favorita-grocery-sales-forecasting\")\nfor i in list_dir:\n    unzip(\"../input/favorita-grocery-sales-forecasting/\"+i, '../input/favorita-grocery-sales-forecasting')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"list_dir =  os.listdir(\"../input/favorita-grocery-sales-forecasting\")\nlist_dir","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"\nfrom datetime import date, timedelta\nimport gc\nimport pandas as pd\nimport numpy as np\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.preprocessing import LabelEncoder\n\nimport lightgbm as lgb\n\ndf_train = pd.read_csv(\n    '../input/train.csv', usecols=[1, 2, 3, 4, 5],\n    dtype={'onpromotion': bool},\n    converters={'unit_sales': lambda u: np.log1p(\n        float(u)) if float(u) > 0 else 0},\n    parse_dates=[\"date\"],\n    skiprows=range(1, 66458909)  # 2016-01-01\n)\n\ndf_test = pd.read_csv(\n    \"../input/test.csv\", usecols=[0, 1, 2, 3, 4],\n    dtype={'onpromotion': bool},\n    parse_dates=[\"date\"]  # , date_parser=parser\n).set_index(\n    ['store_nbr', 'item_nbr', 'date']\n)\n\nitems = pd.read_csv(\n    \"../input/items.csv\",\n).set_index(\"item_nbr\")\n\nstores = pd.read_csv(\n    \"../input/stores.csv\",\n).set_index(\"store_nbr\")\n\nle = LabelEncoder()\nitems['family'] = le.fit_transform(items['family'].values)\n\nstores['city'] = le.fit_transform(stores['city'].values)\nstores['state'] = le.fit_transform(stores['state'].values)\nstores['type'] = le.fit_transform(stores['type'].values)\n\ndf_2017 = df_train.loc[df_train.date>=pd.datetime(2017,1,1)]","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","collapsed":true,"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":false},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}