{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import gc\nimport os\nfrom pathlib import Path\nimport random\nimport sys\n\nfrom tqdm import tqdm_notebook as tqdm\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nfrom IPython.core.display import display, HTML\n\n# --- plotly ---\nfrom plotly import tools, subplots\nimport plotly.offline as py\npy.init_notebook_mode(connected=True)\nimport plotly.graph_objs as go\nimport plotly.express as px\nimport plotly.figure_factory as ff\n\n# --- models ---\nfrom sklearn import preprocessing\nfrom sklearn.model_selection import KFold\nimport lightgbm as lgb\nimport xgboost as xgb\nimport catboost as cb\n\nfrom sklearn.metrics import mean_squared_error","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Original code from https://www.kaggle.com/gemartin/load-data-reduce-memory-usage by @gemartin\n# Modified to support timestamp type, categorical type\n# Modified to add option to use float16 or not. feather format does not support float16.\nfrom pandas.api.types import is_datetime64_any_dtype as is_datetime\nfrom pandas.api.types import is_categorical_dtype\n\ndef reduce_mem_usage(df, use_float16=False):\n    \"\"\" iterate through all the columns of a dataframe and modify the data type\n        to reduce memory usage.        \n    \"\"\"\n    start_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n    \n    for col in df.columns:\n        if is_datetime(df[col]) or is_categorical_dtype(df[col]):\n            # skip datetime type or categorical type\n            continue\n        col_type = df[col].dtype\n        \n        if col_type != object:\n            c_min = df[col].min()\n            c_max = df[col].max()\n            if str(col_type)[:3] == 'int':\n                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n                    df[col] = df[col].astype(np.int8)\n                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n                    df[col] = df[col].astype(np.int16)\n                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n                    df[col] = df[col].astype(np.int32)\n                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n                    df[col] = df[col].astype(np.int64)  \n            else:\n                if use_float16 and c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n                    df[col] = df[col].astype(np.float16)\n                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n                    df[col] = df[col].astype(np.float32)\n                else:\n                    df[col] = df[col].astype(np.float64)\n        else:\n            df[col] = df[col].astype('category')\n\n    end_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))\n    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))\n    \n    return df","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Fit H2O Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"# H2O ML MODEL ======================================================================================================================\n# preproc ===========================\nimport h2o\nfrom h2o.estimators.glm import H2OGeneralizedLinearEstimator\n\n# init ==============================\nh2o.init(max_mem_size='14G')\n\n# import data =======================\ntrain = h2o.import_file(\"../input/ashrae-stack-set-train-fin/train.csv\", header=1)\n\ny = \"target\"\nx = train.columns[0:20]\n\n# fit model =========================\nglm_model = H2OGeneralizedLinearEstimator(\n    family=\"gaussian\", \n    solver='AUTO', \n    alpha=0.5,\n    #lambda=0.0,\n    link='Family_Default',\n    intercept=True,\n    lambda_search=True, \n    nlambdas=100, \n    missing_values_handling='MeanImputation',\n    standardize=True,\n    #nfolds = 5, \n    seed = 1333\n)\nglm_model.train(x=x, y=y, training_frame=train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Eval mod ==========================\n#glm_model.rmse(xval=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# release memory and load test ========\nh2o.remove(train)\ndel train\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Model pred ========================\ntest = h2o.import_file(\"../input/ashrae-stack-set-test-fin/test.csv\", header=1)\npreds = glm_model.predict(test).as_data_frame()\n\n# release memory and load test ========\nh2o.remove(test)\ndel test\ngc.collect()\n\nh2o.cluster().shutdown()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#preds.to_csv(preds, 'preds.csv', index=False, float_format='%.4f')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Link and out subm"},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\ntest_df = pd.read_csv('../input/ashrae-energy-prediction/test.csv', parse_dates=[\"timestamp\"])\nbuilding_meta_df = pd.read_csv('../input/ashrae-energy-prediction/building_metadata.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# leak data\nleak_df = pd.read_feather('../input/ashrae-leak-data-station/leak.feather')\n\nleak_df.fillna(0, inplace=True)\nleak_df = leak_df[(leak_df.timestamp.dt.year > 2016) & (leak_df.timestamp.dt.year < 2019)]\nleak_df.loc[leak_df.meter_reading < 0, 'meter_reading'] = 0 # remove large negative values\nleak_df = leak_df[leak_df.building_id!=245]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['pred'] = np.expm1(preds['predict'])\ntest_df.loc[test_df.pred<0, 'pred'] = 0\n\ntest_df = reduce_mem_usage(test_df)\nleak_df = reduce_mem_usage(leak_df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"leak_df = leak_df.merge(test_df[['building_id', 'meter', 'timestamp', 'pred','row_id']], left_on = ['building_id', 'meter', 'timestamp'], right_on = ['building_id', 'meter', 'timestamp'], how = \"left\")\nleak_df = leak_df.merge(building_meta_df[['building_id', 'site_id']], on='building_id', how='left')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Submit"},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission = pd.read_csv('../input/ashrae-energy-prediction/sample_submission.csv')\nsample_submission['meter_reading'] = test_df.pred\nsample_submission.loc[sample_submission.meter_reading < 0, 'meter_reading'] = 0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.distplot(np.log1p(sample_submission.meter_reading))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"leak_df = leak_df[['meter_reading', 'row_id']].set_index('row_id').dropna()\nsample_submission.loc[leak_df.index, 'meter_reading'] = leak_df['meter_reading']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.distplot(np.log1p(sample_submission.meter_reading))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission.to_csv('submission.csv', index=False, float_format='%.4f')","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":1}