{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Basic library\nimport pandas as pd\nimport numpy as np\nfrom datetime import datetime as dt\nfrom pathlib import Path\n\n# Graph drawing\nimport matplotlib\nimport matplotlib.pyplot as plt\n\nplt.rcParams[\"patch.force_edgecolor\"] = True\n#rc('text', usetex=True)\nfrom IPython.display import display # Allows the use of display() for DataFrames\nimport seaborn as sns\nsns.set(style=\"whitegrid\", palette=\"muted\", color_codes=True)\nsns.set_style(\"whitegrid\", {'grid.linestyle': '--'})\nred = sns.xkcd_rgb[\"light red\"]\ngreen = sns.xkcd_rgb[\"medium green\"]\nblue = sns.xkcd_rgb[\"denim blue\"]\n\n%matplotlib inline\n#%config InlineBackend.figure_format='retina'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/ashrae-energy-prediction/train.csv\", dtype={\"meter\":\"category\"}, parse_dates=True)\ntest = pd.read_csv(\"../input/ashrae-energy-prediction/test.csv\", dtype={\"meter\":\"category\"}, parse_dates=True)\n\nweather_train = pd.read_csv(\"../input/ashrae-energy-prediction/weather_train.csv\", parse_dates=True)\nweather_test = pd.read_csv(\"../input/ashrae-energy-prediction/weather_test.csv\", parse_dates=True)\n\nbuilding = pd.read_csv(\"../input/ashrae-energy-prediction/building_metadata.csv\", dtype={\"primary_use\":\"category\"})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"meter_type = {i: v for i, v in enumerate([\"electricity\", \"chilledwater\", \"steam\", \" hotwater\"])}\nmeter_type","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"for i in range(20):\n    print(i, train[train.building_id==i].timestamp.shape)\n    build_s = building[building.building_id==i]\n    display(build_s)\n    df_s = train[train.building_id==i].copy()\n    df_s.timestamp = pd.to_datetime(df_s.timestamp)\n    site_id = build_s.iloc[0].site_id\n    weather_train_s = weather_train[weather_train.site_id==site_id]\n    meters = np.sort(df_s.meter.unique())\n    for m in meters:\n        df_s_m = df_s[df_s.meter==m].set_index(\"timestamp\")\n        plt.figure(figsize=(25, 5))\n        ax=plt.subplot(111)\n        df_s_m.meter_reading.plot(ax=ax, color=\"r\")\n        plt.title(f\"[TARGET] building_id: {i}, {build_s.iloc[0].primary_use}, meter:{m} {meter_type[int(m)]}, site_id: {site_id}\")\n        plt.xticks(rotation=60)\n        plt.xticks(df_s_m.index[::24*30], [str(d).split(\" \")[0] for d in df_s_m.index[::24*30]], rotation=60)\n        plt.xlim(df_s_m.index[0],df_s_m.index[-1])\n        plt.show()\n        \n        weather_train_s.set_index(\"timestamp\", inplace=True)\n        for c in ['air_temperature', 'cloud_coverage','dew_temperature', 'precip_depth_1_hr', 'sea_level_pressure','wind_direction', 'wind_speed']:\n            plt.figure(figsize=(25, 2))\n            ax=plt.subplot(111)\n            plt.plot(weather_train_s.index, weather_train_s[c])\n            \n            plt.title(f\"{c}\")\n            plt.xticks(weather_train_s.index[::24*30], [d.split(\" \")[0] for d in weather_train_s.index[::24*30]], rotation=60)\n            plt.xlim(weather_train_s.index[0],weather_train_s.index[-1])\n            \n            plt.show()\n        \n    print(\"=\"*100)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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":1}