{"cells":[{"metadata":{"trusted":true},"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 in \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 \"../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# Any results you write to the current directory are saved as output.\nfrom pathlib import Path\nimport seaborn as sns\nimport matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### I am not sure if you are noticing this, so I share this."},{"metadata":{"trusted":true},"cell_type":"code","source":"Input = Path('/kaggle/input/ashrae-feather-format-for-fast-loading')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lists = ['test.feather','train.feather','weather_train.feather','weather_test.feather','building_metadata.feather']\ntest = pd.read_feather(Input/lists[0])\ntrain = pd.read_feather(Input/lists[1])\nwtrain = pd.read_feather(Input/lists[2])\nwtest = pd.read_feather(Input/lists[3])\nbmeta = pd.read_feather(Input/lists[4])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cm = sns.light_palette(\"red\", as_cmap=True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Pearson Correlation of Weather Data."},{"metadata":{},"cell_type":"markdown","source":"### Air_Temperature (Pearson Corr.)"},{"metadata":{"scrolled":true,"trusted":true},"cell_type":"code","source":"table = wtrain.groupby(['site_id','timestamp']\n               ,as_index=False)['air_temperature'].mean()\ntable = table.loc[(table.site_id==0)|(table.site_id==8)|(table.site_id==7)|(table.site_id==11)]\npd.pivot_table(table,index=['timestamp'],columns=['site_id']).corr(method='pearson').style.background_gradient(cmap=cm)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig,ax =plt.subplots(1,2)\nfig.set_size_inches(15, 3)\ntable1 = wtrain.loc[(wtrain.site_id==0)|(wtrain.site_id==8)].set_index('site_id')\npd.pivot_table(table1,index=['timestamp'],columns=['site_id']).air_temperature.plot(ax=ax[0])\ntable2 = wtrain.loc[(wtrain.site_id==7)|(wtrain.site_id==11)].set_index('site_id')\npd.pivot_table(table2,index=['timestamp'],columns=['site_id']).air_temperature.plot(ax=ax[1])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Dew_Temperature (Pearson Corr.)"},{"metadata":{"scrolled":true,"trusted":true},"cell_type":"code","source":"table = wtrain.groupby(['site_id','timestamp']\n               ,as_index=False)['dew_temperature'].max()\ntable = table.loc[(table.site_id==0)|(table.site_id==8)|(table.site_id==7)|(table.site_id==11)]\npd.pivot_table(table,index=['timestamp'],columns=['site_id']).corr(method='pearson').style.background_gradient(cmap=cm)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig,ax =plt.subplots(1,2)\nfig.set_size_inches(15, 3)\ntable1 = wtrain.loc[(wtrain.site_id==0)|(wtrain.site_id==8)].set_index('site_id')\npd.pivot_table(table1,index=['timestamp'],columns=['site_id']).dew_temperature.plot(ax=ax[0])\ntable2 = wtrain.loc[(wtrain.site_id==7)|(wtrain.site_id==11)].set_index('site_id')\npd.pivot_table(table2,index=['timestamp'],columns=['site_id']).dew_temperature.plot(ax=ax[1])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Cloud_Coverage (Pearson Corr.)"},{"metadata":{"scrolled":true,"trusted":true},"cell_type":"code","source":"table = wtrain.groupby(['site_id','timestamp']\n               ,as_index=False)['cloud_coverage'].min()\ntable = table.loc[(table.site_id==0)|(table.site_id==8)|(table.site_id==7)|(table.site_id==11)]\npd.pivot_table(table,index=['timestamp'],columns=['site_id']).corr(method='pearson').style.background_gradient(cmap=cm)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig,ax =plt.subplots(1,2)\nfig.set_size_inches(15, 3)\ntable = wtrain.loc[(wtrain.site_id==0)|(wtrain.site_id==8)].set_index('site_id')\npd.pivot_table(table,index=['timestamp'],columns=['site_id']).cloud_coverage.plot(ax=ax[0])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Sea_Level_Pressure (Pearson Corr.)"},{"metadata":{"scrolled":true,"trusted":true},"cell_type":"code","source":"table = wtrain.groupby(['site_id','timestamp']\n               ,as_index=False)['sea_level_pressure'].mean()\ntable = table.loc[(table.site_id==0)|(table.site_id==8)|(table.site_id==7)|(table.site_id==11)]\npd.pivot_table(table,index=['timestamp'],columns=['site_id']).corr(method='pearson').style.background_gradient(cmap=cm)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig,ax =plt.subplots(1,2)\nfig.set_size_inches(15, 3)\ntable1 = wtrain.loc[(wtrain.site_id==0)|(wtrain.site_id==8)].set_index('site_id')\npd.pivot_table(table1,index=['timestamp'],columns=['site_id']).sea_level_pressure.plot(ax=ax[0])\ntable2 = wtrain.loc[(wtrain.site_id==7)|(wtrain.site_id==11)].set_index('site_id')\npd.pivot_table(table2,index=['timestamp'],columns=['site_id']).sea_level_pressure.plot(ax=ax[1])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Wind_Direction (Pearson Corr.)"},{"metadata":{"scrolled":true,"trusted":true},"cell_type":"code","source":"table = wtrain.groupby(['site_id','timestamp']\n               ,as_index=False)['wind_direction'].mean()\ntable = table.loc[(table.site_id==0)|(table.site_id==8)|(table.site_id==7)|(table.site_id==11)]\npd.pivot_table(table,index=['timestamp'],columns=['site_id']).corr(method='pearson').style.background_gradient(cmap=cm)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig,ax =plt.subplots(1,2)\nfig.set_size_inches(15, 3)\ntable1 = wtrain.loc[(wtrain.site_id==0)|(wtrain.site_id==8)].set_index('site_id')\npd.pivot_table(table1,index=['timestamp'],columns=['site_id']).wind_direction.plot(ax=ax[0])\ntable2 = wtrain.loc[(wtrain.site_id==7)|(wtrain.site_id==11)].set_index('site_id')\npd.pivot_table(table2,index=['timestamp'],columns=['site_id']).wind_direction.plot(ax=ax[1])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Wind_Speed (Pearson Corr.)"},{"metadata":{"trusted":true},"cell_type":"code","source":"table = wtrain.groupby(['site_id','timestamp']\n               ,as_index=False)['wind_speed'].mean()\ntable = table.loc[(table.site_id==0)|(table.site_id==8)|(table.site_id==7)|(table.site_id==11)]\npd.pivot_table(table,index=['timestamp'],columns=['site_id']).corr(method='pearson').style.background_gradient(cmap=cm)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig,ax =plt.subplots(1,2)\nfig.set_size_inches(15, 3)\ntable1 = wtrain.loc[(wtrain.site_id==0)|(wtrain.site_id==8)].set_index('site_id')\npd.pivot_table(table1,index=['timestamp'],columns=['site_id']).wind_speed.plot(ax=ax[0])\ntable2 = wtrain.loc[(wtrain.site_id==7)|(wtrain.site_id==11)].set_index('site_id')\npd.pivot_table(table2,index=['timestamp'],columns=['site_id']).wind_speed.plot(ax=ax[1])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Counting NaN"},{"metadata":{},"cell_type":"markdown","source":"#### Site 0 vs Site 8"},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Missing Values(Site 0)')\nprint(wtrain.loc[wtrain.site_id==0].isnull().sum())\nprint('########################')\nprint('Missing Values(Site 8)')\nprint(wtrain.loc[wtrain.site_id==8].isnull().sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Site 7 vs Site 11"},{"metadata":{"scrolled":true,"trusted":true},"cell_type":"code","source":"print('Missing Values(Site 7)')\nprint(wtrain.loc[wtrain.site_id==7].isnull().sum())\nprint('########################')\nprint('Missing Values(Site 11)')\nprint(wtrain.loc[wtrain.site_id==11].isnull().sum())","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.7.4"}},"nbformat":4,"nbformat_minor":1}