{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# load packages\nimport numpy as np \nimport pandas as pd \nimport lightgbm as lgb\nfrom sklearn import preprocessing\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# load data\nTest = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/test.csv\")\nWeather_train = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/weather_train.csv\")\nTrain = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/train.csv\")\nWeather_test = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/weather_test.csv\")\nSample_submission = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/sample_submission.csv\")\nBuilding = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/building_metadata.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"## Function to reduce the DF size\ndef reduce_mem_usage(df, verbose=True):\n    numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']\n    start_mem = df.memory_usage().sum() / 1024**2    \n    for col in df.columns:\n        col_type = df[col].dtypes\n        if col_type in numerics:\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 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    end_mem = df.memory_usage().sum() / 1024**2\n    if verbose: print('Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction)'.format(end_mem, 100 * (start_mem - end_mem) / start_mem))\n    return df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Test = reduce_mem_usage(Test)\nWeather_train = reduce_mem_usage(Weather_train)\nTrain = reduce_mem_usage(Train)\nWeather_test = reduce_mem_usage(Weather_test)\nBuilding = reduce_mem_usage(Building)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Merge_build_train = Building.merge(Train, left_on='building_id', right_on='building_id')\nMerge_build_train = Building.merge(Train, on='building_id', how = \"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge = Merge_build_train.merge(Weather_train, on=[\"site_id\", \"timestamp\"], how=\"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge['meter_reading_log1p'] = np.log1p(Train['meter_reading'])    \nMerge.timestamp = pd.to_datetime(Merge.timestamp, format=\"%Y-%m-%d %H:%M:%S\")\nMerge[\"hour\"] = Merge.timestamp.dt.hour\nMerge[\"weekday\"] = Merge.timestamp.dt.weekday","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Creating datasets for 4 meter readings\nMerge_meter0 = Merge[Merge.meter == 0]\nMerge_meter1 = Merge[Merge.meter == 1]\nMerge_meter2 = Merge[Merge.meter == 2]\nMerge_meter3 = Merge[Merge.meter == 3]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\ndef predict(Merge_meter):\n    \"\"\"\n    Preparing final dataset with all features.\n    \"\"\"\n    columns = ['site_id','building_id','square_feet', 'year_built',\n       'floor_count','air_temperature', 'cloud_coverage',\n       'dew_temperature', 'precip_depth_1_hr', 'wind_speed', 'hour', 'weekday']\n    column2 = ['meter_reading_log1p']\n    X = Merge_meter[columns].astype(float)\n    y = Merge_meter[column2].astype(float)\n    x_train, x_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)\n    sc = StandardScaler()\n    x_train = sc.fit_transform(x_train)\n    x_test = sc.transform(x_test)\n    d_train = lgb.Dataset(x_train, label=y_train)\n    d_test = lgb.Dataset(x_test, label=y_test)\n    params = {}\n    params['learning_rate'] = 0.003\n    params['boosting_type'] = 'gbdt'\n    params['objective'] = 'regression'\n    params['metric'] = 'binary_logloss'\n    params['sub_feature'] = 0.5\n    params['num_leaves'] = 40\n    params['min_data'] = 50\n    params['max_depth'] = 20\n    params[\"metric\"] = \"rmse\"\n\n    clf = lgb.train(params, train_set=d_train, num_boost_round=600, verbose_eval=200,valid_sets=d_test, early_stopping_rounds=200)\n\n    #Prediction\n    y_pred=clf.predict(x_test)\n\n    return clf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf0 = predict(Merge_meter0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf1 = predict(Merge_meter1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf2 = predict(Merge_meter2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf3 = predict(Merge_meter3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del Building, Merge_build_train, Merge","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del Merge_meter0, Merge_meter1, Merge_meter2, Merge_meter3","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Building2 = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/building_metadata.csv\")\nBuilding2 = reduce_mem_usage(Building2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge_build_test= Building2.merge(Test, on='building_id', how = \"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge2 = Merge_build_test.merge(Weather_test, on=[\"site_id\", \"timestamp\"], how=\"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge2.timestamp = pd.to_datetime(Merge2.timestamp, format=\"%Y-%m-%d %H:%M:%S\")\nMerge2[\"hour\"] = Merge2.timestamp.dt.hour\nMerge2[\"weekday\"] = Merge2.timestamp.dt.weekday","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge2_meter0 = Merge2[Merge2.meter == 0]\nMerge2_meter1 = Merge2[Merge2.meter == 1]\nMerge2_meter2 = Merge2[Merge2.meter == 2]\nMerge2_meter3 = Merge2[Merge2.meter == 3]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_test0 = Merge2_meter0[['site_id','building_id','square_feet', 'year_built',\n       'floor_count','air_temperature', 'cloud_coverage',\n       'dew_temperature', 'precip_depth_1_hr', 'wind_speed', 'hour', 'weekday']]\nx_test1 = Merge2_meter1[['site_id','building_id','square_feet', 'year_built',\n       'floor_count','air_temperature', 'cloud_coverage',\n       'dew_temperature', 'precip_depth_1_hr', 'wind_speed', 'hour', 'weekday']]\nx_test2 = Merge2_meter2[['site_id','building_id','square_feet', 'year_built',\n       'floor_count','air_temperature', 'cloud_coverage',\n       'dew_temperature', 'precip_depth_1_hr', 'wind_speed', 'hour', 'weekday']]\nx_test3 = Merge2_meter3[['site_id','building_id','square_feet', 'year_built',\n       'floor_count','air_temperature', 'cloud_coverage',\n       'dew_temperature', 'precip_depth_1_hr', 'wind_speed', 'hour', 'weekday']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del Merge2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y2_pred0 = clf0.predict(x_test0)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y2_pred1 = clf1.predict(x_test1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y2_pred2 = clf2.predict(x_test2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y2_pred3 = clf3.predict(x_test3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge2_meter0['meter_reading'] = y2_pred0\nMerge2_meter1['meter_reading'] = y2_pred1\nMerge2_meter2['meter_reading'] = y2_pred2\nMerge2_meter3['meter_reading'] = y2_pred3","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge2_meter0 = Merge2_meter0[['row_id','building_id','meter','meter_reading']]\nMerge2_meter1 = Merge2_meter1[['row_id','building_id','meter','meter_reading']]\nMerge2_meter2 = Merge2_meter2[['row_id','building_id','meter','meter_reading']]\nMerge2_meter3 = Merge2_meter3[['row_id','building_id','meter','meter_reading']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge2_final = pd.concat([Merge2_meter0,Merge2_meter1,Merge2_meter2,Merge2_meter3])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del Merge2_meter0, Merge2_meter1, Merge2_meter2, Merge2_meter3","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge2_final['meter_reading_real']=np.expm1(Merge2_final['meter_reading'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Merge2_final","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = Sample_submission.merge(Merge2_final, on=[\"row_id\"], how=\"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = submission[[\"row_id\",\"meter_reading_real\"]]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = submission.rename (columns= {\"meter_reading_real\" : \"meter_reading\"})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = reduce_mem_usage(submission)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from IPython.display import FileLink\nFileLink(r'submission.csv')","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}